Genomic selection models double the accuracy of predicted breeding values for bacterial cold water disease resistance compared to a traditional pedigree-based model in rainbow trout aquaculture.

PubMed

Vallejo, Roger L; Leeds, Timothy D; Gao, Guangtu; Parsons, James E; Martin, Kyle E; Evenhuis, Jason P; Fragomeni, Breno O; Wiens, Gregory D; Palti, Yniv

2017-02-01

Previously, we have shown that bacterial cold water disease (BCWD) resistance in rainbow trout can be improved using traditional family-based selection, but progress has been limited to exploiting only between-family genetic variation. Genomic selection (GS) is a new alternative that enables exploitation of within-family genetic variation. We compared three GS models [single-step genomic best linear unbiased prediction (ssGBLUP), weighted ssGBLUP (wssGBLUP), and BayesB] to predict genomic-enabled breeding values (GEBV) for BCWD resistance in a commercial rainbow trout population, and compared the accuracy of GEBV to traditional estimates of breeding values (EBV) from a pedigree-based BLUP (P-BLUP) model. We also assessed the impact of sampling design on the accuracy of GEBV predictions. For these comparisons, we used BCWD survival phenotypes recorded on 7893 fish from 102 families, of which 1473 fish from 50 families had genotypes [57 K single nucleotide polymorphism (SNP) array]. Naïve siblings of the training fish (n = 930 testing fish) were genotyped to predict their GEBV and mated to produce 138 progeny testing families. In the following generation, 9968 progeny were phenotyped to empirically assess the accuracy of GEBV predictions made on their non-phenotyped parents. The accuracy of GEBV from all tested GS models were substantially higher than the P-BLUP model EBV. The highest increase in accuracy relative to the P-BLUP model was achieved with BayesB (97.2 to 108.8%), followed by wssGBLUP at iteration 2 (94.4 to 97.1%) and 3 (88.9 to 91.2%) and ssGBLUP (83.3 to 85.3%). Reducing the training sample size to n = ~1000 had no negative impact on the accuracy (0.67 to 0.72), but with n = ~500 the accuracy dropped to 0.53 to 0.61 if the training and testing fish were full-sibs, and even substantially lower, to 0.22 to 0.25, when they were not full-sibs. Using progeny performance data, we showed that the accuracy of genomic predictions is substantially higher than estimates obtained from the traditional pedigree-based BLUP model for BCWD resistance. Overall, we found that using a much smaller training sample size compared to similar studies in livestock, GS can substantially improve the selection accuracy and genetic gains for this trait in a commercial rainbow trout breeding population.

Evaluation of approaches for estimating the accuracy of genomic prediction in plant breeding

PubMed Central

2013-01-01

Background In genomic prediction, an important measure of accuracy is the correlation between the predicted and the true breeding values. Direct computation of this quantity for real datasets is not possible, because the true breeding value is unknown. Instead, the correlation between the predicted breeding values and the observed phenotypic values, called predictive ability, is often computed. In order to indirectly estimate predictive accuracy, this latter correlation is usually divided by an estimate of the square root of heritability. In this study we use simulation to evaluate estimates of predictive accuracy for seven methods, four (1 to 4) of which use an estimate of heritability to divide predictive ability computed by cross-validation. Between them the seven methods cover balanced and unbalanced datasets as well as correlated and uncorrelated genotypes. We propose one new indirect method (4) and two direct methods (5 and 6) for estimating predictive accuracy and compare their performances and those of four other existing approaches (three indirect (1 to 3) and one direct (7)) with simulated true predictive accuracy as the benchmark and with each other. Results The size of the estimated genetic variance and hence heritability exerted the strongest influence on the variation in the estimated predictive accuracy. Increasing the number of genotypes considerably increases the time required to compute predictive accuracy by all the seven methods, most notably for the five methods that require cross-validation (Methods 1, 2, 3, 4 and 6). A new method that we propose (Method 5) and an existing method (Method 7) used in animal breeding programs were the fastest and gave the least biased, most precise and stable estimates of predictive accuracy. Of the methods that use cross-validation Methods 4 and 6 were often the best. Conclusions The estimated genetic variance and the number of genotypes had the greatest influence on predictive accuracy. Methods 5 and 7 were the fastest and produced the least biased, the most precise, robust and stable estimates of predictive accuracy. These properties argue for routinely using Methods 5 and 7 to assess predictive accuracy in genomic selection studies. PMID:24314298

Evaluation of approaches for estimating the accuracy of genomic prediction in plant breeding.

PubMed

Ould Estaghvirou, Sidi Boubacar; Ogutu, Joseph O; Schulz-Streeck, Torben; Knaak, Carsten; Ouzunova, Milena; Gordillo, Andres; Piepho, Hans-Peter

2013-12-06

In genomic prediction, an important measure of accuracy is the correlation between the predicted and the true breeding values. Direct computation of this quantity for real datasets is not possible, because the true breeding value is unknown. Instead, the correlation between the predicted breeding values and the observed phenotypic values, called predictive ability, is often computed. In order to indirectly estimate predictive accuracy, this latter correlation is usually divided by an estimate of the square root of heritability. In this study we use simulation to evaluate estimates of predictive accuracy for seven methods, four (1 to 4) of which use an estimate of heritability to divide predictive ability computed by cross-validation. Between them the seven methods cover balanced and unbalanced datasets as well as correlated and uncorrelated genotypes. We propose one new indirect method (4) and two direct methods (5 and 6) for estimating predictive accuracy and compare their performances and those of four other existing approaches (three indirect (1 to 3) and one direct (7)) with simulated true predictive accuracy as the benchmark and with each other. The size of the estimated genetic variance and hence heritability exerted the strongest influence on the variation in the estimated predictive accuracy. Increasing the number of genotypes considerably increases the time required to compute predictive accuracy by all the seven methods, most notably for the five methods that require cross-validation (Methods 1, 2, 3, 4 and 6). A new method that we propose (Method 5) and an existing method (Method 7) used in animal breeding programs were the fastest and gave the least biased, most precise and stable estimates of predictive accuracy. Of the methods that use cross-validation Methods 4 and 6 were often the best. The estimated genetic variance and the number of genotypes had the greatest influence on predictive accuracy. Methods 5 and 7 were the fastest and produced the least biased, the most precise, robust and stable estimates of predictive accuracy. These properties argue for routinely using Methods 5 and 7 to assess predictive accuracy in genomic selection studies.

Dispersal and extrapolation on the accuracy of temporal predictions from distribution models for the Darwin's frog.

PubMed

Uribe-Rivera, David E; Soto-Azat, Claudio; Valenzuela-Sánchez, Andrés; Bizama, Gustavo; Simonetti, Javier A; Pliscoff, Patricio

2017-07-01

Climate change is a major threat to biodiversity; the development of models that reliably predict its effects on species distributions is a priority for conservation biogeography. Two of the main issues for accurate temporal predictions from Species Distribution Models (SDM) are model extrapolation and unrealistic dispersal scenarios. We assessed the consequences of these issues on the accuracy of climate-driven SDM predictions for the dispersal-limited Darwin's frog Rhinoderma darwinii in South America. We calibrated models using historical data (1950-1975) and projected them across 40 yr to predict distribution under current climatic conditions, assessing predictive accuracy through the area under the ROC curve (AUC) and True Skill Statistics (TSS), contrasting binary model predictions against temporal-independent validation data set (i.e., current presences/absences). To assess the effects of incorporating dispersal processes we compared the predictive accuracy of dispersal constrained models with no dispersal limited SDMs; and to assess the effects of model extrapolation on the predictive accuracy of SDMs, we compared this between extrapolated and no extrapolated areas. The incorporation of dispersal processes enhanced predictive accuracy, mainly due to a decrease in the false presence rate of model predictions, which is consistent with discrimination of suitable but inaccessible habitat. This also had consequences on range size changes over time, which is the most used proxy for extinction risk from climate change. The area of current climatic conditions that was absent in the baseline conditions (i.e., extrapolated areas) represents 39% of the study area, leading to a significant decrease in predictive accuracy of model predictions for those areas. Our results highlight (1) incorporating dispersal processes can improve predictive accuracy of temporal transference of SDMs and reduce uncertainties of extinction risk assessments from global change; (2) as geographical areas subjected to novel climates are expected to arise, they must be reported as they show less accurate predictions under future climate scenarios. Consequently, environmental extrapolation and dispersal processes should be explicitly incorporated to report and reduce uncertainties in temporal predictions of SDMs, respectively. Doing so, we expect to improve the reliability of the information we provide for conservation decision makers under future climate change scenarios. © 2017 by the Ecological Society of America.

Genomic-Enabled Prediction Kernel Models with Random Intercepts for Multi-environment Trials.

PubMed

Cuevas, Jaime; Granato, Italo; Fritsche-Neto, Roberto; Montesinos-Lopez, Osval A; Burgueño, Juan; Bandeira E Sousa, Massaine; Crossa, José

2018-03-28

In this study, we compared the prediction accuracy of the main genotypic effect model (MM) without G×E interactions, the multi-environment single variance G×E deviation model (MDs), and the multi-environment environment-specific variance G×E deviation model (MDe) where the random genetic effects of the lines are modeled with the markers (or pedigree). With the objective of further modeling the genetic residual of the lines, we incorporated the random intercepts of the lines ([Formula: see text]) and generated another three models. Each of these 6 models were fitted with a linear kernel method (Genomic Best Linear Unbiased Predictor, GB) and a Gaussian Kernel (GK) method. We compared these 12 model-method combinations with another two multi-environment G×E interactions models with unstructured variance-covariances (MUC) using GB and GK kernels (4 model-method). Thus, we compared the genomic-enabled prediction accuracy of a total of 16 model-method combinations on two maize data sets with positive phenotypic correlations among environments, and on two wheat data sets with complex G×E that includes some negative and close to zero phenotypic correlations among environments. The two models (MDs and MDE with the random intercept of the lines and the GK method) were computationally efficient and gave high prediction accuracy in the two maize data sets. Regarding the more complex G×E wheat data sets, the prediction accuracy of the model-method combination with G×E, MDs and MDe, including the random intercepts of the lines with GK method had important savings in computing time as compared with the G×E interaction multi-environment models with unstructured variance-covariances but with lower genomic prediction accuracy. Copyright © 2018 Cuevas et al.

Genomic-Enabled Prediction Kernel Models with Random Intercepts for Multi-environment Trials

PubMed Central

Cuevas, Jaime; Granato, Italo; Fritsche-Neto, Roberto; Montesinos-Lopez, Osval A.; Burgueño, Juan; Bandeira e Sousa, Massaine; Crossa, José

2018-01-01

In this study, we compared the prediction accuracy of the main genotypic effect model (MM) without G×E interactions, the multi-environment single variance G×E deviation model (MDs), and the multi-environment environment-specific variance G×E deviation model (MDe) where the random genetic effects of the lines are modeled with the markers (or pedigree). With the objective of further modeling the genetic residual of the lines, we incorporated the random intercepts of the lines (l) and generated another three models. Each of these 6 models were fitted with a linear kernel method (Genomic Best Linear Unbiased Predictor, GB) and a Gaussian Kernel (GK) method. We compared these 12 model-method combinations with another two multi-environment G×E interactions models with unstructured variance-covariances (MUC) using GB and GK kernels (4 model-method). Thus, we compared the genomic-enabled prediction accuracy of a total of 16 model-method combinations on two maize data sets with positive phenotypic correlations among environments, and on two wheat data sets with complex G×E that includes some negative and close to zero phenotypic correlations among environments. The two models (MDs and MDE with the random intercept of the lines and the GK method) were computationally efficient and gave high prediction accuracy in the two maize data sets. Regarding the more complex G×E wheat data sets, the prediction accuracy of the model-method combination with G×E, MDs and MDe, including the random intercepts of the lines with GK method had important savings in computing time as compared with the G×E interaction multi-environment models with unstructured variance-covariances but with lower genomic prediction accuracy. PMID:29476023

Improved accuracy of intraocular lens power calculation with the Zeiss IOLMaster.

PubMed

Olsen, Thomas

2007-02-01

This study aimed to demonstrate how the level of accuracy in intraocular lens (IOL) power calculation can be improved with optical biometry using partial optical coherence interferometry (PCI) (Zeiss IOLMaster) and current anterior chamber depth (ACD) prediction algorithms. Intraocular lens power in 461 consecutive cataract operations was calculated using both PCI and ultrasound and the accuracy of the results of each technique were compared. To illustrate the importance of ACD prediction per se, predictions were calculated using both a recently published 5-variable method and the Haigis 2-variable method and the results compared. All calculations were optimized in retrospect to account for systematic errors, including IOL constants and other off-set errors. The average absolute IOL prediction error (observed minus expected refraction) was 0.65 dioptres with ultrasound and 0.43 D with PCI using the 5-variable ACD prediction method (p < 0.00001). The number of predictions within +/- 0.5 D, +/- 1.0 D and +/- 2.0 D of the expected outcome was 62.5%, 92.4% and 99.9% with PCI, compared with 45.5%, 77.3% and 98.4% with ultrasound, respectively (p < 0.00001). The 2-variable ACD method resulted in an average error in PCI predictions of 0.46 D, which was significantly higher than the error in the 5-variable method (p < 0.001). The accuracy of IOL power calculation can be significantly improved using calibrated axial length readings obtained with PCI and modern IOL power calculation formulas incorporating the latest generation ACD prediction algorithms.

Comparing strategies for selection of low-density SNPs for imputation-mediated genomic prediction in U. S. Holsteins.

PubMed

He, Jun; Xu, Jiaqi; Wu, Xiao-Lin; Bauck, Stewart; Lee, Jungjae; Morota, Gota; Kachman, Stephen D; Spangler, Matthew L

2018-04-01

SNP chips are commonly used for genotyping animals in genomic selection but strategies for selecting low-density (LD) SNPs for imputation-mediated genomic selection have not been addressed adequately. The main purpose of the present study was to compare the performance of eight LD (6K) SNP panels, each selected by a different strategy exploiting a combination of three major factors: evenly-spaced SNPs, increased minor allele frequencies, and SNP-trait associations either for single traits independently or for all the three traits jointly. The imputation accuracies from 6K to 80K SNP genotypes were between 96.2 and 98.2%. Genomic prediction accuracies obtained using imputed 80K genotypes were between 0.817 and 0.821 for daughter pregnancy rate, between 0.838 and 0.844 for fat yield, and between 0.850 and 0.863 for milk yield. The two SNP panels optimized on the three major factors had the highest genomic prediction accuracy (0.821-0.863), and these accuracies were very close to those obtained using observed 80K genotypes (0.825-0.868). Further exploration of the underlying relationships showed that genomic prediction accuracies did not respond linearly to imputation accuracies, but were significantly affected by genotype (imputation) errors of SNPs in association with the traits to be predicted. SNPs optimal for map coverage and MAF were favorable for obtaining accurate imputation of genotypes whereas trait-associated SNPs improved genomic prediction accuracies. Thus, optimal LD SNP panels were the ones that combined both strengths. The present results have practical implications on the design of LD SNP chips for imputation-enabled genomic prediction.

Accuracy of Prediction Equations to Assess Percentage of Body Fat in Children and Adolescents with Down Syndrome Compared to Air Displacement Plethysmography

ERIC Educational Resources Information Center

Gonzalez-Aguero, A.; Vicente-Rodriguez, G.; Ara, I.; Moreno, L. A.; Casajus, J. A.

2011-01-01

To determine the accuracy of the published percentage body fat (%BF) prediction equations (Durnin et al., Johnston et al., Brook and Slaughter et al.) from skinfold thickness compared to air displacement plethysmography (ADP) in children and adolescents with Down syndrome (DS). Twenty-eight children and adolescents with DS (10-20 years old; 12…

Mortality Predicted Accuracy for Hepatocellular Carcinoma Patients with Hepatic Resection Using Artificial Neural Network

PubMed Central

Chiu, Herng-Chia; Ho, Te-Wei; Lee, King-Teh; Chen, Hong-Yaw; Ho, Wen-Hsien

2013-01-01

The aim of this present study is firstly to compare significant predictors of mortality for hepatocellular carcinoma (HCC) patients undergoing resection between artificial neural network (ANN) and logistic regression (LR) models and secondly to evaluate the predictive accuracy of ANN and LR in different survival year estimation models. We constructed a prognostic model for 434 patients with 21 potential input variables by Cox regression model. Model performance was measured by numbers of significant predictors and predictive accuracy. The results indicated that ANN had double to triple numbers of significant predictors at 1-, 3-, and 5-year survival models as compared with LR models. Scores of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) of 1-, 3-, and 5-year survival estimation models using ANN were superior to those of LR in all the training sets and most of the validation sets. The study demonstrated that ANN not only had a great number of predictors of mortality variables but also provided accurate prediction, as compared with conventional methods. It is suggested that physicians consider using data mining methods as supplemental tools for clinical decision-making and prognostic evaluation. PMID:23737707

Comparison of Models and Whole-Genome Profiling Approaches for Genomic-Enabled Prediction of Septoria Tritici Blotch, Stagonospora Nodorum Blotch, and Tan Spot Resistance in Wheat.

PubMed

Juliana, Philomin; Singh, Ravi P; Singh, Pawan K; Crossa, Jose; Rutkoski, Jessica E; Poland, Jesse A; Bergstrom, Gary C; Sorrells, Mark E

2017-07-01

The leaf spotting diseases in wheat that include Septoria tritici blotch (STB) caused by , Stagonospora nodorum blotch (SNB) caused by , and tan spot (TS) caused by pose challenges to breeding programs in selecting for resistance. A promising approach that could enable selection prior to phenotyping is genomic selection that uses genome-wide markers to estimate breeding values (BVs) for quantitative traits. To evaluate this approach for seedling and/or adult plant resistance (APR) to STB, SNB, and TS, we compared the predictive ability of least-squares (LS) approach with genomic-enabled prediction models including genomic best linear unbiased predictor (GBLUP), Bayesian ridge regression (BRR), Bayes A (BA), Bayes B (BB), Bayes Cπ (BC), Bayesian least absolute shrinkage and selection operator (BL), and reproducing kernel Hilbert spaces markers (RKHS-M), a pedigree-based model (RKHS-P) and RKHS markers and pedigree (RKHS-MP). We observed that LS gave the lowest prediction accuracies and RKHS-MP, the highest. The genomic-enabled prediction models and RKHS-P gave similar accuracies. The increase in accuracy using genomic prediction models over LS was 48%. The mean genomic prediction accuracies were 0.45 for STB (APR), 0.55 for SNB (seedling), 0.66 for TS (seedling) and 0.48 for TS (APR). We also compared markers from two whole-genome profiling approaches: genotyping by sequencing (GBS) and diversity arrays technology sequencing (DArTseq) for prediction. While, GBS markers performed slightly better than DArTseq, combining markers from the two approaches did not improve accuracies. We conclude that implementing GS in breeding for these diseases would help to achieve higher accuracies and rapid gains from selection. Copyright © 2017 Crop Science Society of America.

Validity of Teacher-Based Vision Screening and Factors Associated with the Accuracy of Vision Screening in Vietnamese Children.

PubMed

Paudel, Prakash; Kovai, Vilas; Naduvilath, Thomas; Phuong, Ha Thanh; Ho, Suit May; Giap, Nguyen Viet

2016-01-01

To assess validity of teacher-based vision screening and elicit factors associated with accuracy of vision screening in Vietnam. After brief training, teachers independently measured visual acuity (VA) in 555 children aged 12-15 years in Ba Ria - Vung Tau Province. Teacher VA measurements were compared to those of refractionists. Sensitivity, specificity, positive predictive value and negative predictive value were calculated for uncorrected VA (UVA) and presenting VA (PVA) 20/40 or worse in either eye. Chi-square, Fisher's exact test and multivariate logistic regression were used to assess factors associated with accuracy of vision screening. Level of significance was set at 5%. Trained teachers in Vietnam demonstrated 86.7% sensitivity, 95.7% specificity, 86.7% positive predictive value and 95.7% negative predictive value in identifying children with visual impairment using the UVA measurement. PVA measurement revealed low accuracy for teachers, which was significantly associated with child's age, sex, spectacle wear and myopic status, but UVA measurement showed no such associations. Better accuracy was achieved in measurement of VA and identification of children with visual impairment using UVA measurement compared to PVA. UVA measurement is recommended for teacher-based vision screening programs.

Leuconostoc mesenteroides growth in food products: prediction and sensitivity analysis by adaptive-network-based fuzzy inference systems.

PubMed

Wang, Hue-Yu; Wen, Ching-Feng; Chiu, Yu-Hsien; Lee, I-Nong; Kao, Hao-Yun; Lee, I-Chen; Ho, Wen-Hsien

2013-01-01

An adaptive-network-based fuzzy inference system (ANFIS) was compared with an artificial neural network (ANN) in terms of accuracy in predicting the combined effects of temperature (10.5 to 24.5°C), pH level (5.5 to 7.5), sodium chloride level (0.25% to 6.25%) and sodium nitrite level (0 to 200 ppm) on the growth rate of Leuconostoc mesenteroides under aerobic and anaerobic conditions. THE ANFIS AND ANN MODELS WERE COMPARED IN TERMS OF SIX STATISTICAL INDICES CALCULATED BY COMPARING THEIR PREDICTION RESULTS WITH ACTUAL DATA: mean absolute percentage error (MAPE), root mean square error (RMSE), standard error of prediction percentage (SEP), bias factor (Bf), accuracy factor (Af), and absolute fraction of variance (R (2)). Graphical plots were also used for model comparison. The learning-based systems obtained encouraging prediction results. Sensitivity analyses of the four environmental factors showed that temperature and, to a lesser extent, NaCl had the most influence on accuracy in predicting the growth rate of Leuconostoc mesenteroides under aerobic and anaerobic conditions. The observed effectiveness of ANFIS for modeling microbial kinetic parameters confirms its potential use as a supplemental tool in predictive mycology. Comparisons between growth rates predicted by ANFIS and actual experimental data also confirmed the high accuracy of the Gaussian membership function in ANFIS. Comparisons of the six statistical indices under both aerobic and anaerobic conditions also showed that the ANFIS model was better than all ANN models in predicting the four kinetic parameters. Therefore, the ANFIS model is a valuable tool for quickly predicting the growth rate of Leuconostoc mesenteroides under aerobic and anaerobic conditions.

Leuconostoc Mesenteroides Growth in Food Products: Prediction and Sensitivity Analysis by Adaptive-Network-Based Fuzzy Inference Systems

PubMed Central

Wang, Hue-Yu; Wen, Ching-Feng; Chiu, Yu-Hsien; Lee, I-Nong; Kao, Hao-Yun; Lee, I-Chen; Ho, Wen-Hsien

2013-01-01

Background An adaptive-network-based fuzzy inference system (ANFIS) was compared with an artificial neural network (ANN) in terms of accuracy in predicting the combined effects of temperature (10.5 to 24.5°C), pH level (5.5 to 7.5), sodium chloride level (0.25% to 6.25%) and sodium nitrite level (0 to 200 ppm) on the growth rate of Leuconostoc mesenteroides under aerobic and anaerobic conditions. Methods The ANFIS and ANN models were compared in terms of six statistical indices calculated by comparing their prediction results with actual data: mean absolute percentage error (MAPE), root mean square error (RMSE), standard error of prediction percentage (SEP), bias factor (Bf), accuracy factor (Af), and absolute fraction of variance (R 2). Graphical plots were also used for model comparison. Conclusions The learning-based systems obtained encouraging prediction results. Sensitivity analyses of the four environmental factors showed that temperature and, to a lesser extent, NaCl had the most influence on accuracy in predicting the growth rate of Leuconostoc mesenteroides under aerobic and anaerobic conditions. The observed effectiveness of ANFIS for modeling microbial kinetic parameters confirms its potential use as a supplemental tool in predictive mycology. Comparisons between growth rates predicted by ANFIS and actual experimental data also confirmed the high accuracy of the Gaussian membership function in ANFIS. Comparisons of the six statistical indices under both aerobic and anaerobic conditions also showed that the ANFIS model was better than all ANN models in predicting the four kinetic parameters. Therefore, the ANFIS model is a valuable tool for quickly predicting the growth rate of Leuconostoc mesenteroides under aerobic and anaerobic conditions. PMID:23705023

Bayesian decision support for coding occupational injury data.

PubMed

Nanda, Gaurav; Grattan, Kathleen M; Chu, MyDzung T; Davis, Letitia K; Lehto, Mark R

2016-06-01

Studies on autocoding injury data have found that machine learning algorithms perform well for categories that occur frequently but often struggle with rare categories. Therefore, manual coding, although resource-intensive, cannot be eliminated. We propose a Bayesian decision support system to autocode a large portion of the data, filter cases for manual review, and assist human coders by presenting them top k prediction choices and a confusion matrix of predictions from Bayesian models. We studied the prediction performance of Single-Word (SW) and Two-Word-Sequence (TW) Naïve Bayes models on a sample of data from the 2011 Survey of Occupational Injury and Illness (SOII). We used the agreement in prediction results of SW and TW models, and various prediction strength thresholds for autocoding and filtering cases for manual review. We also studied the sensitivity of the top k predictions of the SW model, TW model, and SW-TW combination, and then compared the accuracy of the manually assigned codes to SOII data with that of the proposed system. The accuracy of the proposed system, assuming well-trained coders reviewing a subset of only 26% of cases flagged for review, was estimated to be comparable (86.5%) to the accuracy of the original coding of the data set (range: 73%-86.8%). Overall, the TW model had higher sensitivity than the SW model, and the accuracy of the prediction results increased when the two models agreed, and for higher prediction strength thresholds. The sensitivity of the top five predictions was 93%. The proposed system seems promising for coding injury data as it offers comparable accuracy and less manual coding. Accurate and timely coded occupational injury data is useful for surveillance as well as prevention activities that aim to make workplaces safer. Copyright © 2016 Elsevier Ltd and National Safety Council. All rights reserved.

Genomic Prediction of Gene Bank Wheat Landraces.

PubMed

Crossa, José; Jarquín, Diego; Franco, Jorge; Pérez-Rodríguez, Paulino; Burgueño, Juan; Saint-Pierre, Carolina; Vikram, Prashant; Sansaloni, Carolina; Petroli, Cesar; Akdemir, Deniz; Sneller, Clay; Reynolds, Matthew; Tattaris, Maria; Payne, Thomas; Guzman, Carlos; Peña, Roberto J; Wenzl, Peter; Singh, Sukhwinder

2016-07-07

This study examines genomic prediction within 8416 Mexican landrace accessions and 2403 Iranian landrace accessions stored in gene banks. The Mexican and Iranian collections were evaluated in separate field trials, including an optimum environment for several traits, and in two separate environments (drought, D and heat, H) for the highly heritable traits, days to heading (DTH), and days to maturity (DTM). Analyses accounting and not accounting for population structure were performed. Genomic prediction models include genotype × environment interaction (G × E). Two alternative prediction strategies were studied: (1) random cross-validation of the data in 20% training (TRN) and 80% testing (TST) (TRN20-TST80) sets, and (2) two types of core sets, "diversity" and "prediction", including 10% and 20%, respectively, of the total collections. Accounting for population structure decreased prediction accuracy by 15-20% as compared to prediction accuracy obtained when not accounting for population structure. Accounting for population structure gave prediction accuracies for traits evaluated in one environment for TRN20-TST80 that ranged from 0.407 to 0.677 for Mexican landraces, and from 0.166 to 0.662 for Iranian landraces. Prediction accuracy of the 20% diversity core set was similar to accuracies obtained for TRN20-TST80, ranging from 0.412 to 0.654 for Mexican landraces, and from 0.182 to 0.647 for Iranian landraces. The predictive core set gave similar prediction accuracy as the diversity core set for Mexican collections, but slightly lower for Iranian collections. Prediction accuracy when incorporating G × E for DTH and DTM for Mexican landraces for TRN20-TST80 was around 0.60, which is greater than without the G × E term. For Iranian landraces, accuracies were 0.55 for the G × E model with TRN20-TST80. Results show promising prediction accuracies for potential use in germplasm enhancement and rapid introgression of exotic germplasm into elite materials. Copyright © 2016 Crossa et al.

Comparison of univariate and multivariate models for prediction of major and minor elements from laser-induced breakdown spectra with and without masking

NASA Astrophysics Data System (ADS)

Dyar, M. Darby; Fassett, Caleb I.; Giguere, Stephen; Lepore, Kate; Byrne, Sarah; Boucher, Thomas; Carey, CJ; Mahadevan, Sridhar

2016-09-01

This study uses 1356 spectra from 452 geologically-diverse samples, the largest suite of LIBS rock spectra ever assembled, to compare the accuracy of elemental predictions in models that use only spectral regions thought to contain peaks arising from the element of interest versus those that use information in the entire spectrum. Results show that for the elements Si, Al, Ti, Fe, Mg, Ca, Na, K, Ni, Mn, Cr, Co, and Zn, univariate predictions based on single emission lines are by far the least accurate, no matter how carefully the region of channels/wavelengths is chosen and despite the prominence of the selected emission lines. An automated iterative algorithm was developed to sweep through all 5485 channels of data and select the single region that produces the optimal prediction accuracy for each element using univariate analysis. For the eight major elements, use of this technique results in a 35% improvement in prediction accuracy; for minors, the improvement is 13%. The best wavelength region choice for any given univariate analysis is likely to be an inherent property of the specific training set that cannot be generalized. In comparison, multivariate analysis using partial least-squares (PLS) almost universally outperforms univariate analysis. PLS using all the same wavelength regions from the univariate analysis produces results that improve in accuracy by 63% for major elements and 3% for minor element. This difference is likely a reflection of signal to noise ratios, which are far better for major elements than for minor elements, and likely limit their prediction accuracy by any technique. We also compare predictions using specific wavelength ranges for each element against those employing all channels. Masking out channels to focus on emission lines from a specific element that occurs decreases prediction accuracy for major elements but is useful for minor elements with low signals and proportionally much higher noise; use of PLS rather than univariate analysis is still recommended. Finally, we tested the generalizability of our results by analyzing a second data set from a different instrument. Overall prediction accuracies for the mixed data sets are higher than for either set alone for all major and minor elements except Ni, Cr, and Co, where results are roughly comparable.

Evaluating the predictive accuracy and the clinical benefit of a nomogram aimed to predict survival in node-positive prostate cancer patients: External validation on a multi-institutional database.

PubMed

Bianchi, Lorenzo; Schiavina, Riccardo; Borghesi, Marco; Bianchi, Federico Mineo; Briganti, Alberto; Carini, Marco; Terrone, Carlo; Mottrie, Alex; Gacci, Mauro; Gontero, Paolo; Imbimbo, Ciro; Marchioro, Giansilvio; Milanese, Giulio; Mirone, Vincenzo; Montorsi, Francesco; Morgia, Giuseppe; Novara, Giacomo; Porreca, Angelo; Volpe, Alessandro; Brunocilla, Eugenio

2018-04-06

To assess the predictive accuracy and the clinical value of a recent nomogram predicting cancer-specific mortality-free survival after surgery in pN1 prostate cancer patients through an external validation. We evaluated 518 prostate cancer patients treated with radical prostatectomy and pelvic lymph node dissection with evidence of nodal metastases at final pathology, at 10 tertiary centers. External validation was carried out using regression coefficients of the previously published nomogram. The performance characteristics of the model were assessed by quantifying predictive accuracy, according to the area under the curve in the receiver operating characteristic curve and model calibration. Furthermore, we systematically analyzed the specificity, sensitivity, positive predictive value and negative predictive value for each nomogram-derived probability cut-off. Finally, we implemented decision curve analysis, in order to quantify the nomogram's clinical value in routine practice. External validation showed inferior predictive accuracy as referred to in the internal validation (65.8% vs 83.3%, respectively). The discrimination (area under the curve) of the multivariable model was 66.7% (95% CI 60.1-73.0%) by testing with receiver operating characteristic curve analysis. The calibration plot showed an overestimation throughout the range of predicted cancer-specific mortality-free survival rates probabilities. However, in decision curve analysis, the nomogram's use showed a net benefit when compared with the scenarios of treating all patients or none. In an external setting, the nomogram showed inferior predictive accuracy and suboptimal calibration characteristics as compared to that reported in the original population. However, decision curve analysis showed a clinical net benefit, suggesting a clinical implication to correctly manage pN1 prostate cancer patients after surgery. © 2018 The Japanese Urological Association.

An Experimental Study in Determining Energy Expenditure from Treadmill Walking using Hip-Worn Inertial Sensors

PubMed Central

Vathsangam, Harshvardhan; Emken, Adar; Schroeder, E. Todd; Spruijt-Metz, Donna; Sukhatme, Gaurav S.

2011-01-01

This paper describes an experimental study in estimating energy expenditure from treadmill walking using a single hip-mounted triaxial inertial sensor comprised of a triaxial accelerometer and a triaxial gyroscope. Typical physical activity characterization using accelerometer generated counts suffers from two drawbacks - imprecison (due to proprietary counts) and incompleteness (due to incomplete movement description). We address these problems in the context of steady state walking by directly estimating energy expenditure with data from a hip-mounted inertial sensor. We represent the cyclic nature of walking with a Fourier transform of sensor streams and show how one can map this representation to energy expenditure (as measured by V O2 consumption, mL/min) using three regression techniques - Least Squares Regression (LSR), Bayesian Linear Regression (BLR) and Gaussian Process Regression (GPR). We perform a comparative analysis of the accuracy of sensor streams in predicting energy expenditure (measured by RMS prediction accuracy). Triaxial information is more accurate than uniaxial information. LSR based approaches are prone to outlier sensitivity and overfitting. Gyroscopic information showed equivalent if not better prediction accuracy as compared to accelerometers. Combining accelerometer and gyroscopic information provided better accuracy than using either sensor alone. We also analyze the best algorithmic approach among linear and nonlinear methods as measured by RMS prediction accuracy and run time. Nonlinear regression methods showed better prediction accuracy but required an order of magnitude of run time. This paper emphasizes the role of probabilistic techniques in conjunction with joint modeling of triaxial accelerations and rotational rates to improve energy expenditure prediction for steady-state treadmill walking. PMID:21690001

Effect of genetic architecture on the prediction accuracy of quantitative traits in samples of unrelated individuals.

PubMed

Morgante, Fabio; Huang, Wen; Maltecca, Christian; Mackay, Trudy F C

2018-06-01

Predicting complex phenotypes from genomic data is a fundamental aim of animal and plant breeding, where we wish to predict genetic merits of selection candidates; and of human genetics, where we wish to predict disease risk. While genomic prediction models work well with populations of related individuals and high linkage disequilibrium (LD) (e.g., livestock), comparable models perform poorly for populations of unrelated individuals and low LD (e.g., humans). We hypothesized that low prediction accuracies in the latter situation may occur when the genetics architecture of the trait departs from the infinitesimal and additive architecture assumed by most prediction models. We used simulated data for 10,000 lines based on sequence data from a population of unrelated, inbred Drosophila melanogaster lines to evaluate this hypothesis. We show that, even in very simplified scenarios meant as a stress test of the commonly used Genomic Best Linear Unbiased Predictor (G-BLUP) method, using all common variants yields low prediction accuracy regardless of the trait genetic architecture. However, prediction accuracy increases when predictions are informed by the genetic architecture inferred from mapping the top variants affecting main effects and interactions in the training data, provided there is sufficient power for mapping. When the true genetic architecture is largely or partially due to epistatic interactions, the additive model may not perform well, while models that account explicitly for interactions generally increase prediction accuracy. Our results indicate that accounting for genetic architecture can improve prediction accuracy for quantitative traits.

Orion Pad Abort 1 Flight Test: Simulation Predictions Versus Flight Data

NASA Technical Reports Server (NTRS)

Stillwater, Ryan Allanque; Merritt, Deborah S.

2011-01-01

The presentation covers the pre-flight simulation predictions of the Orion Pad Abort 1. The pre-flight simulation predictions are compared to the Orion Pad Abort 1 flight test data. Finally the flight test data is compared to the updated simulation predictions, which show a ove rall improvement in the accuracy of the simulation predictions.

Medium- and Long-term Prediction of LOD Change by the Leap-step Autoregressive Model

NASA Astrophysics Data System (ADS)

Wang, Qijie

2015-08-01

The accuracy of medium- and long-term prediction of length of day (LOD) change base on combined least-square and autoregressive (LS+AR) deteriorates gradually. Leap-step autoregressive (LSAR) model can significantly reduce the edge effect of the observation sequence. Especially, LSAR model greatly improves the resolution of signals’ low-frequency components. Therefore, it can improve the efficiency of prediction. In this work, LSAR is used to forecast the LOD change. The LOD series from EOP 08 C04 provided by IERS is modeled by both the LSAR and AR models. The results of the two models are analyzed and compared. When the prediction length is between 10-30 days, the accuracy improvement is less than 10%. When the prediction length amounts to above 30 day, the accuracy improved obviously, with the maximum being around 19%. The results show that the LSAR model has higher prediction accuracy and stability in medium- and long-term prediction.

Quantitative fetal fibronectin and cervical length to predict preterm birth in asymptomatic women with previous cervical surgery.

PubMed

Vandermolen, Brooke I; Hezelgrave, Natasha L; Smout, Elizabeth M; Abbott, Danielle S; Seed, Paul T; Shennan, Andrew H

2016-10-01

Quantitative fetal fibronectin testing has demonstrated accuracy for prediction of spontaneous preterm birth in asymptomatic women with a history of preterm birth. Predictive accuracy in women with previous cervical surgery (a potentially different risk mechanism) is not known. We sought to compare the predictive accuracy of cervicovaginal fluid quantitative fetal fibronectin and cervical length testing in asymptomatic women with previous cervical surgery to that in women with 1 previous preterm birth. We conducted a prospective blinded secondary analysis of a larger observational study of cervicovaginal fluid quantitative fetal fibronectin concentration in asymptomatic women measured with a Hologic 10Q system (Hologic, Marlborough, MA). Prediction of spontaneous preterm birth (<30, <34, and <37 weeks) with cervicovaginal fluid quantitative fetal fibronectin concentration in primiparous women who had undergone at least 1 invasive cervical procedure (n = 473) was compared with prediction in women who had previous spontaneous preterm birth, preterm prelabor rupture of membranes, or late miscarriage (n = 821). Relationship with cervical length was explored. The rate of spontaneous preterm birth <34 weeks in the cervical surgery group was 3% compared with 9% in previous spontaneous preterm birth group. Receiver operating characteristic curves comparing quantitative fetal fibronectin for prediction at all 3 gestational end points were comparable between the cervical surgery and previous spontaneous preterm birth groups (34 weeks: area under the curve, 0.78 [95% confidence interval 0.64-0.93] vs 0.71 [95% confidence interval 0.64-0.78]; P = .39). Prediction of spontaneous preterm birth using cervical length compared with quantitative fetal fibronectin for prediction of preterm birth <34 weeks of gestation offered similar prediction (area under the curve, 0.88 [95% confidence interval 0.79-0.96] vs 0.77 [95% confidence interval 0.62-0.92], P = .12 in the cervical surgery group; and 0.77 [95% confidence interval 0.70-0.84] vs 0.74 [95% confidence interval 0.67-0.81], P = .32 in the previous spontaneous preterm birth group). Prediction of spontaneous preterm birth using cervicovaginal fluid quantitative fetal fibronectin in asymptomatic women with cervical surgery is valid, and has comparative accuracy to that in women with a history of spontaneous preterm birth. Copyright © 2016 Elsevier Inc. All rights reserved.

Predictive Validity and Accuracy of Oral Reading Fluency for English Learners

ERIC Educational Resources Information Center

Vanderwood, Michael L.; Tung, Catherine Y.; Checca, C. Jason

2014-01-01

The predictive validity and accuracy of an oral reading fluency (ORF) measure for a statewide assessment in English language arts was examined for second-grade native English speakers (NESs) and English learners (ELs) with varying levels of English proficiency. In addition to comparing ELs with native English speakers, the impact of English…

Genomic Prediction of Gene Bank Wheat Landraces

PubMed Central

Crossa, José; Jarquín, Diego; Franco, Jorge; Pérez-Rodríguez, Paulino; Burgueño, Juan; Saint-Pierre, Carolina; Vikram, Prashant; Sansaloni, Carolina; Petroli, Cesar; Akdemir, Deniz; Sneller, Clay; Reynolds, Matthew; Tattaris, Maria; Payne, Thomas; Guzman, Carlos; Peña, Roberto J.; Wenzl, Peter; Singh, Sukhwinder

2016-01-01

This study examines genomic prediction within 8416 Mexican landrace accessions and 2403 Iranian landrace accessions stored in gene banks. The Mexican and Iranian collections were evaluated in separate field trials, including an optimum environment for several traits, and in two separate environments (drought, D and heat, H) for the highly heritable traits, days to heading (DTH), and days to maturity (DTM). Analyses accounting and not accounting for population structure were performed. Genomic prediction models include genotype × environment interaction (G × E). Two alternative prediction strategies were studied: (1) random cross-validation of the data in 20% training (TRN) and 80% testing (TST) (TRN20-TST80) sets, and (2) two types of core sets, “diversity” and “prediction”, including 10% and 20%, respectively, of the total collections. Accounting for population structure decreased prediction accuracy by 15–20% as compared to prediction accuracy obtained when not accounting for population structure. Accounting for population structure gave prediction accuracies for traits evaluated in one environment for TRN20-TST80 that ranged from 0.407 to 0.677 for Mexican landraces, and from 0.166 to 0.662 for Iranian landraces. Prediction accuracy of the 20% diversity core set was similar to accuracies obtained for TRN20-TST80, ranging from 0.412 to 0.654 for Mexican landraces, and from 0.182 to 0.647 for Iranian landraces. The predictive core set gave similar prediction accuracy as the diversity core set for Mexican collections, but slightly lower for Iranian collections. Prediction accuracy when incorporating G × E for DTH and DTM for Mexican landraces for TRN20-TST80 was around 0.60, which is greater than without the G × E term. For Iranian landraces, accuracies were 0.55 for the G × E model with TRN20-TST80. Results show promising prediction accuracies for potential use in germplasm enhancement and rapid introgression of exotic germplasm into elite materials. PMID:27172218

Validity of Predictive Equations for Resting Energy Expenditure Developed for Obese Patients: Impact of Body Composition Method

PubMed Central

Achamrah, Najate; Jésus, Pierre; Grigioni, Sébastien; Rimbert, Agnès; Petit, André; Déchelotte, Pierre; Folope, Vanessa; Coëffier, Moïse

2018-01-01

Predictive equations have been specifically developed for obese patients to estimate resting energy expenditure (REE). Body composition (BC) assessment is needed for some of these equations. We assessed the impact of BC methods on the accuracy of specific predictive equations developed in obese patients. REE was measured (mREE) by indirect calorimetry and BC assessed by bioelectrical impedance analysis (BIA) and dual-energy X-ray absorptiometry (DXA). mREE, percentages of prediction accuracy (±10% of mREE) were compared. Predictive equations were studied in 2588 obese patients. Mean mREE was 1788 ± 6.3 kcal/24 h. Only the Müller (BIA) and Harris & Benedict (HB) equations provided REE with no difference from mREE. The Huang, Müller, Horie-Waitzberg, and HB formulas provided a higher accurate prediction (>60% of cases). The use of BIA provided better predictions of REE than DXA for the Huang and Müller equations. Inversely, the Horie-Waitzberg and Lazzer formulas provided a higher accuracy using DXA. Accuracy decreased when applied to patients with BMI ≥ 40, except for the Horie-Waitzberg and Lazzer (DXA) formulas. Müller equations based on BIA provided a marked improvement of REE prediction accuracy than equations not based on BC. The interest of BC to improve REE predictive equations accuracy in obese patients should be confirmed. PMID:29320432

Accuracy of Predicted Genomic Breeding Values in Purebred and Crossbred Pigs.

PubMed

Hidalgo, André M; Bastiaansen, John W M; Lopes, Marcos S; Harlizius, Barbara; Groenen, Martien A M; de Koning, Dirk-Jan

2015-05-26

Genomic selection has been widely implemented in dairy cattle breeding when the aim is to improve performance of purebred animals. In pigs, however, the final product is a crossbred animal. This may affect the efficiency of methods that are currently implemented for dairy cattle. Therefore, the objective of this study was to determine the accuracy of predicted breeding values in crossbred pigs using purebred genomic and phenotypic data. A second objective was to compare the predictive ability of SNPs when training is done in either single or multiple populations for four traits: age at first insemination (AFI); total number of piglets born (TNB); litter birth weight (LBW); and litter variation (LVR). We performed marker-based and pedigree-based predictions. Within-population predictions for the four traits ranged from 0.21 to 0.72. Multi-population prediction yielded accuracies ranging from 0.18 to 0.67. Predictions across purebred populations as well as predicting genetic merit of crossbreds from their purebred parental lines for AFI performed poorly (not significantly different from zero). In contrast, accuracies of across-population predictions and accuracies of purebred to crossbred predictions for LBW and LVR ranged from 0.08 to 0.31 and 0.11 to 0.31, respectively. Accuracy for TNB was zero for across-population prediction, whereas for purebred to crossbred prediction it ranged from 0.08 to 0.22. In general, marker-based outperformed pedigree-based prediction across populations and traits. However, in some cases pedigree-based prediction performed similarly or outperformed marker-based prediction. There was predictive ability when purebred populations were used to predict crossbred genetic merit using an additive model in the populations studied. AFI was the only exception, indicating that predictive ability depends largely on the genetic correlation between PB and CB performance, which was 0.31 for AFI. Multi-population prediction was no better than within-population prediction for the purebred validation set. Accuracy of prediction was very trait-dependent. Copyright © 2015 Hidalgo et al.

Genomic Prediction of Seed Quality Traits Using Advanced Barley Breeding Lines.

PubMed

Nielsen, Nanna Hellum; Jahoor, Ahmed; Jensen, Jens Due; Orabi, Jihad; Cericola, Fabio; Edriss, Vahid; Jensen, Just

2016-01-01

Genomic selection was recently introduced in plant breeding. The objective of this study was to develop genomic prediction for important seed quality parameters in spring barley. The aim was to predict breeding values without expensive phenotyping of large sets of lines. A total number of 309 advanced spring barley lines tested at two locations each with three replicates were phenotyped and each line was genotyped by Illumina iSelect 9Kbarley chip. The population originated from two different breeding sets, which were phenotyped in two different years. Phenotypic measurements considered were: seed size, protein content, protein yield, test weight and ergosterol content. A leave-one-out cross-validation strategy revealed high prediction accuracies ranging between 0.40 and 0.83. Prediction across breeding sets resulted in reduced accuracies compared to the leave-one-out strategy. Furthermore, predicting across full and half-sib-families resulted in reduced prediction accuracies. Additionally, predictions were performed using reduced marker sets and reduced training population sets. In conclusion, using less than 200 lines in the training set can result in low prediction accuracy, and the accuracy will then be highly dependent on the family structure of the selected training set. However, the results also indicate that relatively small training sets (200 lines) are sufficient for genomic prediction in commercial barley breeding. In addition, our results indicate a minimum marker set of 1,000 to decrease the risk of low prediction accuracy for some traits or some families.

Genomic Prediction of Seed Quality Traits Using Advanced Barley Breeding Lines

PubMed Central

Nielsen, Nanna Hellum; Jahoor, Ahmed; Jensen, Jens Due; Orabi, Jihad; Cericola, Fabio; Edriss, Vahid; Jensen, Just

2016-01-01

Genomic selection was recently introduced in plant breeding. The objective of this study was to develop genomic prediction for important seed quality parameters in spring barley. The aim was to predict breeding values without expensive phenotyping of large sets of lines. A total number of 309 advanced spring barley lines tested at two locations each with three replicates were phenotyped and each line was genotyped by Illumina iSelect 9Kbarley chip. The population originated from two different breeding sets, which were phenotyped in two different years. Phenotypic measurements considered were: seed size, protein content, protein yield, test weight and ergosterol content. A leave-one-out cross-validation strategy revealed high prediction accuracies ranging between 0.40 and 0.83. Prediction across breeding sets resulted in reduced accuracies compared to the leave-one-out strategy. Furthermore, predicting across full and half-sib-families resulted in reduced prediction accuracies. Additionally, predictions were performed using reduced marker sets and reduced training population sets. In conclusion, using less than 200 lines in the training set can result in low prediction accuracy, and the accuracy will then be highly dependent on the family structure of the selected training set. However, the results also indicate that relatively small training sets (200 lines) are sufficient for genomic prediction in commercial barley breeding. In addition, our results indicate a minimum marker set of 1,000 to decrease the risk of low prediction accuracy for some traits or some families. PMID:27783639

Improving Fermi Orbit Determination and Prediction in an Uncertain Atmospheric Drag Environment

NASA Technical Reports Server (NTRS)

Vavrina, Matthew A.; Newman, Clark P.; Slojkowski, Steven E.; Carpenter, J. Russell

2014-01-01

Orbit determination and prediction of the Fermi Gamma-ray Space Telescope trajectory is strongly impacted by the unpredictability and variability of atmospheric density and the spacecraft's ballistic coefficient. Operationally, Global Positioning System point solutions are processed with an extended Kalman filter for orbit determination, and predictions are generated for conjunction assessment with secondary objects. When these predictions are compared to Joint Space Operations Center radar-based solutions, the close approach distance between the two predictions can greatly differ ahead of the conjunction. This work explores strategies for improving prediction accuracy and helps to explain the prediction disparities. Namely, a tuning analysis is performed to determine atmospheric drag modeling and filter parameters that can improve orbit determination as well as prediction accuracy. A 45% improvement in three-day prediction accuracy is realized by tuning the ballistic coefficient and atmospheric density stochastic models, measurement frequency, and other modeling and filter parameters.

PPCM: Combing multiple classifiers to improve protein-protein interaction prediction

DOE PAGES

Yao, Jianzhuang; Guo, Hong; Yang, Xiaohan

2015-08-01

Determining protein-protein interaction (PPI) in biological systems is of considerable importance, and prediction of PPI has become a popular research area. Although different classifiers have been developed for PPI prediction, no single classifier seems to be able to predict PPI with high confidence. We postulated that by combining individual classifiers the accuracy of PPI prediction could be improved. We developed a method called protein-protein interaction prediction classifiers merger (PPCM), and this method combines output from two PPI prediction tools, GO2PPI and Phyloprof, using Random Forests algorithm. The performance of PPCM was tested by area under the curve (AUC) using anmore » assembled Gold Standard database that contains both positive and negative PPI pairs. Our AUC test showed that PPCM significantly improved the PPI prediction accuracy over the corresponding individual classifiers. We found that additional classifiers incorporated into PPCM could lead to further improvement in the PPI prediction accuracy. Furthermore, cross species PPCM could achieve competitive and even better prediction accuracy compared to the single species PPCM. This study established a robust pipeline for PPI prediction by integrating multiple classifiers using Random Forests algorithm. Ultimately, this pipeline will be useful for predicting PPI in nonmodel species.« less

The novel application of artificial neural network on bioelectrical impedance analysis to assess the body composition in elderly

PubMed Central

2013-01-01

Background This study aims to improve accuracy of Bioelectrical Impedance Analysis (BIA) prediction equations for estimating fat free mass (FFM) of the elderly by using non-linear Back Propagation Artificial Neural Network (BP-ANN) model and to compare the predictive accuracy with the linear regression model by using energy dual X-ray absorptiometry (DXA) as reference method. Methods A total of 88 Taiwanese elderly adults were recruited in this study as subjects. Linear regression equations and BP-ANN prediction equation were developed using impedances and other anthropometrics for predicting the reference FFM measured by DXA (FFMDXA) in 36 male and 26 female Taiwanese elderly adults. The FFM estimated by BIA prediction equations using traditional linear regression model (FFMLR) and BP-ANN model (FFMANN) were compared to the FFMDXA. The measuring results of an additional 26 elderly adults were used to validate than accuracy of the predictive models. Results The results showed the significant predictors were impedance, gender, age, height and weight in developed FFMLR linear model (LR) for predicting FFM (coefficient of determination, r2 = 0.940; standard error of estimate (SEE) = 2.729 kg; root mean square error (RMSE) = 2.571kg, P < 0.001). The above predictors were set as the variables of the input layer by using five neurons in the BP-ANN model (r2 = 0.987 with a SD = 1.192 kg and relatively lower RMSE = 1.183 kg), which had greater (improved) accuracy for estimating FFM when compared with linear model. The results showed a better agreement existed between FFMANN and FFMDXA than that between FFMLR and FFMDXA. Conclusion When compared the performance of developed prediction equations for estimating reference FFMDXA, the linear model has lower r2 with a larger SD in predictive results than that of BP-ANN model, which indicated ANN model is more suitable for estimating FFM. PMID:23388042

Predicting Survival From Large Echocardiography and Electronic Health Record Datasets: Optimization With Machine Learning.

PubMed

Samad, Manar D; Ulloa, Alvaro; Wehner, Gregory J; Jing, Linyuan; Hartzel, Dustin; Good, Christopher W; Williams, Brent A; Haggerty, Christopher M; Fornwalt, Brandon K

2018-06-09

The goal of this study was to use machine learning to more accurately predict survival after echocardiography. Predicting patient outcomes (e.g., survival) following echocardiography is primarily based on ejection fraction (EF) and comorbidities. However, there may be significant predictive information within additional echocardiography-derived measurements combined with clinical electronic health record data. Mortality was studied in 171,510 unselected patients who underwent 331,317 echocardiograms in a large regional health system. We investigated the predictive performance of nonlinear machine learning models compared with that of linear logistic regression models using 3 different inputs: 1) clinical variables, including 90 cardiovascular-relevant International Classification of Diseases, Tenth Revision, codes, and age, sex, height, weight, heart rate, blood pressures, low-density lipoprotein, high-density lipoprotein, and smoking; 2) clinical variables plus physician-reported EF; and 3) clinical variables and EF, plus 57 additional echocardiographic measurements. Missing data were imputed with a multivariate imputation by using a chained equations algorithm (MICE). We compared models versus each other and baseline clinical scoring systems by using a mean area under the curve (AUC) over 10 cross-validation folds and across 10 survival durations (6 to 60 months). Machine learning models achieved significantly higher prediction accuracy (all AUC >0.82) over common clinical risk scores (AUC = 0.61 to 0.79), with the nonlinear random forest models outperforming logistic regression (p < 0.01). The random forest model including all echocardiographic measurements yielded the highest prediction accuracy (p < 0.01 across all models and survival durations). Only 10 variables were needed to achieve 96% of the maximum prediction accuracy, with 6 of these variables being derived from echocardiography. Tricuspid regurgitation velocity was more predictive of survival than LVEF. In a subset of studies with complete data for the top 10 variables, multivariate imputation by chained equations yielded slightly reduced predictive accuracies (difference in AUC of 0.003) compared with the original data. Machine learning can fully utilize large combinations of disparate input variables to predict survival after echocardiography with superior accuracy. Copyright © 2018 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.

What is the Best Model Specification and Earth Observation Product for Predicting Regional Grain Yields in Food Insecure Countries?

NASA Astrophysics Data System (ADS)

Davenport, F., IV; Harrison, L.; Shukla, S.; Husak, G. J.; Funk, C. C.

2017-12-01

We evaluate the predictive accuracy of an ensemble of empirical model specifications that use earth observation data to predict sub-national grain yields in Mexico and East Africa. Products that are actively used for seasonal drought monitoring are tested as yield predictors. Our research is driven by the fact that East Africa is a region where decisions regarding agricultural production are critical to preventing the loss of economic livelihoods and human life. Regional grain yield forecasts can be used to anticipate availability and prices of key staples, which can turn can inform decisions about targeting humanitarian response such as food aid. Our objective is to identify-for a given region, grain, and time year- what type of model and/or earth observation can most accurately predict end of season yields. We fit a set of models to county level panel data from Mexico, Kenya, Sudan, South Sudan, and Somalia. We then examine out of sample predicative accuracy using various linear and non-linear models that incorporate spatial and time varying coefficients. We compare accuracy within and across models that use predictor variables from remotely sensed measures of precipitation, temperature, soil moisture, and other land surface processes. We also examine at what point in the season a given model or product is most useful for determining predictive accuracy. Finally we compare predictive accuracy across a variety of agricultural regimes including high intensity irrigated commercial agricultural and rain fed subsistence level farms.

Influence of outliers on accuracy estimation in genomic prediction in plant breeding.

PubMed

Estaghvirou, Sidi Boubacar Ould; Ogutu, Joseph O; Piepho, Hans-Peter

2014-10-01

Outliers often pose problems in analyses of data in plant breeding, but their influence on the performance of methods for estimating predictive accuracy in genomic prediction studies has not yet been evaluated. Here, we evaluate the influence of outliers on the performance of methods for accuracy estimation in genomic prediction studies using simulation. We simulated 1000 datasets for each of 10 scenarios to evaluate the influence of outliers on the performance of seven methods for estimating accuracy. These scenarios are defined by the number of genotypes, marker effect variance, and magnitude of outliers. To mimic outliers, we added to one observation in each simulated dataset, in turn, 5-, 8-, and 10-times the error SD used to simulate small and large phenotypic datasets. The effect of outliers on accuracy estimation was evaluated by comparing deviations in the estimated and true accuracies for datasets with and without outliers. Outliers adversely influenced accuracy estimation, more so at small values of genetic variance or number of genotypes. A method for estimating heritability and predictive accuracy in plant breeding and another used to estimate accuracy in animal breeding were the most accurate and resistant to outliers across all scenarios and are therefore preferable for accuracy estimation in genomic prediction studies. The performances of the other five methods that use cross-validation were less consistent and varied widely across scenarios. The computing time for the methods increased as the size of outliers and sample size increased and the genetic variance decreased. Copyright © 2014 Ould Estaghvirou et al.

Longitudinal Temporal and Probabilistic Prediction of Survival in a Cohort of Patients With Advanced Cancer

PubMed Central

Perez-Cruz, Pedro E.; dos Santos, Renata; Silva, Thiago Buosi; Crovador, Camila Souza; Nascimento, Maria Salete de Angelis; Hall, Stacy; Fajardo, Julieta; Bruera, Eduardo; Hui, David

2014-01-01

Context Survival prognostication is important during end-of-life. The accuracy of clinician prediction of survival (CPS) over time has not been well characterized. Objectives To examine changes in prognostication accuracy during the last 14 days of life in a cohort of patients with advanced cancer admitted to two acute palliative care units and to compare the accuracy between the temporal and probabilistic approaches. Methods Physicians and nurses prognosticated survival daily for cancer patients in two hospitals until death/discharge using two prognostic approaches: temporal and probabilistic. We assessed accuracy for each method daily during the last 14 days of life comparing accuracy at day −14 (baseline) with accuracy at each time point using a test of proportions. Results 6718 temporal and 6621 probabilistic estimations were provided by physicians and nurses for 311 patients, respectively. Median (interquartile range) survival was 8 (4, 20) days. Temporal CPS had low accuracy (10–40%) and did not change over time. In contrast, probabilistic CPS was significantly more accurate (p<.05 at each time point) but decreased close to death. Conclusion Probabilistic CPS was consistently more accurate than temporal CPS over the last 14 days of life; however, its accuracy decreased as patients approached death. Our findings suggest that better tools to predict impending death are necessary. PMID:24746583

The use of genomic information increases the accuracy of breeding value predictions for sea louse (Caligus rogercresseyi) resistance in Atlantic salmon (Salmo salar).

PubMed

Correa, Katharina; Bangera, Rama; Figueroa, René; Lhorente, Jean P; Yáñez, José M

2017-01-31

Sea lice infestations caused by Caligus rogercresseyi are a main concern to the salmon farming industry due to associated economic losses. Resistance to this parasite was shown to have low to moderate genetic variation and its genetic architecture was suggested to be polygenic. The aim of this study was to compare accuracies of breeding value predictions obtained with pedigree-based best linear unbiased prediction (P-BLUP) methodology against different genomic prediction approaches: genomic BLUP (G-BLUP), Bayesian Lasso, and Bayes C. To achieve this, 2404 individuals from 118 families were measured for C. rogercresseyi count after a challenge and genotyped using 37 K single nucleotide polymorphisms. Accuracies were assessed using fivefold cross-validation and SNP densities of 0.5, 1, 5, 10, 25 and 37 K. Accuracy of genomic predictions increased with increasing SNP density and was higher than pedigree-based BLUP predictions by up to 22%. Both Bayesian and G-BLUP methods can predict breeding values with higher accuracies than pedigree-based BLUP, however, G-BLUP may be the preferred method because of reduced computation time and ease of implementation. A relatively low marker density (i.e. 10 K) is sufficient for maximal increase in accuracy when using G-BLUP or Bayesian methods for genomic prediction of C. rogercresseyi resistance in Atlantic salmon.

Researches on High Accuracy Prediction Methods of Earth Orientation Parameters

NASA Astrophysics Data System (ADS)

Xu, X. Q.

2015-09-01

The Earth rotation reflects the coupling process among the solid Earth, atmosphere, oceans, mantle, and core of the Earth on multiple spatial and temporal scales. The Earth rotation can be described by the Earth's orientation parameters, which are abbreviated as EOP (mainly including two polar motion components PM_X and PM_Y, and variation in the length of day ΔLOD). The EOP is crucial in the transformation between the terrestrial and celestial reference systems, and has important applications in many areas such as the deep space exploration, satellite precise orbit determination, and astrogeodynamics. However, the EOP products obtained by the space geodetic technologies generally delay by several days to two weeks. The growing demands for modern space navigation make high-accuracy EOP prediction be a worthy topic. This thesis is composed of the following three aspects, for the purpose of improving the EOP forecast accuracy. (1) We analyze the relation between the length of the basic data series and the EOP forecast accuracy, and compare the EOP prediction accuracy for the linear autoregressive (AR) model and the nonlinear artificial neural network (ANN) method by performing the least squares (LS) extrapolations. The results show that the high precision forecast of EOP can be realized by appropriate selection of the basic data series length according to the required time span of EOP prediction: for short-term prediction, the basic data series should be shorter, while for the long-term prediction, the series should be longer. The analysis also showed that the LS+AR model is more suitable for the short-term forecasts, while the LS+ANN model shows the advantages in the medium- and long-term forecasts. (2) We develop for the first time a new method which combines the autoregressive model and Kalman filter (AR+Kalman) in short-term EOP prediction. The equations of observation and state are established using the EOP series and the autoregressive coefficients respectively, which are used to improve/re-evaluate the AR model. Comparing to the single AR model, the AR+Kalman method performs better in the prediction of UT1-UTC and ΔLOD, and the improvement in the prediction of the polar motion is significant. (3) Following the successful Earth Orientation Parameter Prediction Comparison Campaign (EOP PCC), the Earth Orientation Parameter Combination of Prediction Pilot Project (EOPC PPP) was sponsored in 2010. As one of the participants from China, we update and submit the short- and medium-term (1 to 90 days) EOP predictions every day. From the current comparative statistics, our prediction accuracy is on the medium international level. We will carry out more innovative researches to improve the EOP forecast accuracy and enhance our level in EOP forecast.

Can nutrient status of four woody plant species be predicted using field spectrometry?

NASA Astrophysics Data System (ADS)

Ferwerda, Jelle G.; Skidmore, Andrew K.

This paper demonstrates the potential of hyperspectral remote sensing to predict the chemical composition (i.e., nitrogen, phosphorous, calcium, potassium, sodium, and magnesium) of three tree species (i.e., willow, mopane and olive) and one shrub species (i.e., heather). Reflectance spectra, derivative spectra and continuum-removed spectra were compared in terms of predictive power. Results showed that the best predictions for nitrogen, phosphorous, and magnesium occur when using derivative spectra, and the best predictions for sodium, potassium, and calcium occur when using continuum-removed data. To test whether a general model for multiple species is also valid for individual species, a bootstrapping routine was applied. Prediction accuracies for the individual species were lower then prediction accuracies obtained for the combined dataset for all except one element/species combination, indicating that indices with high prediction accuracies at the landscape scale are less appropriate to detect the chemical content of individual species.

Developing Local Oral Reading Fluency Cut Scores for Predicting High-Stakes Test Performance

ERIC Educational Resources Information Center

Grapin, Sally L.; Kranzler, John H.; Waldron, Nancy; Joyce-Beaulieu, Diana; Algina, James

2017-01-01

This study evaluated the classification accuracy of a second grade oral reading fluency curriculum-based measure (R-CBM) in predicting third grade state test performance. It also compared the long-term classification accuracy of local and publisher-recommended R-CBM cut scores. Participants were 266 students who were divided into a calibration…

Genomic Prediction Accounting for Residual Heteroskedasticity

PubMed Central

Ou, Zhining; Tempelman, Robert J.; Steibel, Juan P.; Ernst, Catherine W.; Bates, Ronald O.; Bello, Nora M.

2015-01-01

Whole-genome prediction (WGP) models that use single-nucleotide polymorphism marker information to predict genetic merit of animals and plants typically assume homogeneous residual variance. However, variability is often heterogeneous across agricultural production systems and may subsequently bias WGP-based inferences. This study extends classical WGP models based on normality, heavy-tailed specifications and variable selection to explicitly account for environmentally-driven residual heteroskedasticity under a hierarchical Bayesian mixed-models framework. WGP models assuming homogeneous or heterogeneous residual variances were fitted to training data generated under simulation scenarios reflecting a gradient of increasing heteroskedasticity. Model fit was based on pseudo-Bayes factors and also on prediction accuracy of genomic breeding values computed on a validation data subset one generation removed from the simulated training dataset. Homogeneous vs. heterogeneous residual variance WGP models were also fitted to two quantitative traits, namely 45-min postmortem carcass temperature and loin muscle pH, recorded in a swine resource population dataset prescreened for high and mild residual heteroskedasticity, respectively. Fit of competing WGP models was compared using pseudo-Bayes factors. Predictive ability, defined as the correlation between predicted and observed phenotypes in validation sets of a five-fold cross-validation was also computed. Heteroskedastic error WGP models showed improved model fit and enhanced prediction accuracy compared to homoskedastic error WGP models although the magnitude of the improvement was small (less than two percentage points net gain in prediction accuracy). Nevertheless, accounting for residual heteroskedasticity did improve accuracy of selection, especially on individuals of extreme genetic merit. PMID:26564950

Artificial neural network modeling using clinical and knowledge independent variables predicts salt intake reduction behavior

PubMed Central

Isma’eel, Hussain A.; Sakr, George E.; Almedawar, Mohamad M.; Fathallah, Jihan; Garabedian, Torkom; Eddine, Savo Bou Zein

2015-01-01

Background High dietary salt intake is directly linked to hypertension and cardiovascular diseases (CVDs). Predicting behaviors regarding salt intake habits is vital to guide interventions and increase their effectiveness. We aim to compare the accuracy of an artificial neural network (ANN) based tool that predicts behavior from key knowledge questions along with clinical data in a high cardiovascular risk cohort relative to the least square models (LSM) method. Methods We collected knowledge, attitude and behavior data on 115 patients. A behavior score was calculated to classify patients’ behavior towards reducing salt intake. Accuracy comparison between ANN and regression analysis was calculated using the bootstrap technique with 200 iterations. Results Starting from a 69-item questionnaire, a reduced model was developed and included eight knowledge items found to result in the highest accuracy of 62% CI (58-67%). The best prediction accuracy in the full and reduced models was attained by ANN at 66% and 62%, respectively, compared to full and reduced LSM at 40% and 34%, respectively. The average relative increase in accuracy over all in the full and reduced models is 82% and 102%, respectively. Conclusions Using ANN modeling, we can predict salt reduction behaviors with 66% accuracy. The statistical model has been implemented in an online calculator and can be used in clinics to estimate the patient’s behavior. This will help implementation in future research to further prove clinical utility of this tool to guide therapeutic salt reduction interventions in high cardiovascular risk individuals. PMID:26090333

Genomic selection for crossbred performance accounting for breed-specific effects.

PubMed

Lopes, Marcos S; Bovenhuis, Henk; Hidalgo, André M; van Arendonk, Johan A M; Knol, Egbert F; Bastiaansen, John W M

2017-06-26

Breed-specific effects are observed when the same allele of a given genetic marker has a different effect depending on its breed origin, which results in different allele substitution effects across breeds. In such a case, single-breed breeding values may not be the most accurate predictors of crossbred performance. Our aim was to estimate the contribution of alleles from each parental breed to the genetic variance of traits that are measured in crossbred offspring, and to compare the prediction accuracies of estimated direct genomic values (DGV) from a traditional genomic selection model (GS) that are trained on purebred or crossbred data, with accuracies of DGV from a model that accounts for breed-specific effects (BS), trained on purebred or crossbred data. The final dataset was composed of 924 Large White, 924 Landrace and 924 two-way cross (F1) genotyped and phenotyped animals. The traits evaluated were litter size (LS) and gestation length (GL) in pigs. The genetic correlation between purebred and crossbred performance was higher than 0.88 for both LS and GL. For both traits, the additive genetic variance was larger for alleles inherited from the Large White breed compared to alleles inherited from the Landrace breed (0.74 and 0.56 for LS, and 0.42 and 0.40 for GL, respectively). The highest prediction accuracies of crossbred performance were obtained when training was done on crossbred data. For LS, prediction accuracies were the same for GS and BS DGV (0.23), while for GL, prediction accuracy for BS DGV was similar to the accuracy of GS DGV (0.53 and 0.52, respectively). In this study, training on crossbred data resulted in higher prediction accuracy than training on purebred data and evidence of breed-specific effects for LS and GL was demonstrated. However, when training was done on crossbred data, both GS and BS models resulted in similar prediction accuracies. In future studies, traits with a lower genetic correlation between purebred and crossbred performance should be included to further assess the value of the BS model in genomic predictions.

Parameter prediction based on Improved Process neural network and ARMA error compensation in Evaporation Process

NASA Astrophysics Data System (ADS)

Qian, Xiaoshan

2018-01-01

The traditional model of evaporation process parameters have continuity and cumulative characteristics of the prediction error larger issues, based on the basis of the process proposed an adaptive particle swarm neural network forecasting method parameters established on the autoregressive moving average (ARMA) error correction procedure compensated prediction model to predict the results of the neural network to improve prediction accuracy. Taking a alumina plant evaporation process to analyze production data validation, and compared with the traditional model, the new model prediction accuracy greatly improved, can be used to predict the dynamic process of evaporation of sodium aluminate solution components.

A comparison of accuracy validation methods for genomic and pedigree-based predictions of swine litter size traits using Large White and simulated data.

PubMed

Putz, A M; Tiezzi, F; Maltecca, C; Gray, K A; Knauer, M T

2018-02-01

The objective of this study was to compare and determine the optimal validation method when comparing accuracy from single-step GBLUP (ssGBLUP) to traditional pedigree-based BLUP. Field data included six litter size traits. Simulated data included ten replicates designed to mimic the field data in order to determine the method that was closest to the true accuracy. Data were split into training and validation sets. The methods used were as follows: (i) theoretical accuracy derived from the prediction error variance (PEV) of the direct inverse (iLHS), (ii) approximated accuracies from the accf90(GS) program in the BLUPF90 family of programs (Approx), (iii) correlation between predictions and the single-step GEBVs from the full data set (GEBV Full ), (iv) correlation between predictions and the corrected phenotypes of females from the full data set (Y c ), (v) correlation from method iv divided by the square root of the heritability (Y ch ) and (vi) correlation between sire predictions and the average of their daughters' corrected phenotypes (Y cs ). Accuracies from iLHS increased from 0.27 to 0.37 (37%) in the Large White. Approximation accuracies were very consistent and close in absolute value (0.41 to 0.43). Both iLHS and Approx were much less variable than the corrected phenotype methods (ranging from 0.04 to 0.27). On average, simulated data showed an increase in accuracy from 0.34 to 0.44 (29%) using ssGBLUP. Both iLHS and Y ch approximated the increase well, 0.30 to 0.46 and 0.36 to 0.45, respectively. GEBV Full performed poorly in both data sets and is not recommended. Results suggest that for within-breed selection, theoretical accuracy using PEV was consistent and accurate. When direct inversion is infeasible to get the PEV, correlating predictions to the corrected phenotypes divided by the square root of heritability is adequate given a large enough validation data set. © 2017 Blackwell Verlag GmbH.

Experimental evaluation of radiosity for room sound-field prediction.

PubMed

Hodgson, Murray; Nosal, Eva-Marie

2006-08-01

An acoustical radiosity model was evaluated for how it performs in predicting real room sound fields. This was done by comparing radiosity predictions with experimental results for three existing rooms--a squash court, a classroom, and an office. Radiosity predictions were also compared with those by ray tracing--a "reference" prediction model--for both specular and diffuse surface reflection. Comparisons were made for detailed and discretized echograms, sound-decay curves, sound-propagation curves, and the variations with frequency of four room-acoustical parameters--EDT, RT, D50, and C80. In general, radiosity and diffuse ray tracing gave very similar predictions. Predictions by specular ray tracing were often very different. Radiosity agreed well with experiment in some cases, less well in others. Definitive conclusions regarding the accuracy with which the rooms were modeled, or the accuracy of the radiosity approach, were difficult to draw. The results suggest that radiosity predicts room sound fields with some accuracy, at least as well as diffuse ray tracing and, in general, better than specular ray tracing. The predictions of detailed echograms are less accurate, those of derived room-acoustical parameters more accurate. The results underline the need to develop experimental methods for accurately characterizing the absorptive and reflective characteristics of room surfaces, possible including phase.

Using Subjective and Objective Measures to Predict Level of Reading Fluency at the End of First Grade

ERIC Educational Resources Information Center

Morris, Darrell; Pennell, Ashley M.; Perney, Jan; Trathen, Woodrow

2018-01-01

This study compared reading rate to reading fluency (as measured by a rating scale). After listening to first graders read short passages, we assigned an overall fluency rating (low, average, or high) to each reading. We then used predictive discriminant analyses to determine which of five measures--accuracy, rate (objective); accuracy, phrasing,…

Analysis of algorithms for predicting canopy fuel

Treesearch

Katharine L. Gray; Elizabeth Reinhardt

2003-01-01

We compared observed canopy fuel characteristics with those predicted by existing biomass algorithms. We specifically examined the accuracy of the biomass equations developed by Brown (1978. We used destructively sampled data obtained at 5 different study areas. We compared predicted and observed quantities of foliage and crown biomass for individual trees in our study...

Improving the Accuracy of Software-Based Energy Analysis for Residential Buildings (Presentation)

DOE Office of Scientific and Technical Information (OSTI.GOV)

Polly, B.

2011-09-01

This presentation describes the basic components of software-based energy analysis for residential buildings, explores the concepts of 'error' and 'accuracy' when analysis predictions are compared to measured data, and explains how NREL is working to continuously improve the accuracy of energy analysis methods.

Mean Platelet Volume, Red Cell Distribution Width to Platelet Count Ratio, Globulin Platelet Index, and 16 Other Indirect Noninvasive Fibrosis Scores: How Much Do Routine Blood Tests Tell About Liver Fibrosis in Chronic Hepatitis C?

PubMed

Thandassery, Ragesh B; Al Kaabi, Saad; Soofi, Madiha E; Mohiuddin, Syed A; John, Anil K; Al Mohannadi, Muneera; Al Ejji, Khalid; Yakoob, Rafie; Derbala, Moutaz F; Wani, Hamidullah; Sharma, Manik; Al Dweik, Nazeeh; Butt, Mohammed T; Kamel, Yasser M; Sultan, Khaleel; Pasic, Fuad; Singh, Rajvir

2016-07-01

Many indirect noninvasive scores to predict liver fibrosis are calculated from routine blood investigations. Only limited studies have compared their efficacy head to head. We aimed to compare these scores with liver biopsy fibrosis stages in patients with chronic hepatitis C. From blood investigations of 1602 patients with chronic hepatitis C who underwent a liver biopsy before initiation of antiviral treatment, 19 simple noninvasive scores were calculated. The area under the receiver operating characteristic curves and diagnostic accuracy of each of these scores were calculated (with reference to the Scheuer staging) and compared. The mean age of the patients was 41.8±9.6 years (1365 men). The most common genotype was genotype 4 (65.6%). Significant fibrosis, advanced fibrosis, and cirrhosis were seen in 65.1%, 25.6, and 6.6% of patients, respectively. All the scores except the aspartate transaminase (AST) alanine transaminase ratio, Pohl score, mean platelet volume, fibro-alpha, and red cell distribution width to platelet count ratio index showed high predictive accuracy for the stages of fibrosis. King's score (cutoff, 17.5) showed the highest predictive accuracy for significant and advanced fibrosis. King's score, Göteborg university cirrhosis index, APRI (the AST/platelet count ratio index), and Fibrosis-4 (FIB-4) had the highest predictive accuracy for cirrhosis, with the APRI (cutoff, 2) and FIB-4 (cutoff, 3.25) showing the highest diagnostic accuracy.We derived the study score 8.5 - 0.2(albumin, g/dL) +0.01(AST, IU/L) -0.02(platelet count, 10/L), which at a cutoff of >4.7 had a predictive accuracy of 0.868 (95% confidence interval, 0.833-0.904) for cirrhosis. King's score for significant and advanced fibrosis and the APRI or FIB-4 score for cirrhosis could be the best simple indirect noninvasive scores.

Genomic prediction of reproduction traits for Merino sheep.

PubMed

Bolormaa, S; Brown, D J; Swan, A A; van der Werf, J H J; Hayes, B J; Daetwyler, H D

2017-06-01

Economically important reproduction traits in sheep, such as number of lambs weaned and litter size, are expressed only in females and later in life after most selection decisions are made, which makes them ideal candidates for genomic selection. Accurate genomic predictions would lead to greater genetic gain for these traits by enabling accurate selection of young rams with high genetic merit. The aim of this study was to design and evaluate the accuracy of a genomic prediction method for female reproduction in sheep using daughter trait deviations (DTD) for sires and ewe phenotypes (when individual ewes were genotyped) for three reproduction traits: number of lambs born (NLB), litter size (LSIZE) and number of lambs weaned. Genomic best linear unbiased prediction (GBLUP), BayesR and pedigree BLUP analyses of the three reproduction traits measured on 5340 sheep (4503 ewes and 837 sires) with real and imputed genotypes for 510 174 SNPs were performed. The prediction of breeding values using both sire and ewe trait records was validated in Merino sheep. Prediction accuracy was evaluated by across sire family and random cross-validations. Accuracies of genomic estimated breeding values (GEBVs) were assessed as the mean Pearson correlation adjusted by the accuracy of the input phenotypes. The addition of sire DTD into the prediction analysis resulted in higher accuracies compared with using only ewe records in genomic predictions or pedigree BLUP. Using GBLUP, the average accuracy based on the combined records (ewes and sire DTD) was 0.43 across traits, but the accuracies varied by trait and type of cross-validations. The accuracies of GEBVs from random cross-validations (range 0.17-0.61) were higher than were those from sire family cross-validations (range 0.00-0.51). The GEBV accuracies of 0.41-0.54 for NLB and LSIZE based on the combined records were amongst the highest in the study. Although BayesR was not significantly different from GBLUP in prediction accuracy, it identified several candidate genes which are known to be associated with NLB and LSIZE. The approach provides a way to make use of all data available in genomic prediction for traits that have limited recording. © 2017 Stichting International Foundation for Animal Genetics.

Longitudinal temporal and probabilistic prediction of survival in a cohort of patients with advanced cancer.

PubMed

Perez-Cruz, Pedro E; Dos Santos, Renata; Silva, Thiago Buosi; Crovador, Camila Souza; Nascimento, Maria Salete de Angelis; Hall, Stacy; Fajardo, Julieta; Bruera, Eduardo; Hui, David

2014-11-01

Survival prognostication is important during the end of life. The accuracy of clinician prediction of survival (CPS) over time has not been well characterized. The aims of the study were to examine changes in prognostication accuracy during the last 14 days of life in a cohort of patients with advanced cancer admitted to two acute palliative care units and to compare the accuracy between the temporal and probabilistic approaches. Physicians and nurses prognosticated survival daily for cancer patients in two hospitals until death/discharge using two prognostic approaches: temporal and probabilistic. We assessed accuracy for each method daily during the last 14 days of life comparing accuracy at Day -14 (baseline) with accuracy at each time point using a test of proportions. A total of 6718 temporal and 6621 probabilistic estimations were provided by physicians and nurses for 311 patients, respectively. Median (interquartile range) survival was 8 days (4-20 days). Temporal CPS had low accuracy (10%-40%) and did not change over time. In contrast, probabilistic CPS was significantly more accurate (P < .05 at each time point) but decreased close to death. Probabilistic CPS was consistently more accurate than temporal CPS over the last 14 days of life; however, its accuracy decreased as patients approached death. Our findings suggest that better tools to predict impending death are necessary. Copyright © 2014 American Academy of Hospice and Palliative Medicine. Published by Elsevier Inc. All rights reserved.

Prediction-Oriented Marker Selection (PROMISE): With Application to High-Dimensional Regression.

PubMed

Kim, Soyeon; Baladandayuthapani, Veerabhadran; Lee, J Jack

2017-06-01

In personalized medicine, biomarkers are used to select therapies with the highest likelihood of success based on an individual patient's biomarker/genomic profile. Two goals are to choose important biomarkers that accurately predict treatment outcomes and to cull unimportant biomarkers to reduce the cost of biological and clinical verifications. These goals are challenging due to the high dimensionality of genomic data. Variable selection methods based on penalized regression (e.g., the lasso and elastic net) have yielded promising results. However, selecting the right amount of penalization is critical to simultaneously achieving these two goals. Standard approaches based on cross-validation (CV) typically provide high prediction accuracy with high true positive rates but at the cost of too many false positives. Alternatively, stability selection (SS) controls the number of false positives, but at the cost of yielding too few true positives. To circumvent these issues, we propose prediction-oriented marker selection (PROMISE), which combines SS with CV to conflate the advantages of both methods. Our application of PROMISE with the lasso and elastic net in data analysis shows that, compared to CV, PROMISE produces sparse solutions, few false positives, and small type I + type II error, and maintains good prediction accuracy, with a marginal decrease in the true positive rates. Compared to SS, PROMISE offers better prediction accuracy and true positive rates. In summary, PROMISE can be applied in many fields to select regularization parameters when the goals are to minimize false positives and maximize prediction accuracy.

Can machine-learning improve cardiovascular risk prediction using routine clinical data?

PubMed Central

Kai, Joe; Garibaldi, Jonathan M.; Qureshi, Nadeem

2017-01-01

Background Current approaches to predict cardiovascular risk fail to identify many people who would benefit from preventive treatment, while others receive unnecessary intervention. Machine-learning offers opportunity to improve accuracy by exploiting complex interactions between risk factors. We assessed whether machine-learning can improve cardiovascular risk prediction. Methods Prospective cohort study using routine clinical data of 378,256 patients from UK family practices, free from cardiovascular disease at outset. Four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, neural networks) were compared to an established algorithm (American College of Cardiology guidelines) to predict first cardiovascular event over 10-years. Predictive accuracy was assessed by area under the ‘receiver operating curve’ (AUC); and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) to predict 7.5% cardiovascular risk (threshold for initiating statins). Findings 24,970 incident cardiovascular events (6.6%) occurred. Compared to the established risk prediction algorithm (AUC 0.728, 95% CI 0.723–0.735), machine-learning algorithms improved prediction: random forest +1.7% (AUC 0.745, 95% CI 0.739–0.750), logistic regression +3.2% (AUC 0.760, 95% CI 0.755–0.766), gradient boosting +3.3% (AUC 0.761, 95% CI 0.755–0.766), neural networks +3.6% (AUC 0.764, 95% CI 0.759–0.769). The highest achieving (neural networks) algorithm predicted 4,998/7,404 cases (sensitivity 67.5%, PPV 18.4%) and 53,458/75,585 non-cases (specificity 70.7%, NPV 95.7%), correctly predicting 355 (+7.6%) more patients who developed cardiovascular disease compared to the established algorithm. Conclusions Machine-learning significantly improves accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment, while avoiding unnecessary treatment of others. PMID:28376093

Can machine-learning improve cardiovascular risk prediction using routine clinical data?

PubMed

Weng, Stephen F; Reps, Jenna; Kai, Joe; Garibaldi, Jonathan M; Qureshi, Nadeem

2017-01-01

Current approaches to predict cardiovascular risk fail to identify many people who would benefit from preventive treatment, while others receive unnecessary intervention. Machine-learning offers opportunity to improve accuracy by exploiting complex interactions between risk factors. We assessed whether machine-learning can improve cardiovascular risk prediction. Prospective cohort study using routine clinical data of 378,256 patients from UK family practices, free from cardiovascular disease at outset. Four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, neural networks) were compared to an established algorithm (American College of Cardiology guidelines) to predict first cardiovascular event over 10-years. Predictive accuracy was assessed by area under the 'receiver operating curve' (AUC); and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) to predict 7.5% cardiovascular risk (threshold for initiating statins). 24,970 incident cardiovascular events (6.6%) occurred. Compared to the established risk prediction algorithm (AUC 0.728, 95% CI 0.723-0.735), machine-learning algorithms improved prediction: random forest +1.7% (AUC 0.745, 95% CI 0.739-0.750), logistic regression +3.2% (AUC 0.760, 95% CI 0.755-0.766), gradient boosting +3.3% (AUC 0.761, 95% CI 0.755-0.766), neural networks +3.6% (AUC 0.764, 95% CI 0.759-0.769). The highest achieving (neural networks) algorithm predicted 4,998/7,404 cases (sensitivity 67.5%, PPV 18.4%) and 53,458/75,585 non-cases (specificity 70.7%, NPV 95.7%), correctly predicting 355 (+7.6%) more patients who developed cardiovascular disease compared to the established algorithm. Machine-learning significantly improves accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment, while avoiding unnecessary treatment of others.

Prediction of Industrial Electric Energy Consumption in Anhui Province Based on GA-BP Neural Network

NASA Astrophysics Data System (ADS)

Zhang, Jiajing; Yin, Guodong; Ni, Youcong; Chen, Jinlan

2018-01-01

In order to improve the prediction accuracy of industrial electrical energy consumption, a prediction model of industrial electrical energy consumption was proposed based on genetic algorithm and neural network. The model use genetic algorithm to optimize the weights and thresholds of BP neural network, and the model is used to predict the energy consumption of industrial power in Anhui Province, to improve the prediction accuracy of industrial electric energy consumption in Anhui province. By comparing experiment of GA-BP prediction model and BP neural network model, the GA-BP model is more accurate with smaller number of neurons in the hidden layer.

Effectiveness of link prediction for face-to-face behavioral networks.

PubMed

Tsugawa, Sho; Ohsaki, Hiroyuki

2013-01-01

Research on link prediction for social networks has been actively pursued. In link prediction for a given social network obtained from time-windowed observation, new link formation in the network is predicted from the topology of the obtained network. In contrast, recent advances in sensing technology have made it possible to obtain face-to-face behavioral networks, which are social networks representing face-to-face interactions among people. However, the effectiveness of link prediction techniques for face-to-face behavioral networks has not yet been explored in depth. To clarify this point, here we investigate the accuracy of conventional link prediction techniques for networks obtained from the history of face-to-face interactions among participants at an academic conference. Our findings were (1) that conventional link prediction techniques predict new link formation with a precision of 0.30-0.45 and a recall of 0.10-0.20, (2) that prolonged observation of social networks often degrades the prediction accuracy, (3) that the proposed decaying weight method leads to higher prediction accuracy than can be achieved by observing all records of communication and simply using them unmodified, and (4) that the prediction accuracy for face-to-face behavioral networks is relatively high compared to that for non-social networks, but not as high as for other types of social networks.

A fast and robust iterative algorithm for prediction of RNA pseudoknotted secondary structures

PubMed Central

2014-01-01

Background Improving accuracy and efficiency of computational methods that predict pseudoknotted RNA secondary structures is an ongoing challenge. Existing methods based on free energy minimization tend to be very slow and are limited in the types of pseudoknots that they can predict. Incorporating known structural information can improve prediction accuracy; however, there are not many methods for prediction of pseudoknotted structures that can incorporate structural information as input. There is even less understanding of the relative robustness of these methods with respect to partial information. Results We present a new method, Iterative HFold, for pseudoknotted RNA secondary structure prediction. Iterative HFold takes as input a pseudoknot-free structure, and produces a possibly pseudoknotted structure whose energy is at least as low as that of any (density-2) pseudoknotted structure containing the input structure. Iterative HFold leverages strengths of earlier methods, namely the fast running time of HFold, a method that is based on the hierarchical folding hypothesis, and the energy parameters of HotKnots V2.0. Our experimental evaluation on a large data set shows that Iterative HFold is robust with respect to partial information, with average accuracy on pseudoknotted structures steadily increasing from roughly 54% to 79% as the user provides up to 40% of the input structure. Iterative HFold is much faster than HotKnots V2.0, while having comparable accuracy. Iterative HFold also has significantly better accuracy than IPknot on our HK-PK and IP-pk168 data sets. Conclusions Iterative HFold is a robust method for prediction of pseudoknotted RNA secondary structures, whose accuracy with more than 5% information about true pseudoknot-free structures is better than that of IPknot, and with about 35% information about true pseudoknot-free structures compares well with that of HotKnots V2.0 while being significantly faster. Iterative HFold and all data used in this work are freely available at http://www.cs.ubc.ca/~hjabbari/software.php. PMID:24884954

Semi-supervised learning for genomic prediction of novel traits with small reference populations: an application to residual feed intake in dairy cattle.

PubMed

Yao, Chen; Zhu, Xiaojin; Weigel, Kent A

2016-11-07

Genomic prediction for novel traits, which can be costly and labor-intensive to measure, is often hampered by low accuracy due to the limited size of the reference population. As an option to improve prediction accuracy, we introduced a semi-supervised learning strategy known as the self-training model, and applied this method to genomic prediction of residual feed intake (RFI) in dairy cattle. We describe a self-training model that is wrapped around a support vector machine (SVM) algorithm, which enables it to use data from animals with and without measured phenotypes. Initially, a SVM model was trained using data from 792 animals with measured RFI phenotypes. Then, the resulting SVM was used to generate self-trained phenotypes for 3000 animals for which RFI measurements were not available. Finally, the SVM model was re-trained using data from up to 3792 animals, including those with measured and self-trained RFI phenotypes. Incorporation of additional animals with self-trained phenotypes enhanced the accuracy of genomic predictions compared to that of predictions that were derived from the subset of animals with measured phenotypes. The optimal ratio of animals with self-trained phenotypes to animals with measured phenotypes (2.5, 2.0, and 1.8) and the maximum increase achieved in prediction accuracy measured as the correlation between predicted and actual RFI phenotypes (5.9, 4.1, and 2.4%) decreased as the size of the initial training set (300, 400, and 500 animals with measured phenotypes) increased. The optimal number of animals with self-trained phenotypes may be smaller when prediction accuracy is measured as the mean squared error rather than the correlation between predicted and actual RFI phenotypes. Our results demonstrate that semi-supervised learning models that incorporate self-trained phenotypes can achieve genomic prediction accuracies that are comparable to those obtained with models using larger training sets that include only animals with measured phenotypes. Semi-supervised learning can be helpful for genomic prediction of novel traits, such as RFI, for which the size of reference population is limited, in particular, when the animals to be predicted and the animals in the reference population originate from the same herd-environment.

External validation and comparison of two nomograms predicting the probability of Gleason sum upgrading between biopsy and radical prostatectomy pathology in two patient populations: a retrospective cohort study.

PubMed

Utsumi, Takanobu; Oka, Ryo; Endo, Takumi; Yano, Masashi; Kamijima, Shuichi; Kamiya, Naoto; Fujimura, Masaaki; Sekita, Nobuyuki; Mikami, Kazuo; Hiruta, Nobuyuki; Suzuki, Hiroyoshi

2015-11-01

The aim of this study is to validate and compare the predictive accuracy of two nomograms predicting the probability of Gleason sum upgrading between biopsy and radical prostatectomy pathology among representative patients with prostate cancer. We previously developed a nomogram, as did Chun et al. In this validation study, patients originated from two centers: Toho University Sakura Medical Center (n = 214) and Chibaken Saiseikai Narashino Hospital (n = 216). We assessed predictive accuracy using area under the curve values and constructed calibration plots to grasp the tendency for each institution. Both nomograms showed a high predictive accuracy in each institution, although the constructed calibration plots of the two nomograms underestimated the actual probability in Toho University Sakura Medical Center. Clinicians need to use calibration plots for each institution to correctly understand the tendency of each nomogram for their patients, even if each nomogram has a good predictive accuracy. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Prediction of arterial oxygen partial pressure after changes in FIO₂: validation and clinical application of a novel formula.

PubMed

Al-Otaibi, H M; Hardman, J G

2011-11-01

Existing methods allow prediction of Pa(O₂) during adjustment of Fi(O₂). However, these are cumbersome and lack sufficient accuracy for use in the clinical setting. The present studies aim to extend the validity of a novel formula designed to predict Pa(O₂) during adjustment of Fi(O₂) and to compare it with the current methods. Sixty-seven new data sets were collected from 46 randomly selected, mechanically ventilated patients. Each data set consisted of two subsets (before and 20 min after Fi(O₂) adjustment) and contained ventilator settings, pH, and arterial blood gas values. We compared the accuracy of Pa(O₂) prediction using a new formula (which utilizes only the pre-adjustment Pa(O₂) and pre- and post-adjustment Fi(O₂) with prediction using assumptions of constant Pa(O₂)/Fi(O₂) or constant Pa(O₂)/Pa(O₂). Subsequently, 20 clinicians predicted Pa(O₂) using the new formula and using Nunn's isoshunt diagram. The accuracy of the clinician's predictions was examined. The 95% limits of agreement (LA(95%)) between predicted and measured Pa(O₂) in the patient group were: new formula 0.11 (2.0) kPa, Pa(O₂)/Fi(O₂) -1.9 (4.4) kPa, and Pa(O₂)/Pa(O₂) -1.0 (3.6) kPa. The LA(95%) of clinicians' predictions of Pa(O₂) were 0.56 (3.6) kPa (new formula) and -2.7 (6.4) kPa (isoshunt diagram). The new formula's prediction of changes in Pa(O₂) is acceptably accurate and reliable and better than any other existing method. Its use by clinicians appears to improve accuracy over the most popular existing method. The simplicity of the new method may allow its regular use in the critical care setting.

Randomized, controlled trial of standard-definition white-light, high-definition white-light, and narrow-band imaging colonoscopy for the detection of colon polyps and prediction of polyp histology.

PubMed

Rastogi, Amit; Early, Dayna S; Gupta, Neil; Bansal, Ajay; Singh, Vikas; Ansstas, Michael; Jonnalagadda, Sreenivasa S; Hovis, Christine E; Gaddam, Srinivas; Wani, Sachin B; Edmundowicz, Steven A; Sharma, Prateek

2011-09-01

Missing adenomas and the inability to accurately differentiate between polyp histology remain the main limitations of standard-definition white-light (SD-WL) colonoscopy. To compare the adenoma detection rates of SD-WL with those of high-definition white-light (HD-WL) and narrow-band imaging (NBI) as well as the accuracy of predicting polyp histology. Multicenter, prospective, randomized, controlled trial. Two academic medical centers in the United States. Subjects undergoing screening or surveillance colonoscopy. Subjects were randomized to undergo colonoscopy with one of the following: SD-WL, HD-WL, or NBI. The proportion of subjects detected with adenomas, adenomas detected per subject, and the accuracy of predicting polyp histology real time. A total of 630 subjects were included. The proportion of subjects with adenomas was 38.6% with SD-WL compared with 45.7% with HD-WL and 46.2% with NBI (P = .17 and P = .14, respectively). Adenomas detected per subject were 0.69 with SD-WL compared with 1.12 with HD-WL and 1.13 with NBI (P = .016 and P = .014, respectively). HD-WL and NBI detected more subjects with flat and right-sided adenomas compared with SD-WL (all P values <.005). NBI had a superior sensitivity (90%) and accuracy (82%) to predict adenomas compared with SD-WL and HD-WL (all P values <.005). Academic medical centers with experienced endoscopists. There was no difference in the proportion of subjects with adenomas detected with SD-WL, HD-WL, and NBI. However, HD-WL and NBI detected significantly more adenomas per subject (>60%) compared with SD-WL. NBI had the highest accuracy in predicting adenomas in real time during colonoscopy. ( NCT 00614770.). Copyright © 2011 American Society for Gastrointestinal Endoscopy. Published by Mosby, Inc. All rights reserved.

Potential and limits to unravel the genetic architecture and predict the variation of Fusarium head blight resistance in European winter wheat (Triticum aestivum L.).

PubMed

Jiang, Y; Zhao, Y; Rodemann, B; Plieske, J; Kollers, S; Korzun, V; Ebmeyer, E; Argillier, O; Hinze, M; Ling, J; Röder, M S; Ganal, M W; Mette, M F; Reif, J C

2015-03-01

Genome-wide mapping approaches in diverse populations are powerful tools to unravel the genetic architecture of complex traits. The main goals of our study were to investigate the potential and limits to unravel the genetic architecture and to identify the factors determining the accuracy of prediction of the genotypic variation of Fusarium head blight (FHB) resistance in wheat (Triticum aestivum L.) based on data collected with a diverse panel of 372 European varieties. The wheat lines were phenotyped in multi-location field trials for FHB resistance and genotyped with 782 simple sequence repeat (SSR) markers, and 9k and 90k single-nucleotide polymorphism (SNP) arrays. We applied genome-wide association mapping in combination with fivefold cross-validations and observed surprisingly high accuracies of prediction for marker-assisted selection based on the detected quantitative trait loci (QTLs). Using a random sample of markers not selected for marker-trait associations revealed only a slight decrease in prediction accuracy compared with marker-based selection exploiting the QTL information. The same picture was confirmed in a simulation study, suggesting that relatedness is a main driver of the accuracy of prediction in marker-assisted selection of FHB resistance. When the accuracy of prediction of three genomic selection models was contrasted for the three marker data sets, no significant differences in accuracies among marker platforms and genomic selection models were observed. Marker density impacted the accuracy of prediction only marginally. Consequently, genomic selection of FHB resistance can be implemented most cost-efficiently based on low- to medium-density SNP arrays.

Genomic Prediction Accounting for Residual Heteroskedasticity.

PubMed

Ou, Zhining; Tempelman, Robert J; Steibel, Juan P; Ernst, Catherine W; Bates, Ronald O; Bello, Nora M

2015-11-12

Whole-genome prediction (WGP) models that use single-nucleotide polymorphism marker information to predict genetic merit of animals and plants typically assume homogeneous residual variance. However, variability is often heterogeneous across agricultural production systems and may subsequently bias WGP-based inferences. This study extends classical WGP models based on normality, heavy-tailed specifications and variable selection to explicitly account for environmentally-driven residual heteroskedasticity under a hierarchical Bayesian mixed-models framework. WGP models assuming homogeneous or heterogeneous residual variances were fitted to training data generated under simulation scenarios reflecting a gradient of increasing heteroskedasticity. Model fit was based on pseudo-Bayes factors and also on prediction accuracy of genomic breeding values computed on a validation data subset one generation removed from the simulated training dataset. Homogeneous vs. heterogeneous residual variance WGP models were also fitted to two quantitative traits, namely 45-min postmortem carcass temperature and loin muscle pH, recorded in a swine resource population dataset prescreened for high and mild residual heteroskedasticity, respectively. Fit of competing WGP models was compared using pseudo-Bayes factors. Predictive ability, defined as the correlation between predicted and observed phenotypes in validation sets of a five-fold cross-validation was also computed. Heteroskedastic error WGP models showed improved model fit and enhanced prediction accuracy compared to homoskedastic error WGP models although the magnitude of the improvement was small (less than two percentage points net gain in prediction accuracy). Nevertheless, accounting for residual heteroskedasticity did improve accuracy of selection, especially on individuals of extreme genetic merit. Copyright © 2016 Ou et al.

Improving Prediction Accuracy for WSN Data Reduction by Applying Multivariate Spatio-Temporal Correlation

PubMed Central

Carvalho, Carlos; Gomes, Danielo G.; Agoulmine, Nazim; de Souza, José Neuman

2011-01-01

This paper proposes a method based on multivariate spatial and temporal correlation to improve prediction accuracy in data reduction for Wireless Sensor Networks (WSN). Prediction of data not sent to the sink node is a technique used to save energy in WSNs by reducing the amount of data traffic. However, it may not be very accurate. Simulations were made involving simple linear regression and multiple linear regression functions to assess the performance of the proposed method. The results show a higher correlation between gathered inputs when compared to time, which is an independent variable widely used for prediction and forecasting. Prediction accuracy is lower when simple linear regression is used, whereas multiple linear regression is the most accurate one. In addition to that, our proposal outperforms some current solutions by about 50% in humidity prediction and 21% in light prediction. To the best of our knowledge, we believe that we are probably the first to address prediction based on multivariate correlation for WSN data reduction. PMID:22346626

The Efficacy of Violence Prediction: A Meta-Analytic Comparison of Nine Risk Assessment Tools

ERIC Educational Resources Information Center

Yang, Min; Wong, Stephen C. P.; Coid, Jeremy

2010-01-01

Actuarial risk assessment tools are used extensively to predict future violence, but previous studies comparing their predictive accuracies have produced inconsistent findings as a result of various methodological issues. We conducted meta-analyses of the effect sizes of 9 commonly used risk assessment tools and their subscales to compare their…

Genomic relationships based on X chromosome markers and accuracy of genomic predictions with and without X chromosome markers

PubMed Central

2014-01-01

Background Although the X chromosome is the second largest bovine chromosome, markers on the X chromosome are not used for genomic prediction in some countries and populations. In this study, we presented a method for computing genomic relationships using X chromosome markers, investigated the accuracy of imputation from a low density (7K) to the 54K SNP (single nucleotide polymorphism) panel, and compared the accuracy of genomic prediction with and without using X chromosome markers. Methods The impact of considering X chromosome markers on prediction accuracy was assessed using data from Nordic Holstein bulls and different sets of SNPs: (a) the 54K SNPs for reference and test animals, (b) SNPs imputed from the 7K to the 54K SNP panel for test animals, (c) SNPs imputed from the 7K to the 54K panel for half of the reference animals, and (d) the 7K SNP panel for all animals. Beagle and Findhap were used for imputation. GBLUP (genomic best linear unbiased prediction) models with or without X chromosome markers and with or without a residual polygenic effect were used to predict genomic breeding values for 15 traits. Results Averaged over the two imputation datasets, correlation coefficients between imputed and true genotypes for autosomal markers, pseudo-autosomal markers, and X-specific markers were 0.971, 0.831 and 0.935 when using Findhap, and 0.983, 0.856 and 0.937 when using Beagle. Estimated reliabilities of genomic predictions based on the imputed datasets using Findhap or Beagle were very close to those using the real 54K data. Genomic prediction using all markers gave slightly higher reliabilities than predictions without X chromosome markers. Based on our data which included only bulls, using a G matrix that accounted for sex-linked relationships did not improve prediction, compared with a G matrix that did not account for sex-linked relationships. A model that included a polygenic effect did not recover the loss of prediction accuracy from exclusion of X chromosome markers. Conclusions The results from this study suggest that markers on the X chromosome contribute to accuracy of genomic predictions and should be used for routine genomic evaluation. PMID:25080199

A Method of Calculating Functional Independence Measure at Discharge from Functional Independence Measure Effectiveness Predicted by Multiple Regression Analysis Has a High Degree of Predictive Accuracy.

PubMed

Tokunaga, Makoto; Watanabe, Susumu; Sonoda, Shigeru

2017-09-01

Multiple linear regression analysis is often used to predict the outcome of stroke rehabilitation. However, the predictive accuracy may not be satisfactory. The objective of this study was to elucidate the predictive accuracy of a method of calculating motor Functional Independence Measure (mFIM) at discharge from mFIM effectiveness predicted by multiple regression analysis. The subjects were 505 patients with stroke who were hospitalized in a convalescent rehabilitation hospital. The formula "mFIM at discharge = mFIM effectiveness × (91 points - mFIM at admission) + mFIM at admission" was used. By including the predicted mFIM effectiveness obtained through multiple regression analysis in this formula, we obtained the predicted mFIM at discharge (A). We also used multiple regression analysis to directly predict mFIM at discharge (B). The correlation between the predicted and the measured values of mFIM at discharge was compared between A and B. The correlation coefficients were .916 for A and .878 for B. Calculating mFIM at discharge from mFIM effectiveness predicted by multiple regression analysis had a higher degree of predictive accuracy of mFIM at discharge than that directly predicted. Copyright © 2017 National Stroke Association. Published by Elsevier Inc. All rights reserved.

Bridging the gap between marker-assisted and genomic selection of heading time and plant height in hybrid wheat.

PubMed

Zhao, Y; Mette, M F; Gowda, M; Longin, C F H; Reif, J C

2014-06-01

Based on data from field trials with a large collection of 135 elite winter wheat inbred lines and 1604 F1 hybrids derived from them, we compared the accuracy of prediction of marker-assisted selection and current genomic selection approaches for the model traits heading time and plant height in a cross-validation approach. For heading time, the high accuracy seen with marker-assisted selection severely dropped with genomic selection approaches RR-BLUP (ridge regression best linear unbiased prediction) and BayesCπ, whereas for plant height, accuracy was low with marker-assisted selection as well as RR-BLUP and BayesCπ. Differences in the linkage disequilibrium structure of the functional and single-nucleotide polymorphism markers relevant for the two traits were identified in a simulation study as a likely explanation for the different trends in accuracies of prediction. A new genomic selection approach, weighted best linear unbiased prediction (W-BLUP), designed to treat the effects of known functional markers more appropriately, proved to increase the accuracy of prediction for both traits and thus closes the gap between marker-assisted and genomic selection.

Bridging the gap between marker-assisted and genomic selection of heading time and plant height in hybrid wheat

PubMed Central

Zhao, Y; Mette, M F; Gowda, M; Longin, C F H; Reif, J C

2014-01-01

Based on data from field trials with a large collection of 135 elite winter wheat inbred lines and 1604 F1 hybrids derived from them, we compared the accuracy of prediction of marker-assisted selection and current genomic selection approaches for the model traits heading time and plant height in a cross-validation approach. For heading time, the high accuracy seen with marker-assisted selection severely dropped with genomic selection approaches RR-BLUP (ridge regression best linear unbiased prediction) and BayesCπ, whereas for plant height, accuracy was low with marker-assisted selection as well as RR-BLUP and BayesCπ. Differences in the linkage disequilibrium structure of the functional and single-nucleotide polymorphism markers relevant for the two traits were identified in a simulation study as a likely explanation for the different trends in accuracies of prediction. A new genomic selection approach, weighted best linear unbiased prediction (W-BLUP), designed to treat the effects of known functional markers more appropriately, proved to increase the accuracy of prediction for both traits and thus closes the gap between marker-assisted and genomic selection. PMID:24518889

Ontario multidetector computed tomographic coronary angiography study: field evaluation of diagnostic accuracy.

PubMed

Chow, Benjamin J W; Freeman, Michael R; Bowen, James M; Levin, Leslie; Hopkins, Robert B; Provost, Yves; Tarride, Jean-Eric; Dennie, Carole; Cohen, Eric A; Marcuzzi, Dan; Iwanochko, Robert; Moody, Alan R; Paul, Narinder; Parker, John D; O'Reilly, Daria J; Xie, Feng; Goeree, Ron

2011-06-13

Computed tomographic coronary angiography (CTCA) has gained clinical acceptance for the detection of obstructive coronary artery disease. Although single-center studies have demonstrated excellent accuracy, multicenter studies have yielded variable results. The true diagnostic accuracy of CTCA in the "real world" remains uncertain. We conducted a field evaluation comparing multidetector CTCA with invasive CA (ICA) to understand CTCA's diagnostic accuracy in a real-world setting. A multicenter cohort study of patients awaiting ICA was conducted between September 2006 and June 2009. All patients had either a low or an intermediate pretest probability for coronary artery disease and underwent CTCA and ICA within 10 days. The results of CTCA and ICA were interpreted visually by local expert observers who were blinded to all clinical data and imaging results. Using a patient-based analysis (diameter stenosis ≥50%) of 169 patients, the sensitivity, specificity, positive predictive value, and negative predictive value were 81.3% (95% confidence interval [CI], 71.0%-89.1%), 93.3% (95% CI, 85.9%-97.5%), 91.6% (95% CI, 82.5%-96.8%), and 84.7% (95% CI, 76.0%-91.2%), respectively; the area under receiver operating characteristic curve was 0.873. The diagnostic accuracy varied across centers (P < .001), with a sensitivity, specificity, positive predictive value, and negative predictive value ranging from 50.0% to 93.2%, 92.0% to 100%, 84.6% to 100%, and 42.9% to 94.7%, respectively. Compared with ICA, CTCA appears to have good accuracy; however, there was variability in diagnostic accuracy across centers. Factors affecting institutional variability need to be better understood before CTCA is universally adopted. Additional real-world evaluations are needed to fully understand the impact of CTCA on clinical care. clinicaltrials.gov Identifier: NCT00371891.

Accuracy of glenohumeral joint injections: comparing approach and experience of provider.

PubMed

Tobola, Allison; Cook, Chad; Cassas, Kyle J; Hawkins, Richard J; Wienke, Jeffrey R; Tolan, Stefan; Kissenberth, Michael J

2011-10-01

The purpose of this study was to prospectively evaluate the accuracy of three different approaches used for glenohumeral injections. In addition, the accuracy of the injection was compared to the experience and confidence of the provider. One-hundred six consecutive patients with shoulder pain underwent attempted intra-articular injection either posteriorly, supraclavicularly, or anteriorly. Each approach was performed by an experienced and inexperienced provider. A musculoskeletal radiologist blinded to technique used and provider interpreted fluoroscopic images to determine accuracy. Providers were blinded to these results. The accuracy of the anterior approach regardless of experience was 64.7%, the posterior approach was 45.7%, and the supraclavicular approach was 45.5%. With each approach, experience did not provide an advantage. For the anterior approach, the experienced provider was 50% accurate compared to 85.7%. For the posterior approach, the experienced provider had a 42.1% accuracy rate compared to 50%. The experienced provider was accurate 50% of the time in the supraclavicular approach compared to 38.5%. The providers were not able to predict their accuracy regardless of experience. The experienced providers, when compared to those who were less experienced, were more likely to be overconfident, particularly with the anterior and supraclavicular approaches. There was no statistically significant difference between the 3 approaches. The anterior approach was the most accurate, independent of the experience level of the provider. The posterior approach produced the lowest level of confidence regardless of experience. The experienced providers were not able to accurately predict the results of their injections, and were more likely to be overconfident with the anterior and supraclavicular approaches. Copyright © 2011 Journal of Shoulder and Elbow Surgery Board of Trustees. Published by Mosby, Inc. All rights reserved.

Boosted classification trees result in minor to modest improvement in the accuracy in classifying cardiovascular outcomes compared to conventional classification trees

PubMed Central

Austin, Peter C; Lee, Douglas S

2011-01-01

Purpose: Classification trees are increasingly being used to classifying patients according to the presence or absence of a disease or health outcome. A limitation of classification trees is their limited predictive accuracy. In the data-mining and machine learning literature, boosting has been developed to improve classification. Boosting with classification trees iteratively grows classification trees in a sequence of reweighted datasets. In a given iteration, subjects that were misclassified in the previous iteration are weighted more highly than subjects that were correctly classified. Classifications from each of the classification trees in the sequence are combined through a weighted majority vote to produce a final classification. The authors' objective was to examine whether boosting improved the accuracy of classification trees for predicting outcomes in cardiovascular patients. Methods: We examined the utility of boosting classification trees for classifying 30-day mortality outcomes in patients hospitalized with either acute myocardial infarction or congestive heart failure. Results: Improvements in the misclassification rate using boosted classification trees were at best minor compared to when conventional classification trees were used. Minor to modest improvements to sensitivity were observed, with only a negligible reduction in specificity. For predicting cardiovascular mortality, boosted classification trees had high specificity, but low sensitivity. Conclusions: Gains in predictive accuracy for predicting cardiovascular outcomes were less impressive than gains in performance observed in the data mining literature. PMID:22254181

Diagnostic accuracy of liver fibrosis based on red cell distribution width (RDW) to platelet ratio with fibroscan in chronic hepatitis B

NASA Astrophysics Data System (ADS)

Sembiring, J.; Jones, F.

2018-03-01

Red cell Distribution Width (RDW) and platelet ratio (RPR) can predict liver fibrosis and cirrhosis in chronic hepatitis B with relatively high accuracy. RPR was superior to other non-invasive methods to predict liver fibrosis, such as AST and ALT ratio, AST and platelet ratio Index and FIB-4. The aim of this study was to assess diagnostic accuracy liver fibrosis by using RDW and platelets ratio in chronic hepatitis B patients based on compared with Fibroscan. This cross-sectional study was conducted at Adam Malik Hospital from January-June 2015. We examine 34 patients hepatitis B chronic, screen RDW, platelet, and fibroscan. Data were statistically analyzed. The result RPR with ROC procedure has an accuracy of 72.3% (95% CI: 84.1% - 97%). In this study, the RPR had a moderate ability to predict fibrosis degree (p = 0.029 with AUC> 70%). The cutoff value RPR was 0.0591, sensitivity and spesificity were 71.4% and 60%, Positive Prediction Value (PPV) was 55.6% and Negative Predictions Value (NPV) was 75%, positive likelihood ratio was 1.79 and negative likelihood ratio was 0.48. RPR have the ability to predict the degree of liver fibrosis in chronic hepatitis B patients with moderate accuracy.

Gender Differences in Structured Risk Assessment: Comparing the Accuracy of Five Instruments

ERIC Educational Resources Information Center

Coid, Jeremy; Yang, Min; Ullrich, Simone; Zhang, Tianqiang; Sizmur, Steve; Roberts, Colin; Farrington, David P.; Rogers, Robert D.

2009-01-01

Structured risk assessment should guide clinical risk management, but it is uncertain which instrument has the highest predictive accuracy among men and women. In the present study, the authors compared the Psychopathy Checklist-Revised (PCL-R; R. D. Hare, 1991, 2003); the Historical, Clinical, Risk Management-20 (HCR-20; C. D. Webster, K. S.…

Addressing issues associated with evaluating prediction models for survival endpoints based on the concordance statistic.

PubMed

Wang, Ming; Long, Qi

2016-09-01

Prediction models for disease risk and prognosis play an important role in biomedical research, and evaluating their predictive accuracy in the presence of censored data is of substantial interest. The standard concordance (c) statistic has been extended to provide a summary measure of predictive accuracy for survival models. Motivated by a prostate cancer study, we address several issues associated with evaluating survival prediction models based on c-statistic with a focus on estimators using the technique of inverse probability of censoring weighting (IPCW). Compared to the existing work, we provide complete results on the asymptotic properties of the IPCW estimators under the assumption of coarsening at random (CAR), and propose a sensitivity analysis under the mechanism of noncoarsening at random (NCAR). In addition, we extend the IPCW approach as well as the sensitivity analysis to high-dimensional settings. The predictive accuracy of prediction models for cancer recurrence after prostatectomy is assessed by applying the proposed approaches. We find that the estimated predictive accuracy for the models in consideration is sensitive to NCAR assumption, and thus identify the best predictive model. Finally, we further evaluate the performance of the proposed methods in both settings of low-dimensional and high-dimensional data under CAR and NCAR through simulations. © 2016, The International Biometric Society.

Dynamic Filtering Improves Attentional State Prediction with fNIRS

NASA Technical Reports Server (NTRS)

Harrivel, Angela R.; Weissman, Daniel H.; Noll, Douglas C.; Huppert, Theodore; Peltier, Scott J.

2016-01-01

Brain activity can predict a person's level of engagement in an attentional task. However, estimates of brain activity are often confounded by measurement artifacts and systemic physiological noise. The optimal method for filtering this noise - thereby increasing such state prediction accuracy - remains unclear. To investigate this, we asked study participants to perform an attentional task while we monitored their brain activity with functional near infrared spectroscopy (fNIRS). We observed higher state prediction accuracy when noise in the fNIRS hemoglobin [Hb] signals was filtered with a non-stationary (adaptive) model as compared to static regression (84% +/- 6% versus 72% +/- 15%).

Predicting juvenile recidivism: new method, old problems.

PubMed

Benda, B B

1987-01-01

This prediction study compared three statistical procedures for accuracy using two assessment methods. The criterion is return to a juvenile prison after the first release, and the models tested are logit analysis, predictive attribute analysis, and a Burgess procedure. No significant differences are found between statistics in prediction.

Application of gene expression programming and neural networks to predict adverse events of radical hysterectomy in cervical cancer patients.

PubMed

Kusy, Maciej; Obrzut, Bogdan; Kluska, Jacek

2013-12-01

The aim of this article was to compare gene expression programming (GEP) method with three types of neural networks in the prediction of adverse events of radical hysterectomy in cervical cancer patients. One-hundred and seven patients treated by radical hysterectomy were analyzed. Each record representing a single patient consisted of 10 parameters. The occurrence and lack of perioperative complications imposed a two-class classification problem. In the simulations, GEP algorithm was compared to a multilayer perceptron (MLP), a radial basis function network neural, and a probabilistic neural network. The generalization ability of the models was assessed on the basis of their accuracy, the sensitivity, the specificity, and the area under the receiver operating characteristic curve (AUROC). The GEP classifier provided best results in the prediction of the adverse events with the accuracy of 71.96 %. Comparable but slightly worse outcomes were obtained using MLP, i.e., 71.87 %. For each of measured indices: accuracy, sensitivity, specificity, and the AUROC, the standard deviation was the smallest for the models generated by GEP classifier.

Feature Selection Methods for Zero-Shot Learning of Neural Activity.

PubMed

Caceres, Carlos A; Roos, Matthew J; Rupp, Kyle M; Milsap, Griffin; Crone, Nathan E; Wolmetz, Michael E; Ratto, Christopher R

2017-01-01

Dimensionality poses a serious challenge when making predictions from human neuroimaging data. Across imaging modalities, large pools of potential neural features (e.g., responses from particular voxels, electrodes, and temporal windows) have to be related to typically limited sets of stimuli and samples. In recent years, zero-shot prediction models have been introduced for mapping between neural signals and semantic attributes, which allows for classification of stimulus classes not explicitly included in the training set. While choices about feature selection can have a substantial impact when closed-set accuracy, open-set robustness, and runtime are competing design objectives, no systematic study of feature selection for these models has been reported. Instead, a relatively straightforward feature stability approach has been adopted and successfully applied across models and imaging modalities. To characterize the tradeoffs in feature selection for zero-shot learning, we compared correlation-based stability to several other feature selection techniques on comparable data sets from two distinct imaging modalities: functional Magnetic Resonance Imaging and Electrocorticography. While most of the feature selection methods resulted in similar zero-shot prediction accuracies and spatial/spectral patterns of selected features, there was one exception; A novel feature/attribute correlation approach was able to achieve those accuracies with far fewer features, suggesting the potential for simpler prediction models that yield high zero-shot classification accuracy.

The drivers of wildfire enlargement do not exhibit scale thresholds in southeastern Australian forests.

PubMed

Price, Owen F; Penman, Trent; Bradstock, Ross; Borah, Rittick

2016-10-01

Wildfires are complex adaptive systems, and have been hypothesized to exhibit scale-dependent transitions in the drivers of fire spread. Among other things, this makes the prediction of final fire size from conditions at the ignition difficult. We test this hypothesis by conducting a multi-scale statistical modelling of the factors determining whether fires reached 10 ha, then 100 ha then 1000 ha and the final size of fires >1000 ha. At each stage, the predictors were measures of weather, fuels, topography and fire suppression. The objectives were to identify differences among the models indicative of scale transitions, assess the accuracy of the multi-step method for predicting fire size (compared to predicting final size from initial conditions) and to quantify the importance of the predictors. The data were 1116 fires that occurred in the eucalypt forests of New South Wales between 1985 and 2010. The models were similar at the different scales, though there were subtle differences. For example, the presence of roads affected whether fires reached 10 ha but not larger scales. Weather was the most important predictor overall, though fuel load, topography and ease of suppression all showed effects. Overall, there was no evidence that fires have scale-dependent transitions in behaviour. The models had a predictive accuracy of 73%, 66%, 72% and 53% accuracy at 10 ha, 100 ha, 1000 ha and final size scales. When these steps were combined, the overall accuracy for predicting the size of fires was 62%, while the accuracy of the one step model was only 20%. Thus, the multi-scale approach was an improvement on the single scale approach, even though the predictive accuracy was probably insufficient for use as an operational tool. The analysis has also provided further evidence of the important role of weather, compared to fuel, suppression and topography in driving fire behaviour. Copyright © 2016. Published by Elsevier Ltd.

Comparison of baseline removal methods for laser-induced breakdown spectroscopy of geological samples

NASA Astrophysics Data System (ADS)

Dyar, M. Darby; Giguere, Stephen; Carey, CJ; Boucher, Thomas

2016-12-01

This project examines the causes, effects, and optimization of continuum removal in laser-induced breakdown spectroscopy (LIBS) to produce the best possible prediction accuracy of elemental composition in geological samples. We compare prediction accuracy resulting from several different techniques for baseline removal, including asymmetric least squares (ALS), adaptive iteratively reweighted penalized least squares (Air-PLS), fully automatic baseline correction (FABC), continuous wavelet transformation, median filtering, polynomial fitting, the iterative thresholding Dietrich method, convex hull/rubber band techniques, and a newly-developed technique for Custom baseline removal (BLR). We assess the predictive performance of these methods using partial least-squares analysis for 13 elements of geological interest, expressed as the weight percentages of SiO2, Al2O3, TiO2, FeO, MgO, CaO, Na2O, K2O, and the parts per million concentrations of Ni, Cr, Zn, Mn, and Co. We find that previously published methods for baseline subtraction generally produce equivalent prediction accuracies for major elements. When those pre-existing methods are used, automated optimization of their adjustable parameters is always necessary to wring the best predictive accuracy out of a data set; ideally, it should be done for each individual variable. The new technique of Custom BLR produces significant improvements in prediction accuracy over existing methods across varying geological data sets, instruments, and varying analytical conditions. These results also demonstrate the dual objectives of the continuum removal problem: removing a smooth underlying signal to fit individual peaks (univariate analysis) versus using feature selection to select only those channels that contribute to best prediction accuracy for multivariate analyses. Overall, the current practice of using generalized, one-method-fits-all-spectra baseline removal results in poorer predictive performance for all methods. The extra steps needed to optimize baseline removal for each predicted variable and empower multivariate techniques with the best possible input data for optimal prediction accuracy are shown to be well worth the slight increase in necessary computations and complexity.

Effectiveness of Link Prediction for Face-to-Face Behavioral Networks

PubMed Central

Tsugawa, Sho; Ohsaki, Hiroyuki

2013-01-01

Research on link prediction for social networks has been actively pursued. In link prediction for a given social network obtained from time-windowed observation, new link formation in the network is predicted from the topology of the obtained network. In contrast, recent advances in sensing technology have made it possible to obtain face-to-face behavioral networks, which are social networks representing face-to-face interactions among people. However, the effectiveness of link prediction techniques for face-to-face behavioral networks has not yet been explored in depth. To clarify this point, here we investigate the accuracy of conventional link prediction techniques for networks obtained from the history of face-to-face interactions among participants at an academic conference. Our findings were (1) that conventional link prediction techniques predict new link formation with a precision of 0.30–0.45 and a recall of 0.10–0.20, (2) that prolonged observation of social networks often degrades the prediction accuracy, (3) that the proposed decaying weight method leads to higher prediction accuracy than can be achieved by observing all records of communication and simply using them unmodified, and (4) that the prediction accuracy for face-to-face behavioral networks is relatively high compared to that for non-social networks, but not as high as for other types of social networks. PMID:24339956

Comparison of linear and non-linear models for predicting energy expenditure from raw accelerometer data.

PubMed

Montoye, Alexander H K; Begum, Munni; Henning, Zachary; Pfeiffer, Karin A

2017-02-01

This study had three purposes, all related to evaluating energy expenditure (EE) prediction accuracy from body-worn accelerometers: (1) compare linear regression to linear mixed models, (2) compare linear models to artificial neural network models, and (3) compare accuracy of accelerometers placed on the hip, thigh, and wrists. Forty individuals performed 13 activities in a 90 min semi-structured, laboratory-based protocol. Participants wore accelerometers on the right hip, right thigh, and both wrists and a portable metabolic analyzer (EE criterion). Four EE prediction models were developed for each accelerometer: linear regression, linear mixed, and two ANN models. EE prediction accuracy was assessed using correlations, root mean square error (RMSE), and bias and was compared across models and accelerometers using repeated-measures analysis of variance. For all accelerometer placements, there were no significant differences for correlations or RMSE between linear regression and linear mixed models (correlations: r  =  0.71-0.88, RMSE: 1.11-1.61 METs; p  >  0.05). For the thigh-worn accelerometer, there were no differences in correlations or RMSE between linear and ANN models (ANN-correlations: r  =  0.89, RMSE: 1.07-1.08 METs. Linear models-correlations: r  =  0.88, RMSE: 1.10-1.11 METs; p  >  0.05). Conversely, one ANN had higher correlations and lower RMSE than both linear models for the hip (ANN-correlation: r  =  0.88, RMSE: 1.12 METs. Linear models-correlations: r  =  0.86, RMSE: 1.18-1.19 METs; p  <  0.05), and both ANNs had higher correlations and lower RMSE than both linear models for the wrist-worn accelerometers (ANN-correlations: r  =  0.82-0.84, RMSE: 1.26-1.32 METs. Linear models-correlations: r  =  0.71-0.73, RMSE: 1.55-1.61 METs; p  <  0.01). For studies using wrist-worn accelerometers, machine learning models offer a significant improvement in EE prediction accuracy over linear models. Conversely, linear models showed similar EE prediction accuracy to machine learning models for hip- and thigh-worn accelerometers and may be viable alternative modeling techniques for EE prediction for hip- or thigh-worn accelerometers.

Analytic Guided-Search Model of Human Performance Accuracy in Target- Localization Search Tasks

NASA Technical Reports Server (NTRS)

Eckstein, Miguel P.; Beutter, Brent R.; Stone, Leland S.

2000-01-01

Current models of human visual search have extended the traditional serial/parallel search dichotomy. Two successful models for predicting human visual search are the Guided Search model and the Signal Detection Theory model. Although these models are inherently different, it has been difficult to compare them because the Guided Search model is designed to predict response time, while Signal Detection Theory models are designed to predict performance accuracy. Moreover, current implementations of the Guided Search model require the use of Monte-Carlo simulations, a method that makes fitting the model's performance quantitatively to human data more computationally time consuming. We have extended the Guided Search model to predict human accuracy in target-localization search tasks. We have also developed analytic expressions that simplify simulation of the model to the evaluation of a small set of equations using only three free parameters. This new implementation and extension of the Guided Search model will enable direct quantitative comparisons with human performance in target-localization search experiments and with the predictions of Signal Detection Theory and other search accuracy models.

Comparing the accuracy of personality judgements by the self and knowledgeable others.

PubMed

Kolar, D W; Funder, D C; Colvin, C R

1996-06-01

In this article we compare the accuracy of personality judgements by the self and by knowledgeable others. Self- and acquaintance judgements of general personality attributes were used to predict general, videotaped behavioral criteria. Results slightly favored the predictive validity of personality judgements made by single acquaintances over self-judgements, and significantly favored the aggregated personality judgements of two acquaintances over self-judgements. These findings imply that the most valid source for personality judgements that are relevant to patterns of overt behavior may not be self-reports but the consensus of the judgement of the community of one's peers.

Accuracy and Calibration of High Explosive Thermodynamic Equations of State

DTIC Science & Technology

2010-08-01

physics descriptions, but can also mean increased calibration complexity. A generalized extent of aluminum reaction, the Jones-Wilkins-Lee ( JWL ) based...predictions compared to experiments 3 3 PAX-30 JWL and JWLB cylinder test predictions compared to experiments 4 4 PAX-29 JWL and JWLB cylinder test...predictions compared to experiments 5 5 Experiment and modeling comparisons for HMX/AI 85/15 7 TABLES 1 LX-14 JWL and JWLB cylinder test velocity

The Comparative Accuracy of Two Hydrologic Models in Simulating Warm-Season Runoff for Two Small, Hillslope Catchments

EPA Science Inventory

Runoff prediction is a cornerstone of water resources planning, and therefore modeling performance is a key issue. This paper investigates the comparative advantages of conceptual versus process- based models in predicting warm season runoff for upland, low-yield micro-catchments...

Empirical Accuracies of U.S. Space Surveillance Network Reentry Predictions

NASA Technical Reports Server (NTRS)

Johnson, Nicholas L.

2008-01-01

The U.S. Space Surveillance Network (SSN) issues formal satellite reentry predictions for objects which have the potential for generating debris which could pose a hazard to people or property on Earth. These prognostications, known as Tracking and Impact Prediction (TIP) messages, are nominally distributed at daily intervals beginning four days prior to the anticipated reentry and several times during the final 24 hours in orbit. The accuracy of these messages depends on the nature of the satellite s orbit, the characteristics of the space vehicle, solar activity, and many other factors. Despite the many influences on the time and the location of reentry, a useful assessment of the accuracies of TIP messages can be derived and compared with the official accuracies included with each TIP message. This paper summarizes the results of a study of numerous uncontrolled reentries of spacecraft and rocket bodies from nearly circular orbits over a span of several years. Insights are provided into the empirical accuracies and utility of SSN TIP messages.

Comparison of Three Risk Scores to Predict Outcomes of Severe Lower Gastrointestinal Bleeding

PubMed Central

Camus, Marine; Jensen, Dennis M.; Ohning, Gordon V.; Kovacs, Thomas O.; Jutabha, Rome; Ghassemi, Kevin A.; Machicado, Gustavo A.; Dulai, Gareth S.; Jensen, Mary Ellen; Gornbein, Jeffrey A.

2014-01-01

Background & aims Improved medical decisions by using a score at the initial patient triage level may lead to improvements in patient management, outcomes, and resource utilization. There is no validated score for management of lower gastrointestinal bleeding (LGIB) unlike for upper GIB. The aim of our study was to compare the accuracies of 3 different prognostic scores (CURE Hemostasis prognosis score, Charlston index and ASA score) for the prediction of 30 day rebleeding, surgery and death in severe LGIB. Methods Data on consecutive patients hospitalized with severe GI bleeding from January 2006 to October 2011 in our two-tertiary academic referral centers were prospectively collected. Sensitivities, specificities, accuracies and area under the receiver operating characteristic (AUROC) were computed for three scores for predictions of rebleeding, surgery and mortality at 30 days. Results 235 consecutive patients with LGIB were included between 2006 and 2011. 23% of patients rebled, 6% had surgery, and 7.7% of patients died. The accuracies of each score never reached 70% for predicting rebleeding or surgery in either. The ASA score had a highest accuracy for predicting mortality within 30 days (83.5%) whereas the CURE Hemostasis prognosis score and the Charlson index both had accuracies less than 75% for the prediction of death within 30 days. Conclusions ASA score could be useful to predict death within 30 days. However a new score is still warranted to predict all 30 days outcomes (rebleeding, surgery and death) in LGIB. PMID:25599218

Predicting maximal strength of quadriceps from submaximal performance in individuals with knee joint osteoarthritis.

PubMed

McNair, Peter J; Colvin, Matt; Reid, Duncan

2011-02-01

To compare the accuracy of 12 maximal strength (1-repetition maximum [1-RM]) equations for predicting quadriceps strength in people with osteoarthritis (OA) of the knee joint. Eighteen subjects with OA of the knee joint attended a rehabilitation gymnasium on 3 occasions: 1) a familiarization session, 2) a session where the 1-RM of the quadriceps was established using a weights machine for an open-chain knee extension exercise and a leg press exercise, and 3) a session where the subjects performed with a load at which they could lift for approximately 10 repetitions only. The data were used in 12 prediction equations to calculate 1-RM strength and compared to the actual 1-RM data. Data were examined using Bland and Altman graphs and statistics, intraclass correlation coefficients (ICCs), and typical error values between the actual 1-RM and the respective 1-RM prediction equation data. Difference scores (predicted 1-RM--actual 1-RM) across the injured and control legs were also compared. For the knee extension exercise, the Brown, Brzycki, Epley, Lander, Mayhew et al, Poliquin, and Wathen prediction equations demonstrated the greatest levels of predictive accuracy. All of the ICCs were high (range 0.96–0.99), and typical errors were between 3% and 4%. For the knee press exercise, the Adams, Berger, Kemmler et al, and O'Conner et al equations demonstrated the greatest levels of predictive accuracy. All of the ICCs were high (range 0.95-0.98), and the typical errors ranged from 5.9-6.3%. This study provided evidence supporting the use of prediction equations to assess maximal strength in individuals with a knee joint with OA.

A comparison between Bayes discriminant analysis and logistic regression for prediction of debris flow in southwest Sichuan, China

NASA Astrophysics Data System (ADS)

Xu, Wenbo; Jing, Shaocai; Yu, Wenjuan; Wang, Zhaoxian; Zhang, Guoping; Huang, Jianxi

2013-11-01

In this study, the high risk areas of Sichuan Province with debris flow, Panzhihua and Liangshan Yi Autonomous Prefecture, were taken as the studied areas. By using rainfall and environmental factors as the predictors and based on the different prior probability combinations of debris flows, the prediction of debris flows was compared in the areas with statistical methods: logistic regression (LR) and Bayes discriminant analysis (BDA). The results through the comprehensive analysis show that (a) with the mid-range scale prior probability, the overall predicting accuracy of BDA is higher than those of LR; (b) with equal and extreme prior probabilities, the overall predicting accuracy of LR is higher than those of BDA; (c) the regional predicting models of debris flows with rainfall factors only have worse performance than those introduced environmental factors, and the predicting accuracies of occurrence and nonoccurrence of debris flows have been changed in the opposite direction as the supplemented information.

Efficacy of Transcerebellar Diameter/Abdominal Circumference Versus Head Circumference/Abdominal Circumference in Predicting Asymmetric Intrauterine Growth Retardation

PubMed Central

Bhimarao; Bhat, Venkataramana; Gowda, Puttanna VN

2015-01-01

Background The high incidence of IUGR and its low recognition lead to increasing perinatal morbidity and mortality for which prediction of IUGR with timely management decisions is of paramount importance. Many studies have compared the efficacy of several gestational age independent parameters and found that TCD/AC is a better predictor of asymmetric IUGR. Aim To compare the accuracy of transcerebellar diameter/abdominal circumference with head circumference/abdominal circumference in predicting asymmetric intrauterine growth retardation after 20 weeks of gestation. Materials and Methods The prospective study was conducted over a period of one year on 50 clinically suspected IUGR pregnancies who were evaluated with 3.5 MHz frequency ultrasound scanner by a single sonologist. BPD, HC, AC and FL along with TCD were measured for assessing the sonological gestational age. Two morphometric ratios- TCD/AC and HC/AC were calculated. Estimated fetal weight was calculated for all these pregnancies and its percentile was determined. Statistical Methods The TCD/AC and HC/AC ratios were correlated with advancing gestational age to know if these were related to GA. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and diagnostic accuracy (DA) for TCD/AC and HC/AC ratios in evaluating IUGR fetuses were calculated. Results In the present study, linear relation of TCD and HC in IUGR fetuses with gestation was noted. The sensitivity, specificity, PPV, NPV & DA were 88%, 93.5%, 77.1%, 96.3% & 92.4% respectively for TCD/AC ratio versus 84%, 92%, 72.4%, 95.8% & 90.4% respectively for HC/AC ratio in predicting IUGR. Conclusion Both ratios were gestational age independent and can be used in detecting IUGR with good diagnostic accuracy. However, TCD/AC ratio had a better diagnostic validity and accuracy compared to HC/AC ratio in predicting asymmetric IUGR. PMID:26557588

Predicting grain yield using canopy hyperspectral reflectance in wheat breeding data.

PubMed

Montesinos-López, Osval A; Montesinos-López, Abelardo; Crossa, José; de Los Campos, Gustavo; Alvarado, Gregorio; Suchismita, Mondal; Rutkoski, Jessica; González-Pérez, Lorena; Burgueño, Juan

2017-01-01

Modern agriculture uses hyperspectral cameras to obtain hundreds of reflectance data measured at discrete narrow bands to cover the whole visible light spectrum and part of the infrared and ultraviolet light spectra, depending on the camera. This information is used to construct vegetation indices (VI) (e.g., green normalized difference vegetation index or GNDVI, simple ratio or SRa, etc.) which are used for the prediction of primary traits (e.g., biomass). However, these indices only use some bands and are cultivar-specific; therefore they lose considerable information and are not robust for all cultivars. This study proposes models that use all available bands as predictors to increase prediction accuracy; we compared these approaches with eight conventional vegetation indexes (VIs) constructed using only some bands. The data set we used comes from CIMMYT's global wheat program and comprises 1170 genotypes evaluated for grain yield (ton/ha) in five environments (Drought, Irrigated, EarlyHeat, Melgas and Reduced Irrigated); the reflectance data were measured in 250 discrete narrow bands ranging between 392 and 851 nm. The proposed models for the simultaneous analysis of all the bands were ordinal least square (OLS), Bayes B, principal components with Bayes B, functional B-spline, functional Fourier and functional partial least square. The results of these models were compared with the OLS performed using as predictors each of the eight VIs individually and combined. We found that using all bands simultaneously increased prediction accuracy more than using VI alone. The Splines and Fourier models had the best prediction accuracy for each of the nine time-points under study. Combining image data collected at different time-points led to a small increase in prediction accuracy relative to models that use data from a single time-point. Also, using bands with heritabilities larger than 0.5 only in Drought as predictor variables showed improvements in prediction accuracy.

Genomic prediction in animals and plants: simulation of data, validation, reporting, and benchmarking.

PubMed

Daetwyler, Hans D; Calus, Mario P L; Pong-Wong, Ricardo; de Los Campos, Gustavo; Hickey, John M

2013-02-01

The genomic prediction of phenotypes and breeding values in animals and plants has developed rapidly into its own research field. Results of genomic prediction studies are often difficult to compare because data simulation varies, real or simulated data are not fully described, and not all relevant results are reported. In addition, some new methods have been compared only in limited genetic architectures, leading to potentially misleading conclusions. In this article we review simulation procedures, discuss validation and reporting of results, and apply benchmark procedures for a variety of genomic prediction methods in simulated and real example data. Plant and animal breeding programs are being transformed by the use of genomic data, which are becoming widely available and cost-effective to predict genetic merit. A large number of genomic prediction studies have been published using both simulated and real data. The relative novelty of this area of research has made the development of scientific conventions difficult with regard to description of the real data, simulation of genomes, validation and reporting of results, and forward in time methods. In this review article we discuss the generation of simulated genotype and phenotype data, using approaches such as the coalescent and forward in time simulation. We outline ways to validate simulated data and genomic prediction results, including cross-validation. The accuracy and bias of genomic prediction are highlighted as performance indicators that should be reported. We suggest that a measure of relatedness between the reference and validation individuals be reported, as its impact on the accuracy of genomic prediction is substantial. A large number of methods were compared in example simulated and real (pine and wheat) data sets, all of which are publicly available. In our limited simulations, most methods performed similarly in traits with a large number of quantitative trait loci (QTL), whereas in traits with fewer QTL variable selection did have some advantages. In the real data sets examined here all methods had very similar accuracies. We conclude that no single method can serve as a benchmark for genomic prediction. We recommend comparing accuracy and bias of new methods to results from genomic best linear prediction and a variable selection approach (e.g., BayesB), because, together, these methods are appropriate for a range of genetic architectures. An accompanying article in this issue provides a comprehensive review of genomic prediction methods and discusses a selection of topics related to application of genomic prediction in plants and animals.

Genomic Prediction in Animals and Plants: Simulation of Data, Validation, Reporting, and Benchmarking

PubMed Central

Daetwyler, Hans D.; Calus, Mario P. L.; Pong-Wong, Ricardo; de los Campos, Gustavo; Hickey, John M.

2013-01-01

The genomic prediction of phenotypes and breeding values in animals and plants has developed rapidly into its own research field. Results of genomic prediction studies are often difficult to compare because data simulation varies, real or simulated data are not fully described, and not all relevant results are reported. In addition, some new methods have been compared only in limited genetic architectures, leading to potentially misleading conclusions. In this article we review simulation procedures, discuss validation and reporting of results, and apply benchmark procedures for a variety of genomic prediction methods in simulated and real example data. Plant and animal breeding programs are being transformed by the use of genomic data, which are becoming widely available and cost-effective to predict genetic merit. A large number of genomic prediction studies have been published using both simulated and real data. The relative novelty of this area of research has made the development of scientific conventions difficult with regard to description of the real data, simulation of genomes, validation and reporting of results, and forward in time methods. In this review article we discuss the generation of simulated genotype and phenotype data, using approaches such as the coalescent and forward in time simulation. We outline ways to validate simulated data and genomic prediction results, including cross-validation. The accuracy and bias of genomic prediction are highlighted as performance indicators that should be reported. We suggest that a measure of relatedness between the reference and validation individuals be reported, as its impact on the accuracy of genomic prediction is substantial. A large number of methods were compared in example simulated and real (pine and wheat) data sets, all of which are publicly available. In our limited simulations, most methods performed similarly in traits with a large number of quantitative trait loci (QTL), whereas in traits with fewer QTL variable selection did have some advantages. In the real data sets examined here all methods had very similar accuracies. We conclude that no single method can serve as a benchmark for genomic prediction. We recommend comparing accuracy and bias of new methods to results from genomic best linear prediction and a variable selection approach (e.g., BayesB), because, together, these methods are appropriate for a range of genetic architectures. An accompanying article in this issue provides a comprehensive review of genomic prediction methods and discusses a selection of topics related to application of genomic prediction in plants and animals. PMID:23222650

ShinyGPAS: interactive genomic prediction accuracy simulator based on deterministic formulas.

PubMed

Morota, Gota

2017-12-20

Deterministic formulas for the accuracy of genomic predictions highlight the relationships among prediction accuracy and potential factors influencing prediction accuracy prior to performing computationally intensive cross-validation. Visualizing such deterministic formulas in an interactive manner may lead to a better understanding of how genetic factors control prediction accuracy. The software to simulate deterministic formulas for genomic prediction accuracy was implemented in R and encapsulated as a web-based Shiny application. Shiny genomic prediction accuracy simulator (ShinyGPAS) simulates various deterministic formulas and delivers dynamic scatter plots of prediction accuracy versus genetic factors impacting prediction accuracy, while requiring only mouse navigation in a web browser. ShinyGPAS is available at: https://chikudaisei.shinyapps.io/shinygpas/ . ShinyGPAS is a shiny-based interactive genomic prediction accuracy simulator using deterministic formulas. It can be used for interactively exploring potential factors that influence prediction accuracy in genome-enabled prediction, simulating achievable prediction accuracy prior to genotyping individuals, or supporting in-class teaching. ShinyGPAS is open source software and it is hosted online as a freely available web-based resource with an intuitive graphical user interface.

Accuracy of endoscopic ultrasonography for diagnosing ulcerative early gastric cancers

PubMed Central

Park, Jin-Seok; Kim, Hyungkil; Bang, Byongwook; Kwon, Kyesook; Shin, Youngwoon

2016-01-01

Abstract Although endoscopic ultrasonography (EUS) is the first-choice imaging modality for predicting the invasion depth of early gastric cancer (EGC), the prediction accuracy of EUS is significantly decreased when EGC is combined with ulceration. The aim of present study was to compare the accuracy of EUS and conventional endoscopy (CE) for determining the depth of EGC. In addition, the various clinic-pathologic factors affecting the diagnostic accuracy of EUS, with a particular focus on endoscopic ulcer shapes, were evaluated. We retrospectively reviewed data from 236 consecutive patients with ulcerative EGC. All patients underwent EUS for estimating tumor invasion depth, followed by either curative surgery or endoscopic treatment. The diagnostic accuracy of EUS and CE was evaluated by comparing the final histologic result of resected specimen. The correlation between accuracy of EUS and characteristics of EGC (tumor size, histology, location in stomach, tumor invasion depth, and endoscopic ulcer shapes) was analyzed. Endoscopic ulcer shapes were classified into 3 groups: definite ulcer, superficial ulcer, and ill-defined ulcer. The overall accuracy of EUS and CE for predicting the invasion depth in ulcerative EGC was 68.6% and 55.5%, respectively. Of the 236 patients, 36 patients were classified as definite ulcers, 98 were superficial ulcers, and 102 were ill-defined ulcers, In univariate analysis, EUS accuracy was associated with invasion depth (P = 0.023), tumor size (P = 0.034), and endoscopic ulcer shapes (P = 0.001). In multivariate analysis, there is a significant association between superficial ulcer in CE and EUS accuracy (odds ratio: 2.977; 95% confidence interval: 1.255–7.064; P = 0.013). The accuracy of EUS for determining tumor invasion depth in ulcerative EGC was superior to that of CE. In addition, ulcer shape was an important factor that affected EUS accuracy. PMID:27472672

Breeding Jatropha curcas by genomic selection: A pilot assessment of the accuracy of predictive models.

PubMed

Azevedo Peixoto, Leonardo de; Laviola, Bruno Galvêas; Alves, Alexandre Alonso; Rosado, Tatiana Barbosa; Bhering, Leonardo Lopes

2017-01-01

Genomic wide selection is a promising approach for improving the selection accuracy in plant breeding, particularly in species with long life cycles, such as Jatropha. Therefore, the objectives of this study were to estimate the genetic parameters for grain yield (GY) and the weight of 100 seeds (W100S) using restricted maximum likelihood (REML); to compare the performance of GWS methods to predict GY and W100S; and to estimate how many markers are needed to train the GWS model to obtain the maximum accuracy. Eight GWS models were compared in terms of predictive ability. The impact that the marker density had on the predictive ability was investigated using a varying number of markers, from 2 to 1,248. Because the genetic variance between evaluated genotypes was significant, it was possible to obtain selection gain. All of the GWS methods tested in this study can be used to predict GY and W100S in Jatropha. A training model fitted using 1,000 and 800 markers is sufficient to capture the maximum genetic variance and, consequently, maximum prediction ability of GY and W100S, respectively. This study demonstrated the applicability of genome-wide prediction to identify useful genetic sources of GY and W100S for Jatropha breeding. Further research is needed to confirm the applicability of the proposed approach to other complex traits.

Dynamic filtering improves attentional state prediction with fNIRS

PubMed Central

Harrivel, Angela R.; Weissman, Daniel H.; Noll, Douglas C.; Huppert, Theodore; Peltier, Scott J.

2016-01-01

Brain activity can predict a person’s level of engagement in an attentional task. However, estimates of brain activity are often confounded by measurement artifacts and systemic physiological noise. The optimal method for filtering this noise – thereby increasing such state prediction accuracy – remains unclear. To investigate this, we asked study participants to perform an attentional task while we monitored their brain activity with functional near infrared spectroscopy (fNIRS). We observed higher state prediction accuracy when noise in the fNIRS hemoglobin [Hb] signals was filtered with a non-stationary (adaptive) model as compared to static regression (84% ± 6% versus 72% ± 15%). PMID:27231602

Protein docking prediction using predicted protein-protein interface.

PubMed

Li, Bin; Kihara, Daisuke

2012-01-10

Many important cellular processes are carried out by protein complexes. To provide physical pictures of interacting proteins, many computational protein-protein prediction methods have been developed in the past. However, it is still difficult to identify the correct docking complex structure within top ranks among alternative conformations. We present a novel protein docking algorithm that utilizes imperfect protein-protein binding interface prediction for guiding protein docking. Since the accuracy of protein binding site prediction varies depending on cases, the challenge is to develop a method which does not deteriorate but improves docking results by using a binding site prediction which may not be 100% accurate. The algorithm, named PI-LZerD (using Predicted Interface with Local 3D Zernike descriptor-based Docking algorithm), is based on a pair wise protein docking prediction algorithm, LZerD, which we have developed earlier. PI-LZerD starts from performing docking prediction using the provided protein-protein binding interface prediction as constraints, which is followed by the second round of docking with updated docking interface information to further improve docking conformation. Benchmark results on bound and unbound cases show that PI-LZerD consistently improves the docking prediction accuracy as compared with docking without using binding site prediction or using the binding site prediction as post-filtering. We have developed PI-LZerD, a pairwise docking algorithm, which uses imperfect protein-protein binding interface prediction to improve docking accuracy. PI-LZerD consistently showed better prediction accuracy over alternative methods in the series of benchmark experiments including docking using actual docking interface site predictions as well as unbound docking cases.

Diagnostic accuracy of 3D-transvaginal ultrasound in detecting uterine cavity abnormalities in infertile patients as compared with hysteroscopy.

PubMed

Apirakviriya, Chayanis; Rungruxsirivorn, Tassawan; Phupong, Vorapong; Wisawasukmongchol, Wirach

2016-05-01

To assess diagnostic accuracy of 3D transvaginal ultrasound (3D-TVS) compared with hysteroscopy in detecting uterine cavity abnormalities in infertile women. This prospective observational cross-sectional study was conducted during the July 2013 to December 2013 study period. Sixty-nine women with infertility were enrolled. In the mid to late follicular phase of each subject's menstrual cycle, 3D transvaginal ultrasound and hysteroscopy were performed on the same day in each patient. Hysteroscopy is widely considered to be the gold standard method for investigation of the uterine cavity. Uterine cavity characteristics and abnormalities were recorded. Diagnostic accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and positive and negative likelihood ratios were evaluated. Hysteroscopy was successfully performed in all subjects. Hysteroscopy diagnosed pathological findings in 22 of 69 cases (31.8%). There were 18 endometrial polyps, 3 submucous myomas, and 1 septate uterus. Three-dimensional transvaginal ultrasound in comparison with hysteroscopy had 84.1% diagnostic accuracy, 68.2% sensitivity, 91.5% specificity, 79% positive predictive value, and 86% negative predictive value. The positive and negative likelihood ratios were 8.01 and 0.3, respectively. 3D-TVS successfully detected every case of submucous myoma and uterine anomaly. For detection of endometrial polyps, 3D-TVS had 61.1% sensitivity, 91.5% specificity, and 83.1% diagnostic accuracy. 3D-TVS demonstrated 84.1% diagnostic accuracy for detecting uterine cavity abnormalities in infertile women. A significant percentage of infertile patients had evidence of uterine cavity pathology. Hysteroscopy is, therefore, recommended for accurate detection and diagnosis of uterine cavity lesion. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Population variation in isotopic composition of shorebird feathers: Implications for determining molting grounds

USGS Publications Warehouse

Torres-Dowdall, J.; Farmer, A.H.; Bucher, E.H.; Rye, R.O.; Landis, G.

2009-01-01

Stable isotope analyses have revolutionized the study of migratory connectivity. However, as with all tools, their limitations must be understood in order to derive the maximum benefit of a particular application. The goal of this study was to evaluate the efficacy of stable isotopes of C, N, H, O and S for assigning known-origin feathers to the molting sites of migrant shorebird species wintering and breeding in Argentina. Specific objectives were to: 1) compare the efficacy of the technique for studying shorebird species with different migration patterns, life histories and habitat-use patterns; 2) evaluate the grouping of species with similar migration and habitat use patterns in a single analysis to potentially improve prediction accuracy; and 3) evaluate the potential gains in prediction accuracy that might be achieved from using multiple stable isotopes. The efficacy of stable isotope ratios to determine origin was found to vary with species. While one species (White-rumped Sandpiper, Calidris fuscicollis) had high levels of accuracy assigning samples to known origin (91% of samples correctly assigned), another (Collared Plover, Charadrius collaris) showed low levels of accuracy (52% of samples correctly assigned). Intra-individual variability may account for this difference in efficacy. The prediction model for three species with similar migration and habitat-use patterns performed poorly compared with the model for just one of the species (71% versus 91% of samples correctly assigned). Thus, combining multiple sympatric species may not improve model prediction accuracy. Increasing the number of stable isotopes in the analyses increased the accuracy of assigning shorebirds to their molting origin, but the best combination - involving a subset of all the isotopes analyzed - varied among species.

Predicting Voice Disorder Status From Smoothed Measures of Cepstral Peak Prominence Using Praat and Analysis of Dysphonia in Speech and Voice (ADSV).

PubMed

Sauder, Cara; Bretl, Michelle; Eadie, Tanya

2017-09-01

The purposes of this study were to (1) determine and compare the diagnostic accuracy of a single acoustic measure, smoothed cepstral peak prominence (CPPS), to predict voice disorder status from connected speech samples using two software systems: Analysis of Dysphonia in Speech and Voice (ADSV) and Praat; and (2) to determine the relationship between measures of CPPS generated from these programs. This is a retrospective cross-sectional study. Measures of CPPS were obtained from connected speech recordings of 100 subjects with voice disorders and 70 nondysphonic subjects without vocal complaints using commercially available ADSV and freely downloadable Praat software programs. Logistic regression and receiver operating characteristic (ROC) analyses were used to evaluate and compare the diagnostic accuracy of CPPS measures. Relationships between CPPS measures from the programs were determined. Results showed acceptable overall accuracy rates (75% accuracy, ADSV; 82% accuracy, Praat) and area under the ROC curves (area under the curve [AUC] = 0.81, ADSV; AUC = 0.91, Praat) for predicting voice disorder status, with slight differences in sensitivity and specificity. CPPS measures derived from Praat were uniquely predictive of disorder status above and beyond CPPS measures from ADSV (χ 2 (1) = 40.71, P < 0.001). CPPS measures from both programs were significantly and highly correlated (r = 0.88, P < 0.001). A single acoustic measure of CPPS was highly predictive of voice disorder status using either program. Clinicians may consider using CPPS to complement clinical voice evaluation and screening protocols. Copyright © 2017 The Voice Foundation. Published by Elsevier Inc. All rights reserved.

The influence of delaying judgments of learning on metacognitive accuracy: a meta-analytic review.

PubMed

Rhodes, Matthew G; Tauber, Sarah K

2011-01-01

Many studies have examined the accuracy of predictions of future memory performance solicited through judgments of learning (JOLs). Among the most robust findings in this literature is that delaying predictions serves to substantially increase the relative accuracy of JOLs compared with soliciting JOLs immediately after study, a finding termed the delayed JOL effect. The meta-analyses reported in the current study examined the predominant theoretical accounts as well as potential moderators of the delayed JOL effect. The first meta-analysis examined the relative accuracy of delayed compared with immediate JOLs across 4,554 participants (112 effect sizes) through gamma correlations between JOLs and memory accuracy. Those data showed that delaying JOLs leads to robust benefits to relative accuracy (g = 0.93). The second meta-analysis examined memory performance for delayed compared with immediate JOLs across 3,807 participants (98 effect sizes). Those data showed that delayed JOLs result in a modest but reliable benefit for memory performance relative to immediate JOLs (g = 0.08). Findings from these meta-analyses are well accommodated by theories suggesting that delayed JOL accuracy reflects access to more diagnostic information from long-term memory rather than being a by-product of a retrieval opportunity. However, these data also suggest that theories proposing that the delayed JOL effect results from a memorial benefit or the match between the cues available for JOLs and those available at test may also provide viable explanatory mechanisms necessary for a comprehensive account.

Contingency Awareness Shapes Acquisition and Extinction of Emotional Responses in a Conditioning Model of Pain-Related Fear

PubMed Central

Labrenz, Franziska; Icenhour, Adriane; Benson, Sven; Elsenbruch, Sigrid

2015-01-01

As a fundamental learning process, fear conditioning promotes the formation of associations between predictive cues and biologically significant signals. In its application to pain, conditioning may provide important insight into mechanisms underlying pain-related fear, although knowledge especially in interoceptive pain paradigms remains scarce. Furthermore, while the influence of contingency awareness on excitatory learning is subject of ongoing debate, its role in pain-related acquisition is poorly understood and essentially unknown regarding extinction as inhibitory learning. Therefore, we addressed the impact of contingency awareness on learned emotional responses to pain- and safety-predictive cues in a combined dataset of two pain-related conditioning studies. In total, 75 healthy participants underwent differential fear acquisition, during which rectal distensions as interoceptive unconditioned stimuli (US) were repeatedly paired with a predictive visual cue (conditioned stimulus; CS+) while another cue (CS−) was presented unpaired. During extinction, both CS were presented without US. CS valence, indicating learned emotional responses, and CS-US contingencies were assessed on visual analog scales (VAS). Based on an integrative measure of contingency accuracy, a median-split was performed to compare groups with low vs. high contingency accuracy regarding learned emotional responses. To investigate predictive value of contingency accuracy, regression analyses were conducted. Highly accurate individuals revealed more pronounced negative emotional responses to CS+ and increased positive responses to CS− when compared to participants with low contingency accuracy. Following extinction, highly accurate individuals had fully extinguished pain-predictive cue properties, while exhibiting persistent positive emotional responses to safety signals. In contrast, individuals with low accuracy revealed equally positive emotional responses to both, CS+ and CS−. Contingency accuracy predicted variance in the formation of positive responses to safety cues while no predictive value was found for danger cues following acquisition and for neither cue following extinction. Our findings underscore specific roles of learned danger and safety in pain-related acquisition and extinction. Contingency accuracy appears to distinctly impact learned emotional responses to safety and danger cues, supporting aversive learning to occur independently from CS-US awareness. The interplay of cognitive and emotional factors in shaping excitatory and inhibitory pain-related learning may contribute to altered pain processing, underscoring its clinical relevance in chronic pain. PMID:26640433

Contingency Awareness Shapes Acquisition and Extinction of Emotional Responses in a Conditioning Model of Pain-Related Fear.

PubMed

Labrenz, Franziska; Icenhour, Adriane; Benson, Sven; Elsenbruch, Sigrid

2015-01-01

As a fundamental learning process, fear conditioning promotes the formation of associations between predictive cues and biologically significant signals. In its application to pain, conditioning may provide important insight into mechanisms underlying pain-related fear, although knowledge especially in interoceptive pain paradigms remains scarce. Furthermore, while the influence of contingency awareness on excitatory learning is subject of ongoing debate, its role in pain-related acquisition is poorly understood and essentially unknown regarding extinction as inhibitory learning. Therefore, we addressed the impact of contingency awareness on learned emotional responses to pain- and safety-predictive cues in a combined dataset of two pain-related conditioning studies. In total, 75 healthy participants underwent differential fear acquisition, during which rectal distensions as interoceptive unconditioned stimuli (US) were repeatedly paired with a predictive visual cue (conditioned stimulus; CS(+)) while another cue (CS(-)) was presented unpaired. During extinction, both CS were presented without US. CS valence, indicating learned emotional responses, and CS-US contingencies were assessed on visual analog scales (VAS). Based on an integrative measure of contingency accuracy, a median-split was performed to compare groups with low vs. high contingency accuracy regarding learned emotional responses. To investigate predictive value of contingency accuracy, regression analyses were conducted. Highly accurate individuals revealed more pronounced negative emotional responses to CS(+) and increased positive responses to CS(-) when compared to participants with low contingency accuracy. Following extinction, highly accurate individuals had fully extinguished pain-predictive cue properties, while exhibiting persistent positive emotional responses to safety signals. In contrast, individuals with low accuracy revealed equally positive emotional responses to both, CS(+) and CS(-). Contingency accuracy predicted variance in the formation of positive responses to safety cues while no predictive value was found for danger cues following acquisition and for neither cue following extinction. Our findings underscore specific roles of learned danger and safety in pain-related acquisition and extinction. Contingency accuracy appears to distinctly impact learned emotional responses to safety and danger cues, supporting aversive learning to occur independently from CS-US awareness. The interplay of cognitive and emotional factors in shaping excitatory and inhibitory pain-related learning may contribute to altered pain processing, underscoring its clinical relevance in chronic pain.

Artificial neural networks: Predicting head CT findings in elderly patients presenting with minor head injury after a fall.

PubMed

Dusenberry, Michael W; Brown, Charles K; Brewer, Kori L

2017-02-01

To construct an artificial neural network (ANN) model that can predict the presence of acute CT findings with both high sensitivity and high specificity when applied to the population of patients≥age 65years who have incurred minor head injury after a fall. An ANN was created in the Python programming language using a population of 514 patients ≥ age 65 years presenting to the ED with minor head injury after a fall. The patient dataset was divided into three parts: 60% for "training", 20% for "cross validation", and 20% for "testing". Sensitivity, specificity, positive and negative predictive values, and accuracy were determined by comparing the model's predictions to the actual correct answers for each patient. On the "cross validation" data, the model attained a sensitivity ("recall") of 100.00%, specificity of 78.95%, PPV ("precision") of 78.95%, NPV of 100.00%, and accuracy of 88.24% in detecting the presence of positive head CTs. On the "test" data, the model attained a sensitivity of 97.78%, specificity of 89.47%, PPV of 88.00%, NPV of 98.08%, and accuracy of 93.14% in detecting the presence of positive head CTs. ANNs show great potential for predicting CT findings in the population of patients ≥ 65 years of age presenting with minor head injury after a fall. As a good first step, the ANN showed comparable sensitivity, predictive values, and accuracy, with a much higher specificity than the existing decision rules in clinical usage for predicting head CTs with acute intracranial findings. Copyright © 2016 Elsevier Inc. All rights reserved.

Clinical Inquiry: What's the best way to predict the success of a trial of labor after a previous C-section?

PubMed

Warren, Johanna B; Hamilton, Andrew

2015-12-01

Seven validated prospective scoring systems, and one unvalidated system, predict a successful TOLAC based on a variety of clinical factors. The systems use different outcome statistics, so their predictive accuracy can't be directly compared.

The importance of information on relatives for the prediction of genomic breeding values and the implications for the makeup of reference data sets in livestock breeding schemes.

PubMed

Clark, Samuel A; Hickey, John M; Daetwyler, Hans D; van der Werf, Julius H J

2012-02-09

The theory of genomic selection is based on the prediction of the effects of genetic markers in linkage disequilibrium with quantitative trait loci. However, genomic selection also relies on relationships between individuals to accurately predict genetic value. This study aimed to examine the importance of information on relatives versus that of unrelated or more distantly related individuals on the estimation of genomic breeding values. Simulated and real data were used to examine the effects of various degrees of relationship on the accuracy of genomic selection. Genomic Best Linear Unbiased Prediction (gBLUP) was compared to two pedigree based BLUP methods, one with a shallow one generation pedigree and the other with a deep ten generation pedigree. The accuracy of estimated breeding values for different groups of selection candidates that had varying degrees of relationships to a reference data set of 1750 animals was investigated. The gBLUP method predicted breeding values more accurately than BLUP. The most accurate breeding values were estimated using gBLUP for closely related animals. Similarly, the pedigree based BLUP methods were also accurate for closely related animals, however when the pedigree based BLUP methods were used to predict unrelated animals, the accuracy was close to zero. In contrast, gBLUP breeding values, for animals that had no pedigree relationship with animals in the reference data set, allowed substantial accuracy. An animal's relationship to the reference data set is an important factor for the accuracy of genomic predictions. Animals that share a close relationship to the reference data set had the highest accuracy from genomic predictions. However a baseline accuracy that is driven by the reference data set size and the overall population effective population size enables gBLUP to estimate a breeding value for unrelated animals within a population (breed), using information previously ignored by pedigree based BLUP methods.

Prognostic accuracy of cerebroplacental ratio and middle cerebral artery Doppler for adverse perinatal outcome: systematic review and meta‐analysis

PubMed Central

De Boer, M. A.; Heymans, M. W.; Schoonmade, L. J.; Bossuyt, P. M. M.; Mol, B. W. J.; De Groot, C. J. M.; Bax, C. J.

2018-01-01

ABSTRACT Objective Doppler ultrasonographic assessment of the cerebroplacental ratio (CPR) and middle cerebral artery (MCA) is widely used as an adjunct to umbilical artery (UA) Doppler to identify fetuses at risk of adverse perinatal outcome. However, reported estimates of its accuracy vary considerably. The aim of this study was to review systematically the prognostic accuracies of CPR and MCA Doppler in predicting adverse perinatal outcome, and to compare these with UA Doppler, in order to identify whether CPR and MCA Doppler evaluation are of added value to UA Doppler. Methods PubMed, EMBASE, the Cochrane Library and ClinicalTrials.gov were searched, from inception to June 2016, for studies on the prognostic accuracy of UA Doppler compared with CPR and/or MCA Doppler in the prediction of adverse perinatal outcome in women with a singleton pregnancy of any risk profile. Risk of bias and concerns about applicability were assessed using the QUADAS‐2 (Quality Assessment of Diagnostic Accuracy Studies‐2) tool. Meta‐analysis was performed for multiple adverse perinatal outcomes. Using hierarchal summary receiver–operating characteristics meta‐regression models, the prognostic accuracy of CPR vs MCA Doppler was compared indirectly, and CPR and MCA Doppler vs UA Doppler compared directly. Results The search identified 4693 articles, of which 128 studies (involving 47 748 women) were included. Risk of bias or suboptimal reporting was detected in 120/128 studies (94%) and substantial heterogeneity was found, which limited subgroup analyses for fetal growth and gestational age. A large variation was observed in reported sensitivities and specificities, and in thresholds used. CPR outperformed UA Doppler in the prediction of composite adverse outcome (as defined in the included studies) (P < 0.001) and emergency delivery for fetal distress (P = 0.003), but was comparable to UA Doppler for the other outcomes. MCA Doppler performed significantly worse than did UA Doppler in the prediction of low Apgar score (P = 0.017) and emergency delivery for fetal distress (P = 0.034). CPR outperformed MCA Doppler in the prediction of composite adverse outcome (P < 0.001) and emergency delivery for fetal distress (P = 0.013). Conclusion Calculating the CPR with MCA Doppler can add value to UA Doppler assessment in the prediction of adverse perinatal outcome in women with a singleton pregnancy. However, it is unclear to which subgroup of pregnant women this applies. The effectiveness of the CPR in guiding clinical management needs to be evaluated in clinical trials. © 2017 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of the International Society of Ultrasound in Obstetrics and Gynecology. PMID:28708272

Feature Selection Methods for Zero-Shot Learning of Neural Activity

PubMed Central

Caceres, Carlos A.; Roos, Matthew J.; Rupp, Kyle M.; Milsap, Griffin; Crone, Nathan E.; Wolmetz, Michael E.; Ratto, Christopher R.

2017-01-01

Dimensionality poses a serious challenge when making predictions from human neuroimaging data. Across imaging modalities, large pools of potential neural features (e.g., responses from particular voxels, electrodes, and temporal windows) have to be related to typically limited sets of stimuli and samples. In recent years, zero-shot prediction models have been introduced for mapping between neural signals and semantic attributes, which allows for classification of stimulus classes not explicitly included in the training set. While choices about feature selection can have a substantial impact when closed-set accuracy, open-set robustness, and runtime are competing design objectives, no systematic study of feature selection for these models has been reported. Instead, a relatively straightforward feature stability approach has been adopted and successfully applied across models and imaging modalities. To characterize the tradeoffs in feature selection for zero-shot learning, we compared correlation-based stability to several other feature selection techniques on comparable data sets from two distinct imaging modalities: functional Magnetic Resonance Imaging and Electrocorticography. While most of the feature selection methods resulted in similar zero-shot prediction accuracies and spatial/spectral patterns of selected features, there was one exception; A novel feature/attribute correlation approach was able to achieve those accuracies with far fewer features, suggesting the potential for simpler prediction models that yield high zero-shot classification accuracy. PMID:28690513

Combined ECG, Echocardiographic, and Biomarker Criteria for Diagnosing Acute Myocardial Infarction in Out-of-Hospital Cardiac Arrest Patients.

PubMed

Lee, Sang-Eun; Uhm, Jae-Sun; Kim, Jong-Youn; Pak, Hui-Nam; Lee, Moon-Hyoung; Joung, Boyoung

2015-07-01

Acute coronary lesions commonly trigger out-of-hospital cardiac arrest (OHCA). However, the prevalence of coronary artery disease (CAD) in Asian patients with OHCA and whether electrocardiogram (ECG) and other findings might predict acute myocardial infarction (AMI) have not been fully elucidated. Of 284 consecutive resuscitated OHCA patients seen between January 2006 and July 2013, we enrolled 135 patients who had undergone coronary evaluation. ECGs, echocardiography, and biomarkers were compared between patients with or without CAD. We included 135 consecutive patients aged 54 years (interquartile range 45-65) with sustained return of spontaneous circulation after OHCA between 2006 and 2012. Sixty six (45%) patients had CAD. The initial rhythm was shockable and non-shockable in 110 (81%) and 25 (19%) patients, respectively. ST-segment elevation predicted CAD with 42% sensitivity, 87% specificity, and 65% accuracy. ST elevation and/or regional wall motion abnormality (RWMA) showed 68% sensitivity, 52% specificity, and 70% accuracy in the prediction of CAD. Finally, a combination of ST elevation and/or RWMA and/or troponin T elevation predicted CAD with 94% sensitivity, 17% specificity, and 55% accuracy. In patients with OHCA without obvious non-cardiac causes, selection for coronary angiogram based on the combined criterion could detect 94% of CADs. However, compared with ECG only criteria, the combined criterion failed to improve diagnostic accuracy with a lower specificity.

A hybrid PSO-SVM-based method for predicting the friction coefficient between aircraft tire and coating

NASA Astrophysics Data System (ADS)

Zhan, Liwei; Li, Chengwei

2017-02-01

A hybrid PSO-SVM-based model is proposed to predict the friction coefficient between aircraft tire and coating. The presented hybrid model combines a support vector machine (SVM) with particle swarm optimization (PSO) technique. SVM has been adopted to solve regression problems successfully. Its regression accuracy is greatly related to optimizing parameters such as the regularization constant C , the parameter gamma γ corresponding to RBF kernel and the epsilon parameter \\varepsilon in the SVM training procedure. However, the friction coefficient which is predicted based on SVM has yet to be explored between aircraft tire and coating. The experiment reveals that drop height and tire rotational speed are the factors affecting friction coefficient. Bearing in mind, the friction coefficient can been predicted using the hybrid PSO-SVM-based model by the measured friction coefficient between aircraft tire and coating. To compare regression accuracy, a grid search (GS) method and a genetic algorithm (GA) are used to optimize the relevant parameters (C , γ and \\varepsilon ), respectively. The regression accuracy could be reflected by the coefficient of determination ({{R}2} ). The result shows that the hybrid PSO-RBF-SVM-based model has better accuracy compared with the GS-RBF-SVM- and GA-RBF-SVM-based models. The agreement of this model (PSO-RBF-SVM) with experiment data confirms its good performance.

Three-dimensional virtual planning in orthognathic surgery enhances the accuracy of soft tissue prediction.

PubMed

Van Hemelen, Geert; Van Genechten, Maarten; Renier, Lieven; Desmedt, Maria; Verbruggen, Elric; Nadjmi, Nasser

2015-07-01

Throughout the history of computing, shortening the gap between the physical and digital world behind the screen has always been strived for. Recent advances in three-dimensional (3D) virtual surgery programs have reduced this gap significantly. Although 3D assisted surgery is now widely available for orthognathic surgery, one might still argue whether a 3D virtual planning approach is a better alternative to a conventional two-dimensional (2D) planning technique. The purpose of this study was to compare the accuracy of a traditional 2D technique and a 3D computer-aided prediction method. A double blind randomised prospective study was performed to compare the prediction accuracy of a traditional 2D planning technique versus a 3D computer-aided planning approach. The accuracy of the hard and soft tissue profile predictions using both planning methods was investigated. There was a statistically significant difference between 2D and 3D soft tissue planning (p < 0.05). The statistically significant difference found between 2D and 3D planning and the actual soft tissue outcome was not confirmed by a statistically significant difference between methods. The 3D planning approach provides more accurate soft tissue planning. However, the 2D orthognathic planning is comparable to 3D planning when it comes to hard tissue planning. This study provides relevant results for choosing between 3D and 2D planning in clinical practice. Copyright © 2015 European Association for Cranio-Maxillo-Facial Surgery. Published by Elsevier Ltd. All rights reserved.

3D Cloud Field Prediction using A-Train Data and Machine Learning Techniques

NASA Astrophysics Data System (ADS)

Johnson, C. L.

2017-12-01

Validation of cloud process parameterizations used in global climate models (GCMs) would greatly benefit from observed 3D cloud fields at the size comparable to that of a GCM grid cell. For the highest resolution simulations, surface grid cells are on the order of 100 km by 100 km. CloudSat/CALIPSO data provides 1 km width of detailed vertical cloud fraction profile (CFP) and liquid and ice water content (LWC/IWC). This work utilizes four machine learning algorithms to create nonlinear regressions of CFP, LWC, and IWC data using radiances, surface type and location of measurement as predictors and applies the regression equations to off-track locations generating 3D cloud fields for 100 km by 100 km domains. The CERES-CloudSat-CALIPSO-MODIS (C3M) merged data set for February 2007 is used. Support Vector Machines, Artificial Neural Networks, Gaussian Processes and Decision Trees are trained on 1000 km of continuous C3M data. Accuracy is computed using existing vertical profiles that are excluded from the training data and occur within 100 km of the training data. Accuracy of the four algorithms is compared. Average accuracy for one day of predicted data is 86% for the most successful algorithm. The methodology for training the algorithms, determining valid prediction regions and applying the equations off-track is discussed. Predicted 3D cloud fields are provided as inputs to the Ed4 NASA LaRC Fu-Liou radiative transfer code and resulting TOA radiances compared to observed CERES/MODIS radiances. Differences in computed radiances using predicted profiles and observed radiances are compared.

Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests

PubMed Central

2011-01-01

Background Dementia and cognitive impairment associated with aging are a major medical and social concern. Neuropsychological testing is a key element in the diagnostic procedures of Mild Cognitive Impairment (MCI), but has presently a limited value in the prediction of progression to dementia. We advance the hypothesis that newer statistical classification methods derived from data mining and machine learning methods like Neural Networks, Support Vector Machines and Random Forests can improve accuracy, sensitivity and specificity of predictions obtained from neuropsychological testing. Seven non parametric classifiers derived from data mining methods (Multilayer Perceptrons Neural Networks, Radial Basis Function Neural Networks, Support Vector Machines, CART, CHAID and QUEST Classification Trees and Random Forests) were compared to three traditional classifiers (Linear Discriminant Analysis, Quadratic Discriminant Analysis and Logistic Regression) in terms of overall classification accuracy, specificity, sensitivity, Area under the ROC curve and Press'Q. Model predictors were 10 neuropsychological tests currently used in the diagnosis of dementia. Statistical distributions of classification parameters obtained from a 5-fold cross-validation were compared using the Friedman's nonparametric test. Results Press' Q test showed that all classifiers performed better than chance alone (p < 0.05). Support Vector Machines showed the larger overall classification accuracy (Median (Me) = 0.76) an area under the ROC (Me = 0.90). However this method showed high specificity (Me = 1.0) but low sensitivity (Me = 0.3). Random Forest ranked second in overall accuracy (Me = 0.73) with high area under the ROC (Me = 0.73) specificity (Me = 0.73) and sensitivity (Me = 0.64). Linear Discriminant Analysis also showed acceptable overall accuracy (Me = 0.66), with acceptable area under the ROC (Me = 0.72) specificity (Me = 0.66) and sensitivity (Me = 0.64). The remaining classifiers showed overall classification accuracy above a median value of 0.63, but for most sensitivity was around or even lower than a median value of 0.5. Conclusions When taking into account sensitivity, specificity and overall classification accuracy Random Forests and Linear Discriminant analysis rank first among all the classifiers tested in prediction of dementia using several neuropsychological tests. These methods may be used to improve accuracy, sensitivity and specificity of Dementia predictions from neuropsychological testing. PMID:21849043

Mean Expected Error in Prediction of Total Body Water: A True Accuracy Comparison between Bioimpedance Spectroscopy and Single Frequency Regression Equations

PubMed Central

Abtahi, Shirin; Abtahi, Farhad; Ellegård, Lars; Johannsson, Gudmundur; Bosaeus, Ingvar

2015-01-01

For several decades electrical bioimpedance (EBI) has been used to assess body fluid distribution and body composition. Despite the development of several different approaches for assessing total body water (TBW), it remains uncertain whether bioimpedance spectroscopic (BIS) approaches are more accurate than single frequency regression equations. The main objective of this study was to answer this question by calculating the expected accuracy of a single measurement for different EBI methods. The results of this study showed that all methods produced similarly high correlation and concordance coefficients, indicating good accuracy as a method. Even the limits of agreement produced from the Bland-Altman analysis indicated that the performance of single frequency, Sun's prediction equations, at population level was close to the performance of both BIS methods; however, when comparing the Mean Absolute Percentage Error value between the single frequency prediction equations and the BIS methods, a significant difference was obtained, indicating slightly better accuracy for the BIS methods. Despite the higher accuracy of BIS methods over 50 kHz prediction equations at both population and individual level, the magnitude of the improvement was small. Such slight improvement in accuracy of BIS methods is suggested insufficient to warrant their clinical use where the most accurate predictions of TBW are required, for example, when assessing over-fluidic status on dialysis. To reach expected errors below 4-5%, novel and individualized approaches must be developed to improve the accuracy of bioimpedance-based methods for the advent of innovative personalized health monitoring applications. PMID:26137489

Canopy Temperature and Vegetation Indices from High-Throughput Phenotyping Improve Accuracy of Pedigree and Genomic Selection for Grain Yield in Wheat

PubMed Central

Rutkoski, Jessica; Poland, Jesse; Mondal, Suchismita; Autrique, Enrique; Pérez, Lorena González; Crossa, José; Reynolds, Matthew; Singh, Ravi

2016-01-01

Genomic selection can be applied prior to phenotyping, enabling shorter breeding cycles and greater rates of genetic gain relative to phenotypic selection. Traits measured using high-throughput phenotyping based on proximal or remote sensing could be useful for improving pedigree and genomic prediction model accuracies for traits not yet possible to phenotype directly. We tested if using aerial measurements of canopy temperature, and green and red normalized difference vegetation index as secondary traits in pedigree and genomic best linear unbiased prediction models could increase accuracy for grain yield in wheat, Triticum aestivum L., using 557 lines in five environments. Secondary traits on training and test sets, and grain yield on the training set were modeled as multivariate, and compared to univariate models with grain yield on the training set only. Cross validation accuracies were estimated within and across-environment, with and without replication, and with and without correcting for days to heading. We observed that, within environment, with unreplicated secondary trait data, and without correcting for days to heading, secondary traits increased accuracies for grain yield by 56% in pedigree, and 70% in genomic prediction models, on average. Secondary traits increased accuracy slightly more when replicated, and considerably less when models corrected for days to heading. In across-environment prediction, trends were similar but less consistent. These results show that secondary traits measured in high-throughput could be used in pedigree and genomic prediction to improve accuracy. This approach could improve selection in wheat during early stages if validated in early-generation breeding plots. PMID:27402362

Variable selection models for genomic selection using whole-genome sequence data and singular value decomposition.

PubMed

Meuwissen, Theo H E; Indahl, Ulf G; Ødegård, Jørgen

2017-12-27

Non-linear Bayesian genomic prediction models such as BayesA/B/C/R involve iteration and mostly Markov chain Monte Carlo (MCMC) algorithms, which are computationally expensive, especially when whole-genome sequence (WGS) data are analyzed. Singular value decomposition (SVD) of the genotype matrix can facilitate genomic prediction in large datasets, and can be used to estimate marker effects and their prediction error variances (PEV) in a computationally efficient manner. Here, we developed, implemented, and evaluated a direct, non-iterative method for the estimation of marker effects for the BayesC genomic prediction model. The BayesC model assumes a priori that markers have normally distributed effects with probability [Formula: see text] and no effect with probability (1 - [Formula: see text]). Marker effects and their PEV are estimated by using SVD and the posterior probability of the marker having a non-zero effect is calculated. These posterior probabilities are used to obtain marker-specific effect variances, which are subsequently used to approximate BayesC estimates of marker effects in a linear model. A computer simulation study was conducted to compare alternative genomic prediction methods, where a single reference generation was used to estimate marker effects, which were subsequently used for 10 generations of forward prediction, for which accuracies were evaluated. SVD-based posterior probabilities of markers having non-zero effects were generally lower than MCMC-based posterior probabilities, but for some regions the opposite occurred, resulting in clear signals for QTL-rich regions. The accuracies of breeding values estimated using SVD- and MCMC-based BayesC analyses were similar across the 10 generations of forward prediction. For an intermediate number of generations (2 to 5) of forward prediction, accuracies obtained with the BayesC model tended to be slightly higher than accuracies obtained using the best linear unbiased prediction of SNP effects (SNP-BLUP model). When reducing marker density from WGS data to 30 K, SNP-BLUP tended to yield the highest accuracies, at least in the short term. Based on SVD of the genotype matrix, we developed a direct method for the calculation of BayesC estimates of marker effects. Although SVD- and MCMC-based marker effects differed slightly, their prediction accuracies were similar. Assuming that the SVD of the marker genotype matrix is already performed for other reasons (e.g. for SNP-BLUP), computation times for the BayesC predictions were comparable to those of SNP-BLUP.

RNA secondary structure prediction with pseudoknots: Contribution of algorithm versus energy model.

PubMed

Jabbari, Hosna; Wark, Ian; Montemagno, Carlo

2018-01-01

RNA is a biopolymer with various applications inside the cell and in biotechnology. Structure of an RNA molecule mainly determines its function and is essential to guide nanostructure design. Since experimental structure determination is time-consuming and expensive, accurate computational prediction of RNA structure is of great importance. Prediction of RNA secondary structure is relatively simpler than its tertiary structure and provides information about its tertiary structure, therefore, RNA secondary structure prediction has received attention in the past decades. Numerous methods with different folding approaches have been developed for RNA secondary structure prediction. While methods for prediction of RNA pseudoknot-free structure (structures with no crossing base pairs) have greatly improved in terms of their accuracy, methods for prediction of RNA pseudoknotted secondary structure (structures with crossing base pairs) still have room for improvement. A long-standing question for improving the prediction accuracy of RNA pseudoknotted secondary structure is whether to focus on the prediction algorithm or the underlying energy model, as there is a trade-off on computational cost of the prediction algorithm versus the generality of the method. The aim of this work is to argue when comparing different methods for RNA pseudoknotted structure prediction, the combination of algorithm and energy model should be considered and a method should not be considered superior or inferior to others if they do not use the same scoring model. We demonstrate that while the folding approach is important in structure prediction, it is not the only important factor in prediction accuracy of a given method as the underlying energy model is also as of great value. Therefore we encourage researchers to pay particular attention in comparing methods with different energy models.

Comparison of Three Risk Scores to Predict Outcomes of Severe Lower Gastrointestinal Bleeding.

PubMed

Camus, Marine; Jensen, Dennis M; Ohning, Gordon V; Kovacs, Thomas O; Jutabha, Rome; Ghassemi, Kevin A; Machicado, Gustavo A; Dulai, Gareth S; Jensen, Mary E; Gornbein, Jeffrey A

2016-01-01

Improved medical decisions by using a score at the initial patient triage level may lead to improvements in patient management, outcomes, and resource utilization. There is no validated score for management of lower gastrointestinal bleeding (LGIB) unlike for upper gastrointestinal bleeding. The aim of our study was to compare the accuracies of 3 different prognostic scores [Center for Ulcer Research and Education Hemostasis prognosis score, Charlson index, and American Society of Anesthesiologists (ASA) score] for the prediction of 30-day rebleeding, surgery, and death in severe LGIB. Data on consecutive patients hospitalized with severe gastrointestinal bleeding from January 2006 to October 2011 in our 2 tertiary academic referral centers were prospectively collected. Sensitivities, specificities, accuracies, and area under the receiver operator characteristic curve were computed for 3 scores for predictions of rebleeding, surgery, and mortality at 30 days. Two hundred thirty-five consecutive patients with LGIB were included between 2006 and 2011. Twenty-three percent of patients rebled, 6% had surgery, and 7.7% of patients died. The accuracies of each score never reached 70% for predicting rebleeding or surgery in either. The ASA score had a highest accuracy for predicting mortality within 30 days (83.5%), whereas the Center for Ulcer Research and Education Hemostasis prognosis score and the Charlson index both had accuracies <75% for the prediction of death within 30 days. ASA score could be useful to predict death within 30 days. However, a new score is still warranted to predict all 30 days outcomes (rebleeding, surgery, and death) in LGIB.

A comparison of multivariate and univariate time series approaches to modelling and forecasting emergency department demand in Western Australia.

PubMed

Aboagye-Sarfo, Patrick; Mai, Qun; Sanfilippo, Frank M; Preen, David B; Stewart, Louise M; Fatovich, Daniel M

2015-10-01

To develop multivariate vector-ARMA (VARMA) forecast models for predicting emergency department (ED) demand in Western Australia (WA) and compare them to the benchmark univariate autoregressive moving average (ARMA) and Winters' models. Seven-year monthly WA state-wide public hospital ED presentation data from 2006/07 to 2012/13 were modelled. Graphical and VARMA modelling methods were used for descriptive analysis and model fitting. The VARMA models were compared to the benchmark univariate ARMA and Winters' models to determine their accuracy to predict ED demand. The best models were evaluated by using error correction methods for accuracy. Descriptive analysis of all the dependent variables showed an increasing pattern of ED use with seasonal trends over time. The VARMA models provided a more precise and accurate forecast with smaller confidence intervals and better measures of accuracy in predicting ED demand in WA than the ARMA and Winters' method. VARMA models are a reliable forecasting method to predict ED demand for strategic planning and resource allocation. While the ARMA models are a closely competing alternative, they under-estimated future ED demand. Copyright © 2015 Elsevier Inc. All rights reserved.

Diagnostic accuracy of tuberculous lymphadenitis fine needle aspiration biopsy confirmed by PCR as gold standard

NASA Astrophysics Data System (ADS)

DSuryadi; Delyuzar; Soekimin

2018-03-01

Indonesia is the second country with the TB (tuberculosis) burden in the world. Improvement in controlling TB and reducing the complications can accelerate early diagnosis and correct treatment. PCR test is a gold standard. However, it is quite expensive for routine diagnosis. Therefore, an accurate and cheaper diagnostic method such as fine needle aspiration biopsy is needed. The study aimsto determine the accuracy of fine needle aspiration biopsy cytology in the diagnosis of tuberculous lymphadenitis. A cross-sectional analytic study was conducted to the samples from patients suspected with tuberculous lymphadenitis. The fine needle aspiration biopsy (FNAB)test was performed and confirmed by PCR test.There is a comparison to the sensitivity, specificity, accuracy, positive predictive value and negative predictive value of both methods. Sensitivity (92.50%), specificity (96.49%), accuracy (94.85%), positive predictive value (94.87%) and negative predictive value (94.83%) were in FNAB test compared to gold standard. We concluded that fine needle aspiration biopsy is a recommendation for a cheaper and accurate diagnostic test for tuberculous lymphadenitis diagnosis.

Evaluating Diagnostic Accuracy of Noninvasive Tests in Assessment of Significant Liver Fibrosis in Chronic Hepatitis C Egyptian Patients.

PubMed

Omran, Dalia; Zayed, Rania A; Nabeel, Mohammed M; Mobarak, Lamiaa; Zakaria, Zeinab; Farid, Azza; Hassany, Mohamed; Saif, Sameh; Mostafa, Muhammad; Saad, Omar Khalid; Yosry, Ayman

2018-05-01

Stage of liver fibrosis is critical for treatment decision and prediction of outcomes in chronic hepatitis C (CHC) patients. We evaluated the diagnostic accuracy of transient elastography (TE)-FibroScan and noninvasive serum markers tests in the assessment of liver fibrosis in CHC patients, in reference to liver biopsy. One-hundred treatment-naive CHC patients were subjected to liver biopsy, TE-FibroScan, and eight serum biomarkers tests; AST/ALT ratio (AAR), AST to platelet ratio index (APRI), age-platelet index (AP index), fibrosis quotient (FibroQ), fibrosis 4 index (FIB-4), cirrhosis discriminant score (CDS), King score, and Goteborg University Cirrhosis Index (GUCI). Receiver operating characteristic curves were constructed to compare the diagnostic accuracy of these noninvasive methods in predicting significant fibrosis in CHC patients. TE-FibroScan predicted significant fibrosis at cutoff value 8.5 kPa with area under the receiver operating characteristic (AUROC) 0.90, sensitivity 83%, specificity 91.5%, positive predictive value (PPV) 91.2%, and negative predictive value (NPV) 84.4%. Serum biomarkers tests showed that AP index and FibroQ had the highest diagnostic accuracy in predicting significant liver fibrosis at cutoff 4.5 and 2.7, AUROC was 0.8 and 0.8 with sensitivity 73.6% and 73.6%, specificity 70.2% and 68.1%, PPV 71.1% and 69.8%, and NPV 72.9% and 72.3%, respectively. Combined AP index and FibroQ had AUROC 0.83 with sensitivity 73.6%, specificity 80.9%, PPV 79.6%, and NPV 75.7% for predicting significant liver fibrosis. APRI, FIB-4, CDS, King score, and GUCI had intermediate accuracy in predicting significant liver fibrosis with AUROC 0.68, 0.78, 0.74, 0.74, and 0.67, respectively, while AAR had low accuracy in predicting significant liver fibrosis. TE-FibroScan is the most accurate noninvasive alternative to liver biopsy. AP index and FibroQ, either as individual tests or combined, have good accuracy in predicting significant liver fibrosis, and are better combined for higher specificity.

Accuracy of four commonly used color vision tests in the identification of cone disorders.

PubMed

Thiadens, Alberta A H J; Hoyng, Carel B; Polling, Jan Roelof; Bernaerts-Biskop, Riet; van den Born, L Ingeborgh; Klaver, Caroline C W

2013-04-01

To determine which color vision test is most appropriate for the identification of cone disorders. In a clinic-based study, four commonly used color vision tests were compared between patients with cone dystrophy (n = 37), controls with normal visual acuity (n = 35), and controls with low vision (n = 39) and legal blindness (n = 11). Mean outcome measures were specificity, sensitivity, positive predictive value and discriminative accuracy of the Ishihara test, Hardy-Rand-Rittler (HRR) test, and the Lanthony and Farnsworth Panel D-15 tests. In the comparison between cone dystrophy and all controls, sensitivity, specificity and predictive value were highest for the HRR and Ishihara tests. When patients were compared to controls with normal vision, discriminative accuracy was highest for the HRR test (c-statistic for PD-axes 1, for T-axis 0.851). When compared to controls with poor vision, discriminative accuracy was again highest for the HRR test (c-statistic for PD-axes 0.900, for T-axis 0.766), followed by the Lanthony Panel D-15 test (c-statistic for PD-axes 0.880, for T-axis 0.500) and Ishihara test (c-statistic 0.886). Discriminative accuracies of all tests did not further decrease when patients were compared to controls who were legally blind. The HRR, Lanthony Panel D-15 and Ishihara all have a high discriminative accuracy to identify cone disorders, but the highest scores were for the HRR test. Poor visual acuity slightly decreased the accuracy of all tests. Our advice is to use the HRR test since this test also allows for evaluation of all three color axes and quantification of color defects.

Medium- and Long-term Prediction of LOD Change with the Leap-step Autoregressive Model

NASA Astrophysics Data System (ADS)

Liu, Q. B.; Wang, Q. J.; Lei, M. F.

2015-09-01

It is known that the accuracies of medium- and long-term prediction of changes of length of day (LOD) based on the combined least-square and autoregressive (LS+AR) decrease gradually. The leap-step autoregressive (LSAR) model is more accurate and stable in medium- and long-term prediction, therefore it is used to forecast the LOD changes in this work. Then the LOD series from EOP 08 C04 provided by IERS (International Earth Rotation and Reference Systems Service) is used to compare the effectiveness of the LSAR and traditional AR methods. The predicted series resulted from the two models show that the prediction accuracy with the LSAR model is better than that from AR model in medium- and long-term prediction.

Office gel sonovaginography for the prediction of posterior deep infiltrating endometriosis: a multicenter prospective observational study.

PubMed

Reid, S; Lu, C; Hardy, N; Casikar, I; Reid, G; Cario, G; Chou, D; Almashat, D; Condous, G

2014-12-01

To use office gel sonovaginography (SVG) to predict posterior deep infiltrating endometriosis (DIE) in women undergoing laparoscopy. This was a multicenter prospective observational study carried out between January 2009 and February 2013. All women were of reproductive age, had a history of chronic pelvic pain and underwent office gel SVG assessment for the prediction of posterior compartment DIE prior to laparoscopic endometriosis surgery. Gel SVG findings were compared with laparoscopic findings to determine the diagnostic accuracy of office gel SVG for the prediction of posterior compartment DIE. In total, 189 women underwent preoperative gel SVG and laparoscopy for endometriosis. At laparoscopy, 57 (30%) women had posterior DIE and 43 (23%) had rectosigmoid/anterior rectal DIE. For the prediction of rectosigmoid/anterior rectal (i.e. bowel) DIE, gel SVG had an accuracy of 92%, sensitivity of 88%, specificity of 93%, positive predictive value (PPV) of 79%, negative predictive value (NPV) of 97%, positive likelihood ratio (LR+) of 12.9 and negative likelihood ratio (LR-) of 0.12 (P = 3.98E-25); for posterior vaginal wall and rectovaginal septum (RVS) DIE, respectively, the accuracy was 95% and 95%, sensitivity was 18% and 18%, specificity was 99% and 100%, PPV was 67% and 100%, NPV was 95% and 95%, LR+ was 32.4 and infinity and LR- was 0.82 and 0.82 (P = 0.009 and P = 0.003). Office gel SVG appears to be an effective outpatient imaging technique for the prediction of bowel DIE, with a higher accuracy for the prediction of rectosigmoid compared with anterior rectal DIE. Although the sensitivity for vaginal and RVS DIE was limited, gel SVG had a high specificity and NPV for all forms of posterior DIE, indicating that a negative gel SVG examination is highly suggestive of the absence of DIE at laparoscopy. Copyright © 2014 ISUOG. Published by John Wiley & Sons Ltd.

Fuzzy regression modeling for tool performance prediction and degradation detection.

PubMed

Li, X; Er, M J; Lim, B S; Zhou, J H; Gan, O P; Rutkowski, L

2010-10-01

In this paper, the viability of using Fuzzy-Rule-Based Regression Modeling (FRM) algorithm for tool performance and degradation detection is investigated. The FRM is developed based on a multi-layered fuzzy-rule-based hybrid system with Multiple Regression Models (MRM) embedded into a fuzzy logic inference engine that employs Self Organizing Maps (SOM) for clustering. The FRM converts a complex nonlinear problem to a simplified linear format in order to further increase the accuracy in prediction and rate of convergence. The efficacy of the proposed FRM is tested through a case study - namely to predict the remaining useful life of a ball nose milling cutter during a dry machining process of hardened tool steel with a hardness of 52-54 HRc. A comparative study is further made between four predictive models using the same set of experimental data. It is shown that the FRM is superior as compared with conventional MRM, Back Propagation Neural Networks (BPNN) and Radial Basis Function Networks (RBFN) in terms of prediction accuracy and learning speed.

Prediction Accuracy of Error Rates for MPTB Space Experiment

NASA Technical Reports Server (NTRS)

Buchner, S. P.; Campbell, A. B.; Davis, D.; McMorrow, D.; Petersen, E. L.; Stassinopoulos, E. G.; Ritter, J. C.

1998-01-01

This paper addresses the accuracy of radiation-induced upset-rate predictions in space using the results of ground-based measurements together with standard environmental and device models. The study is focused on two part types - 16 Mb NEC DRAM's (UPD4216) and 1 Kb SRAM's (AMD93L422) - both of which are currently in space on board the Microelectronics and Photonics Test Bed (MPTB). To date, ground-based measurements of proton-induced single event upset (SEM cross sections as a function of energy have been obtained and combined with models of the proton environment to predict proton-induced error rates in space. The role played by uncertainties in the environmental models will be determined by comparing the modeled radiation environment with the actual environment measured aboard MPTB. Heavy-ion induced upsets have also been obtained from MPTB and will be compared with the "predicted" error rate following ground testing that will be done in the near future. These results should help identify sources of uncertainty in predictions of SEU rates in space.

Increased genomic prediction accuracy in wheat breeding using a large Australian panel.

PubMed

Norman, Adam; Taylor, Julian; Tanaka, Emi; Telfer, Paul; Edwards, James; Martinant, Jean-Pierre; Kuchel, Haydn

2017-12-01

Genomic prediction accuracy within a large panel was found to be substantially higher than that previously observed in smaller populations, and also higher than QTL-based prediction. In recent years, genomic selection for wheat breeding has been widely studied, but this has typically been restricted to population sizes under 1000 individuals. To assess its efficacy in germplasm representative of commercial breeding programmes, we used a panel of 10,375 Australian wheat breeding lines to investigate the accuracy of genomic prediction for grain yield, physical grain quality and other physiological traits. To achieve this, the complete panel was phenotyped in a dedicated field trial and genotyped using a custom Axiom TM Affymetrix SNP array. A high-quality consensus map was also constructed, allowing the linkage disequilibrium present in the germplasm to be investigated. Using the complete SNP array, genomic prediction accuracies were found to be substantially higher than those previously observed in smaller populations and also more accurate compared to prediction approaches using a finite number of selected quantitative trait loci. Multi-trait genetic correlations were also assessed at an additive and residual genetic level, identifying a negative genetic correlation between grain yield and protein as well as a positive genetic correlation between grain size and test weight.

Application of GA-SVM method with parameter optimization for landslide development prediction

NASA Astrophysics Data System (ADS)

Li, X. Z.; Kong, J. M.

2013-10-01

Prediction of landslide development process is always a hot issue in landslide research. So far, many methods for landslide displacement series prediction have been proposed. Support vector machine (SVM) has been proved to be a novel algorithm with good performance. However, the performance strongly depends on the right selection of the parameters (C and γ) of SVM model. In this study, we presented an application of GA-SVM method with parameter optimization in landslide displacement rate prediction. We selected a typical large-scale landslide in some hydro - electrical engineering area of Southwest China as a case. On the basis of analyzing the basic characteristics and monitoring data of the landslide, a single-factor GA-SVM model and a multi-factor GA-SVM model of the landslide were built. Moreover, the models were compared with single-factor and multi-factor SVM models of the landslide. The results show that, the four models have high prediction accuracies, but the accuracies of GA-SVM models are slightly higher than those of SVM models and the accuracies of multi-factor models are slightly higher than those of single-factor models for the landslide prediction. The accuracy of the multi-factor GA-SVM models is the highest, with the smallest RSME of 0.0009 and the biggest RI of 0.9992.

Bootstrap study of genome-enabled prediction reliabilities using haplotype blocks across Nordic Red cattle breeds.

PubMed

Cuyabano, B C D; Su, G; Rosa, G J M; Lund, M S; Gianola, D

2015-10-01

This study compared the accuracy of genome-enabled prediction models using individual single nucleotide polymorphisms (SNP) or haplotype blocks as covariates when using either a single breed or a combined population of Nordic Red cattle. The main objective was to compare predictions of breeding values of complex traits using a combined training population with haplotype blocks, with predictions using a single breed as training population and individual SNP as predictors. To compare the prediction reliabilities, bootstrap samples were taken from the test data set. With the bootstrapped samples of prediction reliabilities, we built and graphed confidence ellipses to allow comparisons. Finally, measures of statistical distances were used to calculate the gain in predictive ability. Our analyses are innovative in the context of assessment of predictive models, allowing a better understanding of prediction reliabilities and providing a statistical basis to effectively calibrate whether one prediction scenario is indeed more accurate than another. An ANOVA indicated that use of haplotype blocks produced significant gains mainly when Bayesian mixture models were used but not when Bayesian BLUP was fitted to the data. Furthermore, when haplotype blocks were used to train prediction models in a combined Nordic Red cattle population, we obtained up to a statistically significant 5.5% average gain in prediction accuracy, over predictions using individual SNP and training the model with a single breed. Copyright © 2015 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Development of variable pathlength UV-vis spectroscopy combined with partial-least-squares regression for wastewater chemical oxygen demand (COD) monitoring.

PubMed

Chen, Baisheng; Wu, Huanan; Li, Sam Fong Yau

2014-03-01

To overcome the challenging task to select an appropriate pathlength for wastewater chemical oxygen demand (COD) monitoring with high accuracy by UV-vis spectroscopy in wastewater treatment process, a variable pathlength approach combined with partial-least squares regression (PLSR) was developed in this study. Two new strategies were proposed to extract relevant information of UV-vis spectral data from variable pathlength measurements. The first strategy was by data fusion with two data fusion levels: low-level data fusion (LLDF) and mid-level data fusion (MLDF). Predictive accuracy was found to improve, indicated by the lower root-mean-square errors of prediction (RMSEP) compared with those obtained for single pathlength measurements. Both fusion levels were found to deliver very robust PLSR models with residual predictive deviations (RPD) greater than 3 (i.e. 3.22 and 3.29, respectively). The second strategy involved calculating the slopes of absorbance against pathlength at each wavelength to generate slope-derived spectra. Without the requirement to select the optimal pathlength, the predictive accuracy (RMSEP) was improved by 20-43% as compared to single pathlength spectroscopy. Comparing to nine-factor models from fusion strategy, the PLSR model from slope-derived spectroscopy was found to be more parsimonious with only five factors and more robust with residual predictive deviation (RPD) of 3.72. It also offered excellent correlation of predicted and measured COD values with R(2) of 0.936. In sum, variable pathlength spectroscopy with the two proposed data analysis strategies proved to be successful in enhancing prediction performance of COD in wastewater and showed high potential to be applied in on-line water quality monitoring. Copyright © 2013 Elsevier B.V. All rights reserved.

Sequence fingerprints distinguish erroneous from correct predictions of intrinsically disordered protein regions.

PubMed

Saravanan, Konda Mani; Dunker, A Keith; Krishnaswamy, Sankaran

2017-12-27

More than 60 prediction methods for intrinsically disordered proteins (IDPs) have been developed over the years, many of which are accessible on the World Wide Web. Nearly, all of these predictors give balanced accuracies in the ~65%-~80% range. Since predictors are not perfect, further studies are required to uncover the role of amino acid residues in native IDP as compared to predicted IDP regions. In the present work, we make use of sequences of 100% predicted IDP regions, false positive disorder predictions, and experimentally determined IDP regions to distinguish the characteristics of native versus predicted IDP regions. A higher occurrence of asparagine is observed in sequences of native IDP regions but not in sequences of false positive predictions of IDP regions. The occurrences of certain combinations of amino acids at the pentapeptide level provide a distinguishing feature in the IDPs with respect to globular proteins. The distinguishing features presented in this paper provide insights into the sequence fingerprints of amino acid residues in experimentally determined as compared to predicted IDP regions. These observations and additional work along these lines should enable the development of improvements in the accuracy of disorder prediction algorithm.

Exploring Mouse Protein Function via Multiple Approaches.

PubMed

Huang, Guohua; Chu, Chen; Huang, Tao; Kong, Xiangyin; Zhang, Yunhua; Zhang, Ning; Cai, Yu-Dong

2016-01-01

Although the number of available protein sequences is growing exponentially, functional protein annotations lag far behind. Therefore, accurate identification of protein functions remains one of the major challenges in molecular biology. In this study, we presented a novel approach to predict mouse protein functions. The approach was a sequential combination of a similarity-based approach, an interaction-based approach and a pseudo amino acid composition-based approach. The method achieved an accuracy of about 0.8450 for the 1st-order predictions in the leave-one-out and ten-fold cross-validations. For the results yielded by the leave-one-out cross-validation, although the similarity-based approach alone achieved an accuracy of 0.8756, it was unable to predict the functions of proteins with no homologues. Comparatively, the pseudo amino acid composition-based approach alone reached an accuracy of 0.6786. Although the accuracy was lower than that of the previous approach, it could predict the functions of almost all proteins, even proteins with no homologues. Therefore, the combined method balanced the advantages and disadvantages of both approaches to achieve efficient performance. Furthermore, the results yielded by the ten-fold cross-validation indicate that the combined method is still effective and stable when there are no close homologs are available. However, the accuracy of the predicted functions can only be determined according to known protein functions based on current knowledge. Many protein functions remain unknown. By exploring the functions of proteins for which the 1st-order predicted functions are wrong but the 2nd-order predicted functions are correct, the 1st-order wrongly predicted functions were shown to be closely associated with the genes encoding the proteins. The so-called wrongly predicted functions could also potentially be correct upon future experimental verification. Therefore, the accuracy of the presented method may be much higher in reality.

Exploring Mouse Protein Function via Multiple Approaches

PubMed Central

Huang, Tao; Kong, Xiangyin; Zhang, Yunhua; Zhang, Ning

2016-01-01

Although the number of available protein sequences is growing exponentially, functional protein annotations lag far behind. Therefore, accurate identification of protein functions remains one of the major challenges in molecular biology. In this study, we presented a novel approach to predict mouse protein functions. The approach was a sequential combination of a similarity-based approach, an interaction-based approach and a pseudo amino acid composition-based approach. The method achieved an accuracy of about 0.8450 for the 1st-order predictions in the leave-one-out and ten-fold cross-validations. For the results yielded by the leave-one-out cross-validation, although the similarity-based approach alone achieved an accuracy of 0.8756, it was unable to predict the functions of proteins with no homologues. Comparatively, the pseudo amino acid composition-based approach alone reached an accuracy of 0.6786. Although the accuracy was lower than that of the previous approach, it could predict the functions of almost all proteins, even proteins with no homologues. Therefore, the combined method balanced the advantages and disadvantages of both approaches to achieve efficient performance. Furthermore, the results yielded by the ten-fold cross-validation indicate that the combined method is still effective and stable when there are no close homologs are available. However, the accuracy of the predicted functions can only be determined according to known protein functions based on current knowledge. Many protein functions remain unknown. By exploring the functions of proteins for which the 1st-order predicted functions are wrong but the 2nd-order predicted functions are correct, the 1st-order wrongly predicted functions were shown to be closely associated with the genes encoding the proteins. The so-called wrongly predicted functions could also potentially be correct upon future experimental verification. Therefore, the accuracy of the presented method may be much higher in reality. PMID:27846315

Prediction of soil properties using imaging spectroscopy: Considering fractional vegetation cover to improve accuracy

NASA Astrophysics Data System (ADS)

Franceschini, M. H. D.; Demattê, J. A. M.; da Silva Terra, F.; Vicente, L. E.; Bartholomeus, H.; de Souza Filho, C. R.

2015-06-01

Spectroscopic techniques have become attractive to assess soil properties because they are fast, require little labor and may reduce the amount of laboratory waste produced when compared to conventional methods. Imaging spectroscopy (IS) can have further advantages compared to laboratory or field proximal spectroscopic approaches such as providing spatially continuous information with a high density. However, the accuracy of IS derived predictions decreases when the spectral mixture of soil with other targets occurs. This paper evaluates the use of spectral data obtained by an airborne hyperspectral sensor (ProSpecTIR-VS - Aisa dual sensor) for prediction of physical and chemical properties of Brazilian highly weathered soils (i.e., Oxisols). A methodology to assess the soil spectral mixture is adapted and a progressive spectral dataset selection procedure, based on bare soil fractional cover, is proposed and tested. Satisfactory performances are obtained specially for the quantification of clay, sand and CEC using airborne sensor data (R2 of 0.77, 0.79 and 0.54; RPD of 2.14, 2.22 and 1.50, respectively), after spectral data selection is performed; although results obtained for laboratory data are more accurate (R2 of 0.92, 0.85 and 0.75; RPD of 3.52, 2.62 and 2.04, for clay, sand and CEC, respectively). Most importantly, predictions based on airborne-derived spectra for which the bare soil fractional cover is not taken into account show considerable lower accuracy, for example for clay, sand and CEC (RPD of 1.52, 1.64 and 1.16, respectively). Therefore, hyperspectral remotely sensed data can be used to predict topsoil properties of highly weathered soils, although spectral mixture of bare soil with vegetation must be considered in order to achieve an improved prediction accuracy.

Artificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks.

PubMed

Catto, James W F; Linkens, Derek A; Abbod, Maysam F; Chen, Minyou; Burton, Julian L; Feeley, Kenneth M; Hamdy, Freddie C

2003-09-15

New techniques for the prediction of tumor behavior are needed, because statistical analysis has a poor accuracy and is not applicable to the individual. Artificial intelligence (AI) may provide these suitable methods. Whereas artificial neural networks (ANN), the best-studied form of AI, have been used successfully, its hidden networks remain an obstacle to its acceptance. Neuro-fuzzy modeling (NFM), another AI method, has a transparent functional layer and is without many of the drawbacks of ANN. We have compared the predictive accuracies of NFM, ANN, and traditional statistical methods, for the behavior of bladder cancer. Experimental molecular biomarkers, including p53 and the mismatch repair proteins, and conventional clinicopathological data were studied in a cohort of 109 patients with bladder cancer. For all three of the methods, models were produced to predict the presence and timing of a tumor relapse. Both methods of AI predicted relapse with an accuracy ranging from 88% to 95%. This was superior to statistical methods (71-77%; P < 0.0006). NFM appeared better than ANN at predicting the timing of relapse (P = 0.073). The use of AI can accurately predict cancer behavior. NFM has a similar or superior predictive accuracy to ANN. However, unlike the impenetrable "black-box" of a neural network, the rules of NFM are transparent, enabling validation from clinical knowledge and the manipulation of input variables to allow exploratory predictions. This technique could be used widely in a variety of areas of medicine.

A novel hybrid decomposition-and-ensemble model based on CEEMD and GWO for short-term PM2.5 concentration forecasting

NASA Astrophysics Data System (ADS)

Niu, Mingfei; Wang, Yufang; Sun, Shaolong; Li, Yongwu

2016-06-01

To enhance prediction reliability and accuracy, a hybrid model based on the promising principle of "decomposition and ensemble" and a recently proposed meta-heuristic called grey wolf optimizer (GWO) is introduced for daily PM2.5 concentration forecasting. Compared with existing PM2.5 forecasting methods, this proposed model has improved the prediction accuracy and hit rates of directional prediction. The proposed model involves three main steps, i.e., decomposing the original PM2.5 series into several intrinsic mode functions (IMFs) via complementary ensemble empirical mode decomposition (CEEMD) for simplifying the complex data; individually predicting each IMF with support vector regression (SVR) optimized by GWO; integrating all predicted IMFs for the ensemble result as the final prediction by another SVR optimized by GWO. Seven benchmark models, including single artificial intelligence (AI) models, other decomposition-ensemble models with different decomposition methods and models with the same decomposition-ensemble method but optimized by different algorithms, are considered to verify the superiority of the proposed hybrid model. The empirical study indicates that the proposed hybrid decomposition-ensemble model is remarkably superior to all considered benchmark models for its higher prediction accuracy and hit rates of directional prediction.

BIG DATA ANALYTICS AND PRECISION ANIMAL AGRICULTURE SYMPOSIUM: Data to decisions.

PubMed

White, B J; Amrine, D E; Larson, R L

2018-04-14

Big data are frequently used in many facets of business and agronomy to enhance knowledge needed to improve operational decisions. Livestock operations collect data of sufficient quantity to perform predictive analytics. Predictive analytics can be defined as a methodology and suite of data evaluation techniques to generate a prediction for specific target outcomes. The objective of this manuscript is to describe the process of using big data and the predictive analytic framework to create tools to drive decisions in livestock production, health, and welfare. The predictive analytic process involves selecting a target variable, managing the data, partitioning the data, then creating algorithms, refining algorithms, and finally comparing accuracy of the created classifiers. The partitioning of the datasets allows model building and refining to occur prior to testing the predictive accuracy of the model with naive data to evaluate overall accuracy. Many different classification algorithms are available for predictive use and testing multiple algorithms can lead to optimal results. Application of a systematic process for predictive analytics using data that is currently collected or that could be collected on livestock operations will facilitate precision animal management through enhanced livestock operational decisions.

Computerized tomography with 3-dimensional reconstruction for the evaluation of renal size and arterial anatomy in the living kidney donor.

PubMed

Janoff, Daniel M; Davol, Patrick; Hazzard, James; Lemmers, Michael J; Paduch, Darius A; Barry, John M

2004-01-01

Computerized tomography (CT) with 3-dimensional (3-D) reconstruction has gained acceptance as an imaging study to evaluate living renal donors. We report our experience with this technique in 199 consecutive patients to validate its predictions of arterial anatomy and kidney volumes. Between January 1997 and March 2002, 199 living donor nephrectomies were performed at our institution using an open technique. During the operation arterial anatomy was recorded as well as kidney weight in 98 patients and displacement volume in 27. Each donor had been evaluated preoperatively by CT angiography with 3-D reconstruction. Arterial anatomy described by a staff radiologist was compared with intraoperative findings. CT estimated volumes were reported. Linear correlation graphs were generated to assess the reliability of CT volume predictions. The accuracy of CT angiography for predicting arterial anatomy was 90.5%. However, as the number of renal arteries increased, predictive accuracy decreased. The ability of CT to predict multiple arteries remained high with a positive predictive value of 95.2%. Calculated CT volume and kidney weight significantly correlated (0.654). However, the coefficient of variation index (how much average CT volume differed from measured intraoperative volume) was 17.8%. CT angiography with 3-D reconstruction accurately predicts arterial vasculature in more than 90% of patients and it can be used to compare renal volumes. However, accuracy decreases with multiple renal arteries and volume comparisons may be inaccurate when the difference in kidney volumes is within 17.8%.

Adaptive time-variant models for fuzzy-time-series forecasting.

PubMed

Wong, Wai-Keung; Bai, Enjian; Chu, Alice Wai-Ching

2010-12-01

A fuzzy time series has been applied to the prediction of enrollment, temperature, stock indices, and other domains. Related studies mainly focus on three factors, namely, the partition of discourse, the content of forecasting rules, and the methods of defuzzification, all of which greatly influence the prediction accuracy of forecasting models. These studies use fixed analysis window sizes for forecasting. In this paper, an adaptive time-variant fuzzy-time-series forecasting model (ATVF) is proposed to improve forecasting accuracy. The proposed model automatically adapts the analysis window size of fuzzy time series based on the prediction accuracy in the training phase and uses heuristic rules to generate forecasting values in the testing phase. The performance of the ATVF model is tested using both simulated and actual time series including the enrollments at the University of Alabama, Tuscaloosa, and the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX). The experiment results show that the proposed ATVF model achieves a significant improvement in forecasting accuracy as compared to other fuzzy-time-series forecasting models.

The Upper and Lower Bounds of the Prediction Accuracies of Ensemble Methods for Binary Classification

PubMed Central

Wang, Xueyi; Davidson, Nicholas J.

2011-01-01

Ensemble methods have been widely used to improve prediction accuracy over individual classifiers. In this paper, we achieve a few results about the prediction accuracies of ensemble methods for binary classification that are missed or misinterpreted in previous literature. First we show the upper and lower bounds of the prediction accuracies (i.e. the best and worst possible prediction accuracies) of ensemble methods. Next we show that an ensemble method can achieve > 0.5 prediction accuracy, while individual classifiers have < 0.5 prediction accuracies. Furthermore, for individual classifiers with different prediction accuracies, the average of the individual accuracies determines the upper and lower bounds. We perform two experiments to verify the results and show that it is hard to achieve the upper and lower bounds accuracies by random individual classifiers and better algorithms need to be developed. PMID:21853162

Determining the end of a musical turn: Effects of tonal cues.

PubMed

Hadley, Lauren V; Sturt, Patrick; Moran, Nikki; Pickering, Martin J

2018-01-01

Successful duetting requires that musicians coordinate their performance with their partners. In the case of turn-taking in improvised performance they need to be able to predict their partner's turn-end in order to accurately time their own entries. Here we investigate the cues used for accurate turn-end prediction in musical improvisations, focusing on the role of tonal structure. In a response-time task, participants more accurately determined the endings of (tonal) jazz than (non-tonal) free improvisation turns. Moreover, for the jazz improvisations, removing low frequency information (<2100Hz) - and hence obscuring the pitch relationships conveying tonality - reduced response accuracy, but removing high frequency information (>2100Hz) had no effect. Neither form of filtering affected response accuracy in the free improvisation condition. We therefore argue that tonal cues aided prediction accuracy for the jazz improvisations compared to the free improvisations. We compare our results with those from related speech research (De Ruiter et al., 2006), to draw comparisons between the structural function of tonality and linguistic syntax. Copyright © 2017. Published by Elsevier B.V.

Prediction and validation of residual feed intake and dry matter intake in Danish lactating dairy cows using mid-infrared spectroscopy of milk.

PubMed

Shetty, N; Løvendahl, P; Lund, M S; Buitenhuis, A J

2017-01-01

The present study explored the effectiveness of Fourier transform mid-infrared (FT-IR) spectral profiles as a predictor for dry matter intake (DMI) and residual feed intake (RFI). The partial least squares regression method was used to develop the prediction models. The models were validated using different external test sets, one randomly leaving out 20% of the records (validation A), the second randomly leaving out 20% of cows (validation B), and a third (for DMI prediction models) randomly leaving out one cow (validation C). The data included 1,044 records from 140 cows; 97 were Danish Holstein and 43 Danish Jersey. Results showed better accuracies for validation A compared with other validation methods. Milk yield (MY) contributed largely to DMI prediction; MY explained 59% of the variation and the validated model error root mean square error of prediction (RMSEP) was 2.24kg. The model was improved by adding live weight (LW) as an additional predictor trait, where the accuracy R 2 increased from 0.59 to 0.72 and error RMSEP decreased from 2.24 to 1.83kg. When only the milk FT-IR spectral profile was used in DMI prediction, a lower prediction ability was obtained, with R 2 =0.30 and RMSEP=2.91kg. However, once the spectral information was added, along with MY and LW as predictors, model accuracy improved and R 2 increased to 0.81 and RMSEP decreased to 1.49kg. Prediction accuracies of RFI changed throughout lactation. The RFI prediction model for the early-lactation stage was better compared with across lactation or mid- and late-lactation stages, with R 2 =0.46 and RMSEP=1.70. The most important spectral wavenumbers that contributed to DMI and RFI prediction models included fat, protein, and lactose peaks. Comparable prediction results were obtained when using infrared-predicted fat, protein, and lactose instead of full spectra, indicating that FT-IR spectral data do not add significant new information to improve DMI and RFI prediction models. Therefore, in practice, if full FT-IR spectral data are not stored, it is possible to achieve similar DMI or RFI prediction results based on standard milk control data. For DMI, the milk fat region was responsible for the major variation in milk spectra; for RFI, the major variation in milk spectra was within the milk protein region. Copyright © 2017 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Analysis of near infrared spectra for age-grading of wild populations of Anopheles gambiae.

PubMed

Krajacich, Benjamin J; Meyers, Jacob I; Alout, Haoues; Dabiré, Roch K; Dowell, Floyd E; Foy, Brian D

2017-11-07

Understanding the age-structure of mosquito populations, especially malaria vectors such as Anopheles gambiae, is important for assessing the risk of infectious mosquitoes, and how vector control interventions may impact this risk. The use of near-infrared spectroscopy (NIRS) for age-grading has been demonstrated previously on laboratory and semi-field mosquitoes, but to date has not been utilized on wild-caught mosquitoes whose age is externally validated via parity status or parasite infection stage. In this study, we developed regression and classification models using NIRS on datasets of wild An. gambiae (s.l.) reared from larvae collected from the field in Burkina Faso, and two laboratory strains. We compared the accuracy of these models for predicting the ages of wild-caught mosquitoes that had been scored for their parity status as well as for positivity for Plasmodium sporozoites. Regression models utilizing variable selection increased predictive accuracy over the more common full-spectrum partial least squares (PLS) approach for cross-validation of the datasets, validation, and independent test sets. Models produced from datasets that included the greatest range of mosquito samples (i.e. different sampling locations and times) had the highest predictive accuracy on independent testing sets, though overall accuracy on these samples was low. For classification, we found that intramodel accuracy ranged between 73.5-97.0% for grouping of mosquitoes into "early" and "late" age classes, with the highest prediction accuracy found in laboratory colonized mosquitoes. However, this accuracy was decreased on test sets, with the highest classification of an independent set of wild-caught larvae reared to set ages being 69.6%. Variation in NIRS data, likely from dietary, genetic, and other factors limits the accuracy of this technique with wild-caught mosquitoes. Alternative algorithms may help improve prediction accuracy, but care should be taken to either maximize variety in models or minimize confounders.

Receiver operating characteristic (ROC) curves: review of methods with applications in diagnostic medicine

NASA Astrophysics Data System (ADS)

Obuchowski, Nancy A.; Bullen, Jennifer A.

2018-04-01

Receiver operating characteristic (ROC) analysis is a tool used to describe the discrimination accuracy of a diagnostic test or prediction model. While sensitivity and specificity are the basic metrics of accuracy, they have many limitations when characterizing test accuracy, particularly when comparing the accuracies of competing tests. In this article we review the basic study design features of ROC studies, illustrate sample size calculations, present statistical methods for measuring and comparing accuracy, and highlight commonly used ROC software. We include descriptions of multi-reader ROC study design and analysis, address frequently seen problems of verification and location bias, discuss clustered data, and provide strategies for testing endpoints in ROC studies. The methods are illustrated with a study of transmission ultrasound for diagnosing breast lesions.

Preoperative prediction of histopathological outcome in basal cell carcinoma: flat surface and multiple small erosions predict superficial basal cell carcinoma in lighter skin types.

PubMed

Ahnlide, I; Zalaudek, I; Nilsson, F; Bjellerup, M; Nielsen, K

2016-10-01

Prediction of the histopathological subtype of basal cell carcinoma (BCC) is important for tailoring optimal treatment, especially in patients with suspected superficial BCC (sBCC). To assess the accuracy of the preoperative prediction of subtypes of BCC in clinical practice, to evaluate whether dermoscopic examination enhances accuracy and to find dermoscopic criteria for discriminating sBCC from other subtypes. The main presurgical diagnosis was compared with the histopathological, postoperative diagnosis of routinely excised skin tumours in a predominantly fair-skinned patient cohort of northern Europe during a study period of 3 years (2011-13). The study period was split in two: during period 1, dermoscopy was optional (850 cases with a pre- or postoperative diagnosis of BCC), while during period 2 (after an educational dermoscopic update) dermoscopy was mandatory (651 cases). A classification tree based on clinical and dermoscopic features for prediction of sBCC was applied. For a total of 3544 excised skin tumours, the sensitivity for the diagnosis of BCC (any subtype) was 93·3%, specificity 91·8%, and the positive predictive value (PPV) 89·0%. The diagnostic accuracy as well as the PPV and the positive likelihood ratio for sBCC were significantly higher when dermoscopy was mandatory. A flat surface and multiple small erosions predicted sBCC. The study shows a high accuracy for an overall diagnosis of BCC and increased accuracy in prediction of sBCC for the period when dermoscopy was applied in all cases. The most discriminating findings for sBCC, based on clinical and dermoscopic features in this fair-skinned population, were a flat surface and multiple small erosions. © 2016 British Association of Dermatologists.

Accuracy of risk scales for predicting repeat self-harm and suicide: a multicentre, population-level cohort study using routine clinical data.

PubMed

Steeg, Sarah; Quinlivan, Leah; Nowland, Rebecca; Carroll, Robert; Casey, Deborah; Clements, Caroline; Cooper, Jayne; Davies, Linda; Knipe, Duleeka; Ness, Jennifer; O'Connor, Rory C; Hawton, Keith; Gunnell, David; Kapur, Nav

2018-04-25

Risk scales are used widely in the management of patients presenting to hospital following self-harm. However, there is evidence that their diagnostic accuracy in predicting repeat self-harm is limited. Their predictive accuracy in population settings, and in identifying those at highest risk of suicide is not known. We compared the predictive accuracy of the Manchester Self-Harm Rule (MSHR), ReACT Self-Harm Rule (ReACT), SAD PERSONS Scale (SPS) and Modified SAD PERSONS Scale (MSPS) in an unselected sample of patients attending hospital following self-harm. Data on 4000 episodes of self-harm presenting to Emergency Departments (ED) between 2010 and 2012 were obtained from four established monitoring systems in England. Episodes were assigned a risk category for each scale and followed up for 6 months. The episode-based repeat rate was 28% (1133/4000) and the incidence of suicide was 0.5% (18/3962). The MSHR and ReACT performed with high sensitivity (98% and 94% respectively) and low specificity (15% and 23%). The SPS and the MSPS performed with relatively low sensitivity (24-29% and 9-12% respectively) and high specificity (76-77% and 90%). The area under the curve was 71% for both MSHR and ReACT, 51% for SPS and 49% for MSPS. Differences in predictive accuracy by subgroup were small. The scales were less accurate at predicting suicide than repeat self-harm. The scales failed to accurately predict repeat self-harm and suicide. The findings support existing clinical guidance not to use risk classification scales alone to determine treatment or predict future risk.

Application of local binary pattern and human visual Fibonacci texture features for classification different medical images

NASA Astrophysics Data System (ADS)

Sanghavi, Foram; Agaian, Sos

2017-05-01

The goal of this paper is to (a) test the nuclei based Computer Aided Cancer Detection system using Human Visual based system on the histopathology images and (b) Compare the results of the proposed system with the Local Binary Pattern and modified Fibonacci -p pattern systems. The system performance is evaluated using different parameters such as accuracy, specificity, sensitivity, positive predictive value, and negative predictive value on 251 prostate histopathology images. The accuracy of 96.69% was observed for cancer detection using the proposed human visual based system compared to 87.42% and 94.70% observed for Local Binary patterns and the modified Fibonacci p patterns.

Comparative effectiveness of i-SCAN™ and high-definition white light characterizing small colonic polyps.

PubMed

Chan, Johanna L; Lin, Li; Feiler, Michael; Wolf, Andrew I; Cardona, Diana M; Gellad, Ziad F

2012-11-07

To evaluate accuracy of in vivo diagnosis of adenomatous vs non-adenomatous polyps using i-SCAN digital chromoendoscopy compared with high-definition white light. This is a single-center comparative effectiveness pilot study. Polyps (n = 103) from 75 average-risk adult outpatients undergoing screening or surveillance colonoscopy between December 1, 2010 and April 1, 2011 were evaluated by two participating endoscopists in an academic outpatient endoscopy center. Polyps were evaluated both with high-definition white light and with i-SCAN to make an in vivo prediction of adenomatous vs non-adenomatous pathology. We determined diagnostic characteristics of i-SCAN and high-definition white light, including sensitivity, specificity, and accuracy, with regards to identifying adenomatous vs non-adenomatous polyps. Histopathologic diagnosis was the gold standard comparison. One hundred and three small polyps, detected from forty-three patients, were included in the analysis. The average size of the polyps evaluated in the analysis was 3.7 mm (SD 1.3 mm, range 2 mm to 8 mm). Formal histopathology revealed that 54/103 (52.4%) were adenomas, 26/103 (25.2%) were hyperplastic, and 23/103 (22.3%) were other diagnoses include "lymphoid aggregates", "non-specific colitis," and "no pathologic diagnosis." Overall, the combined accuracy of endoscopists for predicting adenomas was identical between i-SCAN (71.8%, 95%CI: 62.1%-80.3%) and high-definition white light (71.8%, 95%CI: 62.1%-80.3%). However, the accuracy of each endoscopist differed substantially, where endoscopist A demonstrated 63.0% overall accuracy (95%CI: 50.9%-74.0%) as compared with endoscopist B demonstrating 93.3% overall accuracy (95%CI: 77.9%-99.2%), irrespective of imaging modality. Neither endoscopist demonstrated a significant learning effect with i-SCAN during the study. Though endoscopist A increased accuracy using i-SCAN from 59% (95%CI: 42.1%-74.4%) in the first half to 67.6% (95%CI: 49.5%-82.6%) in the second half, and endoscopist B decreased accuracy using i-SCAN from 100% (95%CI: 80.5%-100.0%) in the first half to 84.6% (95%CI: 54.6%-98.1%) in the second half, neither of these differences were statistically significant. i-SCAN and high-definition white light had similar efficacy predicting polyp histology. Endoscopist training likely plays a critical role in diagnostic test characteristics and deserves further study.

Practical approach to subject-specific estimation of knee joint contact force.

PubMed

Knarr, Brian A; Higginson, Jill S

2015-08-20

Compressive forces experienced at the knee can significantly contribute to cartilage degeneration. Musculoskeletal models enable predictions of the internal forces experienced at the knee, but validation is often not possible, as experimental data detailing loading at the knee joint is limited. Recently available data reporting compressive knee force through direct measurement using instrumented total knee replacements offer a unique opportunity to evaluate the accuracy of models. Previous studies have highlighted the importance of subject-specificity in increasing the accuracy of model predictions; however, these techniques may be unrealistic outside of a research setting. Therefore, the goal of our work was to identify a practical approach for accurate prediction of tibiofemoral knee contact force (KCF). Four methods for prediction of knee contact force were compared: (1) standard static optimization, (2) uniform muscle coordination weighting, (3) subject-specific muscle coordination weighting and (4) subject-specific strength adjustments. Walking trials for three subjects with instrumented knee replacements were used to evaluate the accuracy of model predictions. Predictions utilizing subject-specific muscle coordination weighting yielded the best agreement with experimental data; however this method required in vivo data for weighting factor calibration. Including subject-specific strength adjustments improved models' predictions compared to standard static optimization, with errors in peak KCF less than 0.5 body weight for all subjects. Overall, combining clinical assessments of muscle strength with standard tools available in the OpenSim software package, such as inverse kinematics and static optimization, appears to be a practical method for predicting joint contact force that can be implemented for many applications. Copyright © 2015 Elsevier Ltd. All rights reserved.

Practical approach to subject-specific estimation of knee joint contact force

PubMed Central

Knarr, Brian A.; Higginson, Jill S.

2015-01-01

Compressive forces experienced at the knee can significantly contribute to cartilage degeneration. Musculoskeletal models enable predictions of the internal forces experienced at the knee, but validation is often not possible, as experimental data detailing loading at the knee joint is limited. Recently available data reporting compressive knee force through direct measurement using instrumented total knee replacements offer a unique opportunity to evaluate the accuracy of models. Previous studies have highlighted the importance of subject-specificity in increasing the accuracy of model predictions; however, these techniques may be unrealistic outside of a research setting. Therefore, the goal of our work was to identify a practical approach for accurate prediction of tibiofemoral knee contact force (KCF). Four methods for prediction of knee contact force were compared: (1) standard static optimization, (2) uniform muscle coordination weighting, (3) subject-specific muscle coordination weighting and (4) subject-specific strength adjustments. Walking trials for three subjects with instrumented knee replacements were used to evaluate the accuracy of model predictions. Predictions utilizing subject-specific muscle coordination weighting yielded the best agreement with experimental data, however this method required in vivo data for weighting factor calibration. Including subject-specific strength adjustments improved models’ predictions compared to standard static optimization, with errors in peak KCF less than 0.5 body weight for all subjects. Overall, combining clinical assessments of muscle strength with standard tools available in the OpenSim software package, such as inverse kinematics and static optimization, appears to be a practical method for predicting joint contact force that can be implemented for many applications. PMID:25952546

Ultrasonic prediction of term birth weight in Hispanic women. Accuracy in an outpatient clinic.

PubMed

Nahum, Gerard G; Pham, Krystle Q; McHugh, John P

2003-01-01

To investigate the accuracy of ultrasonic fetal biometric algorithms for estimating term fetal weight. Ultrasonographic fetal biometric assessments were made in 74 Hispanic women who delivered at 37-42 weeks of gestation. Measurements were taken of the fetal biparietal diameter, head circumference, abdominal circumference and femur length. Twenty-seven standard fetal biometric algorithms were assessed for their accuracy in predicting fetal weight. Results were compared to those obtained by merely guessing the mean term birth weight in each case. The correlation between ultrasonically predicted and actual birth weights ranged from 0.52 to 0.79. The different ultrasonic algorithms estimated fetal weight to within +/- 8.6-15.0% (+/- 295-520 g) of actual birth weight as compared with +/- 13.6% (+/- 449 g) for guessing the mean birth weight in each case (mean +/- SD). The mean absolute prediction errors for 17 of the ultrasonic equations (63%) were superior to those obtained by guessing the mean birth weight by 3.2-5.0% (96-154 g) (P < .05). Fourteen algorithms (52%) were more accurate for predicting fetal weight to within +/- 15%, and 20 algorithms (74%) were more accurate for predicting fetal weight to within +/- 10% of actual birth weight than simply guessing the mean birth weight (P < .05). Ten ultrasonic equations (37%) showed significant utility for predicting fetal weight > 4,000 g (likelihood ratio > 5.0). Term fetal weight predictions using the majority of sonographic fetal biometric equations are more accurate, by up to 154 g and 5%, than simply guessing the population-specific mean birth weight.

Improving CSF biomarker accuracy in predicting prevalent and incident Alzheimer disease

PubMed Central

Fagan, A.M.; Williams, M.M.; Ghoshal, N.; Aeschleman, M.; Grant, E.A.; Marcus, D.S.; Mintun, M.A.; Holtzman, D.M.; Morris, J.C.

2011-01-01

Objective: To investigate factors, including cognitive and brain reserve, which may independently predict prevalent and incident dementia of the Alzheimer type (DAT) and to determine whether inclusion of identified factors increases the predictive accuracy of the CSF biomarkers Aβ42, tau, ptau181, tau/Aβ42, and ptau181/Aβ42. Methods: Logistic regression identified variables that predicted prevalent DAT when considered together with each CSF biomarker in a cross-sectional sample of 201 participants with normal cognition and 46 with DAT. The area under the receiver operating characteristic curve (AUC) from the resulting model was compared with the AUC generated using the biomarker alone. In a second sample with normal cognition at baseline and longitudinal data available (n = 213), Cox proportional hazards models identified variables that predicted incident DAT together with each biomarker, and the models' concordance probability estimate (CPE), which was compared to the CPE generated using the biomarker alone. Results: APOE genotype including an ε4 allele, male gender, and smaller normalized whole brain volumes (nWBV) were cross-sectionally associated with DAT when considered together with every biomarker. In the longitudinal sample (mean follow-up = 3.2 years), 14 participants (6.6%) developed DAT. Older age predicted a faster time to DAT in every model, and greater education predicted a slower time in 4 of 5 models. Inclusion of ancillary variables resulted in better cross-sectional prediction of DAT for all biomarkers (p < 0.0021), and better longitudinal prediction for 4 of 5 biomarkers (p < 0.0022). Conclusions: The predictive accuracy of CSF biomarkers is improved by including age, education, and nWBV in analyses. PMID:21228296

Correlation of ground tests and analyses of a dynamically scaled Space Station model configuration

NASA Technical Reports Server (NTRS)

Javeed, Mehzad; Edighoffer, Harold H.; Mcgowan, Paul E.

1993-01-01

Verification of analytical models through correlation with ground test results of a complex space truss structure is demonstrated. A multi-component, dynamically scaled space station model configuration is the focus structure for this work. Previously established test/analysis correlation procedures are used to develop improved component analytical models. Integrated system analytical models, consisting of updated component analytical models, are compared with modal test results to establish the accuracy of system-level dynamic predictions. Design sensitivity model updating methods are shown to be effective for providing improved component analytical models. Also, the effects of component model accuracy and interface modeling fidelity on the accuracy of integrated model predictions is examined.

Thoracic injury rule out criteria and NEXUS chest in predicting the risk of traumatic intra-thoracic injuries: A diagnostic accuracy study.

PubMed

Safari, Saeed; Radfar, Fatemeh; Baratloo, Alireza

2018-05-01

This study aimed to compare the diagnostic accuracy of NEXUS chest and Thoracic Injury Rule out criteria (TIRC) models in predicting the risk of intra-thoracic injuries following blunt multiple trauma. In this diagnostic accuracy study, using the 2 mentioned models, blunt multiple trauma patients over the age of 15 years presenting to emergency department were screened regarding the presence of intra-thoracic injuries that are detectable via chest x-ray and screening performance characteristics of the models were compared. In this study, 3118 patients with the mean (SD) age of 37.4 (16.9) years were studied (57.4% male). Based on TIRC and NEXUS chest, respectively, 1340 (43%) and 1417 (45.4%) patients were deemed in need of radiography performance. Sensitivity, specificity, and positive and negative predictive values of TIRC were 98.95%, 62.70%, 21.19% and 99.83%. These values were 98.61%, 59.94%, 19.97% and 99.76%, for NEXUS chest, respectively. Accuracy of TIRC and NEXUS chest models were 66.04 (95% CI: 64.34-67.70) and 63.50 (95% CI: 61.78-65.19), respectively. TIRC and NEXUS chest models have proper and similar sensitivity in prediction of blunt traumatic intra-thoracic injuries that are detectable via chest x-ray. However, TIRC had a significantly higher specificity in this regard. Copyright © 2018 Elsevier Ltd. All rights reserved.

Prediction of Tubal Ectopic Pregnancy Using Offline Analysis of 3-Dimensional Transvaginal Ultrasonographic Data Sets: An Interobserver and Diagnostic Accuracy Study.

PubMed

Infante, Fernando; Espada Vaquero, Mercedes; Bignardi, Tommaso; Lu, Chuan; Testa, Antonia C; Fauchon, David; Epstein, Elisabeth; Leone, Francesco P G; Van den Bosch, Thierry; Martins, Wellington P; Condous, George

2018-06-01

To assess interobserver reproducibility in detecting tubal ectopic pregnancies by reading data sets from 3-dimensional (3D) transvaginal ultrasonography (TVUS) and comparing it with real-time 2-dimensional (2D) TVUS. Images were initially classified as showing pregnancies of unknown location or tubal ectopic pregnancies on real time 2D TVUS by an experienced sonologist, who acquired 5 3D volumes. Data sets were analyzed offline by 5 observers who had to classify each case as ectopic pregnancy or pregnancy of unknown location. The interobserver reproducibility was evaluated by the Fleiss κ statistic. The performance of each observer in predicting ectopic pregnancies was compared to that of the experienced sonologist. Women were followed until they were reclassified as follows: (1) failed pregnancy of unknown location; (2) intrauterine pregnancy; (3) ectopic pregnancy; or (4) persistent pregnancy of unknown location. Sixty-one women were included. The agreement between reading offline 3D data sets and the first real-time 2D TVUS was very good (80%-82%; κ = 0.89). The overall interobserver agreement among observers reading offline 3D data sets was moderate (κ = 0.52). The diagnostic performance of experienced observers reading offline 3D data sets had accuracy of 78.3% to 85.0%, sensitivity of 66.7% to 81.3%, specificity of 79.5% to 88.4%, positive predictive value of 57.1% to 72.2%, and negative predictive value of 87.5% to 91.3%, compared to the experienced sonologist's real-time 2D TVUS: accuracy of 94.5%, sensitivity of 94.4%, specificity of 94.5%, positive predictive value of 85.0%, and negative predictive value of 98.1%. The diagnostic accuracy of 3D TVUS by reading offline data sets for predicting ectopic pregnancies is dependent on experience. Reading only static 3D data sets without clinical information does not match the diagnostic performance of real time 2D TVUS combined with clinical information obtained during the scan. © 2017 by the American Institute of Ultrasound in Medicine.

NEOadjuvant therapy monitoring with PET and CT in Esophageal Cancer (NEOPEC-trial)

PubMed Central

2008-01-01

Background Surgical resection is the preferred treatment of potentially curable esophageal cancer. To improve long term patient outcome, many institutes apply neoadjuvant chemoradiotherapy. In a large proportion of patients no response to chemoradiotherapy is achieved. These patients suffer from toxic and ineffective neoadjuvant treatment, while appropriate surgical therapy is delayed. For this reason a diagnostic test that allows for accurate prediction of tumor response early during chemoradiotherapy is of crucial importance. CT-scan and endoscopic ultrasound have limited accuracy in predicting histopathologic tumor response. Data suggest that metabolic changes in tumor tissue as measured by FDG-PET predict response better. This study aims to compare FDG-PET and CT-scan for the early prediction of non-response to preoperative chemoradiotherapy in patients with potentially curable esophageal cancer. Methods/design Prognostic accuracy study, embedded in a randomized multicenter Dutch trial comparing neoadjuvant chemoradiotherapy for 5 weeks followed by surgery versus surgery alone for esophageal cancer. This prognostic accuracy study is performed only in the neoadjuvant arm of the randomized trial. In 6 centers, 150 consecutive patients will be included over a 3 year period. FDG-PET and CT-scan will be performed before and 2 weeks after the start of the chemoradiotherapy. All patients complete the 5 weeks regimen of neoadjuvant chemoradiotherapy, regardless the test results. Pathological examination of the surgical resection specimen will be used as reference standard. Responders are defined as patients with < 10% viable residual tumor cells (Mandard-score). Difference in accuracy (area under ROC curve) and negative predictive value between FDG-PET and CT-scan are primary endpoints. Furthermore, an economic evaluation will be performed, comparing survival and costs associated with the use of FDG-PET (or CT-scan) to predict tumor response with survival and costs of neoadjuvant chemoradiotherapy without prediction of response (reference strategy). Discussion The NEOPEC-trial could be the first sufficiently powered study that helps justify implementation of FDG-PET for response-monitoring in patients with esophageal cancer in clinical practice. Trial registration ISRCTN45750457 PMID:18671847

Glucose Prediction Algorithms from Continuous Monitoring Data: Assessment of Accuracy via Continuous Glucose Error-Grid Analysis.

PubMed

Zanderigo, Francesca; Sparacino, Giovanni; Kovatchev, Boris; Cobelli, Claudio

2007-09-01

The aim of this article was to use continuous glucose error-grid analysis (CG-EGA) to assess the accuracy of two time-series modeling methodologies recently developed to predict glucose levels ahead of time using continuous glucose monitoring (CGM) data. We considered subcutaneous time series of glucose concentration monitored every 3 minutes for 48 hours by the minimally invasive CGM sensor Glucoday® (Menarini Diagnostics, Florence, Italy) in 28 type 1 diabetic volunteers. Two prediction algorithms, based on first-order polynomial and autoregressive (AR) models, respectively, were considered with prediction horizons of 30 and 45 minutes and forgetting factors (ff) of 0.2, 0.5, and 0.8. CG-EGA was used on the predicted profiles to assess their point and dynamic accuracies using original CGM profiles as reference. Continuous glucose error-grid analysis showed that the accuracy of both prediction algorithms is overall very good and that their performance is similar from a clinical point of view. However, the AR model seems preferable for hypoglycemia prevention. CG-EGA also suggests that, irrespective of the time-series model, the use of ff = 0.8 yields the highest accurate readings in all glucose ranges. For the first time, CG-EGA is proposed as a tool to assess clinically relevant performance of a prediction method separately at hypoglycemia, euglycemia, and hyperglycemia. In particular, we have shown that CG-EGA can be helpful in comparing different prediction algorithms, as well as in optimizing their parameters.

A comparison of modified versions of the Static-99 and the Sex Offender Risk Appraisal Guide.

PubMed

Nunes, Kevin L; Firestone, Philip; Bradford, John M; Greenberg, David M; Broom, Ian

2002-07-01

The predictive validity of 2 risk assessment instruments for sex offenders, modified versions of the Static-99 and the Sex Offender Risk Appraisal Guide, was examined and compared in a sample of 258 adult male sex offenders. In addition, the independent contributions to the prediction of recidivism made by each instrument and by various phallometric indices were explored. Both instruments demonstrated moderate levels of predictive accuracy for sexual and violent (including sexual) recidivism. They were not significantly different in terms of their predictive accuracy for sexual or violent recidivism, nor did they contribute independently to the prediction of sexual or violent recidivism. Of the phallometric indices examined, only the pedophile index added significantly to the prediction of sexual recidivism, but not violent recidivism, above the Static-99 alone.

Static bending deflection and free vibration analysis of moderate thick symmetric laminated plates using multidimensional wave digital filters

NASA Astrophysics Data System (ADS)

Tseng, Chien-Hsun

2018-06-01

This paper aims to develop a multidimensional wave digital filtering network for predicting static and dynamic behaviors of composite laminate based on the FSDT. The resultant network is, thus, an integrated platform that can perform not only the free vibration but also the bending deflection of moderate thick symmetric laminated plates with low plate side-to-thickness ratios (< = 20). Safeguarded by the Courant-Friedrichs-Levy stability condition with the least restriction in terms of optimization technique, the present method offers numerically high accuracy, stability and efficiency to proceed a wide range of modulus ratios for the FSDT laminated plates. Instead of using a constant shear correction factor (SCF) with a limited numerical accuracy for the bending deflection, an optimum SCF is particularly sought by looking for a minimum ratio of change in the transverse shear energy. This way, it can predict as good results in terms of accuracy for certain cases of bending deflection. Extensive simulation results carried out for the prediction of maximum bending deflection have demonstratively proven that the present method outperforms those based on the higher-order shear deformation and layerwise plate theories. To the best of our knowledge, this is the first work that shows an optimal selection of SCF can significantly increase the accuracy of FSDT-based laminates especially compared to the higher order theory disclaiming any correction. The highest accuracy of overall solution is compared to the 3D elasticity equilibrium one.

Numerical simulation of turbulence flow in a Kaplan turbine -Evaluation on turbine performance prediction accuracy-

NASA Astrophysics Data System (ADS)

Ko, P.; Kurosawa, S.

2014-03-01

The understanding and accurate prediction of the flow behaviour related to cavitation and pressure fluctuation in a Kaplan turbine are important to the design work enhancing the turbine performance including the elongation of the operation life span and the improvement of turbine efficiency. In this paper, high accuracy turbine and cavitation performance prediction method based on entire flow passage for a Kaplan turbine is presented and evaluated. Two-phase flow field is predicted by solving Reynolds-Averaged Navier-Stokes equations expressed by volume of fluid method tracking the free surface and combined with Reynolds Stress model. The growth and collapse of cavitation bubbles are modelled by the modified Rayleigh-Plesset equation. The prediction accuracy is evaluated by comparing with the model test results of Ns 400 Kaplan model turbine. As a result that the experimentally measured data including turbine efficiency, cavitation performance, and pressure fluctuation are accurately predicted. Furthermore, the cavitation occurrence on the runner blade surface and the influence to the hydraulic loss of the flow passage are discussed. Evaluated prediction method for the turbine flow and performance is introduced to facilitate the future design and research works on Kaplan type turbine.

Diagnostic accuracy of ultrasound in upper and lower extremity long bone fractures of emergency department trauma patients.

PubMed

Frouzan, Arash; Masoumi, Kambiz; Delirroyfard, Ali; Mazdaie, Behnaz; Bagherzadegan, Elnaz

2017-08-01

Long bone fractures are common injuries caused by trauma. Some studies have demonstrated that ultrasound has a high sensitivity and specificity in the diagnosis of upper and lower extremity long bone fractures. The aim of this study was to determine the accuracy of ultrasound compared with plain radiography in diagnosis of upper and lower extremity long bone fractures in traumatic patients. This cross-sectional study assessed 100 patients admitted to the emergency department of Imam Khomeini Hospital, Ahvaz, Iran with trauma to the upper and lower extremities, from September 2014 through October 2015. In all patients, first ultrasound and then standard plain radiography for the upper and lower limb was performed. Data were analyzed by SPSS version 21 to determine the specificity and sensitivity. The mean age of patients with upper and lower limb trauma were 31.43±12.32 years and 29.63±5.89 years, respectively. Radius fracture was the most frequent compared to other fractures (27%). Sensitivity, specificity, positive predicted value, and negative predicted value of ultrasound compared with plain radiography in the diagnosis of upper extremity long bones were 95.3%, 87.7%, 87.2% and 96.2%, respectively, and the highest accuracy was observed in left arm fractures (100%). Tibia and fibula fractures were the most frequent types compared to other fractures (89.2%). Sensitivity, specificity, PPV and NPV of ultrasound compared with plain radiography in the diagnosis of upper extremity long bone fractures were 98.6%, 83%, 65.4% and 87.1%, respectively, and the highest accuracy was observed in men, lower ages and femoral fractures. The results of this study showed that ultrasound compared with plain radiography has a high accuracy in the diagnosis of upper and lower extremity long bone fractures.

Comparison of the accuracy of radiography and ultrasonography for detection of articular lesions in horses.

PubMed

Hinz, Antje; Fischer, Andrew T

2011-10-01

To compare the accuracy of ultrasonographic and radiographic examination for evaluation of articular lesions in horses. Cross-sectional study. Horses (n = 137) with articular lesions. Radiographic and ultrasonographic examinations of the affected joint(s) were performed before diagnostic or therapeutic arthroscopic surgery. Findings were recorded and compared to lesions identified during arthroscopy. In 254 joints, 432 lesions were identified by arthroscopy. The overall accuracy was 82.9% for ultrasonography and 62.2% for radiography (P < .0001) with a sensitivity of 91.4% for ultrasonography and 66.7% for radiography (P < .0001). The difference in specificity was not statistically significant (P = .2628). The negative predictive value for ultrasonography was 31.5% and 13.2% for radiography (P = .0022), the difference for the positive predictive value was not statistically significant (P = .3898). The accuracy for ultrasonography and radiography for left versus right joints was equal and corresponded with the overall results. Ultrasonographic evaluation of articular lesions was more accurate than radiographic evaluation. © Copyright 2011 by The American College of Veterinary Surgeons.

Improving accuracy of genomic prediction in Brangus cattle by adding animals with imputed low-density SNP genotypes.

PubMed

Lopes, F B; Wu, X-L; Li, H; Xu, J; Perkins, T; Genho, J; Ferretti, R; Tait, R G; Bauck, S; Rosa, G J M

2018-02-01

Reliable genomic prediction of breeding values for quantitative traits requires the availability of sufficient number of animals with genotypes and phenotypes in the training set. As of 31 October 2016, there were 3,797 Brangus animals with genotypes and phenotypes. These Brangus animals were genotyped using different commercial SNP chips. Of them, the largest group consisted of 1,535 animals genotyped by the GGP-LDV4 SNP chip. The remaining 2,262 genotypes were imputed to the SNP content of the GGP-LDV4 chip, so that the number of animals available for training the genomic prediction models was more than doubled. The present study showed that the pooling of animals with both original or imputed 40K SNP genotypes substantially increased genomic prediction accuracies on the ten traits. By supplementing imputed genotypes, the relative gains in genomic prediction accuracies on estimated breeding values (EBV) were from 12.60% to 31.27%, and the relative gain in genomic prediction accuracies on de-regressed EBV was slightly small (i.e. 0.87%-18.75%). The present study also compared the performance of five genomic prediction models and two cross-validation methods. The five genomic models predicted EBV and de-regressed EBV of the ten traits similarly well. Of the two cross-validation methods, leave-one-out cross-validation maximized the number of animals at the stage of training for genomic prediction. Genomic prediction accuracy (GPA) on the ten quantitative traits was validated in 1,106 newly genotyped Brangus animals based on the SNP effects estimated in the previous set of 3,797 Brangus animals, and they were slightly lower than GPA in the original data. The present study was the first to leverage currently available genotype and phenotype resources in order to harness genomic prediction in Brangus beef cattle. © 2018 Blackwell Verlag GmbH.

Analysis of the Mean Absolute Error (MAE) and the Root Mean Square Error (RMSE) in Assessing Rounding Model

NASA Astrophysics Data System (ADS)

Wang, Weijie; Lu, Yanmin

2018-03-01

Most existing Collaborative Filtering (CF) algorithms predict a rating as the preference of an active user toward a given item, which is always a decimal fraction. Meanwhile, the actual ratings in most data sets are integers. In this paper, we discuss and demonstrate why rounding can bring different influences to these two metrics; prove that rounding is necessary in post-processing of the predicted ratings, eliminate of model prediction bias, improving the accuracy of the prediction. In addition, we also propose two new rounding approaches based on the predicted rating probability distribution, which can be used to round the predicted rating to an optimal integer rating, and get better prediction accuracy compared to the Basic Rounding approach. Extensive experiments on different data sets validate the correctness of our analysis and the effectiveness of our proposed rounding approaches.

Gender differences in structured risk assessment: comparing the accuracy of five instruments.

PubMed

Coid, Jeremy; Yang, Min; Ullrich, Simone; Zhang, Tianqiang; Sizmur, Steve; Roberts, Colin; Farrington, David P; Rogers, Robert D

2009-04-01

Structured risk assessment should guide clinical risk management, but it is uncertain which instrument has the highest predictive accuracy among men and women. In the present study, the authors compared the Psychopathy Checklist-Revised (PCL-R; R. D. Hare, 1991, 2003); the Historical, Clinical, Risk Management-20 (HCR-20; C. D. Webster, K. S. Douglas, D. Eaves, & S. D. Hart, 1997); the Risk Matrix 2000-Violence (RM2000[V]; D. Thornton et al., 2003); the Violence Risk Appraisal Guide (VRAG; V. L. Quinsey, G. T. Harris, M. E. Rice, & C. A. Cormier, 1998); the Offenders Group Reconviction Scale (OGRS; J. B. Copas & P. Marshall, 1998; R. Taylor, 1999); and the total previous convictions among prisoners, prospectively assessed prerelease. The authors compared predischarge measures with subsequent offending and instruments ranked using multivariate regression. Most instruments demonstrated significant but moderate predictive ability. The OGRS ranked highest for violence among men, and the PCL-R and HCR-20 H subscale ranked highest for violence among women. The OGRS and total previous acquisitive convictions demonstrated greatest accuracy in predicting acquisitive offending among men and women. Actuarial instruments requiring no training to administer performed as well as personality assessment and structured risk assessment and were superior among men for violence.

Hadroproduction of t anti-t pair in association with an isolated photon at NLO accuracy matched with parton shower

NASA Astrophysics Data System (ADS)

Kardos, Adam; Trócsányi, Zoltán

2015-05-01

We simulate the hadroproduction of a -pair in association with a hard photon at LHC using the PowHel package. These events are almost fully inclusive with respect to the photon, allowing for any physically relevant isolation of the photon. We use the generated events, stored according to the Les-Houches event format, to make predictions for differential distributions formally at the next-to-leading order (NLO) accuracy and we compare these to existing predictions accurate at NLO using the smooth isolation prescription of Frixione. Our fixed-order predictions include the direct-photon contribution only. We also make predictions for distributions after full parton shower and hadronization using the standard experimental cone-isolation of the photon.

Fatigue life prediction of rotor blade composites: Validation of constant amplitude formulations with variable amplitude experiments

NASA Astrophysics Data System (ADS)

Westphal, T.; Nijssen, R. P. L.

2014-12-01

The effect of Constant Life Diagram (CLD) formulation on the fatigue life prediction under variable amplitude (VA) loading was investigated based on variable amplitude tests using three different load spectra representative for wind turbine loading. Next to the Wisper and WisperX spectra, the recently developed NewWisper2 spectrum was used. Based on these variable amplitude fatigue results the prediction accuracy of 4 CLD formulations is investigated. In the study a piecewise linear CLD based on the S-N curves for 9 load ratios compares favourably in terms of prediction accuracy and conservativeness. For the specific laminate used in this study Boerstra's Multislope model provides a good alternative at reduced test effort.

Accuracy of frozen section in the diagnosis of ovarian tumours.

PubMed

Toneva, F; Wright, H; Razvi, K

2012-07-01

The purpose of our retrospective study was to assess the accuracy of intraoperative frozen section diagnosis compared to final paraffin diagnosis in ovarian tumours at a gynaecological oncology centre in the UK. We analysed 66 cases and observed that frozen section consultation agreed with final paraffin diagnosis in 59 cases, which provided an accuracy of 89.4%. The overall sensitivity and specificity for all tumours were 85.4% and 100%, respectively. The positive predictive value (PPV) and negative predictive value (NPV) were 100% and 89.4%, respectively. Of the seven cases with discordant results, the majority were large, mucinous tumours, which is in line with previous studies. Our study demonstrated that despite its limitations, intraoperative frozen section has a high accuracy and sensitivity for assessing ovarian tumours; however, care needs to be taken with large, mucinous tumours.

Comparison of integrated clustering methods for accurate and stable prediction of building energy consumption data

DOE PAGES

Hsu, David

2015-09-27

Clustering methods are often used to model energy consumption for two reasons. First, clustering is often used to process data and to improve the predictive accuracy of subsequent energy models. Second, stable clusters that are reproducible with respect to non-essential changes can be used to group, target, and interpret observed subjects. However, it is well known that clustering methods are highly sensitive to the choice of algorithms and variables. This can lead to misleading assessments of predictive accuracy and mis-interpretation of clusters in policymaking. This paper therefore introduces two methods to the modeling of energy consumption in buildings: clusterwise regression,more » also known as latent class regression, which integrates clustering and regression simultaneously; and cluster validation methods to measure stability. Using a large dataset of multifamily buildings in New York City, clusterwise regression is compared to common two-stage algorithms that use K-means and model-based clustering with linear regression. Predictive accuracy is evaluated using 20-fold cross validation, and the stability of the perturbed clusters is measured using the Jaccard coefficient. These results show that there seems to be an inherent tradeoff between prediction accuracy and cluster stability. This paper concludes by discussing which clustering methods may be appropriate for different analytical purposes.« less

OH-PRED: prediction of protein hydroxylation sites by incorporating adapted normal distribution bi-profile Bayes feature extraction and physicochemical properties of amino acids.

PubMed

Jia, Cang-Zhi; He, Wen-Ying; Yao, Yu-Hua

2017-03-01

Hydroxylation of proline or lysine residues in proteins is a common post-translational modification event, and such modifications are found in many physiological and pathological processes. Nonetheless, the exact molecular mechanism of hydroxylation remains under investigation. Because experimental identification of hydroxylation is time-consuming and expensive, bioinformatics tools with high accuracy represent desirable alternatives for large-scale rapid identification of protein hydroxylation sites. In view of this, we developed a supporter vector machine-based tool, OH-PRED, for the prediction of protein hydroxylation sites using the adapted normal distribution bi-profile Bayes feature extraction in combination with the physicochemical property indexes of the amino acids. In a jackknife cross validation, OH-PRED yields an accuracy of 91.88% and a Matthew's correlation coefficient (MCC) of 0.838 for the prediction of hydroxyproline sites, and yields an accuracy of 97.42% and a MCC of 0.949 for the prediction of hydroxylysine sites. These results demonstrate that OH-PRED increased significantly the prediction accuracy of hydroxyproline and hydroxylysine sites by 7.37 and 14.09%, respectively, when compared with the latest predictor PredHydroxy. In independent tests, OH-PRED also outperforms previously published methods.

Improving prediction accuracy of cooling load using EMD, PSR and RBFNN

NASA Astrophysics Data System (ADS)

Shen, Limin; Wen, Yuanmei; Li, Xiaohong

2017-08-01

To increase the accuracy for the prediction of cooling load demand, this work presents an EMD (empirical mode decomposition)-PSR (phase space reconstruction) based RBFNN (radial basis function neural networks) method. Firstly, analyzed the chaotic nature of the real cooling load demand, transformed the non-stationary cooling load historical data into several stationary intrinsic mode functions (IMFs) by using EMD. Secondly, compared the RBFNN prediction accuracies of each IMFs and proposed an IMF combining scheme that is combine the lower-frequency components (called IMF4-IMF6 combined) while keep the higher frequency component (IMF1, IMF2, IMF3) and the residual unchanged. Thirdly, reconstruct phase space for each combined components separately, process the highest frequency component (IMF1) by differential method and predict with RBFNN in the reconstructed phase spaces. Real cooling load data of a centralized ice storage cooling systems in Guangzhou are used for simulation. The results show that the proposed hybrid method outperforms the traditional methods.

Estimation of basal metabolic rate in Chinese: are the current prediction equations applicable?

PubMed

Camps, Stefan G; Wang, Nan Xin; Tan, Wei Shuan Kimberly; Henry, C Jeyakumar

2016-08-31

Measurement of basal metabolic rate (BMR) is suggested as a tool to estimate energy requirements. Therefore, BMR prediction equations have been developed in multiple populations because indirect calorimetry is not always feasible. However, there is a paucity of data on BMR measured in overweight and obese adults living in Asia and equations developed for this group of interest. The aim of this study was to develop a new BMR prediction equation for Chinese adults applicable for a large BMI range and compare it with commonly used prediction equations. Subjects were 121 men and 111 women (age: 21-67 years, BMI: 16-41 kg/m(2)). Height, weight, and BMR were measured. Continuous open-circuit indirect calorimetry using a ventilated hood system for 30 min was used to measure BMR. A regression equation was derived using stepwise regression and accuracy was compared to 6 existing equations (Harris-Benedict, Henry, Liu, Yang, Owen and Mifflin). Additionally, the newly derived equation was cross-validated in a separate group of 70 Chinese subjects (26 men and 44 women, age: 21-69 years, BMI: 17-39 kg/m(2)). The equation developed from our data was: BMR (kJ/d) = 52.6 x weight (kg) + 828 x gender + 1960 (women = 0, men = 1; R(2) = 0.81). The accuracy rate (within 10 % accurate) was 78 % which compared well to Owen (70 %), Henry (67 %), Mifflin (67 %), Liu (58 %), Harris-Benedict (45 %) and Yang (37 %) for the whole range of BMI. For a BMI greater than 23, the Singapore equation reached an accuracy rate of 76 %. Cross-validation proved an accuracy rate of 80 %. To date, the newly developed Singapore equation is the most accurate BMR prediction equation in Chinese and is applicable for use in a large BMI range including those overweight and obese.

Prediction of high-dimensional states subject to respiratory motion: a manifold learning approach

NASA Astrophysics Data System (ADS)

Liu, Wenyang; Sawant, Amit; Ruan, Dan

2016-07-01

The development of high-dimensional imaging systems in image-guided radiotherapy provides important pathways to the ultimate goal of real-time full volumetric motion monitoring. Effective motion management during radiation treatment usually requires prediction to account for system latency and extra signal/image processing time. It is challenging to predict high-dimensional respiratory motion due to the complexity of the motion pattern combined with the curse of dimensionality. Linear dimension reduction methods such as PCA have been used to construct a linear subspace from the high-dimensional data, followed by efficient predictions on the lower-dimensional subspace. In this study, we extend such rationale to a more general manifold and propose a framework for high-dimensional motion prediction with manifold learning, which allows one to learn more descriptive features compared to linear methods with comparable dimensions. Specifically, a kernel PCA is used to construct a proper low-dimensional feature manifold, where accurate and efficient prediction can be performed. A fixed-point iterative pre-image estimation method is used to recover the predicted value in the original state space. We evaluated and compared the proposed method with a PCA-based approach on level-set surfaces reconstructed from point clouds captured by a 3D photogrammetry system. The prediction accuracy was evaluated in terms of root-mean-squared-error. Our proposed method achieved consistent higher prediction accuracy (sub-millimeter) for both 200 ms and 600 ms lookahead lengths compared to the PCA-based approach, and the performance gain was statistically significant.

Effects of Recovery Behavior and Strain-Rate Dependence of Stress-Strain Curve on Prediction Accuracy of Thermal Stress Analysis During Casting

NASA Astrophysics Data System (ADS)

Motoyama, Yuichi; Shiga, Hidetoshi; Sato, Takeshi; Kambe, Hiroshi; Yoshida, Makoto

2017-06-01

Recovery behavior (recovery) and strain-rate dependence of the stress-strain curve (strain-rate dependence) are incorporated into constitutive equations of alloys to predict residual stress and thermal stress during casting. Nevertheless, few studies have systematically investigated the effects of these metallurgical phenomena on the prediction accuracy of thermal stress in a casting. This study compares the thermal stress analysis results with in situ thermal stress measurement results of an Al-Si-Cu specimen during casting. The results underscore the importance for the alloy constitutive equation of incorporating strain-rate dependence to predict thermal stress that develops at high temperatures where the alloy shows strong strain-rate dependence of the stress-strain curve. However, the prediction accuracy of the thermal stress developed at low temperatures did not improve by considering the strain-rate dependence. Incorporating recovery into the constitutive equation improved the accuracy of the simulated thermal stress at low temperatures. Results of comparison implied that the constitutive equation should include strain-rate dependence to simulate defects that develop from thermal stress at high temperatures, such as hot tearing and hot cracking. Recovery should be incorporated into the alloy constitutive equation to predict the casting residual stress and deformation caused by the thermal stress developed mainly in the low temperature range.

Prediction accuracy of direct and indirect approaches, and their relationships with prediction ability of calibration models.

PubMed

Belay, T K; Dagnachew, B S; Boison, S A; Ådnøy, T

2018-03-28

Milk infrared spectra are routinely used for phenotyping traits of interest through links developed between the traits and spectra. Predicted individual traits are then used in genetic analyses for estimated breeding value (EBV) or for phenotypic predictions using a single-trait mixed model; this approach is referred to as indirect prediction (IP). An alternative approach [direct prediction (DP)] is a direct genetic analysis of (a reduced dimension of) the spectra using a multitrait model to predict multivariate EBV of the spectral components and, ultimately, also to predict the univariate EBV or phenotype for the traits of interest. We simulated 3 traits under different genetic (low: 0.10 to high: 0.90) and residual (zero to high: ±0.90) correlation scenarios between the 3 traits and assumed the first trait is a linear combination of the other 2 traits. The aim was to compare the IP and DP approaches for predictions of EBV and phenotypes under the different correlation scenarios. We also evaluated relationships between performances of the 2 approaches and the accuracy of calibration equations. Moreover, the effect of using different regression coefficients estimated from simulated phenotypes (β p ), true breeding values (β g ), and residuals (β r ) on performance of the 2 approaches were evaluated. The simulated data contained 2,100 parents (100 sires and 2,000 cows) and 8,000 offspring (4 offspring per cow). Of the 8,000 observations, 2,000 were randomly selected and used to develop links between the first and the other 2 traits using partial least square (PLS) regression analysis. The different PLS regression coefficients, such as β p , β g , and β r , were used in subsequent predictions following the IP and DP approaches. We used BLUP analyses for the remaining 6,000 observations using the true (co)variance components that had been used for the simulation. Accuracy of prediction (of EBV and phenotype) was calculated as a correlation between predicted and true values from the simulations. The results showed that accuracies of EBV prediction were higher in the DP than in the IP approach. The reverse was true for accuracy of phenotypic prediction when using β p but not when using β g and β r , where accuracy of phenotypic prediction in the DP was slightly higher than in the IP approach. Within the DP approach, accuracies of EBV when using β g were higher than when using β p only at the low genetic correlation scenario. However, we found no differences in EBV prediction accuracy between the β p and β g in the IP approach. Accuracy of the calibration models increased with an increase in genetic and residual correlations between the traits. Performance of both approaches increased with an increase in accuracy of the calibration models. In conclusion, the DP approach is a good strategy for EBV prediction but not for phenotypic prediction, where the classical PLS regression-based equations or the IP approach provided better results. The Authors. Published by FASS Inc. and Elsevier Inc. on behalf of the American Dairy Science Association®. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/3.0/).

A threshold-free summary index of prediction accuracy for censored time to event data.

PubMed

Yuan, Yan; Zhou, Qian M; Li, Bingying; Cai, Hengrui; Chow, Eric J; Armstrong, Gregory T

2018-05-10

Prediction performance of a risk scoring system needs to be carefully assessed before its adoption in clinical practice. Clinical preventive care often uses risk scores to screen asymptomatic population. The primary clinical interest is to predict the risk of having an event by a prespecified future time t 0 . Accuracy measures such as positive predictive values have been recommended for evaluating the predictive performance. However, for commonly used continuous or ordinal risk score systems, these measures require a subjective cutoff threshold value that dichotomizes the risk scores. The need for a cutoff value created barriers for practitioners and researchers. In this paper, we propose a threshold-free summary index of positive predictive values that accommodates time-dependent event status and competing risks. We develop a nonparametric estimator and provide an inference procedure for comparing this summary measure between 2 risk scores for censored time to event data. We conduct a simulation study to examine the finite-sample performance of the proposed estimation and inference procedures. Lastly, we illustrate the use of this measure on a real data example, comparing 2 risk score systems for predicting heart failure in childhood cancer survivors. Copyright © 2018 John Wiley & Sons, Ltd.

A comprehensive comparison of network similarities for link prediction and spurious link elimination

NASA Astrophysics Data System (ADS)

Zhang, Peng; Qiu, Dan; Zeng, An; Xiao, Jinghua

2018-06-01

Identifying missing interactions in complex networks, known as link prediction, is realized by estimating the likelihood of the existence of a link between two nodes according to the observed links and nodes' attributes. Similar approaches have also been employed to identify and remove spurious links in networks which is crucial for improving the reliability of network data. In network science, the likelihood for two nodes having a connection strongly depends on their structural similarity. The key to address these two problems thus becomes how to objectively measure the similarity between nodes in networks. In the literature, numerous network similarity metrics have been proposed and their accuracy has been discussed independently in previous works. In this paper, we systematically compare the accuracy of 18 similarity metrics in both link prediction and spurious link elimination when the observed networks are very sparse or consist of inaccurate linking information. Interestingly, some methods have high prediction accuracy, they tend to perform low accuracy in identification spurious interaction. We further find that methods can be classified into several cluster according to their behaviors. This work is useful for guiding future use of these similarity metrics for different purposes.

Role of Cervical Length Measurement for Preterm Delivery Prediction in Women With Threatened Preterm Labor and Cervical Dilatation.

PubMed

Hiersch, Liran; Melamed, Nir; Aviram, Amir; Bardin, Ron; Yogev, Yariv; Ashwal, Eran

2016-12-01

To compare the accuracy and cutoff points for cervical length for predicting preterm delivery in women with threatened preterm labor between those with a closed cervix and cervical dilatation. We conducted a retrospective cohort study of women with singleton pregnancies with threatened preterm labor before 34 weeks. The accuracy of cervical length for predicting preterm delivery was compared between women with cervical dilatation (0.5-3 cm) and those with a closed cervix. The predictive accuracy of cervical length for spontaneous preterm delivery was analyzed with several outcome-specific thresholds. Overall, 1068 women with threatened preterm labor met the inclusion criteria; of them, 276 (25.8%) had cervical dilatation, and 792 (74.2%) had a closed cervix. The risk of preterm delivery before 37 weeks was significantly higher in the cervical dilatation group than the closed cervix group, as well as a shorter assessment-to-delivery interval of within 14 days (P = .001 and .004, respectively). On a multivariable analysis, cervical length was independently associated with the risk of preterm delivery in both groups. There was no significant difference between women with cervical dilatation and those with a closed cervix regarding the area under the receiver operating characteristic curves of cervical length for prediction of preterm delivery before 37 (0.674 versus 0.618; P = .18) and 34 (0.628 versus 0.640; P = .88) weeks and an assessment-to-delivery interval of 14 days (0.686 versus 0.660; P= .72). The negative predictive value of cervical length ranged from 77.4% to 95.7% depending on the different thresholds used. Cervical length was significantly associated with the risk of preterm delivery in women presenting with threatened preterm labor and cervical dilatation of less than 3 cm. However, the predictive accuracy of cervical length as a single measure was relatively limited. © 2016 by the American Institute of Ultrasound in Medicine.

Genomic and pedigree-based prediction for leaf, stem, and stripe rust resistance in wheat.

PubMed

Juliana, Philomin; Singh, Ravi P; Singh, Pawan K; Crossa, Jose; Huerta-Espino, Julio; Lan, Caixia; Bhavani, Sridhar; Rutkoski, Jessica E; Poland, Jesse A; Bergstrom, Gary C; Sorrells, Mark E

2017-07-01

Genomic prediction for seedling and adult plant resistance to wheat rusts was compared to prediction using few markers as fixed effects in a least-squares approach and pedigree-based prediction. The unceasing plant-pathogen arms race and ephemeral nature of some rust resistance genes have been challenging for wheat (Triticum aestivum L.) breeding programs and farmers. Hence, it is important to devise strategies for effective evaluation and exploitation of quantitative rust resistance. One promising approach that could accelerate gain from selection for rust resistance is 'genomic selection' which utilizes dense genome-wide markers to estimate the breeding values (BVs) for quantitative traits. Our objective was to compare three genomic prediction models including genomic best linear unbiased prediction (GBLUP), GBLUP A that was GBLUP with selected loci as fixed effects and reproducing kernel Hilbert spaces-markers (RKHS-M) with least-squares (LS) approach, RKHS-pedigree (RKHS-P), and RKHS markers and pedigree (RKHS-MP) to determine the BVs for seedling and/or adult plant resistance (APR) to leaf rust (LR), stem rust (SR), and stripe rust (YR). The 333 lines in the 45th IBWSN and the 313 lines in the 46th IBWSN were genotyped using genotyping-by-sequencing and phenotyped in replicated trials. The mean prediction accuracies ranged from 0.31-0.74 for LR seedling, 0.12-0.56 for LR APR, 0.31-0.65 for SR APR, 0.70-0.78 for YR seedling, and 0.34-0.71 for YR APR. For most datasets, the RKHS-MP model gave the highest accuracies, while LS gave the lowest. GBLUP, GBLUP A, RKHS-M, and RKHS-P models gave similar accuracies. Using genome-wide marker-based models resulted in an average of 42% increase in accuracy over LS. We conclude that GS is a promising approach for improvement of quantitative rust resistance and can be implemented in the breeding pipeline.

Predictive accuracy of combined genetic and environmental risk scores.

PubMed

Dudbridge, Frank; Pashayan, Nora; Yang, Jian

2018-02-01

The substantial heritability of most complex diseases suggests that genetic data could provide useful risk prediction. To date the performance of genetic risk scores has fallen short of the potential implied by heritability, but this can be explained by insufficient sample sizes for estimating highly polygenic models. When risk predictors already exist based on environment or lifestyle, two key questions are to what extent can they be improved by adding genetic information, and what is the ultimate potential of combined genetic and environmental risk scores? Here, we extend previous work on the predictive accuracy of polygenic scores to allow for an environmental score that may be correlated with the polygenic score, for example when the environmental factors mediate the genetic risk. We derive common measures of predictive accuracy and improvement as functions of the training sample size, chip heritabilities of disease and environmental score, and genetic correlation between disease and environmental risk factors. We consider simple addition of the two scores and a weighted sum that accounts for their correlation. Using examples from studies of cardiovascular disease and breast cancer, we show that improvements in discrimination are generally small but reasonable degrees of reclassification could be obtained with current sample sizes. Correlation between genetic and environmental scores has only minor effects on numerical results in realistic scenarios. In the longer term, as the accuracy of polygenic scores improves they will come to dominate the predictive accuracy compared to environmental scores. © 2017 WILEY PERIODICALS, INC.

Predictive accuracy of combined genetic and environmental risk scores

PubMed Central

Pashayan, Nora; Yang, Jian

2017-01-01

ABSTRACT The substantial heritability of most complex diseases suggests that genetic data could provide useful risk prediction. To date the performance of genetic risk scores has fallen short of the potential implied by heritability, but this can be explained by insufficient sample sizes for estimating highly polygenic models. When risk predictors already exist based on environment or lifestyle, two key questions are to what extent can they be improved by adding genetic information, and what is the ultimate potential of combined genetic and environmental risk scores? Here, we extend previous work on the predictive accuracy of polygenic scores to allow for an environmental score that may be correlated with the polygenic score, for example when the environmental factors mediate the genetic risk. We derive common measures of predictive accuracy and improvement as functions of the training sample size, chip heritabilities of disease and environmental score, and genetic correlation between disease and environmental risk factors. We consider simple addition of the two scores and a weighted sum that accounts for their correlation. Using examples from studies of cardiovascular disease and breast cancer, we show that improvements in discrimination are generally small but reasonable degrees of reclassification could be obtained with current sample sizes. Correlation between genetic and environmental scores has only minor effects on numerical results in realistic scenarios. In the longer term, as the accuracy of polygenic scores improves they will come to dominate the predictive accuracy compared to environmental scores. PMID:29178508

Development of predictive mapping techniques for soil survey and salinity mapping

NASA Astrophysics Data System (ADS)

Elnaggar, Abdelhamid A.

Conventional soil maps represent a valuable source of information about soil characteristics, however they are subjective, very expensive, and time-consuming to prepare. Also, they do not include explicit information about the conceptual mental model used in developing them nor information about their accuracy, in addition to the error associated with them. Decision tree analysis (DTA) was successfully used in retrieving the expert knowledge embedded in old soil survey data. This knowledge was efficiently used in developing predictive soil maps for the study areas in Benton and Malheur Counties, Oregon and accessing their consistency. A retrieved soil-landscape model from a reference area in Harney County was extrapolated to develop a preliminary soil map for the neighboring unmapped part of Malheur County. The developed map had a low prediction accuracy and only a few soil map units (SMUs) were predicted with significant accuracy, mostly those shallow SMUs that have either a lithic contact with the bedrock or developed on a duripan. On the other hand, the developed soil map based on field data was predicted with very high accuracy (overall was about 97%). Salt-affected areas of the Malheur County study area are indicated by their high spectral reflectance and they are easily discriminated from the remote sensing data. However, remote sensing data fails to distinguish between the different classes of soil salinity. Using the DTA method, five classes of soil salinity were successfully predicted with an overall accuracy of about 99%. Moreover, the calculated area of salt-affected soil was overestimated when mapped using remote sensing data compared to that predicted by using DTA. Hence, DTA could be a very helpful approach in developing soil survey and soil salinity maps in more objective, effective, less-expensive and quicker ways based on field data.

Comparison of the influence of plastic and fully covered metal biliary stents on the accuracy of EUS-FNA for the diagnosis of pancreatic cancer.

PubMed

Siddiqui, Ali A; Fein, Michael; Kowalski, Thomas E; Loren, David E; Eloubeidi, Mohamad A

2012-09-01

Prior studies have reported that the presence of prior biliary stent may interfere with EUS visualization of pancreatic tumors. We aimed to compare the influence of the biliary plastic and fully covered self-expanding metal stents (CSEMS) on the accuracy of EUS-FNA cytology in patients with solid pancreatic masses. We conducted a retrospective study evaluating 677 patients with solid pancreatic head/uncinate lesions and a previous biliary stent in whom EUS-FNA was performed. The patients were stratified into two groups: (1) those with a plastic stents and (2) those with CSEMS. Performance characteristics of EUS-FNA including the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were compared between the two groups. The frequency of obtaining an adequate cytology by EUS-FNA was similar in both the CSEMS group and the plastic stent group (97 vs. 97.1 % respectively; p = 1.0). The sensitivity, specificity, and accuracy of EUS-FNA was not significantly different between patients with CSEMS and plastic stents (96.8, 100, 100 % and 97.3, 98, 99.8 %, respectively). The negative predictive value for EUS-FNA was lower in the CSEMS group compared to the plastic stent group (66.6 vs. 78.1 % respectively; p = 0.42). There was one false-positive cytology in the plastic stent group compared to none in the CSEMS group. In a retrospective cohort trial, EUS-FNA was found to be highly accurate and safe in diagnosing patients with suspected pancreatic cancer, even in the presence of a plastic or metallic biliary stent. The presence of a stent did not contribute to a higher false-positive cytology rate.

Connecting clinical and actuarial prediction with rule-based methods.

PubMed

Fokkema, Marjolein; Smits, Niels; Kelderman, Henk; Penninx, Brenda W J H

2015-06-01

Meta-analyses comparing the accuracy of clinical versus actuarial prediction have shown actuarial methods to outperform clinical methods, on average. However, actuarial methods are still not widely used in clinical practice, and there has been a call for the development of actuarial prediction methods for clinical practice. We argue that rule-based methods may be more useful than the linear main effect models usually employed in prediction studies, from a data and decision analytic as well as a practical perspective. In addition, decision rules derived with rule-based methods can be represented as fast and frugal trees, which, unlike main effects models, can be used in a sequential fashion, reducing the number of cues that have to be evaluated before making a prediction. We illustrate the usability of rule-based methods by applying RuleFit, an algorithm for deriving decision rules for classification and regression problems, to a dataset on prediction of the course of depressive and anxiety disorders from Penninx et al. (2011). The RuleFit algorithm provided a model consisting of 2 simple decision rules, requiring evaluation of only 2 to 4 cues. Predictive accuracy of the 2-rule model was very similar to that of a logistic regression model incorporating 20 predictor variables, originally applied to the dataset. In addition, the 2-rule model required, on average, evaluation of only 3 cues. Therefore, the RuleFit algorithm appears to be a promising method for creating decision tools that are less time consuming and easier to apply in psychological practice, and with accuracy comparable to traditional actuarial methods. (c) 2015 APA, all rights reserved).

Flight Test Results: CTAS Cruise/Descent Trajectory Prediction Accuracy for En route ATC Advisories

NASA Technical Reports Server (NTRS)

Green, S.; Grace, M.; Williams, D.

1999-01-01

The Center/TRACON Automation System (CTAS), under development at NASA Ames Research Center, is designed to assist controllers with the management and control of air traffic transitioning to/from congested airspace. This paper focuses on the transition from the en route environment, to high-density terminal airspace, under a time-based arrival-metering constraint. Two flight tests were conducted at the Denver Air Route Traffic Control Center (ARTCC) to study trajectory-prediction accuracy, the key to accurate Decision Support Tool advisories such as conflict detection/resolution and fuel-efficient metering conformance. In collaboration with NASA Langley Research Center, these test were part of an overall effort to research systems and procedures for the integration of CTAS and flight management systems (FMS). The Langley Transport Systems Research Vehicle Boeing 737 airplane flew a combined total of 58 cruise-arrival trajectory runs while following CTAS clearance advisories. Actual trajectories of the airplane were compared to CTAS and FMS predictions to measure trajectory-prediction accuracy and identify the primary sources of error for both. The research airplane was used to evaluate several levels of cockpit automation ranging from conventional avionics to a performance-based vertical navigation (VNAV) FMS. Trajectory prediction accuracy was analyzed with respect to both ARTCC radar tracking and GPS-based aircraft measurements. This paper presents detailed results describing the trajectory accuracy and error sources. Although differences were found in both accuracy and error sources, CTAS accuracy was comparable to the FMS in terms of both meter-fix arrival-time performance (in support of metering) and 4D-trajectory prediction (key to conflict prediction). Overall arrival time errors (mean plus standard deviation) were measured to be approximately 24 seconds during the first flight test (23 runs) and 15 seconds during the second flight test (25 runs). The major source of error during these tests was found to be the predicted winds aloft used by CTAS. Position and velocity estimates of the airplane provided to CTAS by the ATC Host radar tracker were found to be a relatively insignificant error source for the trajectory conditions evaluated. Airplane performance modeling errors within CTAS were found to not significantly affect arrival time errors when the constrained descent procedures were used. The most significant effect related to the flight guidance was observed to be the cross-track and turn-overshoot errors associated with conventional VOR guidance. Lateral navigation (LNAV) guidance significantly reduced both the cross-track and turn-overshoot error. Pilot procedures and VNAV guidance were found to significantly reduce the vertical profile errors associated with atmospheric and aircraft performance model errors.

Predictive performance of genomic selection methods for carcass traits in Hanwoo beef cattle: impacts of the genetic architecture.

PubMed

Mehrban, Hossein; Lee, Deuk Hwan; Moradi, Mohammad Hossein; IlCho, Chung; Naserkheil, Masoumeh; Ibáñez-Escriche, Noelia

2017-01-04

Hanwoo beef is known for its marbled fat, tenderness, juiciness and characteristic flavor, as well as for its low cholesterol and high omega 3 fatty acid contents. As yet, there has been no comprehensive investigation to estimate genomic selection accuracy for carcass traits in Hanwoo cattle using dense markers. This study aimed at evaluating the accuracy of alternative statistical methods that differed in assumptions about the underlying genetic model for various carcass traits: backfat thickness (BT), carcass weight (CW), eye muscle area (EMA), and marbling score (MS). Accuracies of direct genomic breeding values (DGV) for carcass traits were estimated by applying fivefold cross-validation to a dataset including 1183 animals and approximately 34,000 single nucleotide polymorphisms (SNPs). Accuracies of BayesC, Bayesian LASSO (BayesL) and genomic best linear unbiased prediction (GBLUP) methods were similar for BT, EMA and MS. However, for CW, DGV accuracy was 7% higher with BayesC than with BayesL and GBLUP. The increased accuracy of BayesC, compared to GBLUP and BayesL, was maintained for CW, regardless of the training sample size, but not for BT, EMA, and MS. Genome-wide association studies detected consistent large effects for SNPs on chromosomes 6 and 14 for CW. The predictive performance of the models depended on the trait analyzed. For CW, the results showed a clear superiority of BayesC compared to GBLUP and BayesL. These findings indicate the importance of using a proper variable selection method for genomic selection of traits and also suggest that the genetic architecture that underlies CW differs from that of the other carcass traits analyzed. Thus, our study provides significant new insights into the carcass traits of Hanwoo cattle.

Accuracy of prediction of genomic breeding values for residual feed intake and carcass and meat quality traits in Bos taurus, Bos indicus, and composite beef cattle.

PubMed

Bolormaa, S; Pryce, J E; Kemper, K; Savin, K; Hayes, B J; Barendse, W; Zhang, Y; Reich, C M; Mason, B A; Bunch, R J; Harrison, B E; Reverter, A; Herd, R M; Tier, B; Graser, H-U; Goddard, M E

2013-07-01

The aim of this study was to assess the accuracy of genomic predictions for 19 traits including feed efficiency, growth, and carcass and meat quality traits in beef cattle. The 10,181 cattle in our study had real or imputed genotypes for 729,068 SNP although not all cattle were measured for all traits. Animals included Bos taurus, Brahman, composite, and crossbred animals. Genomic EBV (GEBV) were calculated using 2 methods of genomic prediction [BayesR and genomic BLUP (GBLUP)] either using a common training dataset for all breeds or using a training dataset comprising only animals of the same breed. Accuracies of GEBV were assessed using 5-fold cross-validation. The accuracy of genomic prediction varied by trait and by method. Traits with a large number of recorded and genotyped animals and with high heritability gave the greatest accuracy of GEBV. Using GBLUP, the average accuracy was 0.27 across traits and breeds, but the accuracies between breeds and between traits varied widely. When the training population was restricted to animals from the same breed as the validation population, GBLUP accuracies declined by an average of 0.04. The greatest decline in accuracy was found for the 4 composite breeds. The BayesR accuracies were greater by an average of 0.03 than GBLUP accuracies, particularly for traits with known genes of moderate to large effect mutations segregating. The accuracies of 0.43 to 0.48 for IGF-I traits were among the greatest in the study. Although accuracies are low compared with those observed in dairy cattle, genomic selection would still be beneficial for traits that are hard to improve by conventional selection, such as tenderness and residual feed intake. BayesR identified many of the same quantitative trait loci as a genomewide association study but appeared to map them more precisely. All traits appear to be highly polygenic with thousands of SNP independently associated with each trait.

Sweat loss prediction using a multi-model approach

NASA Astrophysics Data System (ADS)

Xu, Xiaojiang; Santee, William R.

2011-07-01

A new multi-model approach (MMA) for sweat loss prediction is proposed to improve prediction accuracy. MMA was computed as the average of sweat loss predicted by two existing thermoregulation models: i.e., the rational model SCENARIO and the empirical model Heat Strain Decision Aid (HSDA). Three independent physiological datasets, a total of 44 trials, were used to compare predictions by MMA, SCENARIO, and HSDA. The observed sweat losses were collected under different combinations of uniform ensembles, environmental conditions (15-40°C, RH 25-75%), and exercise intensities (250-600 W). Root mean square deviation (RMSD), residual plots, and paired t tests were used to compare predictions with observations. Overall, MMA reduced RMSD by 30-39% in comparison with either SCENARIO or HSDA, and increased the prediction accuracy to 66% from 34% or 55%. Of the MMA predictions, 70% fell within the range of mean observed value ± SD, while only 43% of SCENARIO and 50% of HSDA predictions fell within the same range. Paired t tests showed that differences between observations and MMA predictions were not significant, but differences between observations and SCENARIO or HSDA predictions were significantly different for two datasets. Thus, MMA predicted sweat loss more accurately than either of the two single models for the three datasets used. Future work will be to evaluate MMA using additional physiological data to expand the scope of populations and conditions.

Prediction of beta-turns from amino acid sequences using the residue-coupled model.

PubMed

Guruprasad, K; Shukla, S

2003-04-01

We evaluated the prediction of beta-turns from amino acid sequences using the residue-coupled model with an enlarged representative protein data set selected from the Protein Data Bank. Our results show that the probability values derived from a data set comprising 425 protein chains yielded an overall beta-turn prediction accuracy 68.74%, compared with 94.7% reported earlier on a data set of 30 proteins using the same method. However, we noted that the overall beta-turn prediction accuracy using probability values derived from the 30-protein data set reduces to 40.74% when tested on the data set comprising 425 protein chains. In contrast, using probability values derived from the 425 data set used in this analysis, the overall beta-turn prediction accuracy yielded consistent results when tested on either the 30-protein data set (64.62%) used earlier or a more recent representative data set comprising 619 protein chains (64.66%) or on a jackknife data set comprising 476 representative protein chains (63.38%). We therefore recommend the use of probability values derived from the 425 representative protein chains data set reported here, which gives more realistic and consistent predictions of beta-turns from amino acid sequences.

A Multicriteria Approach to Find Predictive and Sparse Models with Stable Feature Selection for High-Dimensional Data.

PubMed

Bommert, Andrea; Rahnenführer, Jörg; Lang, Michel

2017-01-01

Finding a good predictive model for a high-dimensional data set can be challenging. For genetic data, it is not only important to find a model with high predictive accuracy, but it is also important that this model uses only few features and that the selection of these features is stable. This is because, in bioinformatics, the models are used not only for prediction but also for drawing biological conclusions which makes the interpretability and reliability of the model crucial. We suggest using three target criteria when fitting a predictive model to a high-dimensional data set: the classification accuracy, the stability of the feature selection, and the number of chosen features. As it is unclear which measure is best for evaluating the stability, we first compare a variety of stability measures. We conclude that the Pearson correlation has the best theoretical and empirical properties. Also, we find that for the stability assessment behaviour it is most important that a measure contains a correction for chance or large numbers of chosen features. Then, we analyse Pareto fronts and conclude that it is possible to find models with a stable selection of few features without losing much predictive accuracy.

Systematic bias of correlation coefficient may explain negative accuracy of genomic prediction.

PubMed

Zhou, Yao; Vales, M Isabel; Wang, Aoxue; Zhang, Zhiwu

2017-09-01

Accuracy of genomic prediction is commonly calculated as the Pearson correlation coefficient between the predicted and observed phenotypes in the inference population by using cross-validation analysis. More frequently than expected, significant negative accuracies of genomic prediction have been reported in genomic selection studies. These negative values are surprising, given that the minimum value for prediction accuracy should hover around zero when randomly permuted data sets are analyzed. We reviewed the two common approaches for calculating the Pearson correlation and hypothesized that these negative accuracy values reflect potential bias owing to artifacts caused by the mathematical formulas used to calculate prediction accuracy. The first approach, Instant accuracy, calculates correlations for each fold and reports prediction accuracy as the mean of correlations across fold. The other approach, Hold accuracy, predicts all phenotypes in all fold and calculates correlation between the observed and predicted phenotypes at the end of the cross-validation process. Using simulated and real data, we demonstrated that our hypothesis is true. Both approaches are biased downward under certain conditions. The biases become larger when more fold are employed and when the expected accuracy is low. The bias of Instant accuracy can be corrected using a modified formula. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Comparing Magnetic Resonance Imaging and High-Resolution Dynamic Ultrasonography for Diagnosis of Plantar Plate Pathology: A Case Series.

PubMed

Donegan, Ryan J; Stauffer, Anthony; Heaslet, Michael; Poliskie, Michael

Plantar plate pathology has gained noticeable attention in recent years as an etiology of lesser metatarsophalangeal joint pain. The heightened clinical awareness has led to the need for more effective diagnostic imaging accuracy. Numerous reports have established the accuracy of both magnetic resonance imaging and ultrasonography for the diagnosis of plantar plate pathology. However, no conclusions have been made regarding which is the superior imaging modality. The present study reports a case series directly comparing high-resolution dynamic ultrasonography and magnetic resonance imaging. A multicenter retrospective comparison of magnetic resonance imaging versus high-resolution dynamic ultrasonography to evaluate plantar plate pathology with surgical confirmation was conducted. The sensitivity, specificity, and positive and negative predictive values for magnetic resonance imaging were 60%, 100%, 100%, and 33%, respectively. The overall diagnostic accuracy compared with the intraoperative findings was 66%. The sensitivity, specificity, and positive and negative predictive values for high-resolution dynamic ultrasound imaging were 100%, 100%, 100%, and 100%, respectively. The overall diagnostic accuracy compared with the intraoperative findings was 100%. The p value using Fisher's exact test for magnetic resonance imaging and high-resolution dynamic ultrasonography was p = .45, a difference that was not statistically significant. High-resolution dynamic ultrasonography had greater accuracy than magnetic resonance imaging in diagnosing lesser metatarsophalangeal joint plantar plate pathology, although the difference was not statistically significant. The present case series suggests that high-resolution dynamic ultrasonography can be considered an equally accurate imaging modality for plantar plate pathology at a potential cost savings compared with magnetic resonance imaging. Therefore, high-resolution dynamic ultrasonography warrants further investigation in a prospective study. Copyright © 2016 American College of Foot and Ankle Surgeons. Published by Elsevier Inc. All rights reserved.

Minimalist ensemble algorithms for genome-wide protein localization prediction.

PubMed

Lin, Jhih-Rong; Mondal, Ananda Mohan; Liu, Rong; Hu, Jianjun

2012-07-03

Computational prediction of protein subcellular localization can greatly help to elucidate its functions. Despite the existence of dozens of protein localization prediction algorithms, the prediction accuracy and coverage are still low. Several ensemble algorithms have been proposed to improve the prediction performance, which usually include as many as 10 or more individual localization algorithms. However, their performance is still limited by the running complexity and redundancy among individual prediction algorithms. This paper proposed a novel method for rational design of minimalist ensemble algorithms for practical genome-wide protein subcellular localization prediction. The algorithm is based on combining a feature selection based filter and a logistic regression classifier. Using a novel concept of contribution scores, we analyzed issues of algorithm redundancy, consensus mistakes, and algorithm complementarity in designing ensemble algorithms. We applied the proposed minimalist logistic regression (LR) ensemble algorithm to two genome-wide datasets of Yeast and Human and compared its performance with current ensemble algorithms. Experimental results showed that the minimalist ensemble algorithm can achieve high prediction accuracy with only 1/3 to 1/2 of individual predictors of current ensemble algorithms, which greatly reduces computational complexity and running time. It was found that the high performance ensemble algorithms are usually composed of the predictors that together cover most of available features. Compared to the best individual predictor, our ensemble algorithm improved the prediction accuracy from AUC score of 0.558 to 0.707 for the Yeast dataset and from 0.628 to 0.646 for the Human dataset. Compared with popular weighted voting based ensemble algorithms, our classifier-based ensemble algorithms achieved much better performance without suffering from inclusion of too many individual predictors. We proposed a method for rational design of minimalist ensemble algorithms using feature selection and classifiers. The proposed minimalist ensemble algorithm based on logistic regression can achieve equal or better prediction performance while using only half or one-third of individual predictors compared to other ensemble algorithms. The results also suggested that meta-predictors that take advantage of a variety of features by combining individual predictors tend to achieve the best performance. The LR ensemble server and related benchmark datasets are available at http://mleg.cse.sc.edu/LRensemble/cgi-bin/predict.cgi.

Minimalist ensemble algorithms for genome-wide protein localization prediction

PubMed Central

2012-01-01

Background Computational prediction of protein subcellular localization can greatly help to elucidate its functions. Despite the existence of dozens of protein localization prediction algorithms, the prediction accuracy and coverage are still low. Several ensemble algorithms have been proposed to improve the prediction performance, which usually include as many as 10 or more individual localization algorithms. However, their performance is still limited by the running complexity and redundancy among individual prediction algorithms. Results This paper proposed a novel method for rational design of minimalist ensemble algorithms for practical genome-wide protein subcellular localization prediction. The algorithm is based on combining a feature selection based filter and a logistic regression classifier. Using a novel concept of contribution scores, we analyzed issues of algorithm redundancy, consensus mistakes, and algorithm complementarity in designing ensemble algorithms. We applied the proposed minimalist logistic regression (LR) ensemble algorithm to two genome-wide datasets of Yeast and Human and compared its performance with current ensemble algorithms. Experimental results showed that the minimalist ensemble algorithm can achieve high prediction accuracy with only 1/3 to 1/2 of individual predictors of current ensemble algorithms, which greatly reduces computational complexity and running time. It was found that the high performance ensemble algorithms are usually composed of the predictors that together cover most of available features. Compared to the best individual predictor, our ensemble algorithm improved the prediction accuracy from AUC score of 0.558 to 0.707 for the Yeast dataset and from 0.628 to 0.646 for the Human dataset. Compared with popular weighted voting based ensemble algorithms, our classifier-based ensemble algorithms achieved much better performance without suffering from inclusion of too many individual predictors. Conclusions We proposed a method for rational design of minimalist ensemble algorithms using feature selection and classifiers. The proposed minimalist ensemble algorithm based on logistic regression can achieve equal or better prediction performance while using only half or one-third of individual predictors compared to other ensemble algorithms. The results also suggested that meta-predictors that take advantage of a variety of features by combining individual predictors tend to achieve the best performance. The LR ensemble server and related benchmark datasets are available at http://mleg.cse.sc.edu/LRensemble/cgi-bin/predict.cgi. PMID:22759391

Pharmacokinetics of low-dose nedaplatin and validation of AUC prediction in patients with non-small-cell lung carcinoma.

PubMed

Niioka, Takenori; Uno, Tsukasa; Yasui-Furukori, Norio; Takahata, Takenori; Shimizu, Mikiko; Sugawara, Kazunobu; Tateishi, Tomonori

2007-04-01

The aim of this study was to determine the pharmacokinetics of low-dose nedaplatin combined with paclitaxel and radiation therapy in patients having non-small-cell lung carcinoma and establish the optimal dosage regimen for low-dose nedaplatin. We also evaluated predictive accuracy of reported formulas to estimate the area under the plasma concentration-time curve (AUC) of low-dose nedaplatin. A total of 19 patients were administered a constant intravenous infusion of 20 mg/m(2) body surface area (BSA) nedaplatin for an hour, and blood samples were collected at 1, 2, 3, 4, 6, 8, and 19 h after the administration. Plasma concentrations of unbound platinum were measured, and the actual value of platinum AUC (actual AUC) was calculated based on these data. The predicted value of platinum AUC (predicted AUC) was determined by three predictive methods reported in previous studies, consisting of Bayesian method, limited sampling strategies with plasma concentration at a single time point, and simple formula method (SFM) without measured plasma concentration. Three error indices, mean prediction error (ME, measure of bias), mean absolute error (MAE, measure of accuracy), and root mean squared prediction error (RMSE, measure of precision), were obtained from the difference between the actual and the predicted AUC, to compare the accuracy between the three predictive methods. The AUC showed more than threefold inter-patient variation, and there was a favorable correlation between nedaplatin clearance and creatinine clearance (Ccr) (r = 0.832, P < 0.01). In three error indices, MAE and RMSE showed significant difference between the three AUC predictive methods, and the method of SFM had the most favorable results, in which %ME, %MAE, and %RMSE were 5.5, 10.7, and 15.4, respectively. The dosage regimen of low-dose nedaplatin should be established based on Ccr rather than on BSA. Since prediction accuracy of SFM, which did not require measured plasma concentration, was most favorable among the three methods evaluated in this study, SFM could be the most practical method to predict AUC of low-dose nedaplatin in a clinical situation judging from its high accuracy in predicting AUC without measured plasma concentration.

A Statistical Evaluation of the Diagnostic Performance of MEDAS-The Medical Emergency Decision Assistance System

PubMed Central

Georgakis, D. Christine; Trace, David A.; Naeymi-Rad, Frank; Evens, Martha

1990-01-01

Medical expert systems require comprehensive evaluation of their diagnostic accuracy. The usefulness of these systems is limited without established evaluation methods. We propose a new methodology for evaluating the diagnostic accuracy and the predictive capacity of a medical expert system. We have adapted to the medical domain measures that have been used in the social sciences to examine the performance of human experts in the decision making process. Thus, in addition to the standard summary measures, we use measures of agreement and disagreement, and Goodman and Kruskal's λ and τ measures of predictive association. This methodology is illustrated by a detailed retrospective evaluation of the diagnostic accuracy of the MEDAS system. In a study using 270 patients admitted to the North Chicago Veterans Administration Hospital, diagnoses produced by MEDAS are compared with the discharge diagnoses of the attending physicians. The results of the analysis confirm the high diagnostic accuracy and predictive capacity of the MEDAS system. Overall, the agreement of the MEDAS system with the “gold standard” diagnosis of the attending physician has reached a 90% level.

Feature Extraction of Electronic Nose Signals Using QPSO-Based Multiple KFDA Signal Processing

PubMed Central

Wen, Tailai; Huang, Daoyu; Lu, Kun; Deng, Changjian; Zeng, Tanyue; Yu, Song; He, Zhiyi

2018-01-01

The aim of this research was to enhance the classification accuracy of an electronic nose (E-nose) in different detecting applications. During the learning process of the E-nose to predict the types of different odors, the prediction accuracy was not quite satisfying because the raw features extracted from sensors’ responses were regarded as the input of a classifier without any feature extraction processing. Therefore, in order to obtain more useful information and improve the E-nose’s classification accuracy, in this paper, a Weighted Kernels Fisher Discriminant Analysis (WKFDA) combined with Quantum-behaved Particle Swarm Optimization (QPSO), i.e., QWKFDA, was presented to reprocess the original feature matrix. In addition, we have also compared the proposed method with quite a few previously existing ones including Principal Component Analysis (PCA), Locality Preserving Projections (LPP), Fisher Discriminant Analysis (FDA) and Kernels Fisher Discriminant Analysis (KFDA). Experimental results proved that QWKFDA is an effective feature extraction method for E-nose in predicting the types of wound infection and inflammable gases, which shared much higher classification accuracy than those of the contrast methods. PMID:29382146

Feature Extraction of Electronic Nose Signals Using QPSO-Based Multiple KFDA Signal Processing.

PubMed

Wen, Tailai; Yan, Jia; Huang, Daoyu; Lu, Kun; Deng, Changjian; Zeng, Tanyue; Yu, Song; He, Zhiyi

2018-01-29

The aim of this research was to enhance the classification accuracy of an electronic nose (E-nose) in different detecting applications. During the learning process of the E-nose to predict the types of different odors, the prediction accuracy was not quite satisfying because the raw features extracted from sensors' responses were regarded as the input of a classifier without any feature extraction processing. Therefore, in order to obtain more useful information and improve the E-nose's classification accuracy, in this paper, a Weighted Kernels Fisher Discriminant Analysis (WKFDA) combined with Quantum-behaved Particle Swarm Optimization (QPSO), i.e., QWKFDA, was presented to reprocess the original feature matrix. In addition, we have also compared the proposed method with quite a few previously existing ones including Principal Component Analysis (PCA), Locality Preserving Projections (LPP), Fisher Discriminant Analysis (FDA) and Kernels Fisher Discriminant Analysis (KFDA). Experimental results proved that QWKFDA is an effective feature extraction method for E-nose in predicting the types of wound infection and inflammable gases, which shared much higher classification accuracy than those of the contrast methods.

Real-data comparison of data mining methods in prediction of diabetes in iran.

PubMed

Tapak, Lily; Mahjub, Hossein; Hamidi, Omid; Poorolajal, Jalal

2013-09-01

Diabetes is one of the most common non-communicable diseases in developing countries. Early screening and diagnosis play an important role in effective prevention strategies. This study compared two traditional classification methods (logistic regression and Fisher linear discriminant analysis) and four machine-learning classifiers (neural networks, support vector machines, fuzzy c-mean, and random forests) to classify persons with and without diabetes. The data set used in this study included 6,500 subjects from the Iranian national non-communicable diseases risk factors surveillance obtained through a cross-sectional survey. The obtained sample was based on cluster sampling of the Iran population which was conducted in 2005-2009 to assess the prevalence of major non-communicable disease risk factors. Ten risk factors that are commonly associated with diabetes were selected to compare the performance of six classifiers in terms of sensitivity, specificity, total accuracy, and area under the receiver operating characteristic (ROC) curve criteria. Support vector machines showed the highest total accuracy (0.986) as well as area under the ROC (0.979). Also, this method showed high specificity (1.000) and sensitivity (0.820). All other methods produced total accuracy of more than 85%, but for all methods, the sensitivity values were very low (less than 0.350). The results of this study indicate that, in terms of sensitivity, specificity, and overall classification accuracy, the support vector machine model ranks first among all the classifiers tested in the prediction of diabetes. Therefore, this approach is a promising classifier for predicting diabetes, and it should be further investigated for the prediction of other diseases.

Comparison of Two Predictive Models for Short-Term Mortality in Patients after Severe Traumatic Brain Injury.

PubMed

Kesmarky, Klara; Delhumeau, Cecile; Zenobi, Marie; Walder, Bernhard

2017-07-15

The Glasgow Coma Scale (GCS) and the Abbreviated Injury Score of the head region (HAIS) are validated prognostic factors in traumatic brain injury (TBI). The aim of this study was to compare the prognostic performance of an alternative predictive model including motor GCS, pupillary reactivity, age, HAIS, and presence of multi-trauma for short-term mortality with a reference predictive model including motor GCS, pupil reaction, and age (IMPACT core model). A secondary analysis of a prospective epidemiological cohort study in Switzerland including patients after severe TBI (HAIS >3) with the outcome death at 14 days was performed. Performance of prediction, accuracy of discrimination (area under the receiver operating characteristic curve [AUROC]), calibration, and validity of the two predictive models were investigated. The cohort included 808 patients (median age, 56; interquartile range, 33-71), median GCS at hospital admission 3 (3-14), abnormal pupil reaction 29%, with a death rate of 29.7% at 14 days. The alternative predictive model had a higher accuracy of discrimination to predict death at 14 days than the reference predictive model (AUROC 0.852, 95% confidence interval [CI] 0.824-0.880 vs. AUROC 0.826, 95% CI 0.795-0.857; p < 0.0001). The alternative predictive model had an equivalent calibration, compared with the reference predictive model Hosmer-Lemeshow p values (Chi2 8.52, Hosmer-Lemeshow p = 0.345 vs. Chi2 8.66, Hosmer-Lemeshow p = 0.372). The optimism-corrected value of AUROC for the alternative predictive model was 0.845. After severe TBI, a higher performance of prediction for short-term mortality was observed with the alternative predictive model, compared with the reference predictive model.

ZCURVE 3.0: identify prokaryotic genes with higher accuracy as well as automatically and accurately select essential genes

PubMed Central

Hua, Zhi-Gang; Lin, Yan; Yuan, Ya-Zhou; Yang, De-Chang; Wei, Wen; Guo, Feng-Biao

2015-01-01

In 2003, we developed an ab initio program, ZCURVE 1.0, to find genes in bacterial and archaeal genomes. In this work, we present the updated version (i.e. ZCURVE 3.0). Using 422 prokaryotic genomes, the average accuracy was 93.7% with the updated version, compared with 88.7% with the original version. Such results also demonstrate that ZCURVE 3.0 is comparable with Glimmer 3.02 and may provide complementary predictions to it. In fact, the joint application of the two programs generated better results by correctly finding more annotated genes while also containing fewer false-positive predictions. As the exclusive function, ZCURVE 3.0 contains one post-processing program that can identify essential genes with high accuracy (generally >90%). We hope ZCURVE 3.0 will receive wide use with the web-based running mode. The updated ZCURVE can be freely accessed from http://cefg.uestc.edu.cn/zcurve/ or http://tubic.tju.edu.cn/zcurveb/ without any restrictions. PMID:25977299

Heart imaging: the accuracy of the 64-MSCT in the detection of coronary artery disease.

PubMed

Alessandri, N; Di Matteo, A; Rondoni, G; Petrassi, M; Tufani, F; Ferrari, R; Laghi, A

2009-01-01

At present, coronary angiography represents the gold standard technique for the diagnosis of coronary artery disease. Our aim is to compare the conventional coronary angiography to the coronary 64-multislice spiral computed tomography (64-MSCT), a new and non-invasive cardiac imaging technique. The last generation of MSCT scanners show a better imaging quality, due to a greater spatial and temporal resolution. Four expert observers (two cardiologists and two radiologists) have compared the angiographic data with the accuracy of the 64-MSCT in the detection and evaluation of coronary vessels stenoses. From the data obtained, the sensibility, the specificity and the accuracy of the coronary 64-MSCT have been defined. We have enrolled 75 patients (57 male, 18 female, mean age 61.83 +/- 10.38; range 30-80 years) with known or suspected coronary artery disease. The above population has been divided into 3 groups: Group A (Gr. A) with 40 patients (mean age 60.7 +/- 12.5) affected by both non-significant and significant coronary artery disease; Group B (Gr. B) with 25 patients (mean age 60.3 +/- 14.6) who underwent to percutaneous coronary intervention (PCI); Group C (Gr. C) with 10 patients (mean age 54.20 +/- 13.7) without any coronary angiographic stenoses. All the patients underwent non-invasive exams, conventional coronary angiography and coronary 64-MSCT. The comparison of the data obtained has been carried out according to a per group analysis, per patient analysis and per segment analysis. Moreover, the accuracy of the 64-MSCT has been defined for the detection of >75%, 50-75% and <50% coronary stenoses. Coronary angiography has identified significant coronary artery disease in 75% of the patients in the Gr. A and in 73% of the patients in the Gr. B. No coronary stenoses have been detected in Gr. C. According to a per segment analysis, in Gr. A, 36% of the segments analysed have shown a coronary stenosis (37% stenoses >75%, 32% stenoses 50-75% and 31% stenoses <50%). In Gr. B, 32% of the segments have shown a coronary stenosis (33% stenoses >75%, 29% stenoses 50-75% and 38% stenoses <50%). In-stent disease has been shown in only 4 of the 29 coronary stents identified. In Gr. A, coronary 64-MSCT has confirmed the angiographic results in the 93% of cases (sensibility 93%, specificity 100%, positive predictive value 100% and negative predictive value 83%) while, in Gr. B, this confirm has been obtained only in 64% of cases (sensibility 64%, specificity 100%, positive predictive value 100% and negative predictive value 50%). In Gr. C, we have observed a complete agreement between angiographic and CT data (sensibility, specificity, positive predictive value and negative predictive value 100%). According to a per segment analysis, the angiographic results have been confirmed in 98% of cases in Gr. A (sensibility 98%, specificity 94%, positive predictive value 90% and negative predictive value 94%) but only in 55% of cases in Gr. B (sensibility 55%, specificity 90%, positive predictive value 71% and negative predictive value 81%). Moreover, only 1 of the 4 in-stent restenoses has been detected (sensibility 25%, specificity 100%, positive predictive value 100% and negative predictive value 77%). Coronary angiography has detected a greater number of coronary stenoses than the 64-MSCT. 64-MSCT has demonstrated better accuracy in the study of coronary vessels wider than 2 mm, while its accuracy is lower for smaller vessels (diameter < 2.5 mm) and for the identification of in-stent restenosis, because there is a reduced image quality for these vessels and therefore a lower accuracy in the coronary stenosis detection. Nevertheless, 64-MSCT shows high accuracy and it can be considered a comparative but not a substitutive exam of the coronary angiography. Several technical limitations of the 64-MSCT are responsible of its lower accuracy versus the conventional coronary angiography, but solving these technical problems could give us a new non-invasive imaging technique for the study of coronary stents.

Intra-Operative Frozen Sections for Ovarian Tumors – A Tertiary Center Experience

PubMed Central

Arshad, Nur Zaiti Md; Ng, Beng Kwang; Paiman, Noor Asmaliza Md; Mahdy, Zaleha Abdullah; Noor, Rushdan Mohd

2018-01-01

Background: Accuracy of diagnosis with intra-operative frozen sections is extremely important in the evaluation of ovarian tumors so that appropriate surgical procedures can be selected. Study design: All patients who with intra-operative frozen sections for ovarian masses in a tertiary center over nine years from June 2008 until April 2017 were reviewed. Frozen section diagnosis and final histopathological reports were compared. Main outcome measures: Sensitivity, specificity, positive and negative predictive values of intra-operative frozen section as compared to final histopathological results for ovarian tumors. Results: A total of 92 cases were recruited for final evaluation. The frozen section diagnoses were comparable with the final histopathological reports in 83.7% of cases. The sensitivity, specificity, positive predictive value and negative predictive value for benign and malignant ovarian tumors were 95.6%, 85.1%, 86.0% and 95.2% and 69.2%, 100%, 100% and 89.2% respectively. For borderline ovarian tumors, the sensitivity and specificity were 76.2% and 88.7%, respectively; the positive predictive value was 66.7% and the negative predictive value was 92.7%. Conclusion: The accuracy of intra-operative frozen section diagnoses for ovarian tumors is high and this approach remains a reliable option in assessing ovarian masses intra-operatively. PMID:29373916

Accurate disulfide-bonding network predictions improve ab initio structure prediction of cysteine-rich proteins

PubMed Central

Yang, Jing; He, Bao-Ji; Jang, Richard; Zhang, Yang; Shen, Hong-Bin

2015-01-01

Abstract Motivation: Cysteine-rich proteins cover many important families in nature but there are currently no methods specifically designed for modeling the structure of these proteins. The accuracy of disulfide connectivity pattern prediction, particularly for the proteins of higher-order connections, e.g. >3 bonds, is too low to effectively assist structure assembly simulations. Results: We propose a new hierarchical order reduction protocol called Cyscon for disulfide-bonding prediction. The most confident disulfide bonds are first identified and bonding prediction is then focused on the remaining cysteine residues based on SVR training. Compared with purely machine learning-based approaches, Cyscon improved the average accuracy of connectivity pattern prediction by 21.9%. For proteins with more than 5 disulfide bonds, Cyscon improved the accuracy by 585% on the benchmark set of PDBCYS. When applied to 158 non-redundant cysteine-rich proteins, Cyscon predictions helped increase (or decrease) the TM-score (or RMSD) of the ab initio QUARK modeling by 12.1% (or 14.4%). This result demonstrates a new avenue to improve the ab initio structure modeling for cysteine-rich proteins. Availability and implementation: http://www.csbio.sjtu.edu.cn/bioinf/Cyscon/ Contact: zhng@umich.edu or hbshen@sjtu.edu.cn Supplementary information: Supplementary data are available at Bioinformatics online. PMID:26254435

Application of XGBoost algorithm in hourly PM2.5 concentration prediction

NASA Astrophysics Data System (ADS)

Pan, Bingyue

2018-02-01

In view of prediction techniques of hourly PM2.5 concentration in China, this paper applied the XGBoost(Extreme Gradient Boosting) algorithm to predict hourly PM2.5 concentration. The monitoring data of air quality in Tianjin city was analyzed by using XGBoost algorithm. The prediction performance of the XGBoost method is evaluated by comparing observed and predicted PM2.5 concentration using three measures of forecast accuracy. The XGBoost method is also compared with the random forest algorithm, multiple linear regression, decision tree regression and support vector machines for regression models using computational results. The results demonstrate that the XGBoost algorithm outperforms other data mining methods.

TH-CD-207A-07: Prediction of High Dimensional State Subject to Respiratory Motion: A Manifold Learning Approach

DOE Office of Scientific and Technical Information (OSTI.GOV)

Liu, W; Sawant, A; Ruan, D

Purpose: The development of high dimensional imaging systems (e.g. volumetric MRI, CBCT, photogrammetry systems) in image-guided radiotherapy provides important pathways to the ultimate goal of real-time volumetric/surface motion monitoring. This study aims to develop a prediction method for the high dimensional state subject to respiratory motion. Compared to conventional linear dimension reduction based approaches, our method utilizes manifold learning to construct a descriptive feature submanifold, where more efficient and accurate prediction can be performed. Methods: We developed a prediction framework for high-dimensional state subject to respiratory motion. The proposed method performs dimension reduction in a nonlinear setting to permit moremore » descriptive features compared to its linear counterparts (e.g., classic PCA). Specifically, a kernel PCA is used to construct a proper low-dimensional feature manifold, where low-dimensional prediction is performed. A fixed-point iterative pre-image estimation method is applied subsequently to recover the predicted value in the original state space. We evaluated and compared the proposed method with PCA-based method on 200 level-set surfaces reconstructed from surface point clouds captured by the VisionRT system. The prediction accuracy was evaluated with respect to root-mean-squared-error (RMSE) for both 200ms and 600ms lookahead lengths. Results: The proposed method outperformed PCA-based approach with statistically higher prediction accuracy. In one-dimensional feature subspace, our method achieved mean prediction accuracy of 0.86mm and 0.89mm for 200ms and 600ms lookahead lengths respectively, compared to 0.95mm and 1.04mm from PCA-based method. The paired t-tests further demonstrated the statistical significance of the superiority of our method, with p-values of 6.33e-3 and 5.78e-5, respectively. Conclusion: The proposed approach benefits from the descriptiveness of a nonlinear manifold and the prediction reliability in such low dimensional manifold. The fixed-point iterative approach turns out to work well practically for the pre-image recovery. Our approach is particularly suitable to facilitate managing respiratory motion in image-guide radiotherapy. This work is supported in part by NIH grant R01 CA169102-02.« less

Validation of a new radiographic measurement of acetabular version: the transverse axis distance (TAD).

PubMed

Nitschke, Ashley; Lambert, Jeffery R; Glueck, Deborah H; Jesse, Mary Kristen; Mei-Dan, Omer; Strickland, Colin; Petersen, Brian

2015-11-01

This study has three aims: (1) validate a new radiographic measure of acetabular version, the transverse axis distance (TAD) by showing equivalent TAD accuracy in predicting CT equatorial acetabular version when compared to a previously validated, but more cumbersome, radiographic measure, the p/a ratio; (2) establish predictive equations of CT acetabular version from TAD; (3) calculate a sensitive and specific cut point for predicting excessive CT acetabular anteversion using TAD. A 14-month retrospective review was performed of patients who had undergone a dedicated MSK CT pelvis study and who also had a technically adequate AP pelvis radiograph. Two trained observers measured the radiographic p/a ratio, TAD, and CT acetabular equatorial version for 110 hips on a PACS workstation. Mixed model analysis was used to find prediction equations, and ROC analysis was used to evaluate the diagnostic accuracy of p/a ratio and TAD. CT equatorial acetabular version can accurately be predicted from either p/a ratio (p < 0.001) or TAD (p < 0.001). The diagnostic accuracies of p/a ratio and TAD are comparable (p =0.46). Patients whose TAD is higher than 17 mm may have excessive acetabular anteversion. For that cutpoint, the sensitivity of TAD is 0.73, with specificity of 0.82. TAD is an accurate radiographic predictor of CT acetabular anteversion and provides an easy-to-use and intuitive point-of-care assessment of acetabular version in patients with hip pain.

Speaker-sensitive emotion recognition via ranking: Studies on acted and spontaneous speech☆

PubMed Central

Cao, Houwei; Verma, Ragini; Nenkova, Ani

2014-01-01

We introduce a ranking approach for emotion recognition which naturally incorporates information about the general expressivity of speakers. We demonstrate that our approach leads to substantial gains in accuracy compared to conventional approaches. We train ranking SVMs for individual emotions, treating the data from each speaker as a separate query, and combine the predictions from all rankers to perform multi-class prediction. The ranking method provides two natural benefits. It captures speaker specific information even in speaker-independent training/testing conditions. It also incorporates the intuition that each utterance can express a mix of possible emotion and that considering the degree to which each emotion is expressed can be productively exploited to identify the dominant emotion. We compare the performance of the rankers and their combination to standard SVM classification approaches on two publicly available datasets of acted emotional speech, Berlin and LDC, as well as on spontaneous emotional data from the FAU Aibo dataset. On acted data, ranking approaches exhibit significantly better performance compared to SVM classification both in distinguishing a specific emotion from all others and in multi-class prediction. On the spontaneous data, which contains mostly neutral utterances with a relatively small portion of less intense emotional utterances, ranking-based classifiers again achieve much higher precision in identifying emotional utterances than conventional SVM classifiers. In addition, we discuss the complementarity of conventional SVM and ranking-based classifiers. On all three datasets we find dramatically higher accuracy for the test items on whose prediction the two methods agree compared to the accuracy of individual methods. Furthermore on the spontaneous data the ranking and standard classification are complementary and we obtain marked improvement when we combine the two classifiers by late-stage fusion. PMID:25422534

Speaker-sensitive emotion recognition via ranking: Studies on acted and spontaneous speech☆

PubMed

Cao, Houwei; Verma, Ragini; Nenkova, Ani

2015-01-01

We introduce a ranking approach for emotion recognition which naturally incorporates information about the general expressivity of speakers. We demonstrate that our approach leads to substantial gains in accuracy compared to conventional approaches. We train ranking SVMs for individual emotions, treating the data from each speaker as a separate query, and combine the predictions from all rankers to perform multi-class prediction. The ranking method provides two natural benefits. It captures speaker specific information even in speaker-independent training/testing conditions. It also incorporates the intuition that each utterance can express a mix of possible emotion and that considering the degree to which each emotion is expressed can be productively exploited to identify the dominant emotion. We compare the performance of the rankers and their combination to standard SVM classification approaches on two publicly available datasets of acted emotional speech, Berlin and LDC, as well as on spontaneous emotional data from the FAU Aibo dataset. On acted data, ranking approaches exhibit significantly better performance compared to SVM classification both in distinguishing a specific emotion from all others and in multi-class prediction. On the spontaneous data, which contains mostly neutral utterances with a relatively small portion of less intense emotional utterances, ranking-based classifiers again achieve much higher precision in identifying emotional utterances than conventional SVM classifiers. In addition, we discuss the complementarity of conventional SVM and ranking-based classifiers. On all three datasets we find dramatically higher accuracy for the test items on whose prediction the two methods agree compared to the accuracy of individual methods. Furthermore on the spontaneous data the ranking and standard classification are complementary and we obtain marked improvement when we combine the two classifiers by late-stage fusion.

Comparing stream-specific to generalized temperature models to guide salmonid management in a changing climate

USGS Publications Warehouse

Andrew K. Carlson,; William W. Taylor,; Hartikainen, Kelsey M.; Dana M. Infante,; Beard, Douglas; Lynch, Abigail

2017-01-01

Global climate change is predicted to increase air and stream temperatures and alter thermal habitat suitability for growth and survival of coldwater fishes, including brook charr (Salvelinus fontinalis), brown trout (Salmo trutta), and rainbow trout (Oncorhynchus mykiss). In a changing climate, accurate stream temperature modeling is increasingly important for sustainable salmonid management throughout the world. However, finite resource availability (e.g. funding, personnel) drives a tradeoff between thermal model accuracy and efficiency (i.e. cost-effective applicability at management-relevant spatial extents). Using different projected climate change scenarios, we compared the accuracy and efficiency of stream-specific and generalized (i.e. region-specific) temperature models for coldwater salmonids within and outside the State of Michigan, USA, a region with long-term stream temperature data and productive coldwater fisheries. Projected stream temperature warming between 2016 and 2056 ranged from 0.1 to 3.8 °C in groundwater-dominated streams and 0.2–6.8 °C in surface-runoff dominated systems in the State of Michigan. Despite their generally lower accuracy in predicting exact stream temperatures, generalized models accurately projected salmonid thermal habitat suitability in 82% of groundwater-dominated streams, including those with brook charr (80% accuracy), brown trout (89% accuracy), and rainbow trout (75% accuracy). In contrast, generalized models predicted thermal habitat suitability in runoff-dominated streams with much lower accuracy (54%). These results suggest that, amidst climate change and constraints in resource availability, generalized models are appropriate to forecast thermal conditions in groundwater-dominated streams within and outside Michigan and inform regional-level salmonid management strategies that are practical for coldwater fisheries managers, policy makers, and the public. We recommend fisheries professionals reserve resource-intensive stream-specific models for runoff-dominated systems containing high-priority fisheries resources (e.g. trophy individuals, endangered species) that will be directly impacted by projected stream warming.

Influence of sex and ethnic tooth-size differences on mixed-dentition space analysis

PubMed Central

Altherr, Edward R.; Koroluk, Lorne D.; Phillips, Ceib

2013-01-01

Introduction Most mixed-dentition space analyses were developed by using subjects of northwestern European descent and unspecified sex. The purpose of this study was to determine the predictive accuracy of the Tanaka-Johnston analysis in white and black subjects in North Carolina. Methods A total of 120 subjects (30 males and 30 females in each ethnic group) were recruited from clinics at the University of North Carolina School of Dentistry. Ethnicity was verified to 2 previous generations. All subjects were less than 21 years of age and had a full complement of permanent teeth. Digital calipers were used to measure the mesiodistal widths of all teeth on study models fabricated from alginate impressions. The predicted widths of the canines and the premolars in both arches were compared with the actual measured widths. Results In the maxillary arch, there was a significant interaction of ethnicity and sex on the predictive accuracy of the Tanaka-Johnston analysis (P = .03, factorial ANOVA). The predictive accuracy was significantly overestimated in the white female group (P <.001, least square means). In the mandibular arch, there was no significant interaction between ethnicity and sex (P = .49). Conclusions The Tanaka-Johnston analysis significantly overestimated in females (P <.0001) and underestimated in blacks (P <.0001) (factorial ANOVA). Regression equations were developed to increase the predictive accuracy in both arches. (Am J Orthod Dentofacial Orthop 2007;132:332-9) PMID:17826601

Real time shear wave elastography in chronic liver diseases: Accuracy for predicting liver fibrosis, in comparison with serum markers

PubMed Central

Jeong, Jae Yoon; Kim, Tae Yeob; Sohn, Joo Hyun; Kim, Yongsoo; Jeong, Woo Kyoung; Oh, Young-Ha; Yoo, Kyo-Sang

2014-01-01

AIM: To evaluate the correlation between liver stiffness measurement (LSM) by real-time shear wave elastography (SWE) and liver fibrosis stage and the accuracy of LSM for predicting significant and advanced fibrosis, in comparison with serum markers. METHODS: We consecutively analyzed 70 patients with various chronic liver diseases. Liver fibrosis was staged from F0 to F4 according to the Batts and Ludwig scoring system. Significant and advanced fibrosis was defined as stage F ≥ 2 and F ≥ 3, respectively. The accuracy of prediction for fibrosis was analyzed using receiver operating characteristic curves. RESULTS: Seventy patients, 15 were belonged to F0-F1 stage, 20 F2, 13 F3 and 22 F4. LSM was increased with progression of fibrosis stage (F0-F1: 6.77 ± 1.72, F2: 9.98 ± 3.99, F3: 15.80 ± 7.73, and F4: 22.09 ± 10.09, P < 0.001). Diagnostic accuracies of LSM for prediction of F ≥ 2 and F ≥ 3 were 0.915 (95%CI: 0.824-0.968, P < 0.001) and 0.913 (95%CI: 0.821-0.967, P < 0.001), respectively. The cut-off values of LSM for prediction of F ≥ 2 and F ≥ 3 were 8.6 kPa with 78.2% sensitivity and 93.3% specificity and 10.46 kPa with 88.6% sensitivity and 80.0% specificity, respectively. However, there were no significant differences between LSM and serum hyaluronic acid and type IV collagen in diagnostic accuracy. CONCLUSION: SWE showed a significant correlation with the severity of liver fibrosis and was useful and accurate to predict significant and advanced fibrosis, comparable with serum markers. PMID:25320528

Real time shear wave elastography in chronic liver diseases: accuracy for predicting liver fibrosis, in comparison with serum markers.

PubMed

Jeong, Jae Yoon; Kim, Tae Yeob; Sohn, Joo Hyun; Kim, Yongsoo; Jeong, Woo Kyoung; Oh, Young-Ha; Yoo, Kyo-Sang

2014-10-14

To evaluate the correlation between liver stiffness measurement (LSM) by real-time shear wave elastography (SWE) and liver fibrosis stage and the accuracy of LSM for predicting significant and advanced fibrosis, in comparison with serum markers. We consecutively analyzed 70 patients with various chronic liver diseases. Liver fibrosis was staged from F0 to F4 according to the Batts and Ludwig scoring system. Significant and advanced fibrosis was defined as stage F ≥ 2 and F ≥ 3, respectively. The accuracy of prediction for fibrosis was analyzed using receiver operating characteristic curves. Seventy patients, 15 were belonged to F0-F1 stage, 20 F2, 13 F3 and 22 F4. LSM was increased with progression of fibrosis stage (F0-F1: 6.77 ± 1.72, F2: 9.98 ± 3.99, F3: 15.80 ± 7.73, and F4: 22.09 ± 10.09, P < 0.001). Diagnostic accuracies of LSM for prediction of F ≥ 2 and F ≥ 3 were 0.915 (95%CI: 0.824-0.968, P < 0.001) and 0.913 (95%CI: 0.821-0.967, P < 0.001), respectively. The cut-off values of LSM for prediction of F ≥ 2 and F ≥ 3 were 8.6 kPa with 78.2% sensitivity and 93.3% specificity and 10.46 kPa with 88.6% sensitivity and 80.0% specificity, respectively. However, there were no significant differences between LSM and serum hyaluronic acid and type IV collagen in diagnostic accuracy. SWE showed a significant correlation with the severity of liver fibrosis and was useful and accurate to predict significant and advanced fibrosis, comparable with serum markers.

Sensitivity, Specificity, Predictive Values, and Accuracy of Three Diagnostic Tests to Predict Inferior Alveolar Nerve Blockade Failure in Symptomatic Irreversible Pulpitis

PubMed Central

Rodríguez-Wong, Laura; Noguera-González, Danny; Esparza-Villalpando, Vicente; Montero-Aguilar, Mauricio

2017-01-01

Introduction The inferior alveolar nerve block (IANB) is the most common anesthetic technique used on mandibular teeth during root canal treatment. Its success in the presence of preoperative inflammation is still controversial. The aim of this study was to evaluate the sensitivity, specificity, predictive values, and accuracy of three diagnostic tests used to predict IANB failure in symptomatic irreversible pulpitis (SIP). Methodology A cross-sectional study was carried out on the mandibular molars of 53 patients with SIP. All patients received a single cartridge of mepivacaine 2% with 1 : 100000 epinephrine using the IANB technique. Three diagnostic clinical tests were performed to detect anesthetic failure. Anesthetic failure was defined as a positive painful response to any of the three tests. Sensitivity, specificity, predictive values, accuracy, and ROC curves were calculated and compared and significant differences were analyzed. Results IANB failure was determined in 71.7% of the patients. The sensitivity scores for the three tests (lip numbness, the cold stimuli test, and responsiveness during endodontic access) were 0.03, 0.35, and 0.55, respectively, and the specificity score was determined as 1 for all of the tests. Clinically, none of the evaluated tests demonstrated a high enough accuracy (0.30, 0.53, and 0.68 for lip numbness, the cold stimuli test, and responsiveness during endodontic access, resp.). A comparison of the areas under the curve in the ROC analyses showed statistically significant differences between the three tests (p < 0.05). Conclusion None of the analyzed tests demonstrated a high enough accuracy to be considered a reliable diagnostic tool for the prediction of anesthetic failure. PMID:28694714

[Comparison of three stand-level biomass estimation methods].

PubMed

Dong, Li Hu; Li, Feng Ri

2016-12-01

At present, the forest biomass methods of regional scale attract most of attention of the researchers, and developing the stand-level biomass model is popular. Based on the forestry inventory data of larch plantation (Larix olgensis) in Jilin Province, we used non-linear seemly unrelated regression (NSUR) to estimate the parameters in two additive system of stand-level biomass equations, i.e., stand-level biomass equations including the stand variables and stand biomass equations including the biomass expansion factor (i.e., Model system 1 and Model system 2), listed the constant biomass expansion factor for larch plantation and compared the prediction accuracy of three stand-level biomass estimation methods. The results indicated that for two additive system of biomass equations, the adjusted coefficient of determination (R a 2 ) of the total and stem equations was more than 0.95, the root mean squared error (RMSE), the mean prediction error (MPE) and the mean absolute error (MAE) were smaller. The branch and foliage biomass equations were worse than total and stem biomass equations, and the adjusted coefficient of determination (R a 2 ) was less than 0.95. The prediction accuracy of a constant biomass expansion factor was relatively lower than the prediction accuracy of Model system 1 and Model system 2. Overall, although stand-level biomass equation including the biomass expansion factor belonged to the volume-derived biomass estimation method, and was different from the stand biomass equations including stand variables in essence, but the obtained prediction accuracy of the two methods was similar. The constant biomass expansion factor had the lower prediction accuracy, and was inappropriate. In addition, in order to make the model parameter estimation more effective, the established stand-level biomass equations should consider the additivity in a system of all tree component biomass and total biomass equations.

Assessment of MRI-Based Automated Fetal Cerebral Cortical Folding Measures in Prediction of Gestational Age in the Third Trimester.

PubMed

Wu, J; Awate, S P; Licht, D J; Clouchoux, C; du Plessis, A J; Avants, B B; Vossough, A; Gee, J C; Limperopoulos, C

2015-07-01

Traditional methods of dating a pregnancy based on history or sonographic assessment have a large variation in the third trimester. We aimed to assess the ability of various quantitative measures of brain cortical folding on MR imaging in determining fetal gestational age in the third trimester. We evaluated 8 different quantitative cortical folding measures to predict gestational age in 33 healthy fetuses by using T2-weighted fetal MR imaging. We compared the accuracy of the prediction of gestational age by these cortical folding measures with the accuracy of prediction by brain volume measurement and by a previously reported semiquantitative visual scale of brain maturity. Regression models were constructed, and measurement biases and variances were determined via a cross-validation procedure. The cortical folding measures are accurate in the estimation and prediction of gestational age (mean of the absolute error, 0.43 ± 0.45 weeks) and perform better than (P = .024) brain volume (mean of the absolute error, 0.72 ± 0.61 weeks) or sonography measures (SDs approximately 1.5 weeks, as reported in literature). Prediction accuracy is comparable with that of the semiquantitative visual assessment score (mean, 0.57 ± 0.41 weeks). Quantitative cortical folding measures such as global average curvedness can be an accurate and reliable estimator of gestational age and brain maturity for healthy fetuses in the third trimester and have the potential to be an indicator of brain-growth delays for at-risk fetuses and preterm neonates. © 2015 by American Journal of Neuroradiology.

Early prediction of lung cancer recurrence after stereotactic radiotherapy using second order texture statistics

NASA Astrophysics Data System (ADS)

Mattonen, Sarah A.; Palma, David A.; Haasbeek, Cornelis J. A.; Senan, Suresh; Ward, Aaron D.

2014-03-01

Benign radiation-induced lung injury is a common finding following stereotactic ablative radiotherapy (SABR) for lung cancer, and is often difficult to differentiate from a recurring tumour due to the ablative doses and highly conformal treatment with SABR. Current approaches to treatment response assessment have shown limited ability to predict recurrence within 6 months of treatment. The purpose of our study was to evaluate the accuracy of second order texture statistics for prediction of eventual recurrence based on computed tomography (CT) images acquired within 6 months of treatment, and compare with the performance of first order appearance and lesion size measures. Consolidative and ground-glass opacity (GGO) regions were manually delineated on post-SABR CT images. Automatic consolidation expansion was also investigated to act as a surrogate for GGO position. The top features for prediction of recurrence were all texture features within the GGO and included energy, entropy, correlation, inertia, and first order texture (standard deviation of density). These predicted recurrence with 2-fold cross validation (CV) accuracies of 70-77% at 2- 5 months post-SABR, with energy, entropy, and first order texture having leave-one-out CV accuracies greater than 80%. Our results also suggest that automatic expansion of the consolidation region could eliminate the need for manual delineation, and produced reproducible results when compared to manually delineated GGO. If validated on a larger data set, this could lead to a clinically useful computer-aided diagnosis system for prediction of recurrence within 6 months of SABR and allow for early salvage therapy for patients with recurrence.

In vivo real-time assessment of colorectal polyp histology using an optical biopsy forceps system based on laser-induced fluorescence spectroscopy.

PubMed

Rath, Timo; Tontini, Gian E; Vieth, Michael; Nägel, Andreas; Neurath, Markus F; Neumann, Helmut

2016-06-01

In order to reduce time, costs, and risks associated with resection of diminutive colorectal polyps, the American Society for Gastrointestinal Endoscopy (ASGE) recently proposed performance thresholds that new technologies should meet for the accurate real-time assessment of histology of colorectal polyps. In this study, we prospectively assessed whether laser-induced fluorescence spectroscopy (LIFS), using the new WavSTAT4 optical biopsy system, can meet the ASGE criteria. 27 patients undergoing screening or surveillance colonoscopy were included. The histology of 137 diminutive colorectal polyps was predicted in real time using LIFS and findings were compared with the results of conventional histopathological examination. The accuracy of predicting polyp histology with WavSTAT4 was assessed according to the ASGE criteria. The overall accuracy of LIFS using WavSTAT4 for predicting polyp histology was 84.7 % with sensitivity, specificity, and negative predictive value (NPV) of 81.8 %, 85.2 %, and 96.1 %. When only distal colorectal diminutive polyps were considered, the NPV for excluding adenomatous histology increased to 100 % (accuracy 82.4 %, sensitivity 100 %, specificity 80.6 %). On-site, LIFS correctly predicted the recommended surveillance intervals with an accuracy of 88.9 % (24/27 patients) when compared with histology-based United States guideline recommendations; in the 3 patients for whom LIFS- and histopathology-based recommended surveillance intervals differed, LIFS predicted shorter surveillance intervals. From the data of this pilot study, LIFS using the WavSTAT4 system appears accurate enough to allow distal colorectal polyps to be left in place and nearly reaches the threshold to "resect and discard" them without pathologic assessment. WavSTAT4 therefore has the potential to reduce costs and risks associated with the removal of diminutive colorectal polyps. © Georg Thieme Verlag KG Stuttgart · New York.

Predicting oropharyngeal tumor volume throughout the course of radiation therapy from pretreatment computed tomography data using general linear models.

PubMed

Yock, Adam D; Rao, Arvind; Dong, Lei; Beadle, Beth M; Garden, Adam S; Kudchadker, Rajat J; Court, Laurence E

2014-05-01

The purpose of this work was to develop and evaluate the accuracy of several predictive models of variation in tumor volume throughout the course of radiation therapy. Nineteen patients with oropharyngeal cancers were imaged daily with CT-on-rails for image-guided alignment per an institutional protocol. The daily volumes of 35 tumors in these 19 patients were determined and used to generate (1) a linear model in which tumor volume changed at a constant rate, (2) a general linear model that utilized the power fit relationship between the daily and initial tumor volumes, and (3) a functional general linear model that identified and exploited the primary modes of variation between time series describing the changing tumor volumes. Primary and nodal tumor volumes were examined separately. The accuracy of these models in predicting daily tumor volumes were compared with those of static and linear reference models using leave-one-out cross-validation. In predicting the daily volume of primary tumors, the general linear model and the functional general linear model were more accurate than the static reference model by 9.9% (range: -11.6%-23.8%) and 14.6% (range: -7.3%-27.5%), respectively, and were more accurate than the linear reference model by 14.2% (range: -6.8%-40.3%) and 13.1% (range: -1.5%-52.5%), respectively. In predicting the daily volume of nodal tumors, only the 14.4% (range: -11.1%-20.5%) improvement in accuracy of the functional general linear model compared to the static reference model was statistically significant. A general linear model and a functional general linear model trained on data from a small population of patients can predict the primary tumor volume throughout the course of radiation therapy with greater accuracy than standard reference models. These more accurate models may increase the prognostic value of information about the tumor garnered from pretreatment computed tomography images and facilitate improved treatment management.

Transition index maps for urban growth simulation: application of artificial neural networks, weight of evidence and fuzzy multi-criteria evaluation.

PubMed

Shafizadeh-Moghadam, Hossein; Tayyebi, Amin; Helbich, Marco

2017-06-01

Transition index maps (TIMs) are key products in urban growth simulation models. However, their operationalization is still conflicting. Our aim was to compare the prediction accuracy of three TIM-based spatially explicit land cover change (LCC) models in the mega city of Mumbai, India. These LCC models include two data-driven approaches, namely artificial neural networks (ANNs) and weight of evidence (WOE), and one knowledge-based approach which integrates an analytical hierarchical process with fuzzy membership functions (FAHP). Using the relative operating characteristics (ROC), the performance of these three LCC models were evaluated. The results showed 85%, 75%, and 73% accuracy for the ANN, FAHP, and WOE. The ANN was clearly superior compared to the other LCC models when simulating urban growth for the year 2010; hence, ANN was used to predict urban growth for 2020 and 2030. Projected urban growth maps were assessed using statistical measures, including figure of merit, average spatial distance deviation, producer accuracy, and overall accuracy. Based on our findings, we recomend ANNs as an and accurate method for simulating future patterns of urban growth.

Use of APACHE II and SAPS II to predict mortality for hemorrhagic and ischemic stroke patients.

PubMed

Moon, Byeong Hoo; Park, Sang Kyu; Jang, Dong Kyu; Jang, Kyoung Sool; Kim, Jong Tae; Han, Yong Min

2015-01-01

We studied the applicability of the Acute Physiology and Chronic Health Evaluation II (APACHE II) and Simplified Acute Physiology Score II (SAPS II) in patients admitted to the intensive care unit (ICU) with acute stroke and compared the results with the Glasgow Coma Scale (GCS) and National Institutes of Health Stroke Scale (NIHSS). We also conducted a comparative study of accuracy for predicting hemorrhagic and ischemic stroke mortality. Between January 2011 and December 2012, ischemic or hemorrhagic stroke patients admitted to the ICU were included in the study. APACHE II and SAPS II-predicted mortalities were compared using a calibration curve, the Hosmer-Lemeshow goodness-of-fit test, and the receiver operating characteristic (ROC) curve, and the results were compared with the GCS and NIHSS. Overall 498 patients were included in this study. The observed mortality was 26.3%, whereas APACHE II and SAPS II-predicted mortalities were 35.12% and 35.34%, respectively. The mean GCS and NIHSS scores were 9.43 and 21.63, respectively. The calibration curve was close to the line of perfect prediction. The ROC curve showed a slightly better prediction of mortality for APACHE II in hemorrhagic stroke patients and SAPS II in ischemic stroke patients. The GCS and NIHSS were inferior in predicting mortality in both patient groups. Although both the APACHE II and SAPS II systems can be used to measure performance in the neurosurgical ICU setting, the accuracy of APACHE II in hemorrhagic stroke patients and SAPS II in ischemic stroke patients was superior. Copyright © 2014 Elsevier Ltd. All rights reserved.

A Comparative Study of Data Mining Techniques on Football Match Prediction

NASA Astrophysics Data System (ADS)

Rosli, Che Mohamad Firdaus Che Mohd; Zainuri Saringat, Mohd; Razali, Nazim; Mustapha, Aida

2018-05-01

Data prediction have become a trend in today’s business or organization. This paper is set to predict match outcomes for association football from the perspective of football club managers and coaches. This paper explored different data mining techniques used for predicting the match outcomes where the target class is win, draw and lose. The main objective of this research is to find the most accurate data mining technique that fits the nature of football data. The techniques tested are Decision Trees, Neural Networks, Bayesian Network, and k-Nearest Neighbors. The results from the comparative experiments showed that Decision Trees produced the highest average prediction accuracy in the domain of football match prediction by 99.56%.

Higher Order Corrections in the CoLoRFulNNLO Framework

NASA Astrophysics Data System (ADS)

Somogyi, G.; Kardos, A.; Szőr, Z.; Trócsányi, Z.

We discuss the CoLoRFulNNLO method for computing higher order radiative corrections to jet cross sections in perturbative QCD. We apply our method to the calculation of event shapes and jet rates in three-jet production in electron-positron annihilation. We validate our code by comparing our predictions to previous results in the literature and present the jet cone energy fraction distribution at NNLO accuracy. We also present preliminary NNLO results for the three-jet rate using the Durham jet clustering algorithm matched to resummed predictions at NLL accuracy, and a comparison to LEP data.

Clinical time series prediction: Toward a hierarchical dynamical system framework.

PubMed

Liu, Zitao; Hauskrecht, Milos

2015-09-01

Developing machine learning and data mining algorithms for building temporal models of clinical time series is important for understanding of the patient condition, the dynamics of a disease, effect of various patient management interventions and clinical decision making. In this work, we propose and develop a novel hierarchical framework for modeling clinical time series data of varied length and with irregularly sampled observations. Our hierarchical dynamical system framework for modeling clinical time series combines advantages of the two temporal modeling approaches: the linear dynamical system and the Gaussian process. We model the irregularly sampled clinical time series by using multiple Gaussian process sequences in the lower level of our hierarchical framework and capture the transitions between Gaussian processes by utilizing the linear dynamical system. The experiments are conducted on the complete blood count (CBC) panel data of 1000 post-surgical cardiac patients during their hospitalization. Our framework is evaluated and compared to multiple baseline approaches in terms of the mean absolute prediction error and the absolute percentage error. We tested our framework by first learning the time series model from data for the patients in the training set, and then using it to predict future time series values for the patients in the test set. We show that our model outperforms multiple existing models in terms of its predictive accuracy. Our method achieved a 3.13% average prediction accuracy improvement on ten CBC lab time series when it was compared against the best performing baseline. A 5.25% average accuracy improvement was observed when only short-term predictions were considered. A new hierarchical dynamical system framework that lets us model irregularly sampled time series data is a promising new direction for modeling clinical time series and for improving their predictive performance. Copyright © 2014 Elsevier B.V. All rights reserved.

Prediction of Mechanical Properties of Polymers With Various Force Fields

NASA Technical Reports Server (NTRS)

Odegard, Gregory M.; Clancy, Thomas C.; Gates, Thomas S.

2005-01-01

The effect of force field type on the predicted elastic properties of a polyimide is examined using a multiscale modeling technique. Molecular Dynamics simulations are used to predict the atomic structure and elastic properties of the polymer by subjecting a representative volume element of the material to bulk and shear finite deformations. The elastic properties of the polyimide are determined using three force fields: AMBER, OPLS-AA, and MM3. The predicted values of Young s modulus and shear modulus of the polyimide are compared with experimental values. The results indicate that the mechanical properties of the polyimide predicted with the OPLS-AA force field most closely matched those from experiment. The results also indicate that while the complexity of the force field does not have a significant effect on the accuracy of predicted properties, small differences in the force constants and the functional form of individual terms in the force fields determine the accuracy of the force field in predicting the elastic properties of the polyimide.

Accuracy of ultrasonography in the detection of severe hepatic lipidosis in cats.

PubMed

Yeager, A E; Mohammed, H

1992-04-01

The accuracy of ultrasonography in detection of feline hepatic lipidosis was studied retrospectively. The following ultrasonographic criteria were associated positively with severe hepatic lipidosis: the liver hyperechoic, compared with falciform fat; the liver isoechoic or hyperechoic, compared with omental fat; poor visualization of intrahepatic vessel borders; and increased attenuation of sound by the liver. In a group of 36 cats with clinically apparent hepatobiliary disease and in which liver biopsy was done, liver hyperechoic, compared with falciform fat, was the best criterion for diagnosis of severe hepatic lipidosis with 91% sensitivity, 100% specificity, and 100% positive predictive value.

Improving the spectral measurement accuracy based on temperature distribution and spectra-temperature relationship

NASA Astrophysics Data System (ADS)

Li, Zhe; Feng, Jinchao; Liu, Pengyu; Sun, Zhonghua; Li, Gang; Jia, Kebin

2018-05-01

Temperature is usually considered as a fluctuation in near-infrared spectral measurement. Chemometric methods were extensively studied to correct the effect of temperature variations. However, temperature can be considered as a constructive parameter that provides detailed chemical information when systematically changed during the measurement. Our group has researched the relationship between temperature-induced spectral variation (TSVC) and normalized squared temperature. In this study, we focused on the influence of temperature distribution in calibration set. Multi-temperature calibration set selection (MTCS) method was proposed to improve the prediction accuracy by considering the temperature distribution of calibration samples. Furthermore, double-temperature calibration set selection (DTCS) method was proposed based on MTCS method and the relationship between TSVC and normalized squared temperature. We compare the prediction performance of PLS models based on random sampling method and proposed methods. The results from experimental studies showed that the prediction performance was improved by using proposed methods. Therefore, MTCS method and DTCS method will be the alternative methods to improve prediction accuracy in near-infrared spectral measurement.

A specific prediction equation is necessary to estimate peak oxygen uptake in obese patients with metabolic syndrome.

PubMed

Debeaumont, D; Tardif, C; Folope, V; Castres, I; Lemaitre, F; Tourny, C; Dechelotte, P; Thill, C; Darmon, A; Coquart, J B

2016-06-01

The aims were to: (1) compare peak oxygen uptake ([Formula: see text]peak) predicted from four standard equations to actual [Formula: see text]peak measured from a cardiopulmonary exercise test (CPET) in obese patients with metabolic syndrome (MetS), and (2) develop a new equation to accurately estimate [Formula: see text]peak in obese women with MetS. Seventy-five obese patients with MetS performed a CPET. Anthropometric data were also collected for each participant. [Formula: see text]peak was predicted from four prediction equations (from Riddle et al., Hansen et al., Wasserman et al. or Gläser et al.) and then compared with the actual [Formula: see text]peak measured during the CPET. The accuracy of the predictions was determined with the Bland-Altman method. When accuracy was low, a new prediction equation including anthropometric variables was proposed. [Formula: see text]peak predicted from the equation of Wasserman et al. was not significantly different from actual [Formula: see text]peak in women. Moreover, a significant correlation was found between the predicted and actual values (p < 0.001, r = 0.69). In men, no significant difference was noted between actual [Formula: see text]peak and [Formula: see text]peak predicted from the prediction equation of Gläser et al., and these two values were also correlated (p = 0.03, r = 0.44). However, the LoA95% was wide, whatever the prediction equation or gender. Regression analysis suggested a new prediction equation derived from age and height for obese women with MetS. The methods of Wasserman et al. and Gläser et al. are valid to predict [Formula: see text]peak in obese women and men with MetS, respectively. However, the accuracy of the predictions was low for both methods. Consequently, a new prediction equation including age and height was developed for obese women with MetS. However, new prediction equation remains to develop in obese men with MetS.

Comparison of particle tracking algorithms in commercial CFD packages: sedimentation and diffusion.

PubMed

Robinson, Risa J; Snyder, Pam; Oldham, Michael J

2007-05-01

Computational fluid dynamic modeling software has enabled microdosimetry patterns of inhaled toxins and toxicants to be predicted and visualized, and is being used in inhalation toxicology and risk assessment. These predicted microdosimetry patterns in airway structures are derived from predicted airflow patterns within these airways and particle tracking algorithms used in computational fluid dynamics (CFD) software packages. Although these commercial CFD codes have been tested for accuracy under various conditions, they have not been well tested for respiratory flows in general. Nor has their particle tracking algorithm accuracy been well studied. In this study, three software packages, Fluent Discrete Phase Model (DPM), Fluent Fine Particle Model (FPM), and ANSYS CFX, were evaluated. Sedimentation and diffusion were each isolated in a straight tube geometry and tested for accuracy. A range of flow rates corresponding to adult low activity (minute ventilation = 10 L/min) and to heavy exertion (minute ventilation = 60 L/min) were tested by varying the range of dimensionless diffusion and sedimentation parameters found using the Weibel symmetric 23 generation lung morphology. Numerical results for fully developed parabolic and uniform (slip) profiles were compared respectively, to Pich (1972) and Yu (1977) analytical sedimentation solutions. Schum and Yeh (1980) equations for sedimentation were also compared. Numerical results for diffusional deposition were compared to analytical solutions of Ingham (1975) for parabolic and uniform profiles. Significant differences were found among the various CFD software packages and between numerical and analytical solutions. Therefore, it is prudent to validate CFD predictions against analytical solutions in idealized geometry before tackling the complex geometries of the respiratory tract.

The Theory and Practice of Estimating the Accuracy of Dynamic Flight-Determined Coefficients

NASA Technical Reports Server (NTRS)

Maine, R. E.; Iliff, K. W.

1981-01-01

Means of assessing the accuracy of maximum likelihood parameter estimates obtained from dynamic flight data are discussed. The most commonly used analytical predictors of accuracy are derived and compared from both statistical and simplified geometrics standpoints. The accuracy predictions are evaluated with real and simulated data, with an emphasis on practical considerations, such as modeling error. Improved computations of the Cramer-Rao bound to correct large discrepancies due to colored noise and modeling error are presented. The corrected Cramer-Rao bound is shown to be the best available analytical predictor of accuracy, and several practical examples of the use of the Cramer-Rao bound are given. Engineering judgement, aided by such analytical tools, is the final arbiter of accuracy estimation.

Predicting online ratings based on the opinion spreading process

NASA Astrophysics Data System (ADS)

He, Xing-Sheng; Zhou, Ming-Yang; Zhuo, Zhao; Fu, Zhong-Qian; Liu, Jian-Guo

2015-10-01

Predicting users' online ratings is always a challenge issue and has drawn lots of attention. In this paper, we present a rating prediction method by combining the user opinion spreading process with the collaborative filtering algorithm, where user similarity is defined by measuring the amount of opinion a user transfers to another based on the primitive user-item rating matrix. The proposed method could produce a more precise rating prediction for each unrated user-item pair. In addition, we introduce a tunable parameter λ to regulate the preferential diffusion relevant to the degree of both opinion sender and receiver. The numerical results for Movielens and Netflix data sets show that this algorithm has a better accuracy than the standard user-based collaborative filtering algorithm using Cosine and Pearson correlation without increasing computational complexity. By tuning λ, our method could further boost the prediction accuracy when using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) as measurements. In the optimal cases, on Movielens and Netflix data sets, the corresponding algorithmic accuracy (MAE and RMSE) are improved 11.26% and 8.84%, 13.49% and 10.52% compared to the item average method, respectively.

ir-HSP: Improved Recognition of Heat Shock Proteins, Their Families and Sub-types Based On g-Spaced Di-peptide Features and Support Vector Machine

PubMed Central

Meher, Prabina K.; Sahu, Tanmaya K.; Gahoi, Shachi; Rao, Atmakuri R.

2018-01-01

Heat shock proteins (HSPs) play a pivotal role in cell growth and variability. Since conventional approaches are expensive and voluminous protein sequence information is available in the post-genomic era, development of an automated and accurate computational tool is highly desirable for prediction of HSPs, their families and sub-types. Thus, we propose a computational approach for reliable prediction of all these components in a single framework and with higher accuracy as well. The proposed approach achieved an overall accuracy of ~84% in predicting HSPs, ~97% in predicting six different families of HSPs, and ~94% in predicting four types of DnaJ proteins, with bench mark datasets. The developed approach also achieved higher accuracy as compared to most of the existing approaches. For easy prediction of HSPs by experimental scientists, a user friendly web server ir-HSP is made freely accessible at http://cabgrid.res.in:8080/ir-hsp. The ir-HSP was further evaluated for proteome-wide identification of HSPs by using proteome datasets of eight different species, and ~50% of the predicted HSPs in each species were found to be annotated with InterPro HSP families/domains. Thus, the developed computational method is expected to supplement the currently available approaches for prediction of HSPs, to the extent of their families and sub-types. PMID:29379521

Prediction accuracies for growth and wood attributes of interior spruce in space using genotyping-by-sequencing.

PubMed

Gamal El-Dien, Omnia; Ratcliffe, Blaise; Klápště, Jaroslav; Chen, Charles; Porth, Ilga; El-Kassaby, Yousry A

2015-05-09

Genomic selection (GS) in forestry can substantially reduce the length of breeding cycle and increase gain per unit time through early selection and greater selection intensity, particularly for traits of low heritability and late expression. Affordable next-generation sequencing technologies made it possible to genotype large numbers of trees at a reasonable cost. Genotyping-by-sequencing was used to genotype 1,126 Interior spruce trees representing 25 open-pollinated families planted over three sites in British Columbia, Canada. Four imputation algorithms were compared (mean value (MI), singular value decomposition (SVD), expectation maximization (EM), and a newly derived, family-based k-nearest neighbor (kNN-Fam)). Trees were phenotyped for several yield and wood attributes. Single- and multi-site GS prediction models were developed using the Ridge Regression Best Linear Unbiased Predictor (RR-BLUP) and the Generalized Ridge Regression (GRR) to test different assumption about trait architecture. Finally, using PCA, multi-trait GS prediction models were developed. The EM and kNN-Fam imputation methods were superior for 30 and 60% missing data, respectively. The RR-BLUP GS prediction model produced better accuracies than the GRR indicating that the genetic architecture for these traits is complex. GS prediction accuracies for multi-site were high and better than those of single-sites while multi-site predictability produced the lowest accuracies reflecting type-b genetic correlations and deemed unreliable. The incorporation of genomic information in quantitative genetics analyses produced more realistic heritability estimates as half-sib pedigree tended to inflate the additive genetic variance and subsequently both heritability and gain estimates. Principle component scores as representatives of multi-trait GS prediction models produced surprising results where negatively correlated traits could be concurrently selected for using PCA2 and PCA3. The application of GS to open-pollinated family testing, the simplest form of tree improvement evaluation methods, was proven to be effective. Prediction accuracies obtained for all traits greatly support the integration of GS in tree breeding. While the within-site GS prediction accuracies were high, the results clearly indicate that single-site GS models ability to predict other sites are unreliable supporting the utilization of multi-site approach. Principle component scores provided an opportunity for the concurrent selection of traits with different phenotypic optima.

The Accuracy of the Spot Sign and the Blend Sign for Predicting Hematoma Expansion in Patients with Spontaneous Intracerebral Hemorrhage.

PubMed

Zheng, Jun; Yu, Zhiyuan; Xu, Zhao; Li, Mou; Wang, Xiaoze; Lin, Sen; Li, Hao; You, Chao

2017-05-12

BACKGROUND Hematoma expansion is associated with poor outcome in intracerebral hemorrhage (ICH) patients. The spot sign and the blend sign are reliable tools for predicting hematoma expansion in ICH patients. The aim of this study was to compare the accuracy of the two signs in the prediction of hematoma expansion. MATERIAL AND METHODS Patients with spontaneous ICH were screened for the presence of the computed tomography angiography (CTA) spot sign and the non-contrast CT (NCCT) blend sign within 6 hours after onset of symptoms. The sensitivity, specificity, and positive and negative predictive values of the spot sign and the blend sign in predicting hematoma expansion were calculated. The accuracy of the spot sign and the blend sign in predicting hematoma expansion was analyzed by receiver-operator analysis. RESULTS A total of 115 patients were enrolled in this study. The spot sign was observed in 25 (21.74%) patients, whereas the blend sign was observed in 22 (19.13%) patients. Of the 28 patients with hematoma expansion, the CTA spot sign was found on admission CT scans in 16 (57.14%) and the NCCT blend sign in 12 (42.86%), respectively. The sensitivity, specificity, positive predictive value, and negative predictive value of the spot sign for predicting hematoma expansion were 57.14%, 89.66%, 64.00%, and 86.67%, respectively. In contrast, the sensitivity, specificity, positive predictive value, and negative predictive value of the blend sign were 42.86%, 88.51%, 54.55%, and 82.80%, respectively. The area under the curve (AUC) of the spot sign was 0.734, which was higher than that of the blend sign (0.657). CONCLUSIONS Both the spot sign and the blend sign seemed to be good predictors for hematoma expansion, and the spot sign appeared to have better predictive accuracy.

The Accuracy of the Spot Sign and the Blend Sign for Predicting Hematoma Expansion in Patients with Spontaneous Intracerebral Hemorrhage

PubMed Central

Zheng, Jun; Yu, Zhiyuan; Xu, Zhao; Li, Mou; Wang, Xiaoze; Lin, Sen; Li, Hao; You, Chao

2017-01-01

Background Hematoma expansion is associated with poor outcome in intracerebral hemorrhage (ICH) patients. The spot sign and the blend sign are reliable tools for predicting hematoma expansion in ICH patients. The aim of this study was to compare the accuracy of the two signs in the prediction of hematoma expansion. Material/Methods Patients with spontaneous ICH were screened for the presence of the computed tomography angiography (CTA) spot sign and the non-contrast CT (NCCT) blend sign within 6 hours after onset of symptoms. The sensitivity, specificity, and positive and negative predictive values of the spot sign and the blend sign in predicting hematoma expansion were calculated. The accuracy of the spot sign and the blend sign in predicting hematoma expansion was analyzed by receiver-operator analysis. Results A total of 115 patients were enrolled in this study. The spot sign was observed in 25 (21.74%) patients, whereas the blend sign was observed in 22 (19.13%) patients. Of the 28 patients with hematoma expansion, the CTA spot sign was found on admission CT scans in 16 (57.14%) and the NCCT blend sign in 12 (42.86%), respectively. The sensitivity, specificity, positive predictive value, and negative predictive value of the spot sign for predicting hematoma expansion were 57.14%, 89.66%, 64.00%, and 86.67%, respectively. In contrast, the sensitivity, specificity, positive predictive value, and negative predictive value of the blend sign were 42.86%, 88.51%, 54.55%, and 82.80%, respectively. The area under the curve (AUC) of the spot sign was 0.734, which was higher than that of the blend sign (0.657). Conclusions Both the spot sign and the blend sign seemed to be good predictors for hematoma expansion, and the spot sign appeared to have better predictive accuracy. PMID:28498827

Prospects and Potential Uses of Genomic Prediction of Key Performance Traits in Tetraploid Potato.

PubMed

Stich, Benjamin; Van Inghelandt, Delphine

2018-01-01

Genomic prediction is a routine tool in breeding programs of most major animal and plant species. However, its usefulness for potato breeding has not yet been evaluated in detail. The objectives of this study were to (i) examine the prospects of genomic prediction of key performance traits in a diversity panel of tetraploid potato modeling additive, dominance, and epistatic effects, (ii) investigate the effects of size and make up of training set, number of test environments and molecular markers on prediction accuracy, and (iii) assess the effect of including markers from candidate genes on the prediction accuracy. With genomic best linear unbiased prediction (GBLUP), BayesA, BayesCπ, and Bayesian LASSO, four different prediction methods were used for genomic prediction of relative area under disease progress curve after a Phytophthora infestans infection, plant maturity, maturity corrected resistance, tuber starch content, tuber starch yield (TSY), and tuber yield (TY) of 184 tetraploid potato clones or subsets thereof genotyped with the SolCAP 8.3k SNP array. The cross-validated prediction accuracies with GBLUP and the three Bayesian approaches for the six evaluated traits ranged from about 0.5 to about 0.8. For traits with a high expected genetic complexity, such as TSY and TY, we observed an 8% higher prediction accuracy using a model with additive and dominance effects compared with a model with additive effects only. Our results suggest that for oligogenic traits in general and when diagnostic markers are available in particular, the use of Bayesian methods for genomic prediction is highly recommended and that the diagnostic markers should be modeled as fixed effects. The evaluation of the relative performance of genomic prediction vs. phenotypic selection indicated that the former is superior, assuming cycle lengths and selection intensities that are possible to realize in commercial potato breeding programs.

Prospects and Potential Uses of Genomic Prediction of Key Performance Traits in Tetraploid Potato

PubMed Central

Stich, Benjamin; Van Inghelandt, Delphine

2018-01-01

Genomic prediction is a routine tool in breeding programs of most major animal and plant species. However, its usefulness for potato breeding has not yet been evaluated in detail. The objectives of this study were to (i) examine the prospects of genomic prediction of key performance traits in a diversity panel of tetraploid potato modeling additive, dominance, and epistatic effects, (ii) investigate the effects of size and make up of training set, number of test environments and molecular markers on prediction accuracy, and (iii) assess the effect of including markers from candidate genes on the prediction accuracy. With genomic best linear unbiased prediction (GBLUP), BayesA, BayesCπ, and Bayesian LASSO, four different prediction methods were used for genomic prediction of relative area under disease progress curve after a Phytophthora infestans infection, plant maturity, maturity corrected resistance, tuber starch content, tuber starch yield (TSY), and tuber yield (TY) of 184 tetraploid potato clones or subsets thereof genotyped with the SolCAP 8.3k SNP array. The cross-validated prediction accuracies with GBLUP and the three Bayesian approaches for the six evaluated traits ranged from about 0.5 to about 0.8. For traits with a high expected genetic complexity, such as TSY and TY, we observed an 8% higher prediction accuracy using a model with additive and dominance effects compared with a model with additive effects only. Our results suggest that for oligogenic traits in general and when diagnostic markers are available in particular, the use of Bayesian methods for genomic prediction is highly recommended and that the diagnostic markers should be modeled as fixed effects. The evaluation of the relative performance of genomic prediction vs. phenotypic selection indicated that the former is superior, assuming cycle lengths and selection intensities that are possible to realize in commercial potato breeding programs. PMID:29563919

Estimating Subglottal Pressure from Neck-Surface Acceleration during Normal Voice Production

ERIC Educational Resources Information Center

Fryd, Amanda S.; Van Stan, Jarrad H.; Hillman, Robert E.; Mehta, Daryush D.

2016-01-01

Purpose: The purpose of this study was to evaluate the potential for estimating subglottal air pressure using a neck-surface accelerometer and to compare the accuracy of predicting subglottal air pressure relative to predicting acoustic sound pressure level (SPL). Method: Indirect estimates of subglottal pressure (P[subscript sg]') were obtained…

Paraphrasing and Prediction with Self-Explanation as Generative Strategies for Learning Science Principles in a Simulation

ERIC Educational Resources Information Center

Morrison, Jennifer R.; Bol, Linda; Ross, Steven M.; Watson, Ginger S.

2015-01-01

This study examined the incorporation of generative strategies for the guided discovery of physics principles in a simulation. Participants who either paraphrased or predicted and self-explained guided discovery assignments exhibited improved performance on an achievement test as compared to a control group. Calibration accuracy (the…

Research on light rail electric load forecasting based on ARMA model

NASA Astrophysics Data System (ADS)

Huang, Yifan

2018-04-01

The article compares a variety of time series models and combines the characteristics of power load forecasting. Then, a light load forecasting model based on ARMA model is established. Based on this model, a light rail system is forecasted. The prediction results show that the accuracy of the model prediction is high.

Comparing large-scale hydrological model predictions with observed streamflow in the Pacific Northwest: effects of climate and groundwater

Treesearch

Mohammad Safeeq; Guillaume S. Mauger; Gordon E. Grant; Ivan Arismendi; Alan F. Hamlet; Se-Yeun Lee

2014-01-01

Assessing uncertainties in hydrologic models can improve accuracy in predicting future streamflow. Here, simulated streamflows using the Variable Infiltration Capacity (VIC) model at coarse (1/16°) and fine (1/120°) spatial resolutions were evaluated against observed streamflows from 217 watersheds. In...

Benefit of hepatitis C virus core antigen assay in prediction of therapeutic response to interferon and ribavirin combination therapy.

PubMed

Takahashi, Masahiko; Saito, Hidetsugu; Higashimoto, Makiko; Atsukawa, Kazuhiro; Ishii, Hiromasa

2005-01-01

A highly sensitive second-generation hepatitis C virus (HCV) core antigen assay has recently been developed. We compared viral disappearance and first-phase kinetics between commercially available core antigen (Ag) assays, Lumipulse Ortho HCV Ag (Lumipulse-Ag), and a quantitative HCV RNA PCR assay, Cobas Amplicor HCV Monitor test, version 2 (Amplicor M), to estimate the predictive benefit of a sustained viral response (SVR) and non-SVR in 44 genotype 1b patients treated with interferon (IFN) and ribavirin. HCV core Ag negativity could predict SVR on day 1 (sensitivity = 100%, specificity = 85.0%, accuracy = 86.4%), whereas RNA negativity could predict SVR on day 7 (sensitivity = 100%, specificity = 87.2%, accuracy = 88.6%). None of the patients who had detectable serum core Ag or RNA on day 14 achieved SVR (specificity = 100%). The predictive accuracy on day 14 was higher by RNA negativity (93.2%) than that by core Ag negativity (75.0%). The combined predictive criterion of both viral load decline during the first 24 h and basal viral load was also predictive for SVR; the sensitivities of Lumipulse-Ag and Amplicor-M were 45.5 and 47.6%, respectively, and the specificity was 100%. Amplicor-M had better predictive accuracy than Lumipulse-Ag in 2-week disappearance tests because it had better sensitivity. On the other hand, estimates of kinetic parameters were similar regardless of the detection method. Although the correlations between Lumipulse-Ag and Amplicor-M were good both before and 24 h after IFN administration, HCV core Ag seemed to be relatively lower 24 h after IFN administration than before administration. Lumipulse-Ag seems to be useful for detecting the HCV concentration during IFN therapy; however, we still need to understand the characteristics of the assay.

Validation of Models Used to Inform Colorectal Cancer Screening Guidelines: Accuracy and Implications.

PubMed

Rutter, Carolyn M; Knudsen, Amy B; Marsh, Tracey L; Doria-Rose, V Paul; Johnson, Eric; Pabiniak, Chester; Kuntz, Karen M; van Ballegooijen, Marjolein; Zauber, Ann G; Lansdorp-Vogelaar, Iris

2016-07-01

Microsimulation models synthesize evidence about disease processes and interventions, providing a method for predicting long-term benefits and harms of prevention, screening, and treatment strategies. Because models often require assumptions about unobservable processes, assessing a model's predictive accuracy is important. We validated 3 colorectal cancer (CRC) microsimulation models against outcomes from the United Kingdom Flexible Sigmoidoscopy Screening (UKFSS) Trial, a randomized controlled trial that examined the effectiveness of one-time flexible sigmoidoscopy screening to reduce CRC mortality. The models incorporate different assumptions about the time from adenoma initiation to development of preclinical and symptomatic CRC. Analyses compare model predictions to study estimates across a range of outcomes to provide insight into the accuracy of model assumptions. All 3 models accurately predicted the relative reduction in CRC mortality 10 years after screening (predicted hazard ratios, with 95% percentile intervals: 0.56 [0.44, 0.71], 0.63 [0.51, 0.75], 0.68 [0.53, 0.83]; estimated with 95% confidence interval: 0.56 [0.45, 0.69]). Two models with longer average preclinical duration accurately predicted the relative reduction in 10-year CRC incidence. Two models with longer mean sojourn time accurately predicted the number of screen-detected cancers. All 3 models predicted too many proximal adenomas among patients referred to colonoscopy. Model accuracy can only be established through external validation. Analyses such as these are therefore essential for any decision model. Results supported the assumptions that the average time from adenoma initiation to development of preclinical cancer is long (up to 25 years), and mean sojourn time is close to 4 years, suggesting the window for early detection and intervention by screening is relatively long. Variation in dwell time remains uncertain and could have important clinical and policy implications. © The Author(s) 2016.

Predicting the biological condition of streams: Use of geospatial indicators of natural and anthropogenic characteristics of watersheds

USGS Publications Warehouse

Carlisle, D.M.; Falcone, J.; Meador, M.R.

2009-01-01

We developed and evaluated empirical models to predict biological condition of wadeable streams in a large portion of the eastern USA, with the ultimate goal of prediction for unsampled basins. Previous work had classified (i.e., altered vs. unaltered) the biological condition of 920 streams based on a biological assessment of macroinvertebrate assemblages. Predictor variables were limited to widely available geospatial data, which included land cover, topography, climate, soils, societal infrastructure, and potential hydrologic modification. We compared the accuracy of predictions of biological condition class based on models with continuous and binary responses. We also evaluated the relative importance of specific groups and individual predictor variables, as well as the relationships between the most important predictors and biological condition. Prediction accuracy and the relative importance of predictor variables were different for two subregions for which models were created. Predictive accuracy in the highlands region improved by including predictors that represented both natural and human activities. Riparian land cover and road-stream intersections were the most important predictors. In contrast, predictive accuracy in the lowlands region was best for models limited to predictors representing natural factors, including basin topography and soil properties. Partial dependence plots revealed complex and nonlinear relationships between specific predictors and the probability of biological alteration. We demonstrate a potential application of the model by predicting biological condition in 552 unsampled basins across an ecoregion in southeastern Wisconsin (USA). Estimates of the likelihood of biological condition of unsampled streams could be a valuable tool for screening large numbers of basins to focus targeted monitoring of potentially unaltered or altered stream segments. ?? Springer Science+Business Media B.V. 2008.

Patient-Reported Outcomes After Radiation Therapy in Men With Prostate Cancer: A Systematic Review of Prognostic Tool Accuracy and Validity

DOE Office of Scientific and Technical Information (OSTI.GOV)

O'Callaghan, Michael E., E-mail: elspeth.raymond@health.sa.gov.au; Freemasons Foundation Centre for Men's Health, University of Adelaide; Urology Unit, Repatriation General Hospital, SA Health, Flinders Centre for Innovation in Cancer

Purpose: To identify, through a systematic review, all validated tools used for the prediction of patient-reported outcome measures (PROMs) in patients being treated with radiation therapy for prostate cancer, and provide a comparative summary of accuracy and generalizability. Methods and Materials: PubMed and EMBASE were searched from July 2007. Title/abstract screening, full text review, and critical appraisal were undertaken by 2 reviewers, whereas data extraction was performed by a single reviewer. Eligible articles had to provide a summary measure of accuracy and undertake internal or external validation. Tools were recommended for clinical implementation if they had been externally validated and foundmore » to have accuracy ≥70%. Results: The search strategy identified 3839 potential studies, of which 236 progressed to full text review and 22 were included. From these studies, 50 tools predicted gastrointestinal/rectal symptoms, 29 tools predicted genitourinary symptoms, 4 tools predicted erectile dysfunction, and no tools predicted quality of life. For patients treated with external beam radiation therapy, 3 tools could be recommended for the prediction of rectal toxicity, gastrointestinal toxicity, and erectile dysfunction. For patients treated with brachytherapy, 2 tools could be recommended for the prediction of urinary retention and erectile dysfunction. Conclusions: A large number of tools for the prediction of PROMs in prostate cancer patients treated with radiation therapy have been developed. Only a small minority are accurate and have been shown to be generalizable through external validation. This review provides an accessible catalogue of tools that are ready for clinical implementation as well as which should be prioritized for validation.« less

High variation subarctic topsoil pollutant concentration prediction using neural network residual kriging

NASA Astrophysics Data System (ADS)

Sergeev, A. P.; Tarasov, D. A.; Buevich, A. G.; Subbotina, I. E.; Shichkin, A. V.; Sergeeva, M. V.; Lvova, O. A.

2017-06-01

The work deals with the application of neural networks residual kriging (NNRK) to the spatial prediction of the abnormally distributed soil pollutant (Cr). It is known that combination of geostatistical interpolation approaches (kriging) and neural networks leads to significantly better prediction accuracy and productivity. Generalized regression neural networks and multilayer perceptrons are classes of neural networks widely used for the continuous function mapping. Each network has its own pros and cons; however both demonstrated fast training and good mapping possibilities. In the work, we examined and compared two combined techniques: generalized regression neural network residual kriging (GRNNRK) and multilayer perceptron residual kriging (MLPRK). The case study is based on the real data sets on surface contamination by chromium at a particular location of the subarctic Novy Urengoy, Russia, obtained during the previously conducted screening. The proposed models have been built, implemented and validated using ArcGIS and MATLAB environments. The networks structures have been chosen during a computer simulation based on the minimization of the RMSE. MLRPK showed the best predictive accuracy comparing to the geostatistical approach (kriging) and even to GRNNRK.

Comparative decision models for anticipating shortage of food grain production in India

NASA Astrophysics Data System (ADS)

Chattopadhyay, Manojit; Mitra, Subrata Kumar

2018-01-01

This paper attempts to predict food shortages in advance from the analysis of rainfall during the monsoon months along with other inputs used for crop production, such as land used for cereal production, percentage of area covered under irrigation and fertiliser use. We used six binary classification data mining models viz., logistic regression, Multilayer Perceptron, kernel lab-Support Vector Machines, linear discriminant analysis, quadratic discriminant analysis and k-Nearest Neighbors Network, and found that linear discriminant analysis and kernel lab-Support Vector Machines are equally suitable for predicting per capita food shortage with 89.69 % accuracy in overall prediction and 92.06 % accuracy in predicting food shortage ( true negative rate). Advance information of food shortage can help policy makers to take remedial measures in order to prevent devastating consequences arising out of food non-availability.

Prediction of clinical behaviour and treatment for cancers.

PubMed

Futschik, Matthias E; Sullivan, Mike; Reeve, Anthony; Kasabov, Nikola

2003-01-01

Prediction of clinical behaviour and treatment for cancers is based on the integration of clinical and pathological parameters. Recent reports have demonstrated that gene expression profiling provides a powerful new approach for determining disease outcome. If clinical and microarray data each contain independent information then it should be possible to combine these datasets to gain more accurate prognostic information. Here, we have used existing clinical information and microarray data to generate a combined prognostic model for outcome prediction for diffuse large B-cell lymphoma (DLBCL). A prediction accuracy of 87.5% was achieved. This constitutes a significant improvement compared to the previously most accurate prognostic model with an accuracy of 77.6%. The model introduced here may be generally applicable to the combination of various types of molecular and clinical data for improving medical decision support systems and individualising patient care.

A sparse autoencoder-based deep neural network for protein solvent accessibility and contact number prediction.

PubMed

Deng, Lei; Fan, Chao; Zeng, Zhiwen

2017-12-28

Direct prediction of the three-dimensional (3D) structures of proteins from one-dimensional (1D) sequences is a challenging problem. Significant structural characteristics such as solvent accessibility and contact number are essential for deriving restrains in modeling protein folding and protein 3D structure. Thus, accurately predicting these features is a critical step for 3D protein structure building. In this study, we present DeepSacon, a computational method that can effectively predict protein solvent accessibility and contact number by using a deep neural network, which is built based on stacked autoencoder and a dropout method. The results demonstrate that our proposed DeepSacon achieves a significant improvement in the prediction quality compared with the state-of-the-art methods. We obtain 0.70 three-state accuracy for solvent accessibility, 0.33 15-state accuracy and 0.74 Pearson Correlation Coefficient (PCC) for the contact number on the 5729 monomeric soluble globular protein dataset. We also evaluate the performance on the CASP11 benchmark dataset, DeepSacon achieves 0.68 three-state accuracy and 0.69 PCC for solvent accessibility and contact number, respectively. We have shown that DeepSacon can reliably predict solvent accessibility and contact number with stacked sparse autoencoder and a dropout approach.

Development and evaluation of a regression-based model to predict cesium-137 concentration ratios for saltwater fish.

PubMed

Pinder, John E; Rowan, David J; Smith, Jim T

2016-02-01

Data from published studies and World Wide Web sources were combined to develop a regression model to predict (137)Cs concentration ratios for saltwater fish. Predictions were developed from 1) numeric trophic levels computed primarily from random resampling of known food items and 2) K concentrations in the saltwater for 65 samplings from 41 different species from both the Atlantic and Pacific Oceans. A number of different models were initially developed and evaluated for accuracy which was assessed as the ratios of independently measured concentration ratios to those predicted by the model. In contrast to freshwater systems, were K concentrations are highly variable and are an important factor in affecting fish concentration ratios, the less variable K concentrations in saltwater were relatively unimportant in affecting concentration ratios. As a result, the simplest model, which used only trophic level as a predictor, had comparable accuracies to more complex models that also included K concentrations. A test of model accuracy involving comparisons of 56 published concentration ratios from 51 species of marine fish to those predicted by the model indicated that 52 of the predicted concentration ratios were within a factor of 2 of the observed concentration ratios. Copyright © 2015 Elsevier Ltd. All rights reserved.

Diagnostic accuracy of ultrasound in upper and lower extremity long bone fractures of emergency department trauma patients

PubMed Central

Frouzan, Arash; Masoumi, Kambiz; Delirroyfard, Ali; Mazdaie, Behnaz; Bagherzadegan, Elnaz

2017-01-01

Background Long bone fractures are common injuries caused by trauma. Some studies have demonstrated that ultrasound has a high sensitivity and specificity in the diagnosis of upper and lower extremity long bone fractures. Objective The aim of this study was to determine the accuracy of ultrasound compared with plain radiography in diagnosis of upper and lower extremity long bone fractures in traumatic patients. Methods This cross-sectional study assessed 100 patients admitted to the emergency department of Imam Khomeini Hospital, Ahvaz, Iran with trauma to the upper and lower extremities, from September 2014 through October 2015. In all patients, first ultrasound and then standard plain radiography for the upper and lower limb was performed. Data were analyzed by SPSS version 21 to determine the specificity and sensitivity. Results The mean age of patients with upper and lower limb trauma were 31.43±12.32 years and 29.63±5.89 years, respectively. Radius fracture was the most frequent compared to other fractures (27%). Sensitivity, specificity, positive predicted value, and negative predicted value of ultrasound compared with plain radiography in the diagnosis of upper extremity long bones were 95.3%, 87.7%, 87.2% and 96.2%, respectively, and the highest accuracy was observed in left arm fractures (100%). Tibia and fibula fractures were the most frequent types compared to other fractures (89.2%). Sensitivity, specificity, PPV and NPV of ultrasound compared with plain radiography in the diagnosis of upper extremity long bone fractures were 98.6%, 83%, 65.4% and 87.1%, respectively, and the highest accuracy was observed in men, lower ages and femoral fractures. Conclusion The results of this study showed that ultrasound compared with plain radiography has a high accuracy in the diagnosis of upper and lower extremity long bone fractures. PMID:28979747

Bayesian modeling and inference for diagnostic accuracy and probability of disease based on multiple diagnostic biomarkers with and without a perfect reference standard.

PubMed

Jafarzadeh, S Reza; Johnson, Wesley O; Gardner, Ian A

2016-03-15

The area under the receiver operating characteristic (ROC) curve (AUC) is used as a performance metric for quantitative tests. Although multiple biomarkers may be available for diagnostic or screening purposes, diagnostic accuracy is often assessed individually rather than in combination. In this paper, we consider the interesting problem of combining multiple biomarkers for use in a single diagnostic criterion with the goal of improving the diagnostic accuracy above that of an individual biomarker. The diagnostic criterion created from multiple biomarkers is based on the predictive probability of disease, conditional on given multiple biomarker outcomes. If the computed predictive probability exceeds a specified cutoff, the corresponding subject is allocated as 'diseased'. This defines a standard diagnostic criterion that has its own ROC curve, namely, the combined ROC (cROC). The AUC metric for cROC, namely, the combined AUC (cAUC), is used to compare the predictive criterion based on multiple biomarkers to one based on fewer biomarkers. A multivariate random-effects model is proposed for modeling multiple normally distributed dependent scores. Bayesian methods for estimating ROC curves and corresponding (marginal) AUCs are developed when a perfect reference standard is not available. In addition, cAUCs are computed to compare the accuracy of different combinations of biomarkers for diagnosis. The methods are evaluated using simulations and are applied to data for Johne's disease (paratuberculosis) in cattle. Copyright © 2015 John Wiley & Sons, Ltd.

Context Memory Decline in Middle Aged Adults is Related to Changes in Prefrontal Cortex Function

PubMed Central

Kwon, Diana; Maillet, David; Pasvanis, Stamatoula; Ankudowich, Elizabeth; Grady, Cheryl L.; Rajah, M. Natasha

2016-01-01

The ability to encode and retrieve spatial and temporal contextual details of episodic memories (context memory) begins to decline at midlife. In the current study, event-related fMRI was used to investigate the neural correlates of context memory decline in healthy middle aged adults (MA) compared with young adults (YA). Participants were scanned while performing easy and hard versions of spatial and temporal context memory tasks. Scans were obtained at encoding and retrieval. Significant reductions in context memory retrieval accuracy were observed in MA, compared with YA. The fMRI results revealed that overall, both groups exhibited similar patterns of brain activity in parahippocampal cortex, ventral occipito-temporal regions and prefrontal cortex (PFC) during encoding. In contrast, at retrieval, there were group differences in ventral occipito-temporal and PFC activity, due to these regions being more activated in MA, compared with YA. Furthermore, only in YA, increased encoding activity in ventrolateral PFC, and increased retrieval activity in occipital cortex, predicted increased retrieval accuracy. In MA, increased retrieval activity in anterior PFC predicted increased retrieval accuracy. These results suggest that there are changes in PFC contributions to context memory at midlife. PMID:25882039

Accuracy of the actuator disc-RANS approach for predicting the performance and wake of tidal turbines.

PubMed

Batten, W M J; Harrison, M E; Bahaj, A S

2013-02-28

The actuator disc-RANS model has widely been used in wind and tidal energy to predict the wake of a horizontal axis turbine. The model is appropriate where large-scale effects of the turbine on a flow are of interest, for example, when considering environmental impacts, or arrays of devices. The accuracy of the model for modelling the wake of tidal stream turbines has not been demonstrated, and flow predictions presented in the literature for similar modelled scenarios vary significantly. This paper compares the results of the actuator disc-RANS model, where the turbine forces have been derived using a blade-element approach, to experimental data measured in the wake of a scaled turbine. It also compares the results with those of a simpler uniform actuator disc model. The comparisons show that the model is accurate and can predict up to 94 per cent of the variation in the experimental velocity data measured on the centreline of the wake, therefore demonstrating that the actuator disc-RANS model is an accurate approach for modelling a turbine wake, and a conservative approach to predict performance and loads. It can therefore be applied to similar scenarios with confidence.

Prognostic models for renal cell carcinoma recurrence: external validation in a Japanese population.

PubMed

Utsumi, Takanobu; Ueda, Takeshi; Fukasawa, Satoshi; Komaru, Atsushi; Sazuka, Tomokazu; Kawamura, Koji; Imamoto, Takashi; Nihei, Naoki; Suzuki, Hiroyoshi; Ichikawa, Tomohiko

2011-09-01

The aim of the present study was to compare the accuracy of three prognostic models in predicting recurrence-free survival among Japanese patients who underwent nephrectomy for non-metastatic renal cell carcinoma (RCC). Patients originated from two centers: Chiba University Hospital (n = 152) and Chiba Cancer Center (n = 65). The following data were collected: age, sex, clinical presentation, Eastern Cooperative Oncology Group performance status, surgical technique, 1997 tumor-node-metastasis stage, clinical and pathological tumor size, histological subtype, disease recurrence, and progression. Three western models, including Yaycioglu's model, Cindolo's model and Kattan's nomogram, were used to predict recurrence-free survival. Predictive accuracy of these models were validated by using Harrell's concordance-index. Concordance-indexes were 0.795 and 0.745 for Kattan's nomogram, 0.700 and 0.634 for Yaycioglu's model, and 0.700 and 0.634 for Cindolo's model, respectively. Furthermore, the constructed calibration plots of Kattan's nomogram overestimated the predicted probability of recurrence-free survival after 5 years compared with the actual probability. Our findings suggest that despite working better than other predictive tools, Kattan's nomogram needs be used with caution when applied to Japanese patients who have undergone nephrectomy for non-metastatic RCC. © 2011 The Japanese Urological Association.

Relating indices of knowledge structure coherence and accuracy to skill-based performance: Is there utility in using a combination of indices?

PubMed

Schuelke, Matthew J; Day, Eric Anthony; McEntire, Lauren E; Boatman, Jazmine Espejo; Wang, Xiaoqian; Kowollik, Vanessa; Boatman, Paul R

2009-07-01

The authors examined the relative criterion-related validity of knowledge structure coherence and two accuracy-based indices (closeness and correlation) as well as the utility of using a combination of knowledge structure indices in the prediction of skill acquisition and transfer. Findings from an aggregation of 5 independent samples (N = 958) whose participants underwent training on a complex computer simulation indicated that coherence and the accuracy-based indices yielded comparable zero-order predictive validities. Support for the incremental validity of using a combination of indices was mixed; the most, albeit small, gain came in pairing coherence and closeness when predicting transfer. After controlling for baseline skill, general mental ability, and declarative knowledge, only coherence explained a statistically significant amount of unique variance in transfer. Overall, the results suggested that the different indices largely overlap in their representation of knowledge organization, but that coherence better reflects adaptable aspects of knowledge organization important to skill transfer.

Evaluating the accuracy of SHAPE-directed RNA secondary structure predictions

PubMed Central

Sükösd, Zsuzsanna; Swenson, M. Shel; Kjems, Jørgen; Heitsch, Christine E.

2013-01-01

Recent advances in RNA structure determination include using data from high-throughput probing experiments to improve thermodynamic prediction accuracy. We evaluate the extent and nature of improvements in data-directed predictions for a diverse set of 16S/18S ribosomal sequences using a stochastic model of experimental SHAPE data. The average accuracy for 1000 data-directed predictions always improves over the original minimum free energy (MFE) structure. However, the amount of improvement varies with the sequence, exhibiting a correlation with MFE accuracy. Further analysis of this correlation shows that accurate MFE base pairs are typically preserved in a data-directed prediction, whereas inaccurate ones are not. Thus, the positive predictive value of common base pairs is consistently higher than the directed prediction accuracy. Finally, we confirm sequence dependencies in the directability of thermodynamic predictions and investigate the potential for greater accuracy improvements in the worst performing test sequence. PMID:23325843

In silico models for predicting ready biodegradability under REACH: a comparative study.

PubMed

Pizzo, Fabiola; Lombardo, Anna; Manganaro, Alberto; Benfenati, Emilio

2013-10-01

REACH (Registration Evaluation Authorization and restriction of Chemicals) legislation is a new European law which aims to raise the human protection level and environmental health. Under REACH all chemicals manufactured or imported for more than one ton per year must be evaluated for their ready biodegradability. Ready biodegradability is also used as a screening test for persistent, bioaccumulative and toxic (PBT) substances. REACH encourages the use of non-testing methods such as QSAR (quantitative structure-activity relationship) models in order to save money and time and to reduce the number of animals used for scientific purposes. Some QSAR models are available for predicting ready biodegradability. We used a dataset of 722 compounds to test four models: VEGA, TOPKAT, BIOWIN 5 and 6 and START and compared their performance on the basis of the following parameters: accuracy, sensitivity, specificity and Matthew's correlation coefficient (MCC). Performance was analyzed from different points of view. The first calculation was done on the whole dataset and VEGA and TOPKAT gave the best accuracy (88% and 87% respectively). Then we considered the compounds inside and outside the training set: BIOWIN 6 and 5 gave the best results for accuracy (81%) outside training set. Another analysis examined the applicability domain (AD). VEGA had the highest value for compounds inside the AD for all the parameters taken into account. Finally, compounds outside the training set and in the AD of the models were considered to assess predictive ability. VEGA gave the best accuracy results (99%) for this group of chemicals. Generally, START model gave poor results. Since BIOWIN, TOPKAT and VEGA models performed well, they may be used to predict ready biodegradability. Copyright © 2013 Elsevier B.V. All rights reserved.

Reduced fMRI activity predicts relapse in patients recovering from stimulant dependence.

PubMed

Clark, Vincent P; Beatty, Gregory K; Anderson, Robert E; Kodituwakku, Piyadassa; Phillips, John P; Lane, Terran D R; Kiehl, Kent A; Calhoun, Vince D

2014-02-01

Relapse presents a significant problem for patients recovering from stimulant dependence. Here we examined the hypothesis that patterns of brain function obtained at an early stage of abstinence differentiates patients who later relapse versus those who remain abstinent. Forty-five recently abstinent stimulant-dependent patients were tested using a randomized event-related functional MRI (ER-fMRI) design that was developed in order to replicate a previous ERP study of relapse using a selective attention task, and were then monitored until 6 months of verified abstinence or stimulant use occurred. SPM revealed smaller absolute blood oxygen level-dependent (BOLD) response amplitude in bilateral ventral posterior cingulate and right insular cortex in 23 patients positive for relapse to stimulant use compared with 22 who remained abstinent. ER-fMRI, psychiatric, neuropsychological, demographic, personal and family history of drug use were compared in order to form predictive models. ER-fMRI was found to predict abstinence with higher accuracy than any other single measure obtained in this study. Logistic regression using fMRI amplitude in right posterior cingulate and insular cortex predicted abstinence with 77.8% accuracy, which increased to 89.9% accuracy when history of mania was included. Using 10-fold cross-validation, Bayesian logistic regression and multilayer perceptron algorithms provided the highest accuracy of 84.4%. These results, combined with previous studies, suggest that the functional organization of paralimbic brain regions including ventral anterior and posterior cingulate and right insula are related to patients' ability to maintain abstinence. Novel therapies designed to target these paralimbic regions identified using ER-fMRI may improve treatment outcome. Copyright © 2012 Wiley Periodicals, Inc.

The accuracy of the SONOBREAST statistical model in comparison to BI-RADS for the prediction of malignancy in solid breast nodules detected at ultrasonography.

PubMed

Paulinelli, Regis R; Oliveira, Luis-Fernando P; Freitas-Junior, Ruffo; Soares, Leonardo R

2016-01-01

The objective of the present study was to compare the accuracy of SONOBREAST for the prediction of malignancy in solid breast nodules detected at ultrasonography with that of the BI-RADS system and to assess the agreement between these two methods. This prospective study included 274 women and evaluated 500 breast nodules detected at ultrasonography. The probability of malignancy was calculated based on the SONOBREAST model, available at www.sonobreast.com.br, and on the BI-RADS system, with results being compared with the anatomopathology report. The lesions were considered suspect in 171 cases (34.20%), according to both SONOBREAST and BI-RADS. Agreement between the methods was perfect, as shown by a Kappa coefficient of 1 (p<0.001). SONOBREAST and BI-RADS proved identical insofar as sensitivity (95.40%), specificity (78.69%), positive predictive value (48.54%), negative predictive value (98.78%) and accuracy (81.60%) are concerned. With respect to the categorical variables (BI-RADS categories 3, 4 and 5), the area under the receiver operating characteristic (ROC) curve was 94.41 for SONOBREAST (range 92.20-96.62) and 89.99 for BI-RADS (range 86.60-93.37). The accuracy of the SONOBREAST model is identical to that found with BI-RADS when the same parameters are used with respect to the cut-off point at which malignancy is suspected. Regarding the continuous probability of malignancy with BI-RADS categories 3, 4 and 5, SONOBREAST permits a more precise and individualized evaluation. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Comparison of Activity Type Classification Accuracy from Accelerometers Worn on the Hip, Wrists, and Thigh in Young, Apparently Healthy Adults

ERIC Educational Resources Information Center

Montoye, Alexander H. K.; Pivarnik, James M.; Mudd, Lanay M.; Biswas, Subir; Pfeiffer, Karin A.

2016-01-01

The purpose of this article is to compare accuracy of activity type prediction models for accelerometers worn on the hip, wrists, and thigh. Forty-four adults performed sedentary, ambulatory, lifestyle, and exercise activities (14 total, 10 categories) for 3-10 minutes each in a 90-minute semi-structured laboratory protocol. Artificial neural…

Diagnostic accuracy of magnetic resonance imaging, transvaginal, and transrectal ultrasonography in deep infiltrating endometriosis

PubMed Central

Alborzi, Saeed; Rasekhi, Alireza; Shomali, Zahra; Madadi, Gooya; Alborzi, Mahshid; Kazemi, Mahboobeh; Hosseini Nohandani, Azam

2018-01-01

Abstract To determine the diagnostic accuracy of pelvic magnetic resonance imaging (MRI), transvaginal sonography (TVS), and transrectal sonography (TRS) in diagnosis of deep infiltrating endometriosis (DIE). This diagnostic accuracy study was conducted during a 2-year period including a total number of 317 patients with signs and symptoms of endometriosis. All the patients were evaluated by pelvic MRI, TVS, and TRS in the same center. The criterion standard was considered to be the laparoscopy and histopathologic examination. Of 317 patients being included in the present study, 252 tested positive for DIE. The sensitivity, specificity, positive predictive value, and negative predictive value of TVS was found to be 83.3%, 46.1%, 85.7%, and 41.6%, respectively. These variables were 80.5%, 18.6%, 79.3%, and 19.7% for TRS and 90.4%, 66.1%, 91.2%, and 64.1% for MRI, respectively. MRI had the highest accuracy (85.4%) when compared to TVS (75.7%) and TRS (67.8%). The sensitivity of TRS, TVS, and MRI in uterosacral ligament DIE was 82.8%, 70.9%, and 63.6%, respectively. On the contrary, specificity had a reverse trend, favoring MRI (93.9%, 92.8%, and 89.8% for TVS and TRS, respectively). The results of the present study demonstrated that TVS and TRS have appropriate diagnostic accuracy in diagnosis of DIE comparable to MRI. PMID:29465552

Combining cow and bull reference populations to increase accuracy of genomic prediction and genome-wide association studies.

PubMed

Calus, M P L; de Haas, Y; Veerkamp, R F

2013-10-01

Genomic selection holds the promise to be particularly beneficial for traits that are difficult or expensive to measure, such that access to phenotypes on large daughter groups of bulls is limited. Instead, cow reference populations can be generated, potentially supplemented with existing information from the same or (highly) correlated traits available on bull reference populations. The objective of this study, therefore, was to develop a model to perform genomic predictions and genome-wide association studies based on a combined cow and bull reference data set, with the accuracy of the phenotypes differing between the cow and bull genomic selection reference populations. The developed bivariate Bayesian stochastic search variable selection model allowed for an unbalanced design by imputing residuals in the residual updating scheme for all missing records. The performance of this model is demonstrated on a real data example, where the analyzed trait, being milk fat or protein yield, was either measured only on a cow or a bull reference population, or recorded on both. Our results were that the developed bivariate Bayesian stochastic search variable selection model was able to analyze 2 traits, even though animals had measurements on only 1 of 2 traits. The Bayesian stochastic search variable selection model yielded consistently higher accuracy for fat yield compared with a model without variable selection, both for the univariate and bivariate analyses, whereas the accuracy of both models was very similar for protein yield. The bivariate model identified several additional quantitative trait loci peaks compared with the single-trait models on either trait. In addition, the bivariate models showed a marginal increase in accuracy of genomic predictions for the cow traits (0.01-0.05), although a greater increase in accuracy is expected as the size of the bull population increases. Our results emphasize that the chosen value of priors in Bayesian genomic prediction models are especially important in small data sets. Copyright © 2013 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Didactic training vs. computer-based self-learning in the prediction of diminutive colon polyp histology by trainees: a randomized controlled study.

PubMed

Khan, Taimur; Cinnor, Birtukan; Gupta, Neil; Hosford, Lindsay; Bansal, Ajay; Olyaee, Mojtaba S; Wani, Sachin; Rastogi, Amit

2017-12-01

Background and study aim  Experts can accurately predict diminutive polyp histology, but the ideal method to train nonexperts is not known. The aim of the study was to compare accuracy in diminutive polyp histology characterization using narrow-band imaging (NBI) between participants undergoing classroom didactic training vs. computer-based self-learning. Participants and methods  Trainees at two institutions were randomized to classroom didactic training or computer-based self-learning. In didactic training, experienced endoscopists reviewed a presentation on NBI patterns for adenomatous and hyperplastic polyps and 40 NBI videos, along with interactive discussion. The self-learning group reviewed the same presentation of 40 teaching videos independently, without interactive discussion. A total of 40 testing videos of diminutive polyps under NBI were then evaluated by both groups. Performance characteristics were calculated by comparing predicted and actual histology. Fisher's exact test was used and P  < 0.05 was considered significant. Results  A total of 17 trainees participated (8 didactic training and 9 self-learning). A larger proportion of polyps were diagnosed with high confidence in the classroom group (66.5 % vs. 50.8 %; P  < 0.01), although sensitivity (86.9 % vs. 95.0 %) and accuracy (85.7 % vs. 93.9 %) of high-confidence predictions were higher in the self-learning group. However, there was no difference in overall accuracy of histology characterization (83.4 % vs. 87.2 %; P  = 0.19). Similar results were noted when comparing sensitivity and specificity between the groups. Conclusion  The self-learning group showed results on a par with or, for high-confidence predictions, even slightly superior to classroom didactic training for predicting diminutive polyp histology. This approach can help in widespread training and clinical implementation of real-time polyp histology characterization. © Georg Thieme Verlag KG Stuttgart · New York.

Urine sampling techniques in symptomatic primary-care patients: a diagnostic accuracy review.

PubMed

Holm, Anne; Aabenhus, Rune

2016-06-08

Choice of urine sampling technique in urinary tract infection may impact diagnostic accuracy and thus lead to possible over- or undertreatment. Currently no evidencebased consensus exists regarding correct sampling technique of urine from women with symptoms of urinary tract infection in primary care. The aim of this study was to determine the accuracy of urine culture from different sampling-techniques in symptomatic non-pregnant women in primary care. A systematic review was conducted by searching Medline and Embase for clinical studies conducted in primary care using a randomized or paired design to compare the result of urine culture obtained with two or more collection techniques in adult, female, non-pregnant patients with symptoms of urinary tract infection. We evaluated quality of the studies and compared accuracy based on dichotomized outcomes. We included seven studies investigating urine sampling technique in 1062 symptomatic patients in primary care. Mid-stream-clean-catch had a positive predictive value of 0.79 to 0.95 and a negative predictive value close to 1 compared to sterile techniques. Two randomized controlled trials found no difference in infection rate between mid-stream-clean-catch, mid-stream-urine and random samples. At present, no evidence suggests that sampling technique affects the accuracy of the microbiological diagnosis in non-pregnant women with symptoms of urinary tract infection in primary care. However, the evidence presented is in-direct and the difference between mid-stream-clean-catch, mid-stream-urine and random samples remains to be investigated in a paired design to verify the present findings.

Comparison of different risk stratification systems in predicting short-term serious outcome of syncope patients.

PubMed

Safari, Saeed; Baratloo, Alireza; Hashemi, Behrooz; Rahmati, Farhad; Forouzanfar, Mohammad Mehdi; Motamedi, Maryam; Mirmohseni, Ladan

2016-01-01

Determining etiologic causes and prognosis can significantly improve management of syncope patients. The present study aimed to compare the values of San Francisco, Osservatorio Epidemiologico sulla Sincope nel Lazio (OESIL), Boston, and Risk Stratification of Syncope in the Emergency Department (ROSE) score clinical decision rules in predicting the short-term serious outcome of syncope patients. The present diagnostic accuracy study with 1-week follow-up was designed to evaluate the predictive values of the four mentioned clinical decision rules. Screening performance characteristics of each model in predicting mortality, myocardial infarction (MI), and cerebrovascular accidents (CVAs) were calculated and compared. To evaluate the value of each aforementioned model in predicting the outcome, sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio were calculated and receiver-operating curve (ROC) curve analysis was done. A total of 187 patients (mean age: 64.2 ± 17.2 years) were enrolled in the study. Mortality, MI, and CVA were seen in 19 (10.2%), 12 (6.4%), and 36 (19.2%) patients, respectively. Area under the ROC curve for OESIL, San Francisco, Boston, and ROSE models in prediction the risk of 1-week mortality, MI, and CVA was in the 30-70% range, with no significant difference among models ( P > 0.05). The pooled model did not show higher accuracy in prediction of mortality, MI, and CVA compared to others ( P > 0.05). This study revealed the weakness of all four evaluated models in predicting short-term serious outcome of syncope patients referred to the emergency department without any significant advantage for one among others.

SCPRED: accurate prediction of protein structural class for sequences of twilight-zone similarity with predicting sequences.

PubMed

Kurgan, Lukasz; Cios, Krzysztof; Chen, Ke

2008-05-01

Protein structure prediction methods provide accurate results when a homologous protein is predicted, while poorer predictions are obtained in the absence of homologous templates. However, some protein chains that share twilight-zone pairwise identity can form similar folds and thus determining structural similarity without the sequence similarity would be desirable for the structure prediction. The folding type of a protein or its domain is defined as the structural class. Current structural class prediction methods that predict the four structural classes defined in SCOP provide up to 63% accuracy for the datasets in which sequence identity of any pair of sequences belongs to the twilight-zone. We propose SCPRED method that improves prediction accuracy for sequences that share twilight-zone pairwise similarity with sequences used for the prediction. SCPRED uses a support vector machine classifier that takes several custom-designed features as its input to predict the structural classes. Based on extensive design that considers over 2300 index-, composition- and physicochemical properties-based features along with features based on the predicted secondary structure and content, the classifier's input includes 8 features based on information extracted from the secondary structure predicted with PSI-PRED and one feature computed from the sequence. Tests performed with datasets of 1673 protein chains, in which any pair of sequences shares twilight-zone similarity, show that SCPRED obtains 80.3% accuracy when predicting the four SCOP-defined structural classes, which is superior when compared with over a dozen recent competing methods that are based on support vector machine, logistic regression, and ensemble of classifiers predictors. The SCPRED can accurately find similar structures for sequences that share low identity with sequence used for the prediction. The high predictive accuracy achieved by SCPRED is attributed to the design of the features, which are capable of separating the structural classes in spite of their low dimensionality. We also demonstrate that the SCPRED's predictions can be successfully used as a post-processing filter to improve performance of modern fold classification methods.

SCPRED: Accurate prediction of protein structural class for sequences of twilight-zone similarity with predicting sequences

PubMed Central

Kurgan, Lukasz; Cios, Krzysztof; Chen, Ke

2008-01-01

Background Protein structure prediction methods provide accurate results when a homologous protein is predicted, while poorer predictions are obtained in the absence of homologous templates. However, some protein chains that share twilight-zone pairwise identity can form similar folds and thus determining structural similarity without the sequence similarity would be desirable for the structure prediction. The folding type of a protein or its domain is defined as the structural class. Current structural class prediction methods that predict the four structural classes defined in SCOP provide up to 63% accuracy for the datasets in which sequence identity of any pair of sequences belongs to the twilight-zone. We propose SCPRED method that improves prediction accuracy for sequences that share twilight-zone pairwise similarity with sequences used for the prediction. Results SCPRED uses a support vector machine classifier that takes several custom-designed features as its input to predict the structural classes. Based on extensive design that considers over 2300 index-, composition- and physicochemical properties-based features along with features based on the predicted secondary structure and content, the classifier's input includes 8 features based on information extracted from the secondary structure predicted with PSI-PRED and one feature computed from the sequence. Tests performed with datasets of 1673 protein chains, in which any pair of sequences shares twilight-zone similarity, show that SCPRED obtains 80.3% accuracy when predicting the four SCOP-defined structural classes, which is superior when compared with over a dozen recent competing methods that are based on support vector machine, logistic regression, and ensemble of classifiers predictors. Conclusion The SCPRED can accurately find similar structures for sequences that share low identity with sequence used for the prediction. The high predictive accuracy achieved by SCPRED is attributed to the design of the features, which are capable of separating the structural classes in spite of their low dimensionality. We also demonstrate that the SCPRED's predictions can be successfully used as a post-processing filter to improve performance of modern fold classification methods. PMID:18452616

Evaluation of wave runup predictions from numerical and parametric models

USGS Publications Warehouse

Stockdon, Hilary F.; Thompson, David M.; Plant, Nathaniel G.; Long, Joseph W.

2014-01-01

Wave runup during storms is a primary driver of coastal evolution, including shoreline and dune erosion and barrier island overwash. Runup and its components, setup and swash, can be predicted from a parameterized model that was developed by comparing runup observations to offshore wave height, wave period, and local beach slope. Because observations during extreme storms are often unavailable, a numerical model is used to simulate the storm-driven runup to compare to the parameterized model and then develop an approach to improve the accuracy of the parameterization. Numerically simulated and parameterized runup were compared to observations to evaluate model accuracies. The analysis demonstrated that setup was accurately predicted by both the parameterized model and numerical simulations. Infragravity swash heights were most accurately predicted by the parameterized model. The numerical model suffered from bias and gain errors that depended on whether a one-dimensional or two-dimensional spatial domain was used. Nonetheless, all of the predictions were significantly correlated to the observations, implying that the systematic errors can be corrected. The numerical simulations did not resolve the incident-band swash motions, as expected, and the parameterized model performed best at predicting incident-band swash heights. An assimilated prediction using a weighted average of the parameterized model and the numerical simulations resulted in a reduction in prediction error variance. Finally, the numerical simulations were extended to include storm conditions that have not been previously observed. These results indicated that the parameterized predictions of setup may need modification for extreme conditions; numerical simulations can be used to extend the validity of the parameterized predictions of infragravity swash; and numerical simulations systematically underpredict incident swash, which is relatively unimportant under extreme conditions.

Modified linear predictive coding approach for moving target tracking by Doppler radar

NASA Astrophysics Data System (ADS)

Ding, Yipeng; Lin, Xiaoyi; Sun, Ke-Hui; Xu, Xue-Mei; Liu, Xi-Yao

2016-07-01

Doppler radar is a cost-effective tool for moving target tracking, which can support a large range of civilian and military applications. A modified linear predictive coding (LPC) approach is proposed to increase the target localization accuracy of the Doppler radar. Based on the time-frequency analysis of the received echo, the proposed approach first real-time estimates the noise statistical parameters and constructs an adaptive filter to intelligently suppress the noise interference. Then, a linear predictive model is applied to extend the available data, which can help improve the resolution of the target localization result. Compared with the traditional LPC method, which empirically decides the extension data length, the proposed approach develops an error array to evaluate the prediction accuracy and thus, adjust the optimum extension data length intelligently. Finally, the prediction error array is superimposed with the predictor output to correct the prediction error. A series of experiments are conducted to illustrate the validity and performance of the proposed techniques.

Predicting and analyzing DNA-binding domains using a systematic approach to identifying a set of informative physicochemical and biochemical properties

PubMed Central

2011-01-01

Background Existing methods of predicting DNA-binding proteins used valuable features of physicochemical properties to design support vector machine (SVM) based classifiers. Generally, selection of physicochemical properties and determination of their corresponding feature vectors rely mainly on known properties of binding mechanism and experience of designers. However, there exists a troublesome problem for designers that some different physicochemical properties have similar vectors of representing 20 amino acids and some closely related physicochemical properties have dissimilar vectors. Results This study proposes a systematic approach (named Auto-IDPCPs) to automatically identify a set of physicochemical and biochemical properties in the AAindex database to design SVM-based classifiers for predicting and analyzing DNA-binding domains/proteins. Auto-IDPCPs consists of 1) clustering 531 amino acid indices in AAindex into 20 clusters using a fuzzy c-means algorithm, 2) utilizing an efficient genetic algorithm based optimization method IBCGA to select an informative feature set of size m to represent sequences, and 3) analyzing the selected features to identify related physicochemical properties which may affect the binding mechanism of DNA-binding domains/proteins. The proposed Auto-IDPCPs identified m=22 features of properties belonging to five clusters for predicting DNA-binding domains with a five-fold cross-validation accuracy of 87.12%, which is promising compared with the accuracy of 86.62% of the existing method PSSM-400. For predicting DNA-binding sequences, the accuracy of 75.50% was obtained using m=28 features, where PSSM-400 has an accuracy of 74.22%. Auto-IDPCPs and PSSM-400 have accuracies of 80.73% and 82.81%, respectively, applied to an independent test data set of DNA-binding domains. Some typical physicochemical properties discovered are hydrophobicity, secondary structure, charge, solvent accessibility, polarity, flexibility, normalized Van Der Waals volume, pK (pK-C, pK-N, pK-COOH and pK-a(RCOOH)), etc. Conclusions The proposed approach Auto-IDPCPs would help designers to investigate informative physicochemical and biochemical properties by considering both prediction accuracy and analysis of binding mechanism simultaneously. The approach Auto-IDPCPs can be also applicable to predict and analyze other protein functions from sequences. PMID:21342579

Rapid high performance liquid chromatography method development with high prediction accuracy, using 5cm long narrow bore columns packed with sub-2microm particles and Design Space computer modeling.

PubMed

Fekete, Szabolcs; Fekete, Jeno; Molnár, Imre; Ganzler, Katalin

2009-11-06

Many different strategies of reversed phase high performance liquid chromatographic (RP-HPLC) method development are used today. This paper describes a strategy for the systematic development of ultrahigh-pressure liquid chromatographic (UHPLC or UPLC) methods using 5cmx2.1mm columns packed with sub-2microm particles and computer simulation (DryLab((R)) package). Data for the accuracy of computer modeling in the Design Space under ultrahigh-pressure conditions are reported. An acceptable accuracy for these predictions of the computer models is presented. This work illustrates a method development strategy, focusing on time reduction up to a factor 3-5, compared to the conventional HPLC method development and exhibits parts of the Design Space elaboration as requested by the FDA and ICH Q8R1. Furthermore this paper demonstrates the accuracy of retention time prediction at elevated pressure (enhanced flow-rate) and shows that the computer-assisted simulation can be applied with sufficient precision for UHPLC applications (p>400bar). Examples of fast and effective method development in pharmaceutical analysis, both for gradient and isocratic separations are presented.

Predicting the accuracy of ligand overlay methods with Random Forest models.

PubMed

Nandigam, Ravi K; Evans, David A; Erickson, Jon A; Kim, Sangtae; Sutherland, Jeffrey J

2008-12-01

The accuracy of binding mode prediction using standard molecular overlay methods (ROCS, FlexS, Phase, and FieldCompare) is studied. Previous work has shown that simple decision tree modeling can be used to improve accuracy by selection of the best overlay template. This concept is extended to the use of Random Forest (RF) modeling for template and algorithm selection. An extensive data set of 815 ligand-bound X-ray structures representing 5 gene families was used for generating ca. 70,000 overlays using four programs. RF models, trained using standard measures of ligand and protein similarity and Lipinski-related descriptors, are used for automatically selecting the reference ligand and overlay method maximizing the probability of reproducing the overlay deduced from X-ray structures (i.e., using rmsd < or = 2 A as the criteria for success). RF model scores are highly predictive of overlay accuracy, and their use in template and method selection produces correct overlays in 57% of cases for 349 overlay ligands not used for training RF models. The inclusion in the models of protein sequence similarity enables the use of templates bound to related protein structures, yielding useful results even for proteins having no available X-ray structures.

Effects of urban microcellular environments on ray-tracing-based coverage predictions.

PubMed

Liu, Zhongyu; Guo, Lixin; Guan, Xiaowei; Sun, Jiejing

2016-09-01

The ray-tracing (RT) algorithm, which is based on geometrical optics and the uniform theory of diffraction, has become a typical deterministic approach of studying wave-propagation characteristics. Under urban microcellular environments, the RT method highly depends on detailed environmental information. The aim of this paper is to provide help in selecting the appropriate level of accuracy required in building databases to achieve good tradeoffs between database costs and prediction accuracy. After familiarization with the operating procedures of the RT-based prediction model, this study focuses on the effect of errors in environmental information on prediction results. The environmental information consists of two parts, namely, geometric and electrical parameters. The geometric information can be obtained from a digital map of a city. To study the effects of inaccuracies in geometry information (building layout) on RT-based coverage prediction, two different artificial erroneous maps are generated based on the original digital map, and systematic analysis is performed by comparing the predictions with the erroneous maps and measurements or the predictions with the original digital map. To make the conclusion more persuasive, the influence of random errors on RMS delay spread results is investigated. Furthermore, given the electrical parameters' effect on the accuracy of the predicted results of the RT model, the dielectric constant and conductivity of building materials are set with different values. The path loss and RMS delay spread under the same circumstances are simulated by the RT prediction model.

Prediction of composite fatigue life under variable amplitude loading using artificial neural network trained by genetic algorithm

NASA Astrophysics Data System (ADS)

Rohman, Muhamad Nur; Hidayat, Mas Irfan P.; Purniawan, Agung

2018-04-01

Neural networks (NN) have been widely used in application of fatigue life prediction. In the use of fatigue life prediction for polymeric-base composite, development of NN model is necessary with respect to the limited fatigue data and applicable to be used to predict the fatigue life under varying stress amplitudes in the different stress ratios. In the present paper, Multilayer-Perceptrons (MLP) model of neural network is developed, and Genetic Algorithm was employed to optimize the respective weights of NN for prediction of polymeric-base composite materials under variable amplitude loading. From the simulation result obtained with two different composite systems, named E-glass fabrics/epoxy (layups [(±45)/(0)2]S), and E-glass/polyester (layups [90/0/±45/0]S), NN model were trained with fatigue data from two different stress ratios, which represent limited fatigue data, can be used to predict another four and seven stress ratios respectively, with high accuracy of fatigue life prediction. The accuracy of NN prediction were quantified with the small value of mean square error (MSE). When using 33% from the total fatigue data for training, the NN model able to produce high accuracy for all stress ratios. When using less fatigue data during training (22% from the total fatigue data), the NN model still able to produce high coefficient of determination between the prediction result compared with obtained by experiment.

Comparing diagnostic accuracy of bedside ultrasound and radiography for bone fracture screening in multiple trauma patients at the ED.

PubMed

Bolandparvaz, Shahram; Moharamzadeh, Payman; Jamali, Kazem; Pouraghaei, Mahboob; Fadaie, Maryam; Sefidbakht, Sepideh; Shahsavari, Kavous

2013-11-01

Long bone fractures are currently diagnosed using radiography, but radiography has some disadvantages (radiation and being time consuming). The present study compared the diagnostic accuracy of bedside ultrasound and radiography in multiple trauma patients at the emergency department (ED). The study assessed 80 injured patients with multiple trauma from February 2011 to July 2012. The patients were older than 18 years and triaged to the cardiopulmonary resuscitation ward of the ED. Bedside ultrasound and radiography were conducted for them. The findings were separately and blindly assessed by 2 radiologists. Sensitivity, specificity, the positive and negative predictive value, and κ coefficient were measured to assess the accuracy and validity of ultrasound as compared with radiography. The sensitivity of ultrasound for diagnosis of limb bone fractures was not high enough and ranged between 55% and 75% depending on the fracture site. The specificity of this diagnostic method had an acceptable range of 62% to 84%. Ultrasound negative prediction value was higher than other indices under study and ranged between 73% and 83%, but its positive prediction value varied between 33.3% and 71%. The κ coefficient for diagnosis of long bone fractures of upper limb (κ = 0.58) and upper limb joints (κ = 0.47) and long bones of lower limb (κ = 0.52) was within the medium range. However, the value for diagnosing fractures of lower limb joints (κ = 0.47) was relatively low. Bedside ultrasound is not a reliable method for diagnosing fractures of upper and lower limb bones compared with radiography. © 2013 Elsevier Inc. All rights reserved.

Prediction of lithium response in first-episode mania using the LITHium Intelligent Agent (LITHIA): Pilot data and proof-of-concept.

PubMed

Fleck, David E; Ernest, Nicholas; Adler, Caleb M; Cohen, Kelly; Eliassen, James C; Norris, Matthew; Komoroski, Richard A; Chu, Wen-Jang; Welge, Jeffrey A; Blom, Thomas J; DelBello, Melissa P; Strakowski, Stephen M

2017-06-01

Individualized treatment for bipolar disorder based on neuroimaging treatment targets remains elusive. To address this shortcoming, we developed a linguistic machine learning system based on a cascading genetic fuzzy tree (GFT) design called the LITHium Intelligent Agent (LITHIA). Using multiple objectively defined functional magnetic resonance imaging (fMRI) and proton magnetic resonance spectroscopy ( 1 H-MRS) inputs, we tested whether LITHIA could accurately predict the lithium response in participants with first-episode bipolar mania. We identified 20 subjects with first-episode bipolar mania who received an adequate trial of lithium over 8 weeks and both fMRI and 1 H-MRS scans at baseline pre-treatment. We trained LITHIA using 18 1 H-MRS and 90 fMRI inputs over four training runs to classify treatment response and predict symptom reductions. Each training run contained a randomly selected 80% of the total sample and was followed by a 20% validation run. Over a different randomly selected distribution of the sample, we then compared LITHIA to eight common classification methods. LITHIA demonstrated nearly perfect classification accuracy and was able to predict post-treatment symptom reductions at 8 weeks with at least 88% accuracy in training and 80% accuracy in validation. Moreover, LITHIA exceeded the predictive capacity of the eight comparator methods and showed little tendency towards overfitting. The results provided proof-of-concept that a novel GFT is capable of providing control to a multidimensional bioinformatics problem-namely, prediction of the lithium response-in a pilot data set. Future work on this, and similar machine learning systems, could help assign psychiatric treatments more efficiently, thereby optimizing outcomes and limiting unnecessary treatment. © 2017 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Use of genetic programming, logistic regression, and artificial neural nets to predict readmission after coronary artery bypass surgery.

PubMed

Engoren, Milo; Habib, Robert H; Dooner, John J; Schwann, Thomas A

2013-08-01

As many as 14 % of patients undergoing coronary artery bypass surgery are readmitted within 30 days. Readmission is usually the result of morbidity and may lead to death. The purpose of this study is to develop and compare statistical and genetic programming models to predict readmission. Patients were divided into separate Construction and Validation populations. Using 88 variables, logistic regression, genetic programs, and artificial neural nets were used to develop predictive models. Models were first constructed and tested on the Construction populations, then validated on the Validation population. Areas under the receiver operator characteristic curves (AU ROC) were used to compare the models. Two hundred and two patients (7.6 %) in the 2,644 patient Construction group and 216 (8.0 %) of the 2,711 patient Validation group were re-admitted within 30 days of CABG surgery. Logistic regression predicted readmission with AU ROC = .675 ± .021 in the Construction group. Genetic programs significantly improved the accuracy, AU ROC = .767 ± .001, p < .001). Artificial neural nets were less accurate with AU ROC = 0.597 ± .001 in the Construction group. Predictive accuracy of all three techniques fell in the Validation group. However, the accuracy of genetic programming (AU ROC = .654 ± .001) was still trivially but statistically non-significantly better than that of the logistic regression (AU ROC = .644 ± .020, p = .61). Genetic programming and logistic regression provide alternative methods to predict readmission that are similarly accurate.

Homology to peptide pattern for annotation of carbohydrate-active enzymes and prediction of function.

PubMed

Busk, P K; Pilgaard, B; Lezyk, M J; Meyer, A S; Lange, L

2017-04-12

Carbohydrate-active enzymes are found in all organisms and participate in key biological processes. These enzymes are classified in 274 families in the CAZy database but the sequence diversity within each family makes it a major task to identify new family members and to provide basis for prediction of enzyme function. A fast and reliable method for de novo annotation of genes encoding carbohydrate-active enzymes is to identify conserved peptides in the curated enzyme families followed by matching of the conserved peptides to the sequence of interest as demonstrated for the glycosyl hydrolase and the lytic polysaccharide monooxygenase families. This approach not only assigns the enzymes to families but also provides functional prediction of the enzymes with high accuracy. We identified conserved peptides for all enzyme families in the CAZy database with Peptide Pattern Recognition. The conserved peptides were matched to protein sequence for de novo annotation and functional prediction of carbohydrate-active enzymes with the Hotpep method. Annotation of protein sequences from 12 bacterial and 16 fungal genomes to families with Hotpep had an accuracy of 0.84 (measured as F1-score) compared to semiautomatic annotation by the CAZy database whereas the dbCAN HMM-based method had an accuracy of 0.77 with optimized parameters. Furthermore, Hotpep provided a functional prediction with 86% accuracy for the annotated genes. Hotpep is available as a stand-alone application for MS Windows. Hotpep is a state-of-the-art method for automatic annotation and functional prediction of carbohydrate-active enzymes.

Prediction of drug synergy in cancer using ensemble-based machine learning techniques

NASA Astrophysics Data System (ADS)

Singh, Harpreet; Rana, Prashant Singh; Singh, Urvinder

2018-04-01

Drug synergy prediction plays a significant role in the medical field for inhibiting specific cancer agents. It can be developed as a pre-processing tool for therapeutic successes. Examination of different drug-drug interaction can be done by drug synergy score. It needs efficient regression-based machine learning approaches to minimize the prediction errors. Numerous machine learning techniques such as neural networks, support vector machines, random forests, LASSO, Elastic Nets, etc., have been used in the past to realize requirement as mentioned above. However, these techniques individually do not provide significant accuracy in drug synergy score. Therefore, the primary objective of this paper is to design a neuro-fuzzy-based ensembling approach. To achieve this, nine well-known machine learning techniques have been implemented by considering the drug synergy data. Based on the accuracy of each model, four techniques with high accuracy are selected to develop ensemble-based machine learning model. These models are Random forest, Fuzzy Rules Using Genetic Cooperative-Competitive Learning method (GFS.GCCL), Adaptive-Network-Based Fuzzy Inference System (ANFIS) and Dynamic Evolving Neural-Fuzzy Inference System method (DENFIS). Ensembling is achieved by evaluating the biased weighted aggregation (i.e. adding more weights to the model with a higher prediction score) of predicted data by selected models. The proposed and existing machine learning techniques have been evaluated on drug synergy score data. The comparative analysis reveals that the proposed method outperforms others in terms of accuracy, root mean square error and coefficient of correlation.

Accuracy of Physical Examination, Ultrasonography, and Mammography in Predicting Residual Pathologic Tumor Size in Patients Treated With Neoadjuvant Chemotherapy

PubMed Central

Chagpar, Anees B.; Middleton, Lavinia P.; Sahin, Aysegul A.; Dempsey, Peter; Buzdar, Aman U.; Mirza, Attiqa N.; Ames, Fredrick C.; Babiera, Gildy V.; Feig, Barry W.; Hunt, Kelly K.; Kuerer, Henry M.; Meric-Bernstam, Funda; Ross, Merrick I.; Singletary, S Eva

2006-01-01

Objective: To assess the accuracy of physical examination, ultrasonography, and mammography in predicting residual size of breast tumors following neoadjuvant chemotherapy. Background: Neoadjuvant chemotherapy is an accepted part of the management of stage II and III breast cancer. Accurate prediction of residual pathologic tumor size after neoadjuvant chemotherapy is critical in guiding surgical therapy. Although physical examination, ultrasonography, and mammography have all been used to predict residual tumor size, there have been conflicting reports about the accuracy of these methods in the neoadjuvant setting. Methods: We reviewed the records of 189 patients who participated in 1 of 2 protocols using doxorubicin-containing neoadjuvant chemotherapy, and who had assessment by physical examination, ultrasonography, and/or mammography no more than 60 days before their surgical resection. Size correlations were performed using Spearman rho analysis. Clinical and pathologic measurements were also compared categorically using the weighted kappa statistic. Results: Size estimates by physical examination, ultrasonography, and mammography were only moderately correlated with residual pathologic tumor size after neoadjuvant chemotherapy (correlation coefficients: 0.42, 0.42, and 0.41, respectively), with an accuracy of ±1 cm in 66% of patients by physical examination, 75% by ultrasonography, and 70% by mammography. Kappa values (0.24–0.35) indicated poor agreement between clinical and pathologic measurements. Conclusion: Physical examination, ultrasonography, and mammography were only moderately useful for predicting residual pathologic tumor size after neoadjuvant chemotherapy. PMID:16432360

Biochemical methane potential prediction of plant biomasses: Comparing chemical composition versus near infrared methods and linear versus non-linear models.

PubMed

Godin, Bruno; Mayer, Frédéric; Agneessens, Richard; Gerin, Patrick; Dardenne, Pierre; Delfosse, Philippe; Delcarte, Jérôme

2015-01-01

The reliability of different models to predict the biochemical methane potential (BMP) of various plant biomasses using a multispecies dataset was compared. The most reliable prediction models of the BMP were those based on the near infrared (NIR) spectrum compared to those based on the chemical composition. The NIR predictions of local (specific regression and non-linear) models were able to estimate quantitatively, rapidly, cheaply and easily the BMP. Such a model could be further used for biomethanation plant management and optimization. The predictions of non-linear models were more reliable compared to those of linear models. The presentation form (green-dried, silage-dried and silage-wet form) of biomasses to the NIR spectrometer did not influence the performances of the NIR prediction models. The accuracy of the BMP method should be improved to enhance further the BMP prediction models. Copyright © 2014 Elsevier Ltd. All rights reserved.

SU-D-BRB-01: A Comparison of Learning Methods for Knowledge Based Dose Prediction for Coplanar and Non-Coplanar Liver Radiotherapy

DOE Office of Scientific and Technical Information (OSTI.GOV)

Tran, A; Ruan, D; Woods, K

Purpose: The predictive power of knowledge based planning (KBP) has considerable potential in the development of automated treatment planning. Here, we examine the predictive capabilities and accuracy of previously reported KBP methods, as well as an artificial neural networks (ANN) method. Furthermore, we compare the predictive accuracy of these methods on coplanar volumetric-modulated arc therapy (VMAT) and non-coplanar 4π radiotherapy. Methods: 30 liver SBRT patients previously treated using coplanar VMAT were selected for this study. The patients were re-planned using 4π radiotherapy, which involves 20 optimally selected non-coplanar IMRT fields. ANNs were used to incorporate enhanced geometric information including livermore » and PTV size, prescription dose, patient girth, and proximity to beams. The performance of ANN was compared to three methods from statistical voxel dose learning (SVDL), wherein the doses of voxels sharing the same distance to the PTV are approximated by either taking the median of the distribution, non-parametric fitting, or skew-normal fitting. These three methods were shown to be capable of predicting DVH, but only median approximation can predict 3D dose. Prediction methods were tested using leave-one-out cross-validation tests and evaluated using residual sum of squares (RSS) for DVH and 3D dose predictions. Results: DVH prediction using non-parametric fitting had the lowest average RSS with 0.1176(4π) and 0.1633(VMAT), compared to 0.4879(4π) and 1.8744(VMAT) RSS for ANN. 3D dose prediction with median approximation had lower RSS with 12.02(4π) and 29.22(VMAT), compared to 27.95(4π) and 130.9(VMAT) for ANN. Conclusion: Paradoxically, although the ANNs included geometric features in addition to the distances to the PTV, it did not perform better in predicting DVH or 3D dose compared to simpler, faster methods based on the distances alone. The study further confirms that the prediction of 4π non-coplanar plans were more accurate than VMAT. NIH R43CA183390 and R01CA188300.« less

Can species distribution models really predict the expansion of invasive species?

PubMed

Barbet-Massin, Morgane; Rome, Quentin; Villemant, Claire; Courchamp, Franck

2018-01-01

Predictive studies are of paramount importance for biological invasions, one of the biggest threats for biodiversity. To help and better prioritize management strategies, species distribution models (SDMs) are often used to predict the potential invasive range of introduced species. Yet, SDMs have been regularly criticized, due to several strong limitations, such as violating the equilibrium assumption during the invasion process. Unfortunately, validation studies-with independent data-are too scarce to assess the predictive accuracy of SDMs in invasion biology. Yet, biological invasions allow to test SDMs usefulness, by retrospectively assessing whether they would have accurately predicted the latest ranges of invasion. Here, we assess the predictive accuracy of SDMs in predicting the expansion of invasive species. We used temporal occurrence data for the Asian hornet Vespa velutina nigrithorax, a species native to China that is invading Europe with a very fast rate. Specifically, we compared occurrence data from the last stage of invasion (independent validation points) to the climate suitability distribution predicted from models calibrated with data from the early stage of invasion. Despite the invasive species not being at equilibrium yet, the predicted climate suitability of validation points was high. SDMs can thus adequately predict the spread of V. v. nigrithorax, which appears to be-at least partially-climatically driven. In the case of V. v. nigrithorax, SDMs predictive accuracy was slightly but significantly better when models were calibrated with invasive data only, excluding native data. Although more validation studies for other invasion cases are needed to generalize our results, our findings are an important step towards validating the use of SDMs in invasion biology.

Can species distribution models really predict the expansion of invasive species?

PubMed Central

Rome, Quentin; Villemant, Claire; Courchamp, Franck

2018-01-01

Predictive studies are of paramount importance for biological invasions, one of the biggest threats for biodiversity. To help and better prioritize management strategies, species distribution models (SDMs) are often used to predict the potential invasive range of introduced species. Yet, SDMs have been regularly criticized, due to several strong limitations, such as violating the equilibrium assumption during the invasion process. Unfortunately, validation studies–with independent data–are too scarce to assess the predictive accuracy of SDMs in invasion biology. Yet, biological invasions allow to test SDMs usefulness, by retrospectively assessing whether they would have accurately predicted the latest ranges of invasion. Here, we assess the predictive accuracy of SDMs in predicting the expansion of invasive species. We used temporal occurrence data for the Asian hornet Vespa velutina nigrithorax, a species native to China that is invading Europe with a very fast rate. Specifically, we compared occurrence data from the last stage of invasion (independent validation points) to the climate suitability distribution predicted from models calibrated with data from the early stage of invasion. Despite the invasive species not being at equilibrium yet, the predicted climate suitability of validation points was high. SDMs can thus adequately predict the spread of V. v. nigrithorax, which appears to be—at least partially–climatically driven. In the case of V. v. nigrithorax, SDMs predictive accuracy was slightly but significantly better when models were calibrated with invasive data only, excluding native data. Although more validation studies for other invasion cases are needed to generalize our results, our findings are an important step towards validating the use of SDMs in invasion biology. PMID:29509789

Genome-based prediction of test cross performance in two subsequent breeding cycles.

PubMed

Hofheinz, Nina; Borchardt, Dietrich; Weissleder, Knuth; Frisch, Matthias

2012-12-01

Genome-based prediction of genetic values is expected to overcome shortcomings that limit the application of QTL mapping and marker-assisted selection in plant breeding. Our goal was to study the genome-based prediction of test cross performance with genetic effects that were estimated using genotypes from the preceding breeding cycle. In particular, our objectives were to employ a ridge regression approach that approximates best linear unbiased prediction of genetic effects, compare cross validation with validation using genetic material of the subsequent breeding cycle, and investigate the prospects of genome-based prediction in sugar beet breeding. We focused on the traits sugar content and standard molasses loss (ML) and used a set of 310 sugar beet lines to estimate genetic effects at 384 SNP markers. In cross validation, correlations >0.8 between observed and predicted test cross performance were observed for both traits. However, in validation with 56 lines from the next breeding cycle, a correlation of 0.8 could only be observed for sugar content, for standard ML the correlation reduced to 0.4. We found that ridge regression based on preliminary estimates of the heritability provided a very good approximation of best linear unbiased prediction and was not accompanied with a loss in prediction accuracy. We conclude that prediction accuracy assessed with cross validation within one cycle of a breeding program can not be used as an indicator for the accuracy of predicting lines of the next cycle. Prediction of lines of the next cycle seems promising for traits with high heritabilities.

Video image analysis in the Australian meat industry - precision and accuracy of predicting lean meat yield in lamb carcasses.

PubMed

Hopkins, D L; Safari, E; Thompson, J M; Smith, C R

2004-06-01

A wide selection of lamb types of mixed sex (ewes and wethers) were slaughtered at a commercial abattoir and during this process images of 360 carcasses were obtained online using the VIAScan® system developed by Meat and Livestock Australia. Soft tissue depth at the GR site (thickness of tissue over the 12th rib 110 mm from the midline) was measured by an abattoir employee using the AUS-MEAT sheep probe (PGR). Another measure of this thickness was taken in the chiller using a GR knife (NGR). Each carcass was subsequently broken down to a range of trimmed boneless retail cuts and the lean meat yield determined. The current industry model for predicting meat yield uses hot carcass weight (HCW) and tissue depth at the GR site. A low level of accuracy and precision was found when HCW and PGR were used to predict lean meat yield (R(2)=0.19, r.s.d.=2.80%), which could be improved markedly when PGR was replaced by NGR (R(2)=0.41, r.s.d.=2.39%). If the GR measures were replaced by 8 VIAScan® measures then greater prediction accuracy could be achieved (R(2)=0.52, r.s.d.=2.17%). A similar result was achieved when the model was based on principal components (PCs) computed from the 8 VIAScan® measures (R(2)=0.52, r.s.d.=2.17%). The use of PCs also improved the stability of the model compared to a regression model based on HCW and NGR. The transportability of the models was tested by randomly dividing the data set and comparing coefficients and the level of accuracy and precision. Those models based on PCs were superior to those based on regression. It is demonstrated that with the appropriate modeling the VIAScan® system offers a workable method for predicting lean meat yield automatically.

Role of PI-RADS Version 2 for Prediction of Upgrading in Biopsy-Proven Prostate Cancer With Gleason Score 6.

PubMed

Song, Wan; Bang, Seok Hwan; Jeon, Hwang Gyun; Jeong, Byong Chang; Seo, Seong Il; Jeon, Seong Soo; Choi, Han Yong; Kim, Chan Kyo; Lee, Hyun Moo

2018-02-23

The objective of this study was to investigate the effect of Prostate Imaging Reporting and Data System version 2 (PI-RADSv2) on prediction of postoperative Gleason score (GS) upgrading for patients with biopsy GS 6 prostate cancer. We retrospectively reviewed 443 patients who underwent magnetic resonance imaging (MRI) and radical prostatectomy for biopsy-proven GS 6 prostate cancer between January 2011 and December 2013. Preoperative clinical variables and pathologic GS were examined, and all MRI findings were assessed with PI-RADSv2. Receiver operating characteristic curves were used to compare predictive accuracies of multivariate logistic regression models with or without PI-RADSv2. Of the total 443 patients, 297 (67.0%) experienced GS upgrading postoperatively. PI-RADSv2 scores 1 to 3 and 4 to 5 were identified in 157 (25.4%) and 286 (64.6%) patients, respectively, and the rate of GS upgrading was 54.1% and 74.1%, respectively (P < .001). In multivariate analysis, prostate-specific antigen density > 0.16 ng/mL 2 , number of positive cores ≥ 2, maximum percentage of cancer per core > 20, and PI-RADSv2 score 4 to 5 were independent predictors influencing GS upgrading (each P < .05). When predictive accuracies of multivariate models with or without PI-RADSv2 were compared, the model including PI-RADSv2 was shown to have significantly higher accuracy (area under the curve, 0.729 vs. 0.703; P = .041). Use of PI-RADSv2 is an independent predictor of postoperative GS upgrading and increases the predictive accuracy of GS upgrading. PI-RADSv2 might be used as a preoperative imaging tool to determine risk classification and to help counsel patients with regard to treatment decision and prognosis of disease. Copyright © 2018 Elsevier Inc. All rights reserved.

Impact of different training strategies on the accuracy of a Bayesian network for predicting hospital admission.

PubMed

Leegon, Jeffrey; Aronsky, Dominik

2006-01-01

The healthcare environment is constantly changing. Probabilistic clinical decision support systems need to recognize and incorporate the changing patterns and adjust the decision model to maintain high levels of accuracy. Using data from >75,000 ED patients during a 19-month study period we examined the impact of various static and dynamic training strategies on a decision support system designed to predict hospital admission status for ED patients. Training durations ranged from 1 to 12 weeks. During the study period major institutional changes occurred that affected the system's performance level. The average area under the receiver operating characteristic curve was higher and more stable when longer training periods were used. The system showed higher accuracy when retrained an updated with more recent data as compared to static training period. To adjust for temporal trends the accuracy of decision support systems can benefit from longer training periods and retraining with more recent data.

Accuracy of ultrasound for the prediction of placenta accreta.

PubMed

Bowman, Zachary S; Eller, Alexandra G; Kennedy, Anne M; Richards, Douglas S; Winter, Thomas C; Woodward, Paula J; Silver, Robert M

2014-08-01

Ultrasound has been reported to be greater than 90% sensitive for the diagnosis of accreta. Prior studies may be subject to bias because of single expert observers, suspicion for accreta, and knowledge of risk factors. We aimed to assess the accuracy of ultrasound for the prediction of accreta. Patients with accreta at a single academic center were matched to patients with placenta previa, but no accreta, by year of delivery. Ultrasound studies with views of the placenta were collected, deidentified, blinded to clinical history, and placed in random sequence. Six investigators prospectively interpreted each study for the presence of accreta and findings reported to be associated with its diagnosis. Sensitivity, specificity, positive predictive, negative predictive value, and accuracy were calculated. Characteristics of accurate findings were compared using univariate and multivariate analyses. Six investigators examined 229 ultrasound studies from 55 patients with accreta and 56 controls for 1374 independent observations. 1205/1374 (87.7% overall, 90% controls, 84.9% cases) studies were given a diagnosis. There were 371 (27.0%) true positives; 81 (5.9%) false positives; 533 (38.8%) true negatives, 220 (16.0%) false negatives, and 169 (12.3%) with uncertain diagnosis. Sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 53.5%, 88.0%, 82.1%, 64.8%, and 64.8%, respectively. In multivariate analysis, true positives were more likely to have placental lacunae (odds ratio [OR], 1.5; 95% confidence interval [CI], 1.4-1.6), loss of retroplacental clear space (OR, 2.4; 95% CI, 1.1-4.9), or abnormalities on color Doppler (OR, 2.1; 95% CI, 1.8-2.4). Ultrasound for the prediction of placenta accreta may not be as sensitive as previously described. Copyright © 2014 Mosby, Inc. All rights reserved.

Potential of on-line visible and near infrared spectroscopy for measurement of pH for deriving variable rate lime recommendations.

PubMed

Tekin, Yücel; Kuang, Boyan; Mouazen, Abdul M

2013-08-08

This paper aims at exploring the potential of visible and near infrared (vis-NIR) spectroscopy for on-line measurement of soil pH, with the intention to produce variable rate lime recommendation maps. An on-line vis-NIR soil sensor set up to a frame was used in this study. Lime application maps, based on pH predicted by vis-NIR techniques, were compared with maps based on traditional lab-measured pH. The validation of the calibration model using off-line spectra provided excellent prediction accuracy of pH (R2 = 0.85, RMSEP = 0.18 and RPD = 2.52), as compared to very good accuracy obtained with the on-line measured spectra (R2 = 0.81, RMSEP = 0.20 and RPD = 2.14). On-line predicted pH of all points (e.g., 2,160) resulted in the largest overall field virtual lime requirement (1.404 t), as compared to those obtained with 16 validation points off-line prediction (0.28 t), on-line prediction (0.14 t) and laboratory reference measurement (0.48 t). The conclusion is that the vis-NIR spectroscopy can be successfully used for the prediction of soil pH and for deriving lime recommendations. The advantage of the on-line sensor over sampling with limited number of samples is that more detailed information about pH can be obtained, which is the reason for a higher but precise calculated lime recommendation rate.

Potential of On-Line Visible and Near Infrared Spectroscopy for Measurement of pH for Deriving Variable Rate Lime Recommendations

PubMed Central

Tekin, Yücel; Kuang, Boyan; Mouazen, Abdul M.

2013-01-01

This paper aims at exploring the potential of visible and near infrared (vis-NIR) spectroscopy for on-line measurement of soil pH, with the intention to produce variable rate lime recommendation maps. An on-line vis-NIR soil sensor set up to a frame was used in this study. Lime application maps, based on pH predicted by vis-NIR techniques, were compared with maps based on traditional lab-measured pH. The validation of the calibration model using off-line spectra provided excellent prediction accuracy of pH (R2 = 0.85, RMSEP = 0.18 and RPD = 2.52), as compared to very good accuracy obtained with the on-line measured spectra (R2 = 0.81, RMSEP = 0.20 and RPD = 2.14). On-line predicted pH of all points (e.g., 2,160) resulted in the largest overall field virtual lime requirement (1.404 t), as compared to those obtained with 16 validation points off-line prediction (0.28 t), on-line prediction (0.14 t) and laboratory reference measurement (0.48 t). The conclusion is that the vis-NIR spectroscopy can be successfully used for the prediction of soil pH and for deriving lime recommendations. The advantage of the on-line sensor over sampling with limited number of samples is that more detailed information about pH can be obtained, which is the reason for a higher but precise calculated lime recommendation rate. PMID:23966186

Predictive accuracy of a model of volatile anesthetic uptake.

PubMed

Kennedy, R Ross; French, Richard A; Spencer, Christopher

2002-12-01

A computer program that models anesthetic uptake and distribution has been in use in our department for 20 yr as a teaching tool. New anesthesia machines that electronically measure fresh gas flow rates and vaporizer settings allowed us to assess the performance of this model during clinical anesthesia. Gas flow, vaporizer settings, and end-tidal concentrations were collected from the anesthesia machine (Datex S/5 ADU) at 10-s intervals during 30 elective anesthetics. These were entered into the uptake model. Expired anesthetic vapor concentrations were calculated and compared with actual values as measured by the patient monitor (Datex AS/3). Sevoflurane was used in 16 patients and isoflurane in 14 patients. For all patients, the median performance error was -0.24%, the median absolute performance error was 13.7%, divergence was 2.3%/h, and wobble was 3.1%. There was no significant difference between sevoflurane and isoflurane. This model predicted expired concentrations well in these patients. These results are similar to those seen when comparing calculated and actual propofol concentrations in propofol infusion systems and meet published guidelines for the accuracy of models used in target-controlled anesthesia systems. This model may be useful for predicting responses to changes in fresh gas and vapor settings. We compared measured inhaled anesthetic concentrations with those predicted by a model. The method used for comparison has been used to study models of propofol administration. Our model predicts expired isoflurane and sevoflurane concentrations at least as well as common propofol models predict arterial propofol concentrations.

ZCURVE 3.0: identify prokaryotic genes with higher accuracy as well as automatically and accurately select essential genes.

PubMed

Hua, Zhi-Gang; Lin, Yan; Yuan, Ya-Zhou; Yang, De-Chang; Wei, Wen; Guo, Feng-Biao

2015-07-01

In 2003, we developed an ab initio program, ZCURVE 1.0, to find genes in bacterial and archaeal genomes. In this work, we present the updated version (i.e. ZCURVE 3.0). Using 422 prokaryotic genomes, the average accuracy was 93.7% with the updated version, compared with 88.7% with the original version. Such results also demonstrate that ZCURVE 3.0 is comparable with Glimmer 3.02 and may provide complementary predictions to it. In fact, the joint application of the two programs generated better results by correctly finding more annotated genes while also containing fewer false-positive predictions. As the exclusive function, ZCURVE 3.0 contains one post-processing program that can identify essential genes with high accuracy (generally >90%). We hope ZCURVE 3.0 will receive wide use with the web-based running mode. The updated ZCURVE can be freely accessed from http://cefg.uestc.edu.cn/zcurve/ or http://tubic.tju.edu.cn/zcurveb/ without any restrictions. © The Author(s) 2015. Published by Oxford University Press on behalf of Nucleic Acids Research.

Exploring the genetic architecture and improving genomic prediction accuracy for mastitis and milk production traits in dairy cattle by mapping variants to hepatic transcriptomic regions responsive to intra-mammary infection.

PubMed

Fang, Lingzhao; Sahana, Goutam; Ma, Peipei; Su, Guosheng; Yu, Ying; Zhang, Shengli; Lund, Mogens Sandø; Sørensen, Peter

2017-05-12

A better understanding of the genetic architecture of complex traits can contribute to improve genomic prediction. We hypothesized that genomic variants associated with mastitis and milk production traits in dairy cattle are enriched in hepatic transcriptomic regions that are responsive to intra-mammary infection (IMI). Genomic markers [e.g. single nucleotide polymorphisms (SNPs)] from those regions, if included, may improve the predictive ability of a genomic model. We applied a genomic feature best linear unbiased prediction model (GFBLUP) to implement the above strategy by considering the hepatic transcriptomic regions responsive to IMI as genomic features. GFBLUP, an extension of GBLUP, includes a separate genomic effect of SNPs within a genomic feature, and allows differential weighting of the individual marker relationships in the prediction equation. Since GFBLUP is computationally intensive, we investigated whether a SNP set test could be a computationally fast way to preselect predictive genomic features. The SNP set test assesses the association between a genomic feature and a trait based on single-SNP genome-wide association studies. We applied these two approaches to mastitis and milk production traits (milk, fat and protein yield) in Holstein (HOL, n = 5056) and Jersey (JER, n = 1231) cattle. We observed that a majority of genomic features were enriched in genomic variants that were associated with mastitis and milk production traits. Compared to GBLUP, the accuracy of genomic prediction with GFBLUP was marginally improved (3.2 to 3.9%) in within-breed prediction. The highest increase (164.4%) in prediction accuracy was observed in across-breed prediction. The significance of genomic features based on the SNP set test were correlated with changes in prediction accuracy of GFBLUP (P < 0.05). GFBLUP provides a framework for integrating multiple layers of biological knowledge to provide novel insights into the biological basis of complex traits, and to improve the accuracy of genomic prediction. The SNP set test might be used as a first-step to improve GFBLUP models. Approaches like GFBLUP and SNP set test will become increasingly useful, as the functional annotations of genomes keep accumulating for a range of species and traits.

Predictive modeling of respiratory tumor motion for real-time prediction of baseline shifts

NASA Astrophysics Data System (ADS)

Balasubramanian, A.; Shamsuddin, R.; Prabhakaran, B.; Sawant, A.

2017-03-01

Baseline shifts in respiratory patterns can result in significant spatiotemporal changes in patient anatomy (compared to that captured during simulation), in turn, causing geometric and dosimetric errors in the administration of thoracic and abdominal radiotherapy. We propose predictive modeling of the tumor motion trajectories for predicting a baseline shift ahead of its occurrence. The key idea is to use the features of the tumor motion trajectory over a 1 min window, and predict the occurrence of a baseline shift in the 5 s that immediately follow (lookahead window). In this study, we explored a preliminary trend-based analysis with multi-class annotations as well as a more focused binary classification analysis. In both analyses, a number of different inter-fraction and intra-fraction training strategies were studied, both offline as well as online, along with data sufficiency and skew compensation for class imbalances. The performance of different training strategies were compared across multiple machine learning classification algorithms, including nearest neighbor, Naïve Bayes, linear discriminant and ensemble Adaboost. The prediction performance is evaluated using metrics such as accuracy, precision, recall and the area under the curve (AUC) for repeater operating characteristics curve. The key results of the trend-based analysis indicate that (i) intra-fraction training strategies achieve highest prediction accuracies (90.5-91.4%) (ii) the predictive modeling yields lowest accuracies (50-60%) when the training data does not include any information from the test patient; (iii) the prediction latencies are as low as a few hundred milliseconds, and thus conducive for real-time prediction. The binary classification performance is promising, indicated by high AUCs (0.96-0.98). It also confirms the utility of prior data from previous patients, and also the necessity of training the classifier on some initial data from the new patient for reasonable prediction performance. The ability to predict a baseline shift with a sufficient look-ahead window will enable clinical systems or even human users to hold the treatment beam in such situations, thereby reducing the probability of serious geometric and dosimetric errors.

Predictive modeling of respiratory tumor motion for real-time prediction of baseline shifts

PubMed Central

Balasubramanian, A; Shamsuddin, R; Prabhakaran, B; Sawant, A

2017-01-01

Baseline shifts in respiratory patterns can result in significant spatiotemporal changes in patient anatomy (compared to that captured during simulation), in turn, causing geometric and dosimetric errors in the administration of thoracic and abdominal radiotherapy. We propose predictive modeling of the tumor motion trajectories for predicting a baseline shift ahead of its occurrence. The key idea is to use the features of the tumor motion trajectory over a 1 min window, and predict the occurrence of a baseline shift in the 5 s that immediately follow (lookahead window). In this study, we explored a preliminary trend-based analysis with multi-class annotations as well as a more focused binary classification analysis. In both analyses, a number of different inter-fraction and intra-fraction training strategies were studied, both offline as well as online, along with data sufficiency and skew compensation for class imbalances. The performance of different training strategies were compared across multiple machine learning classification algorithms, including nearest neighbor, Naïve Bayes, linear discriminant and ensemble Adaboost. The prediction performance is evaluated using metrics such as accuracy, precision, recall and the area under the curve (AUC) for repeater operating characteristics curve. The key results of the trend-based analysis indicate that (i) intra-fraction training strategies achieve highest prediction accuracies (90.5–91.4%); (ii) the predictive modeling yields lowest accuracies (50–60%) when the training data does not include any information from the test patient; (iii) the prediction latencies are as low as a few hundred milliseconds, and thus conducive for real-time prediction. The binary classification performance is promising, indicated by high AUCs (0.96–0.98). It also confirms the utility of prior data from previous patients, and also the necessity of training the classifier on some initial data from the new patient for reasonable prediction performance. The ability to predict a baseline shift with a sufficient lookahead window will enable clinical systems or even human users to hold the treatment beam in such situations, thereby reducing the probability of serious geometric and dosimetric errors. PMID:28075331

Predictive modeling of respiratory tumor motion for real-time prediction of baseline shifts.

PubMed

Balasubramanian, A; Shamsuddin, R; Prabhakaran, B; Sawant, A

2017-03-07

Baseline shifts in respiratory patterns can result in significant spatiotemporal changes in patient anatomy (compared to that captured during simulation), in turn, causing geometric and dosimetric errors in the administration of thoracic and abdominal radiotherapy. We propose predictive modeling of the tumor motion trajectories for predicting a baseline shift ahead of its occurrence. The key idea is to use the features of the tumor motion trajectory over a 1 min window, and predict the occurrence of a baseline shift in the 5 s that immediately follow (lookahead window). In this study, we explored a preliminary trend-based analysis with multi-class annotations as well as a more focused binary classification analysis. In both analyses, a number of different inter-fraction and intra-fraction training strategies were studied, both offline as well as online, along with data sufficiency and skew compensation for class imbalances. The performance of different training strategies were compared across multiple machine learning classification algorithms, including nearest neighbor, Naïve Bayes, linear discriminant and ensemble Adaboost. The prediction performance is evaluated using metrics such as accuracy, precision, recall and the area under the curve (AUC) for repeater operating characteristics curve. The key results of the trend-based analysis indicate that (i) intra-fraction training strategies achieve highest prediction accuracies (90.5-91.4%); (ii) the predictive modeling yields lowest accuracies (50-60%) when the training data does not include any information from the test patient; (iii) the prediction latencies are as low as a few hundred milliseconds, and thus conducive for real-time prediction. The binary classification performance is promising, indicated by high AUCs (0.96-0.98). It also confirms the utility of prior data from previous patients, and also the necessity of training the classifier on some initial data from the new patient for reasonable prediction performance. The ability to predict a baseline shift with a sufficient look-ahead window will enable clinical systems or even human users to hold the treatment beam in such situations, thereby reducing the probability of serious geometric and dosimetric errors.

Evaluation with 3.0-T MR imaging: predicting the pathological response of triple-negative breast cancer treated with anthracycline and taxane neoadjuvant chemotherapy.

PubMed

Kim, Min Jung; Kim, Eun-Kyung; Park, Seho; Moon, Hee Jung; Kim, Seung Il; Park, Byeong-Woo

2015-09-01

Triple-negative breast cancer (TNBC) which expresses neither hormonal receptors nor HER-2 is associated with poor prognosis and shorter survival. Several studies have suggested that TNBC patients attaining pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) show a longer survival than those without pCR. To assess the accuracy of 3.0-T breast magnetic resonance imaging (MRI) in predicting pCR and to evaluate the clinicoradiologic factors affecting the diagnostic accuracy of 3.0-T breast MRI in TNBC patients treated with anthracycline and taxane (ACD). This retrospective study was approved by the institutional review board; patient consent was not required. Between 2009 and 2012, 35 TNBC patients with 3.0-T breast MRI prior to (n = 26) or after (n = 35) NAC were included. MRI findings were reviewed according to pCR to chemotherapy. The diagnostic accuracy of 3.0-T breast MRI for predicting pCR and the clinicoradiological factors affecting MRI accuracy and response to NAC were analyzed. 3.0-T MRI following NAC with ACD accurately predicted pCR in 91.4% of TNBC patients. The residual tumor size between pathology and 3.0-T MRI in non-pCR cases showed a higher correlation in the Ki-67-positive TNBC group (r = 0.947) than in the Ki-67 negative group (r = 0.375) with statistical trends (P = 0.069). Pre-treatment MRI in the non-pCR group compared to the pCR group showed a larger tumor size (P = 0.030) and non-mass presentation (P = 0.015). 3.0-T MRI in TNBC patients following NAC with ACD showed a high accuracy for predicting pCR to NAC. Ki-67 can affect the diagnostic accuracy of 3.0-T MRI for pCR to NAC with ACD in TNBC patients. © The Foundation Acta Radiologica 2014.

Multi-Stage Target Tracking with Drift Correction and Position Prediction

NASA Astrophysics Data System (ADS)

Chen, Xin; Ren, Keyan; Hou, Yibin

2018-04-01

Most existing tracking methods are hard to combine accuracy and performance, and do not consider the shift between clarity and blur that often occurs. In this paper, we propound a multi-stage tracking framework with two particular modules: position prediction and corrective measure. We conduct tracking based on correlation filter with a corrective measure module to increase both performance and accuracy. Specifically, a convolutional network is used for solving the blur problem in realistic scene, training methodology that training dataset with blur images generated by the three blur algorithms. Then, we propose a position prediction module to reduce the computation cost and make tracker more capable of fast motion. Experimental result shows that our tracking method is more robust compared to others and more accurate on the benchmark sequences.

Genetic Programming as Alternative for Predicting Development Effort of Individual Software Projects

PubMed Central

Chavoya, Arturo; Lopez-Martin, Cuauhtemoc; Andalon-Garcia, Irma R.; Meda-Campaña, M. E.

2012-01-01

Statistical and genetic programming techniques have been used to predict the software development effort of large software projects. In this paper, a genetic programming model was used for predicting the effort required in individually developed projects. Accuracy obtained from a genetic programming model was compared against one generated from the application of a statistical regression model. A sample of 219 projects developed by 71 practitioners was used for generating the two models, whereas another sample of 130 projects developed by 38 practitioners was used for validating them. The models used two kinds of lines of code as well as programming language experience as independent variables. Accuracy results from the model obtained with genetic programming suggest that it could be used to predict the software development effort of individual projects when these projects have been developed in a disciplined manner within a development-controlled environment. PMID:23226305

Analysis of Mining-Induced Subsidence Prediction by Exponent Knothe Model Combined with Insar and Leveling

NASA Astrophysics Data System (ADS)

Chen, Lei; Zhang, Liguo; Tang, Yixian; Zhang, Hong

2018-04-01

The principle of exponent Knothe model was introduced in detail and the variation process of mining subsidence with time was analysed based on the formulas of subsidence, subsidence velocity and subsidence acceleration in the paper. Five scenes of radar images and six levelling measurements were collected to extract ground deformation characteristics in one coal mining area in this study. Then the unknown parameters of exponent Knothe model were estimated by combined levelling data with deformation information along the line of sight obtained by InSAR technique. By compared the fitting and prediction results obtained by InSAR and levelling with that obtained only by levelling, it was shown that the accuracy of fitting and prediction combined with InSAR and levelling was obviously better than the other that. Therefore, the InSAR measurements can significantly improve the fitting and prediction accuracy of exponent Knothe model.

Living Donor Liver Transplantation for Acute Liver Failure : Comparing Guidelines on the Prediction of Liver Transplantation.

PubMed

Yoshida, Kazuhiro; Umeda, Yuzo; Takaki, Akinobu; Nagasaka, Takeshi; Yoshida, Ryuichi; Nobuoka, Daisuke; Kuise, Takashi; Takagi, Kosei; Yasunaka, Tetsuya; Okada, Hiroyuki; Yagi, Takahito; Fujiwara, Toshiyoshi

2017-10-01

Determining the indications for and timing of liver transplantation (LT) for acute liver failure (ALF) is essential. The King's College Hospital (KCH) guidelines and Japanese guidelines are used to predict the need for LT and the outcomes in ALF. These guidelines' accuracy when applied to ALF in different regional and etiological backgrounds may differ. Here we compared the accuracy of new (2010) Japanese guidelines that use a simple scoring system with the 1996 Japanese guidelines and the KCH criteria for living donor liver transplantation (LDLT). We retrospectively analyzed 24 adult ALF patients (18 acute type, 6 sub-acute type) who underwent LDLT in 1998-2009 at our institution. We assessed the accuracies of the 3 guidelines' criteria for ALF. The overall 1-year survival rate was 87.5%. The new and previous Japanese guidelines were superior to the KCH criteria for accurately predicting LT for acute-type ALF (72% vs. 17%). The new Japanese guidelines could identify 13 acute-type ALF patients for LT, based on the timing of encephalopathy onset. Using the previous Japanese guidelines, although the same 13 acute-type ALF patients (72%) had indications for LT, only 4 patients were indicated at the 1st step, and it took an additional 5 days to decide the indication at the 2nd step in the other 9 cases. Our findings showed that the new Japanese guidelines can predict the indications for LT and provide a reliable alternative to the previous Japanese and KCH guidelines.

Municipal water consumption forecast accuracy

NASA Astrophysics Data System (ADS)

Fullerton, Thomas M.; Molina, Angel L.

2010-06-01

Municipal water consumption planning is an active area of research because of infrastructure construction and maintenance costs, supply constraints, and water quality assurance. In spite of that, relatively few water forecast accuracy assessments have been completed to date, although some internal documentation may exist as part of the proprietary "grey literature." This study utilizes a data set of previously published municipal consumption forecasts to partially fill that gap in the empirical water economics literature. Previously published municipal water econometric forecasts for three public utilities are examined for predictive accuracy against two random walk benchmarks commonly used in regional analyses. Descriptive metrics used to quantify forecast accuracy include root-mean-square error and Theil inequality statistics. Formal statistical assessments are completed using four-pronged error differential regression F tests. Similar to studies for other metropolitan econometric forecasts in areas with similar demographic and labor market characteristics, model predictive performances for the municipal water aggregates in this effort are mixed for each of the municipalities included in the sample. Given the competitiveness of the benchmarks, analysts should employ care when utilizing econometric forecasts of municipal water consumption for planning purposes, comparing them to recent historical observations and trends to insure reliability. Comparative results using data from other markets, including regions facing differing labor and demographic conditions, would also be helpful.

Forecasts of geomagnetic activities and HF radio propagation conditions made at Hiraiso/Japan

NASA Technical Reports Server (NTRS)

Marubashi, K.; Miyamoto, Y.; Kidokoro, T.; Ishii, T.

1979-01-01

The Hiraiso Branch of RRL prediction techniques are summarized separately for the 27 day recurrent storm and the flare-associated storm. The storm predictions are compared with the actual geomagnetic activities in two ways. The first one is the comparison on a day to day basis. In the second comparison, the accuracy of the storm predictions during 1965-1976 are evaluated. In addition to the storm prediction, short-term predictions of HF radio propagation conditions are conducted at Hiraiso. The HF propagation predictions are briefly described as an example of the applications of the magnetic storm prediction.

Weather-based prediction of Plasmodium falciparum malaria in epidemic-prone regions of Ethiopia II. Weather-based prediction systems perform comparably to early detection systems in identifying times for interventions.

PubMed

Teklehaimanot, Hailay D; Schwartz, Joel; Teklehaimanot, Awash; Lipsitch, Marc

2004-11-19

Timely and accurate information about the onset of malaria epidemics is essential for effective control activities in epidemic-prone regions. Early warning methods that provide earlier alerts (usually by the use of weather variables) may permit control measures to interrupt transmission earlier in the epidemic, perhaps at the expense of some level of accuracy. Expected case numbers were modeled using a Poisson regression with lagged weather factors in a 4th-degree polynomial distributed lag model. For each week, the numbers of malaria cases were predicted using coefficients obtained using all years except that for which the prediction was being made. The effectiveness of alerts generated by the prediction system was compared against that of alerts based on observed cases. The usefulness of the prediction system was evaluated in cold and hot districts. The system predicts the overall pattern of cases well, yet underestimates the height of the largest peaks. Relative to alerts triggered by observed cases, the alerts triggered by the predicted number of cases performed slightly worse, within 5% of the detection system. The prediction-based alerts were able to prevent 10-25% more cases at a given sensitivity in cold districts than in hot ones. The prediction of malaria cases using lagged weather performed well in identifying periods of increased malaria cases. Weather-derived predictions identified epidemics with reasonable accuracy and better timeliness than early detection systems; therefore, the prediction of malarial epidemics using weather is a plausible alternative to early detection systems.

Predicting the Direction of Stock Market Index Movement Using an Optimized Artificial Neural Network Model.

PubMed

Qiu, Mingyue; Song, Yu

2016-01-01

In the business sector, it has always been a difficult task to predict the exact daily price of the stock market index; hence, there is a great deal of research being conducted regarding the prediction of the direction of stock price index movement. Many factors such as political events, general economic conditions, and traders' expectations may have an influence on the stock market index. There are numerous research studies that use similar indicators to forecast the direction of the stock market index. In this study, we compare two basic types of input variables to predict the direction of the daily stock market index. The main contribution of this study is the ability to predict the direction of the next day's price of the Japanese stock market index by using an optimized artificial neural network (ANN) model. To improve the prediction accuracy of the trend of the stock market index in the future, we optimize the ANN model using genetic algorithms (GA). We demonstrate and verify the predictability of stock price direction by using the hybrid GA-ANN model and then compare the performance with prior studies. Empirical results show that the Type 2 input variables can generate a higher forecast accuracy and that it is possible to enhance the performance of the optimized ANN model by selecting input variables appropriately.

Predicting the Direction of Stock Market Index Movement Using an Optimized Artificial Neural Network Model

PubMed Central

Qiu, Mingyue; Song, Yu

2016-01-01

In the business sector, it has always been a difficult task to predict the exact daily price of the stock market index; hence, there is a great deal of research being conducted regarding the prediction of the direction of stock price index movement. Many factors such as political events, general economic conditions, and traders’ expectations may have an influence on the stock market index. There are numerous research studies that use similar indicators to forecast the direction of the stock market index. In this study, we compare two basic types of input variables to predict the direction of the daily stock market index. The main contribution of this study is the ability to predict the direction of the next day’s price of the Japanese stock market index by using an optimized artificial neural network (ANN) model. To improve the prediction accuracy of the trend of the stock market index in the future, we optimize the ANN model using genetic algorithms (GA). We demonstrate and verify the predictability of stock price direction by using the hybrid GA-ANN model and then compare the performance with prior studies. Empirical results show that the Type 2 input variables can generate a higher forecast accuracy and that it is possible to enhance the performance of the optimized ANN model by selecting input variables appropriately. PMID:27196055

Evaluation of an ensemble of genetic models for prediction of a quantitative trait.

PubMed

Milton, Jacqueline N; Steinberg, Martin H; Sebastiani, Paola

2014-01-01

Many genetic markers have been shown to be associated with common quantitative traits in genome-wide association studies. Typically these associated genetic markers have small to modest effect sizes and individually they explain only a small amount of the variability of the phenotype. In order to build a genetic prediction model without fitting a multiple linear regression model with possibly hundreds of genetic markers as predictors, researchers often summarize the joint effect of risk alleles into a genetic score that is used as a covariate in the genetic prediction model. However, the prediction accuracy can be highly variable and selecting the optimal number of markers to be included in the genetic score is challenging. In this manuscript we present a strategy to build an ensemble of genetic prediction models from data and we show that the ensemble-based method makes the challenge of choosing the number of genetic markers more amenable. Using simulated data with varying heritability and number of genetic markers, we compare the predictive accuracy and inclusion of true positive and false positive markers of a single genetic prediction model and our proposed ensemble method. The results show that the ensemble of genetic models tends to include a larger number of genetic variants than a single genetic model and it is more likely to include all of the true genetic markers. This increased sensitivity is obtained at the price of a lower specificity that appears to minimally affect the predictive accuracy of the ensemble.

Accuracy of Dolphin visual treatment objective (VTO) prediction software on class III patients treated with maxillary advancement and mandibular setback.

PubMed

Peterman, Robert J; Jiang, Shuying; Johe, Rene; Mukherjee, Padma M

2016-12-01

Dolphin® visual treatment objective (VTO) prediction software is routinely utilized by orthodontists during the treatment planning of orthognathic cases to help predict post-surgical soft tissue changes. Although surgical soft tissue prediction is considered to be a vital tool, its accuracy is not well understood in tow-jaw surgical procedures. The objective of this study was to quantify the accuracy of Dolphin Imaging's VTO soft tissue prediction software on class III patients treated with maxillary advancement and mandibular setback and to validate the efficacy of the software in such complex cases. This retrospective study analyzed the records of 14 patients treated with comprehensive orthodontics in conjunction with two-jaw orthognathic surgery. Pre- and post-treatment radiographs were traced and superimposed to determine the actual skeletal movements achieved in surgery. This information was then used to simulate surgery in the software and generate a final soft tissue patient profile prediction. Prediction images were then compared to the actual post-treatment profile photos to determine differences. Dolphin Imaging's software was determined to be accurate within an error range of +/- 2 mm in the X-axis at most landmarks. The lower lip predictions were most inaccurate. Clinically, the observed error suggests that the VTO may be used for demonstration and communication with a patient or consulting practitioner. However, Dolphin should not be useful for precise treatment planning of surgical movements. This program should be used with caution to prevent unrealistic patient expectations and dissatisfaction.

Measurement and interpretation of skin prick test results.

PubMed

van der Valk, J P M; Gerth van Wijk, R; Hoorn, E; Groenendijk, L; Groenendijk, I M; de Jong, N W

2015-01-01

There are several methods to read skin prick test results in type-I allergy testing. A commonly used method is to characterize the wheal size by its 'average diameter'. A more accurate method is to scan the area of the wheal to calculate the actual size. In both methods, skin prick test (SPT) results can be corrected for histamine-sensitivity of the skin by dividing the results of the allergic reaction by the histamine control. The objectives of this study are to compare different techniques of quantifying SPT results, to determine a cut-off value for a positive SPT for histamine equivalent prick -index (HEP) area, and to study the accuracy of predicting cashew nut reactions in double-blind placebo-controlled food challenge (DBPCFC) tests with the different SPT methods. Data of 172 children with cashew nut sensitisation were used for the analysis. All patients underwent a DBPCFC with cashew nut. Per patient, the average diameter and scanned area of the wheal size were recorded. In addition, the same data for the histamine-induced wheal were collected for each patient. The accuracy in predicting the outcome of the DBPCFC using four different SPT readings (i.e. average diameter, area, HEP-index diameter, HEP-index area) were compared in a Receiver-Operating Characteristic (ROC) plot. Characterizing the wheal size by the average diameter method is inaccurate compared to scanning method. A wheal average diameter of 3 mm is generally considered as a positive SPT cut-off value and an equivalent HEP-index area cut-off value of 0.4 was calculated. The four SPT methods yielded a comparable area under the curve (AUC) of 0.84, 0.85, 0.83 and 0.83, respectively. The four methods showed comparable accuracy in predicting cashew nut reactions in a DBPCFC. The 'scanned area method' is theoretically more accurate in determining the wheal area than the 'average diameter method' and is recommended in academic research. A HEP-index area of 0.4 is determined as cut-off value for a positive SPT. However, in clinical practice, the 'average diameter method' is also useful, because this method provides similar accuracy in predicting cashew nut allergic reactions in the DBPCFC. Trial number NTR3572.

Assessment of traffic noise levels in urban areas using different soft computing techniques.

PubMed

Tomić, J; Bogojević, N; Pljakić, M; Šumarac-Pavlović, D

2016-10-01

Available traffic noise prediction models are usually based on regression analysis of experimental data, and this paper presents the application of soft computing techniques in traffic noise prediction. Two mathematical models are proposed and their predictions are compared to data collected by traffic noise monitoring in urban areas, as well as to predictions of commonly used traffic noise models. The results show that application of evolutionary algorithms and neural networks may improve process of development, as well as accuracy of traffic noise prediction.

Gated Auditory Speech Perception in Elderly Hearing Aid Users and Elderly Normal-Hearing Individuals: Effects of Hearing Impairment and Cognitive Capacity

PubMed Central

Lidestam, Björn; Hällgren, Mathias; Rönnberg, Jerker

2014-01-01

This study compared elderly hearing aid (EHA) users and elderly normal-hearing (ENH) individuals on identification of auditory speech stimuli (consonants, words, and final word in sentences) that were different when considering their linguistic properties. We measured the accuracy with which the target speech stimuli were identified, as well as the isolation points (IPs: the shortest duration, from onset, required to correctly identify the speech target). The relationships between working memory capacity, the IPs, and speech accuracy were also measured. Twenty-four EHA users (with mild to moderate hearing impairment) and 24 ENH individuals participated in the present study. Despite the use of their regular hearing aids, the EHA users had delayed IPs and were less accurate in identifying consonants and words compared with the ENH individuals. The EHA users also had delayed IPs for final word identification in sentences with lower predictability; however, no significant between-group difference in accuracy was observed. Finally, there were no significant between-group differences in terms of IPs or accuracy for final word identification in highly predictable sentences. Our results also showed that, among EHA users, greater working memory capacity was associated with earlier IPs and improved accuracy in consonant and word identification. Together, our findings demonstrate that the gated speech perception ability of EHA users was not at the level of ENH individuals, in terms of IPs and accuracy. In addition, gated speech perception was more cognitively demanding for EHA users than for ENH individuals in the absence of semantic context. PMID:25085610

Predicting Transmembrane Helix Packing Arrangements using Residue Contacts and a Force-Directed Algorithm

PubMed Central

Nugent, Timothy; Jones, David T.

2010-01-01

Alpha-helical transmembrane proteins constitute roughly 30% of a typical genome and are involved in a wide variety of important biological processes including cell signalling, transport of membrane-impermeable molecules and cell recognition. Despite significant efforts to predict transmembrane protein topology, comparatively little attention has been directed toward developing a method to pack the helices together. Here, we present a novel approach to predict lipid exposure, residue contacts, helix-helix interactions and finally the optimal helical packing arrangement of transmembrane proteins. Using molecular dynamics data, we have trained and cross-validated a support vector machine (SVM) classifier to predict per residue lipid exposure with 69% accuracy. This information is combined with additional features to train a second SVM to predict residue contacts which are then used to determine helix-helix interaction with up to 65% accuracy under stringent cross-validation on a non-redundant test set. Our method is also able to discriminate native from decoy helical packing arrangements with up to 70% accuracy. Finally, we employ a force-directed algorithm to construct the optimal helical packing arrangement which demonstrates success for proteins containing up to 13 transmembrane helices. This software is freely available as source code from http://bioinf.cs.ucl.ac.uk/memsat/mempack/. PMID:20333233

Comparison of methods for the implementation of genome-assisted evaluation of Spanish dairy cattle.

PubMed

Jiménez-Montero, J A; González-Recio, O; Alenda, R

2013-01-01

The aim of this study was to evaluate methods for genomic evaluation of the Spanish Holstein population as an initial step toward the implementation of routine genomic evaluations. This study provides a description of the population structure of progeny tested bulls in Spain at the genomic level and compares different genomic evaluation methods with regard to accuracy and bias. Two bayesian linear regression models, Bayes-A and Bayesian-LASSO (B-LASSO), as well as a machine learning algorithm, Random-Boosting (R-Boost), and BLUP using a realized genomic relationship matrix (G-BLUP), were compared. Five traits that are currently under selection in the Spanish Holstein population were used: milk yield, fat yield, protein yield, fat percentage, and udder depth. In total, genotypes from 1859 progeny tested bulls were used. The training sets were composed of bulls born before 2005; including 1601 bulls for production and 1574 bulls for type, whereas the testing sets contained 258 and 235 bulls born in 2005 or later for production and type, respectively. Deregressed proofs (DRP) from January 2009 Interbull (Uppsala, Sweden) evaluation were used as the dependent variables for bulls in the training sets, whereas DRP from the December 2011 DRPs Interbull evaluation were used to compare genomic predictions with progeny test results for bulls in the testing set. Genomic predictions were more accurate than traditional pedigree indices for predicting future progeny test results of young bulls. The gain in accuracy, due to inclusion of genomic data varied by trait and ranged from 0.04 to 0.42 Pearson correlation units. Results averaged across traits showed that B-LASSO had the highest accuracy with an advantage of 0.01, 0.03 and 0.03 points in Pearson correlation compared with R-Boost, Bayes-A, and G-BLUP, respectively. The B-LASSO predictions also showed the least bias (0.02, 0.03 and 0.10 SD units less than Bayes-A, R-Boost and G-BLUP, respectively) as measured by mean difference between genomic predictions and progeny test results. The R-Boosting algorithm provided genomic predictions with regression coefficients closer to unity, which is an alternative measure of bias, for 4 out of 5 traits and also resulted in mean squared errors estimates that were 2%, 10%, and 12% smaller than B-LASSO, Bayes-A, and G-BLUP, respectively. The observed prediction accuracy obtained with these methods was within the range of values expected for a population of similar size, suggesting that the prediction method and reference population described herein are appropriate for implementation of routine genome-assisted evaluations in Spanish dairy cattle. R-Boost is a competitive marker regression methodology in terms of predictive ability that can accommodate large data sets. Copyright © 2013 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Analysis of spatial distribution of land cover maps accuracy

NASA Astrophysics Data System (ADS)

Khatami, R.; Mountrakis, G.; Stehman, S. V.

2017-12-01

Land cover maps have become one of the most important products of remote sensing science. However, classification errors will exist in any classified map and affect the reliability of subsequent map usage. Moreover, classification accuracy often varies over different regions of a classified map. These variations of accuracy will affect the reliability of subsequent analyses of different regions based on the classified maps. The traditional approach of map accuracy assessment based on an error matrix does not capture the spatial variation in classification accuracy. Here, per-pixel accuracy prediction methods are proposed based on interpolating accuracy values from a test sample to produce wall-to-wall accuracy maps. Different accuracy prediction methods were developed based on four factors: predictive domain (spatial versus spectral), interpolation function (constant, linear, Gaussian, and logistic), incorporation of class information (interpolating each class separately versus grouping them together), and sample size. Incorporation of spectral domain as explanatory feature spaces of classification accuracy interpolation was done for the first time in this research. Performance of the prediction methods was evaluated using 26 test blocks, with 10 km × 10 km dimensions, dispersed throughout the United States. The performance of the predictions was evaluated using the area under the curve (AUC) of the receiver operating characteristic. Relative to existing accuracy prediction methods, our proposed methods resulted in improvements of AUC of 0.15 or greater. Evaluation of the four factors comprising the accuracy prediction methods demonstrated that: i) interpolations should be done separately for each class instead of grouping all classes together; ii) if an all-classes approach is used, the spectral domain will result in substantially greater AUC than the spatial domain; iii) for the smaller sample size and per-class predictions, the spectral and spatial domain yielded similar AUC; iv) for the larger sample size (i.e., very dense spatial sample) and per-class predictions, the spatial domain yielded larger AUC; v) increasing the sample size improved accuracy predictions with a greater benefit accruing to the spatial domain; and vi) the function used for interpolation had the smallest effect on AUC.

Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space

DOE PAGES

Hansen, Katja; Biegler, Franziska; Ramakrishnan, Raghunathan; ...

2015-06-04

Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstratemore » prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the “holy grail” of chemical accuracy of 1 kcal/mol for both equilibrium and out-of-equilibrium geometries. This remarkable accuracy is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space. The same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies.« less

Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space

PubMed Central

2015-01-01

Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the “holy grail” of chemical accuracy of 1 kcal/mol for both equilibrium and out-of-equilibrium geometries. This remarkable accuracy is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space. In addition, the same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies. PMID:26113956

Comparison of the diagnostic accuracy of a rapid immunochromatographic test and the rapid plasma reagin test for antenatal syphilis screening in Mozambique.

PubMed Central

Montoya, Pablo J.; Lukehart, Sheila A.; Brentlinger, Paula E.; Blanco, Ana J.; Floriano, Florencia; Sairosse, Josefa; Gloyd, Stephen

2006-01-01

OBJECTIVE: Programmes to control syphilis in developing countries are hampered by a lack of laboratory services, delayed diagnosis, and doubts about current screening methods. We aimed to compare the diagnostic accuracy of an immunochromatographic strip (ICS) test and the rapid plasma reagin (RPR) test with the combined gold standard (RPR, Treponema pallidum haemagglutination assay and direct immunofluorescence stain done at a reference laboratory) for the detection of syphilis in pregnancy. METHODS: We included test results from 4789 women attending their first antenatal visit at one of six health facilities in Sofala Province, central Mozambique. We compared diagnostic accuracy (sensitivity, specificity, and positive and negative predictive values) of ICS and RPR done at the health facilities and ICS performed at the reference laboratory. We also made subgroup comparisons by human immunodeficiency virus (HIV) and malaria status. FINDINGS: For active syphilis, the sensitivity of the ICS was 95.3% at the reference laboratory, and 84.1% at the health facility. The sensitivity of the RPR at the health facility was 70.7%. Specificity and positive and negative predictive values showed a similar pattern. The ICS outperformed RPR in all comparisons (P<0.001). CONCLUSION: The diagnostic accuracy of the ICS compared favourably with that of the gold standard. The use of the ICS in Mozambique and similar settings may improve the diagnosis of syphilis in health facilities, both with and without laboratories. PMID:16501726

Limited diagnostic accuracy of magnetic resonance imaging and clinical tests for detecting partial-thickness tears of the rotator cuff.

PubMed

Brockmeyer, Matthias; Schmitt, Cornelia; Haupert, Alexander; Kohn, Dieter; Lorbach, Olaf

2017-12-01

The reliable diagnosis of partial-thickness tears of the rotator cuff is still elusive in clinical practise. Therefore, the purpose of the study was to determine the diagnostic accuracy of MR imaging and clinical tests for detecting partial-thickness tears of the rotator cuff as well as the combination of these parameters. 334 consecutive shoulder arthroscopies for rotator cuff pathologies performed during the time period between 2010 and 2012 were analyzed retrospectively for the findings of common clinical signs for rotator cuff lesions and preoperative MR imaging. These were compared with the intraoperative arthroscopic findings as "gold standard". The reports of the MR imaging were evaluated with regard to the integrity of the rotator cuff. The Ellman Classification was used to define partial-thickness tears of the rotator cuff in accordance with the arthroscopic findings. Descriptive statistics, sensitivity, specificity, positive and negative predictive value were calculated. MR imaging showed 80 partial-thickness and 70 full-thickness tears of the rotator cuff. The arthroscopic examination confirmed 64 partial-thickness tears of which 52 needed debridement or refixation of the rotator cuff. Sensitivity for MR imaging to identify partial-thickness tears was 51.6%, specificity 77.2%, positive predictive value 41.3% and negative predictive value 83.7%. For the Jobe-test, sensitivity was 64.1%, specificity 43.2%, positive predictive value 25.9% and negative predictive value 79.5%. Sensitivity for the Impingement-sign was 76.7%, specificity 46.6%, positive predictive value 30.8% and negative predictive value 86.5%. For the combination of MR imaging, Jobe-test and Impingement-sign sensitivity was 46.9%, specificity 85.4%, positive predictive value 50% and negative predictive value 83.8%. The diagnostic accuracy of MR imaging and clinical tests (Jobe-test and Impingement-sign) alone is limited for detecting partial-thickness tears of the rotator cuff. Additionally, the combination of MR imaging and clinical tests does not improve diagnostic accuracy. Level II, Diagnostic study.

NRfamPred: a proteome-scale two level method for prediction of nuclear receptor proteins and their sub-families.

PubMed

Kumar, Ravindra; Kumari, Bandana; Srivastava, Abhishikha; Kumar, Manish

2014-10-29

Nuclear receptor proteins (NRP) are transcription factor that regulate many vital cellular processes in animal cells. NRPs form a super-family of phylogenetically related proteins and divided into different sub-families on the basis of ligand characteristics and their functions. In the post-genomic era, when new proteins are being added to the database in a high-throughput mode, it becomes imperative to identify new NRPs using information from amino acid sequence alone. In this study we report a SVM based two level prediction systems, NRfamPred, using dipeptide composition of proteins as input. At the 1st level, NRfamPred screens whether the query protein is NRP or non-NRP; if the query protein belongs to NRP class, prediction moves to 2nd level and predicts the sub-family. Using leave-one-out cross-validation, we were able to achieve an overall accuracy of 97.88% at the 1st level and an overall accuracy of 98.11% at the 2nd level with dipeptide composition. Benchmarking on independent datasets showed that NRfamPred had comparable accuracy to other existing methods, developed on the same dataset. Our method predicted the existence of 76 NRPs in the human proteome, out of which 14 are novel NRPs. NRfamPred also predicted the sub-families of these 14 NRPs.

Evaluation of CROES Nephrolithometry Nomogram as a Preoperative Predictive System for Percutaneous Nephrolithotomy Outcomes.

PubMed

Kumar, Sumit; Sreenivas, Jayaram; Karthikeyan, Vilvapathy Senguttuvan; Mallya, Ashwin; Keshavamurthy, Ramaiah

2016-10-01

Scoring systems have been devised to predict outcomes of percutaneous nephrolithotomy (PCNL). CROES nephrolithometry nomogram (CNN) is the latest tool devised to predict stone-free rate (SFR). We aim to compare predictive accuracy of CNN against Guy stone score (GSS) for SFR and postoperative outcomes. Between January 2013 and December 2015, 313 patients undergoing PCNL were analyzed for predictive accuracy of GSS, CNN, and stone burden (SB) for SFR, complications, operation time (OT), and length of hospitalization (LOH). We further stratified patients into risk groups based on CNN and GSS. Mean ± standard deviation (SD) SB was 298.8 ± 235.75 mm 2 . SB, GSS, and CNN (area under curve [AUC]: 0.662, 0.660, 0.673) were found to be predictors of SFR. However, predictability for complications was not as good (AUC: SB 0.583, GSS 0.554, CNN 0.580). Single implicated calix (Adj. OR 3.644; p = 0.027), absence of staghorn calculus (Adj. OR 3.091; p = 0.044), single stone (Adj. OR 3.855; p = 0.002), and single puncture (Adj. OR 2.309; p = 0.048) significantly predicted SFR on multivariate analysis. Charlson comorbidity index (CCI; p = 0.020) and staghorn calculus (p = 0.002) were independent predictors for complications on linear regression. SB and GSS independently predicted OT on multivariate analysis. SB and complications significantly predicted LOH, while GSS and CNN did not predict LOH. CNN offered better risk stratification for residual stones than GSS. CNN and GSS have good preoperative predictive accuracy for SFR. Number of implicated calices may affect SFR, and CCI affects complications. Studies should incorporate these factors in scoring systems and assess if predictability of PCNL outcomes improves.

Accurate genomic predictions for BCWD resistance in rainbow trout are achieved using low-density SNP panels: Evidence that long-range LD is a major contributing factor.

PubMed

Vallejo, Roger L; Silva, Rafael M O; Evenhuis, Jason P; Gao, Guangtu; Liu, Sixin; Parsons, James E; Martin, Kyle E; Wiens, Gregory D; Lourenco, Daniela A L; Leeds, Timothy D; Palti, Yniv

2018-06-05

Previously accurate genomic predictions for Bacterial cold water disease (BCWD) resistance in rainbow trout were obtained using a medium-density single nucleotide polymorphism (SNP) array. Here, the impact of lower-density SNP panels on the accuracy of genomic predictions was investigated in a commercial rainbow trout breeding population. Using progeny performance data, the accuracy of genomic breeding values (GEBV) using 35K, 10K, 3K, 1K, 500, 300 and 200 SNP panels as well as a panel with 70 quantitative trait loci (QTL)-flanking SNP was compared. The GEBVs were estimated using the Bayesian method BayesB, single-step GBLUP (ssGBLUP) and weighted ssGBLUP (wssGBLUP). The accuracy of GEBVs remained high despite the sharp reductions in SNP density, and even with 500 SNP accuracy was higher than the pedigree-based prediction (0.50-0.56 versus 0.36). Furthermore, the prediction accuracy with the 70 QTL-flanking SNP (0.65-0.72) was similar to the panel with 35K SNP (0.65-0.71). Genomewide linkage disequilibrium (LD) analysis revealed strong LD (r 2  ≥ 0.25) spanning on average over 1 Mb across the rainbow trout genome. This long-range LD likely contributed to the accurate genomic predictions with the low-density SNP panels. Population structure analysis supported the hypothesis that long-range LD in this population may be caused by admixture. Results suggest that lower-cost, low-density SNP panels can be used for implementing genomic selection for BCWD resistance in rainbow trout breeding programs. © 2018 The Authors. This article is a U.S. Government work and is in the public domain in the USA. Journal of Animal Breeding and Genetics published by Blackwell Verlag GmbH.

A Comparison of Metamodeling Techniques via Numerical Experiments

NASA Technical Reports Server (NTRS)

Crespo, Luis G.; Kenny, Sean P.; Giesy, Daniel P.

2016-01-01

This paper presents a comparative analysis of a few metamodeling techniques using numerical experiments for the single input-single output case. These experiments enable comparing the models' predictions with the phenomenon they are aiming to describe as more data is made available. These techniques include (i) prediction intervals associated with a least squares parameter estimate, (ii) Bayesian credible intervals, (iii) Gaussian process models, and (iv) interval predictor models. Aspects being compared are computational complexity, accuracy (i.e., the degree to which the resulting prediction conforms to the actual Data Generating Mechanism), reliability (i.e., the probability that new observations will fall inside the predicted interval), sensitivity to outliers, extrapolation properties, ease of use, and asymptotic behavior. The numerical experiments describe typical application scenarios that challenge the underlying assumptions supporting most metamodeling techniques.

Abbreviation of the Follow-Up NIH Stroke Scale Using Factor Analysis

PubMed Central

Raza, Syed Ali; Frankel, Michael R.; Rangaraju, Srikant

2017-01-01

Background The NIH Stroke Scale (NIHSS) is a 15-item measure of stroke-related neurologic deficits that, when measured at 24 h, is highly predictive of long-term functional outcome. We hypothesized that a simplified 24-h scale that incorporates the most predictive components of the NIHSS can retain prognostic accuracy and have improved interrater reliability. Methods In a post hoc analysis of the Interventional Management of Stroke-3 (IMS-3) trial, we performed principal component (PC) analysis to resolve the 24-h NIHSS into PCs. In the PCs that explained the largest proportions of variance, key variables were identified. Using these key variables, the prognostic accuracies (area under the curve [AUC]) for good outcome (3-month modified Rankin Scale [mRS] 0–2) and poor outcome (mRS 5–6) of various abbreviated NIHSS iterations were compared with the total 24-h NIHSS. The results were validated in the NINDS intravenous tissue plasminogen activator (NINDS-TPA) study cohort. Based on previously published data, interrater reliability of the abbreviated 24-h NIHSS (aNIHSS) was compared to the total 24-h NIHSS. Results In 545 IMS-3 participants, 2 PCs explained 60.8% of variance in the 24-h NIHSS. The key variables in PC1 included neglect, arm and leg weakness; while PC2 included level-of-consciousness (LOC) questions, LOC commands, and aphasia. A 3-variable aNIHSS (aphasia, neglect, arm weakness) retained excellent prognostic accuracy for good outcome (AUC = 0.90) as compared to the total 24-h NIHSS (AUC = 0.91), and it was more predictive (p < 0.001) than the baseline NIHSS (AUC = 0.73). The prognostic accuracy of the aNIHSS for good outcome was validated in the NINDS-TPA trial cohort (aNIHSS: AUC = 0.89 vs. total 24-h NIHSS: 0.92). An aNIHSS >9 predicted very poor outcomes (mRS 0–2: 0%, mRS 4–6: 98.5%). The estimated interrater reliability of the aNIHSS was higher than that of the total 24-h NIHSS across 6 published datasets (mean weighted kappa 0.80 vs. 0.73, p < 0.001). Conclusions At 24 h following ischemic stroke, aphasia, neglect, and arm weakness are the most prognostically relevant neurologic findings. The aNIHSS appears to have excellent prognostic accuracy with higher reliability and may be clinically useful. PMID:28968607

Comparison of different risk stratification systems in predicting short-term serious outcome of syncope patients

PubMed Central

Safari, Saeed; Baratloo, Alireza; Hashemi, Behrooz; Rahmati, Farhad; Forouzanfar, Mohammad Mehdi; Motamedi, Maryam; Mirmohseni, Ladan

2016-01-01

Background: Determining etiologic causes and prognosis can significantly improve management of syncope patients. The present study aimed to compare the values of San Francisco, Osservatorio Epidemiologico sulla Sincope nel Lazio (OESIL), Boston, and Risk Stratification of Syncope in the Emergency Department (ROSE) score clinical decision rules in predicting the short-term serious outcome of syncope patients. Materials and Methods: The present diagnostic accuracy study with 1-week follow-up was designed to evaluate the predictive values of the four mentioned clinical decision rules. Screening performance characteristics of each model in predicting mortality, myocardial infarction (MI), and cerebrovascular accidents (CVAs) were calculated and compared. To evaluate the value of each aforementioned model in predicting the outcome, sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio were calculated and receiver-operating curve (ROC) curve analysis was done. Results: A total of 187 patients (mean age: 64.2 ± 17.2 years) were enrolled in the study. Mortality, MI, and CVA were seen in 19 (10.2%), 12 (6.4%), and 36 (19.2%) patients, respectively. Area under the ROC curve for OESIL, San Francisco, Boston, and ROSE models in prediction the risk of 1-week mortality, MI, and CVA was in the 30–70% range, with no significant difference among models (P > 0.05). The pooled model did not show higher accuracy in prediction of mortality, MI, and CVA compared to others (P > 0.05). Conclusion: This study revealed the weakness of all four evaluated models in predicting short-term serious outcome of syncope patients referred to the emergency department without any significant advantage for one among others. PMID:27904602

Rectal cancer staging: Multidetector-row computed tomography diagnostic accuracy in assessment of mesorectal fascia invasion

PubMed Central

Ippolito, Davide; Drago, Silvia Girolama; Franzesi, Cammillo Talei; Fior, Davide; Sironi, Sandro

2016-01-01

AIM: To assess the diagnostic accuracy of multidetector-row computed tomography (MDCT) as compared with conventional magnetic resonance imaging (MRI), in identifying mesorectal fascia (MRF) invasion in rectal cancer patients. METHODS: Ninety-one patients with biopsy proven rectal adenocarcinoma referred for thoracic and abdominal CT staging were enrolled in this study. The contrast-enhanced MDCT scans were performed on a 256 row scanner (ICT, Philips) with the following acquisition parameters: tube voltage 120 KV, tube current 150-300 mAs. Imaging data were reviewed as axial and as multiplanar reconstructions (MPRs) images along the rectal tumor axis. MRI study, performed on 1.5 T with dedicated phased array multicoil, included multiplanar T2 and axial T1 sequences and diffusion weighted images (DWI). Axial and MPR CT images independently were compared to MRI and MRF involvement was determined. Diagnostic accuracy of both modalities was compared and statistically analyzed. RESULTS: According to MRI, the MRF was involved in 51 patients and not involved in 40 patients. DWI allowed to recognize the tumor as a focal mass with high signal intensity on high b-value images, compared with the signal of the normal adjacent rectal wall or with the lower tissue signal intensity background. The number of patients correctly staged by the native axial CT images was 71 out of 91 (41 with involved MRF; 30 with not involved MRF), while by using the MPR 80 patients were correctly staged (45 with involved MRF; 35 with not involved MRF). Local tumor staging suggested by MDCT agreed with those of MRI, obtaining for CT axial images sensitivity and specificity of 80.4% and 75%, positive predictive value (PPV) 80.4%, negative predictive value (NPV) 75% and accuracy 78%; while performing MPR the sensitivity and specificity increased to 88% and 87.5%, PPV was 90%, NPV 85.36% and accuracy 88%. MPR images showed higher diagnostic accuracy, in terms of MRF involvement, than native axial images, as compared to the reference magnetic resonance images. The difference in accuracy was statistically significant (P = 0.02). CONCLUSION: New generation CT scanner, using high resolution MPR images, represents a reliable diagnostic tool in assessment of loco-regional and whole body staging of advanced rectal cancer, especially in patients with MRI contraindications. PMID:27239115

Comparison of two data mining techniques in labeling diagnosis to Iranian pharmacy claim dataset: artificial neural network (ANN) versus decision tree model.

PubMed

Rezaei-Darzi, Ehsan; Farzadfar, Farshad; Hashemi-Meshkini, Amir; Navidi, Iman; Mahmoudi, Mahmoud; Varmaghani, Mehdi; Mehdipour, Parinaz; Soudi Alamdari, Mahsa; Tayefi, Batool; Naderimagham, Shohreh; Soleymani, Fatemeh; Mesdaghinia, Alireza; Delavari, Alireza; Mohammad, Kazem

2014-12-01

This study aimed to evaluate and compare the prediction accuracy of two data mining techniques, including decision tree and neural network models in labeling diagnosis to gastrointestinal prescriptions in Iran. This study was conducted in three phases: data preparation, training phase, and testing phase. A sample from a database consisting of 23 million pharmacy insurance claim records, from 2004 to 2011 was used, in which a total of 330 prescriptions were assessed and used to train and test the models simultaneously. In the training phase, the selected prescriptions were assessed by both a physician and a pharmacist separately and assigned a diagnosis. To test the performance of each model, a k-fold stratified cross validation was conducted in addition to measuring their sensitivity and specificity. Generally, two methods had very similar accuracies. Considering the weighted average of true positive rate (sensitivity) and true negative rate (specificity), the decision tree had slightly higher accuracy in its ability for correct classification (83.3% and 96% versus 80.3% and 95.1%, respectively). However, when the weighted average of ROC area (AUC between each class and all other classes) was measured, the ANN displayed higher accuracies in predicting the diagnosis (93.8% compared with 90.6%). According to the result of this study, artificial neural network and decision tree model represent similar accuracy in labeling diagnosis to GI prescription.

Soccer athletes are superior to non-athletes at perceiving soccer-specific and non-sport specific human biological motion

PubMed Central

Romeas, Thomas; Faubert, Jocelyn

2015-01-01

Recent studies have shown that athletes’ domain specific perceptual-cognitive expertise can transfer to everyday tasks. Here we assessed the perceptual-cognitive expertise of athletes and non-athletes using sport specific and non-sport specific biological motion perception (BMP) tasks. Using a virtual environment, university-level soccer players and university students’ non-athletes were asked to perceive the direction of a point-light walker and to predict the trajectory of a masked-ball during a point-light soccer kick. Angles of presentation were varied for orientation (upright, inverted) and distance (2 m, 4 m, 16 m). Accuracy and reaction time were measured to assess observers’ performance. The results highlighted athletes’ superior ability compared to non-athletes to accurately predict the trajectory of a masked soccer ball presented at 2 m (reaction time), 4 m (accuracy and reaction time), and 16 m (accuracy) of distance. More interestingly, experts also displayed greater performance compared to non-athletes throughout the more fundamental and general point-light walker direction task presented at 2 m (reaction time), 4 m (accuracy and reaction time), and 16 m (reaction time) of distance. In addition, athletes showed a better performance throughout inverted conditions in the walker (reaction time) and soccer kick (accuracy and reaction time) tasks. This implies that during human BMP, athletes demonstrate an advantage for recognizing body kinematics that goes beyond sport specific actions. PMID:26388828

Prediction of persistent hemodynamic depression after carotid angioplasty and stenting using artificial neural network model.

PubMed

Jeon, Jin Pyeong; Kim, Chulho; Oh, Byoung-Doo; Kim, Sun Jeong; Kim, Yu-Seop

2018-01-01

To assess and compare predictive factors for persistent hemodynamic depression (PHD) after carotid artery angioplasty and stenting (CAS) using artificial neural network (ANN) and multiple logistic regression (MLR) or support vector machines (SVM) models. A retrospective data set of patients (n=76) who underwent CAS from 2007 to 2014 was used as input (training cohort) to a back-propagation ANN using TensorFlow platform. PHD was defined when systolic blood pressure was less than 90mmHg or heart rate was less 50 beats/min that lasted for more than one hour. The resulting ANN was prospectively tested in 33 patients (test cohort) and compared with MLR or SVM models according to accuracy and receiver operating characteristics (ROC) curve analysis. No significant difference in baseline characteristics between the training cohort and the test cohort was observed. PHD was observed in 21 (27.6%) patients in the training cohort and 10 (30.3%) patients in the test cohort. In the training cohort, the accuracy of ANN for the prediction of PHD was 98.7% and the area under the ROC curve (AUROC) was 0.961. In the test cohort, the number of correctly classified instances was 32 (97.0%) using the ANN model. In contrast, the accuracy rate of MLR or SVM model was both 75.8%. ANN (AUROC: 0.950; 95% CI [confidence interval]: 0.813-0.996) showed superior predictive performance compared to MLR model (AUROC: 0.796; 95% CI: 0.620-0.915, p<0.001) or SVM model (AUROC: 0.885; 95% CI: 0.725-0.969, p<0.001). The ANN model seems to have more powerful prediction capabilities than MLR or SVM model for persistent hemodynamic depression after CAS. External validation with a large cohort is needed to confirm our results. Copyright © 2017. Published by Elsevier B.V.

Validation of Accelerometer-Based Energy Expenditure Prediction Models in Structured and Simulated Free-Living Settings

ERIC Educational Resources Information Center

Montoye, Alexander H. K.; Conger, Scott A.; Connolly, Christopher P.; Imboden, Mary T.; Nelson, M. Benjamin; Bock, Josh M.; Kaminsky, Leonard A.

2017-01-01

This study compared accuracy of energy expenditure (EE) prediction models from accelerometer data collected in structured and simulated free-living settings. Twenty-four adults (mean age 45.8 years, 50% female) performed two sessions of 11 to 21 activities, wearing four ActiGraph GT9X Link activity monitors (right hip, ankle, both wrists) and a…

The Application of FIA-based Data to Wildlife Habitat Modeling: A Comparative Study

Treesearch

Thomas C., Jr. Edwards; Gretchen G. Moisen; Tracey S. Frescino; Randall J. Schultz

2005-01-01

We evaluated the capability of two types of models, one based on spatially explicit variables derived from FIA data and one using so-called traditional habitat evaluation methods, for predicting the presence of cavity-nesting bird habitat in Fishlake National Forest, Utah. Both models performed equally well, in measures of predictive accuracy, with the FIA-based model...

Multivariate prediction of upper limb prosthesis acceptance or rejection.

PubMed

Biddiss, Elaine A; Chau, Tom T

2008-07-01

To develop a model for prediction of upper limb prosthesis use or rejection. A questionnaire exploring factors in prosthesis acceptance was distributed internationally to individuals with upper limb absence through community-based support groups and rehabilitation hospitals. A total of 191 participants (59 prosthesis rejecters and 132 prosthesis wearers) were included in this study. A logistic regression model, a C5.0 decision tree, and a radial basis function neural network were developed and compared in terms of sensitivity (prediction of prosthesis rejecters), specificity (prediction of prosthesis wearers), and overall cross-validation accuracy. The logistic regression and neural network provided comparable overall accuracies of approximately 84 +/- 3%, specificity of 93%, and sensitivity of 61%. Fitting time-frame emerged as the predominant predictor. Individuals fitted within two years of birth (congenital) or six months of amputation (acquired) were 16 times more likely to continue prosthesis use. To increase rates of prosthesis acceptance, clinical directives should focus on timely, client-centred fitting strategies and the development of improved prostheses and healthcare for individuals with high-level or bilateral limb absence. Multivariate analyses are useful in determining the relative importance of the many factors involved in prosthesis acceptance and rejection.

Effects of modeled tropical sea surface temperature variability on coral reef bleaching predictions

NASA Astrophysics Data System (ADS)

van Hooidonk, R.; Huber, M.

2012-03-01

Future widespread coral bleaching and subsequent mortality has been projected using sea surface temperature (SST) data derived from global, coupled ocean-atmosphere general circulation models (GCMs). While these models possess fidelity in reproducing many aspects of climate, they vary in their ability to correctly capture such parameters as the tropical ocean seasonal cycle and El Niño Southern Oscillation (ENSO) variability. Such weaknesses most likely reduce the accuracy of predicting coral bleaching, but little attention has been paid to the important issue of understanding potential errors and biases, the interaction of these biases with trends, and their propagation in predictions. To analyze the relative importance of various types of model errors and biases in predicting coral bleaching, various intra- and inter-annual frequency bands of observed SSTs were replaced with those frequencies from 24 GCMs 20th century simulations included in the Intergovernmental Panel on Climate Change (IPCC) 4th assessment report. Subsequent thermal stress was calculated and predictions of bleaching were made. These predictions were compared with observations of coral bleaching in the period 1982-2007 to calculate accuracy using an objective measure of forecast quality, the Peirce skill score (PSS). Major findings are that: (1) predictions are most sensitive to the seasonal cycle and inter-annual variability in the ENSO 24-60 months frequency band and (2) because models tend to understate the seasonal cycle at reef locations, they systematically underestimate future bleaching. The methodology we describe can be used to improve the accuracy of bleaching predictions by characterizing the errors and uncertainties involved in the predictions.

Prediction of customer behaviour analysis using classification algorithms

NASA Astrophysics Data System (ADS)

Raju, Siva Subramanian; Dhandayudam, Prabha

2018-04-01

Customer Relationship management plays a crucial role in analyzing of customer behavior patterns and their values with an enterprise. Analyzing of customer data can be efficient performed using various data mining techniques, with the goal of developing business strategies and to enhance the business. In this paper, three classification models (NB, J48, and MLPNN) are studied and evaluated for our experimental purpose. The performance measures of the three classifications are compared using three different parameters (accuracy, sensitivity, specificity) and experimental results expose J48 algorithm has better accuracy with compare to NB and MLPNN algorithm.

Application of a Novel Grey Self-Memory Coupling Model to Forecast the Incidence Rates of Two Notifiable Diseases in China: Dysentery and Gonorrhea

PubMed Central

Guo, Xiaojun; Liu, Sifeng; Wu, Lifeng; Tang, Lingling

2014-01-01

Objective In this study, a novel grey self-memory coupling model was developed to forecast the incidence rates of two notifiable infectious diseases (dysentery and gonorrhea); the effectiveness and applicability of this model was assessed based on its ability to predict the epidemiological trend of infectious diseases in China. Methods The linear model, the conventional GM(1,1) model and the GM(1,1) model with self-memory principle (SMGM(1,1) model) were used to predict the incidence rates of the two notifiable infectious diseases based on statistical incidence data. Both simulation accuracy and prediction accuracy were assessed to compare the predictive performances of the three models. The best-fit model was applied to predict future incidence rates. Results Simulation results show that the SMGM(1,1) model can take full advantage of the systematic multi-time historical data and possesses superior predictive performance compared with the linear model and the conventional GM(1,1) model. By applying the novel SMGM(1,1) model, we obtained the possible incidence rates of the two representative notifiable infectious diseases in China. Conclusion The disadvantages of the conventional grey prediction model, such as sensitivity to initial value, can be overcome by the self-memory principle. The novel grey self-memory coupling model can predict the incidence rates of infectious diseases more accurately than the conventional model, and may provide useful references for making decisions involving infectious disease prevention and control. PMID:25546054

Application of a novel grey self-memory coupling model to forecast the incidence rates of two notifiable diseases in China: dysentery and gonorrhea.

PubMed

Guo, Xiaojun; Liu, Sifeng; Wu, Lifeng; Tang, Lingling

2014-01-01

In this study, a novel grey self-memory coupling model was developed to forecast the incidence rates of two notifiable infectious diseases (dysentery and gonorrhea); the effectiveness and applicability of this model was assessed based on its ability to predict the epidemiological trend of infectious diseases in China. The linear model, the conventional GM(1,1) model and the GM(1,1) model with self-memory principle (SMGM(1,1) model) were used to predict the incidence rates of the two notifiable infectious diseases based on statistical incidence data. Both simulation accuracy and prediction accuracy were assessed to compare the predictive performances of the three models. The best-fit model was applied to predict future incidence rates. Simulation results show that the SMGM(1,1) model can take full advantage of the systematic multi-time historical data and possesses superior predictive performance compared with the linear model and the conventional GM(1,1) model. By applying the novel SMGM(1,1) model, we obtained the possible incidence rates of the two representative notifiable infectious diseases in China. The disadvantages of the conventional grey prediction model, such as sensitivity to initial value, can be overcome by the self-memory principle. The novel grey self-memory coupling model can predict the incidence rates of infectious diseases more accurately than the conventional model, and may provide useful references for making decisions involving infectious disease prevention and control.

Context Memory Decline in Middle Aged Adults is Related to Changes in Prefrontal Cortex Function.

PubMed

Kwon, Diana; Maillet, David; Pasvanis, Stamatoula; Ankudowich, Elizabeth; Grady, Cheryl L; Rajah, M Natasha

2016-06-01

The ability to encode and retrieve spatial and temporal contextual details of episodic memories (context memory) begins to decline at midlife. In the current study, event-related fMRI was used to investigate the neural correlates of context memory decline in healthy middle aged adults (MA) compared with young adults (YA). Participants were scanned while performing easy and hard versions of spatial and temporal context memory tasks. Scans were obtained at encoding and retrieval. Significant reductions in context memory retrieval accuracy were observed in MA, compared with YA. The fMRI results revealed that overall, both groups exhibited similar patterns of brain activity in parahippocampal cortex, ventral occipito-temporal regions and prefrontal cortex (PFC) during encoding. In contrast, at retrieval, there were group differences in ventral occipito-temporal and PFC activity, due to these regions being more activated in MA, compared with YA. Furthermore, only in YA, increased encoding activity in ventrolateral PFC, and increased retrieval activity in occipital cortex, predicted increased retrieval accuracy. In MA, increased retrieval activity in anterior PFC predicted increased retrieval accuracy. These results suggest that there are changes in PFC contributions to context memory at midlife. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Grazing Incidence Optics for X-rays Interferometry

NASA Technical Reports Server (NTRS)

Shipley, Ann; Zissa, David; Cash, Webster; Joy, Marshall

1999-01-01

Grazing incidence mirror parameters and constraints for x-ray interferometry are described. We present interferometer system tolerances and ray trace results used to define mirror surface accuracy requirements. Mirror material, surface figure, roughness, and geometry are evaluated based on analysis results. We also discuss mirror mount design constraints, finite element analysis, environmental issues, and solutions. Challenges associated with quantifying high accuracy mirror surface quality are addressed and test results are compared with theoretical predictions.

Clinical versus actuarial judgment.

PubMed

Dawes, R M; Faust, D; Meehl, P E

1989-03-31

Professionals are frequently consulted to diagnose and predict human behavior; optimal treatment and planning often hinge on the consultant's judgmental accuracy. The consultant may rely on one of two contrasting approaches to decision-making--the clinical and actuarial methods. Research comparing these two approaches shows the actuarial method to be superior. Factors underlying the greater accuracy of actuarial methods, sources of resistance to the scientific findings, and the benefits of increased reliance on actuarial approaches are discussed.

Simple to complex modeling of breathing volume using a motion sensor.

PubMed

John, Dinesh; Staudenmayer, John; Freedson, Patty

2013-06-01

To compare simple and complex modeling techniques to estimate categories of low, medium, and high ventilation (VE) from ActiGraph™ activity counts. Vertical axis ActiGraph™ GT1M activity counts, oxygen consumption and VE were measured during treadmill walking and running, sports, household chores and labor-intensive employment activities. Categories of low (<19.3 l/min), medium (19.3 to 35.4 l/min) and high (>35.4 l/min) VEs were derived from activity intensity classifications (light <2.9 METs, moderate 3.0 to 5.9 METs and vigorous >6.0 METs). We examined the accuracy of two simple techniques (multiple regression and activity count cut-point analyses) and one complex (random forest technique) modeling technique in predicting VE from activity counts. Prediction accuracy of the complex random forest technique was marginally better than the simple multiple regression method. Both techniques accurately predicted VE categories almost 80% of the time. The multiple regression and random forest techniques were more accurate (85 to 88%) in predicting medium VE. Both techniques predicted the high VE (70 to 73%) with greater accuracy than low VE (57 to 60%). Actigraph™ cut-points for light, medium and high VEs were <1381, 1381 to 3660 and >3660 cpm. There were minor differences in prediction accuracy between the multiple regression and the random forest technique. This study provides methods to objectively estimate VE categories using activity monitors that can easily be deployed in the field. Objective estimates of VE should provide a better understanding of the dose-response relationship between internal exposure to pollutants and disease. Copyright © 2013 Elsevier B.V. All rights reserved.

Genome-Enabled Estimates of Additive and Nonadditive Genetic Variances and Prediction of Apple Phenotypes Across Environments

PubMed Central

Kumar, Satish; Molloy, Claire; Muñoz, Patricio; Daetwyler, Hans; Chagné, David; Volz, Richard

2015-01-01

The nonadditive genetic effects may have an important contribution to total genetic variation of phenotypes, so estimates of both the additive and nonadditive effects are desirable for breeding and selection purposes. Our main objectives were to: estimate additive, dominance and epistatic variances of apple (Malus × domestica Borkh.) phenotypes using relationship matrices constructed from genome-wide dense single nucleotide polymorphism (SNP) markers; and compare the accuracy of genomic predictions using genomic best linear unbiased prediction models with or without including nonadditive genetic effects. A set of 247 clonally replicated individuals was assessed for six fruit quality traits at two sites, and also genotyped using an Illumina 8K SNP array. Across several fruit quality traits, the additive, dominance, and epistatic effects contributed about 30%, 16%, and 19%, respectively, to the total phenotypic variance. Models ignoring nonadditive components yielded upwardly biased estimates of additive variance (heritability) for all traits in this study. The accuracy of genomic predicted genetic values (GEGV) varied from about 0.15 to 0.35 for various traits, and these were almost identical for models with or without including nonadditive effects. However, models including nonadditive genetic effects further reduced the bias of GEGV. Between-site genotypic correlations were high (>0.85) for all traits, and genotype-site interaction accounted for <10% of the phenotypic variability. The accuracy of prediction, when the validation set was present only at one site, was generally similar for both sites, and varied from about 0.50 to 0.85. The prediction accuracies were strongly influenced by trait heritability, and genetic relatedness between the training and validation families. PMID:26497141

Genetic Variance Partitioning and Genome-Wide Prediction with Allele Dosage Information in Autotetraploid Potato.

PubMed

Endelman, Jeffrey B; Carley, Cari A Schmitz; Bethke, Paul C; Coombs, Joseph J; Clough, Mark E; da Silva, Washington L; De Jong, Walter S; Douches, David S; Frederick, Curtis M; Haynes, Kathleen G; Holm, David G; Miller, J Creighton; Muñoz, Patricio R; Navarro, Felix M; Novy, Richard G; Palta, Jiwan P; Porter, Gregory A; Rak, Kyle T; Sathuvalli, Vidyasagar R; Thompson, Asunta L; Yencho, G Craig

2018-05-01

As one of the world's most important food crops, the potato ( Solanum tuberosum L.) has spurred innovation in autotetraploid genetics, including in the use of SNP arrays to determine allele dosage at thousands of markers. By combining genotype and pedigree information with phenotype data for economically important traits, the objectives of this study were to (1) partition the genetic variance into additive vs. nonadditive components, and (2) determine the accuracy of genome-wide prediction. Between 2012 and 2017, a training population of 571 clones was evaluated for total yield, specific gravity, and chip fry color. Genomic covariance matrices for additive ( G ), digenic dominant ( D ), and additive × additive epistatic ( G # G ) effects were calculated using 3895 markers, and the numerator relationship matrix ( A ) was calculated from a 13-generation pedigree. Based on model fit and prediction accuracy, mixed model analysis with G was superior to A for yield and fry color but not specific gravity. The amount of additive genetic variance captured by markers was 20% of the total genetic variance for specific gravity, compared to 45% for yield and fry color. Within the training population, including nonadditive effects improved accuracy and/or bias for all three traits when predicting total genotypic value. When six F 1 populations were used for validation, prediction accuracy ranged from 0.06 to 0.63 and was consistently lower (0.13 on average) without allele dosage information. We conclude that genome-wide prediction is feasible in potato and that it will improve selection for breeding value given the substantial amount of nonadditive genetic variance in elite germplasm. Copyright © 2018 by the Genetics Society of America.

Outcomes and Complications After Endovascular Treatment of Brain Arteriovenous Malformations: A Prognostication Attempt Using Artificial Intelligence.

PubMed

Asadi, Hamed; Kok, Hong Kuan; Looby, Seamus; Brennan, Paul; O'Hare, Alan; Thornton, John

2016-12-01

To identify factors influencing outcome in brain arteriovenous malformations (BAVM) treated with endovascular embolization. We also assessed the feasibility of using machine learning techniques to prognosticate and predict outcome and compared this to conventional statistical analyses. A retrospective study of patients undergoing endovascular treatment of BAVM during a 22-year period in a national neuroscience center was performed. Clinical presentation, imaging, procedural details, complications, and outcome were recorded. The data was analyzed with artificial intelligence techniques to identify predictors of outcome and assess accuracy in predicting clinical outcome at final follow-up. One-hundred ninety-nine patients underwent treatment for BAVM with a mean follow-up duration of 63 months. The commonest clinical presentation was intracranial hemorrhage (56%). During the follow-up period, there were 51 further hemorrhagic events, comprising spontaneous hemorrhage (n = 27) and procedural related hemorrhage (n = 24). All spontaneous events occurred in previously embolized BAVMs remote from the procedure. Complications included ischemic stroke in 10%, symptomatic hemorrhage in 9.8%, and mortality rate of 4.7%. Standard regression analysis model had an accuracy of 43% in predicting final outcome (mortality), with the type of treatment complication identified as the most important predictor. The machine learning model showed superior accuracy of 97.5% in predicting outcome and identified the presence or absence of nidal fistulae as the most important factor. BAVMs can be treated successfully by endovascular techniques or combined with surgery and radiosurgery with an acceptable risk profile. Machine learning techniques can predict final outcome with greater accuracy and may help individualize treatment based on key predicting factors. Copyright © 2016 Elsevier Inc. All rights reserved.

Assessment of a remote sensing-based model for predicting malaria transmission risk in villages of Chiapas, Mexico

NASA Technical Reports Server (NTRS)

Beck, L. R.; Rodriguez, M. H.; Dister, S. W.; Rodriguez, A. D.; Washino, R. K.; Roberts, D. R.; Spanner, M. A.

1997-01-01

A blind test of two remote sensing-based models for predicting adult populations of Anopheles albimanus in villages, an indicator of malaria transmission risk, was conducted in southern Chiapas, Mexico. One model was developed using a discriminant analysis approach, while the other was based on regression analysis. The models were developed in 1992 for an area around Tapachula, Chiapas, using Landsat Thematic Mapper (TM) satellite data and geographic information system functions. Using two remotely sensed landscape elements, the discriminant model was able to successfully distinguish between villages with high and low An. albimanus abundance with an overall accuracy of 90%. To test the predictive capability of the models, multitemporal TM data were used to generate a landscape map of the Huixtla area, northwest of Tapachula, where the models were used to predict risk for 40 villages. The resulting predictions were not disclosed until the end of the test. Independently, An. albimanus abundance data were collected in the 40 randomly selected villages for which the predictions had been made. These data were subsequently used to assess the models' accuracies. The discriminant model accurately predicted 79% of the high-abundance villages and 50% of the low-abundance villages, for an overall accuracy of 70%. The regression model correctly identified seven of the 10 villages with the highest mosquito abundance. This test demonstrated that remote sensing-based models generated for one area can be used successfully in another, comparable area.

A prediction model of compressor with variable-geometry diffuser based on elliptic equation and partial least squares

PubMed Central

Yang, Chuanlei; Wang, Yinyan; Wang, Hechun

2018-01-01

To achieve a much more extensive intake air flow range of the diesel engine, a variable-geometry compressor (VGC) is introduced into a turbocharged diesel engine. However, due to the variable diffuser vane angle (DVA), the prediction for the performance of the VGC becomes more difficult than for a normal compressor. In the present study, a prediction model comprising an elliptical equation and a PLS (partial least-squares) model was proposed to predict the performance of the VGC. The speed lines of the pressure ratio map and the efficiency map were fitted with the elliptical equation, and the coefficients of the elliptical equation were introduced into the PLS model to build the polynomial relationship between the coefficients and the relative speed, the DVA. Further, the maximal order of the polynomial was investigated in detail to reduce the number of sub-coefficients and achieve acceptable fit accuracy simultaneously. The prediction model was validated with sample data and in order to present the superiority of compressor performance prediction, the prediction results of this model were compared with those of the look-up table and back-propagation neural networks (BPNNs). The validation and comparison results show that the prediction accuracy of the new developed model is acceptable, and this model is much more suitable than the look-up table and the BPNN methods under the same condition in VGC performance prediction. Moreover, the new developed prediction model provides a novel and effective prediction solution for the VGC and can be used to improve the accuracy of the thermodynamic model for turbocharged diesel engines in the future. PMID:29410849

A prediction model of compressor with variable-geometry diffuser based on elliptic equation and partial least squares.

PubMed

Li, Xu; Yang, Chuanlei; Wang, Yinyan; Wang, Hechun

2018-01-01

To achieve a much more extensive intake air flow range of the diesel engine, a variable-geometry compressor (VGC) is introduced into a turbocharged diesel engine. However, due to the variable diffuser vane angle (DVA), the prediction for the performance of the VGC becomes more difficult than for a normal compressor. In the present study, a prediction model comprising an elliptical equation and a PLS (partial least-squares) model was proposed to predict the performance of the VGC. The speed lines of the pressure ratio map and the efficiency map were fitted with the elliptical equation, and the coefficients of the elliptical equation were introduced into the PLS model to build the polynomial relationship between the coefficients and the relative speed, the DVA. Further, the maximal order of the polynomial was investigated in detail to reduce the number of sub-coefficients and achieve acceptable fit accuracy simultaneously. The prediction model was validated with sample data and in order to present the superiority of compressor performance prediction, the prediction results of this model were compared with those of the look-up table and back-propagation neural networks (BPNNs). The validation and comparison results show that the prediction accuracy of the new developed model is acceptable, and this model is much more suitable than the look-up table and the BPNN methods under the same condition in VGC performance prediction. Moreover, the new developed prediction model provides a novel and effective prediction solution for the VGC and can be used to improve the accuracy of the thermodynamic model for turbocharged diesel engines in the future.

Time Series Analysis for Forecasting Hospital Census: Application to the Neonatal Intensive Care Unit

PubMed Central

Hoover, Stephen; Jackson, Eric V.; Paul, David; Locke, Robert

2016-01-01

Summary Background Accurate prediction of future patient census in hospital units is essential for patient safety, health outcomes, and resource planning. Forecasting census in the Neonatal Intensive Care Unit (NICU) is particularly challenging due to limited ability to control the census and clinical trajectories. The fixed average census approach, using average census from previous year, is a forecasting alternative used in clinical practice, but has limitations due to census variations. Objective Our objectives are to: (i) analyze the daily NICU census at a single health care facility and develop census forecasting models, (ii) explore models with and without patient data characteristics obtained at the time of admission, and (iii) evaluate accuracy of the models compared with the fixed average census approach. Methods We used five years of retrospective daily NICU census data for model development (January 2008 – December 2012, N=1827 observations) and one year of data for validation (January – December 2013, N=365 observations). Best-fitting models of ARIMA and linear regression were applied to various 7-day prediction periods and compared using error statistics. Results The census showed a slightly increasing linear trend. Best fitting models included a non-seasonal model, ARIMA(1,0,0), seasonal ARIMA models, ARIMA(1,0,0)x(1,1,2)7 and ARIMA(2,1,4)x(1,1,2)14, as well as a seasonal linear regression model. Proposed forecasting models resulted on average in 36.49% improvement in forecasting accuracy compared with the fixed average census approach. Conclusions Time series models provide higher prediction accuracy under different census conditions compared with the fixed average census approach. Presented methodology is easily applicable in clinical practice, can be generalized to other care settings, support short- and long-term census forecasting, and inform staff resource planning. PMID:27437040

Time Series Analysis for Forecasting Hospital Census: Application to the Neonatal Intensive Care Unit.

PubMed

Capan, Muge; Hoover, Stephen; Jackson, Eric V; Paul, David; Locke, Robert

2016-01-01

Accurate prediction of future patient census in hospital units is essential for patient safety, health outcomes, and resource planning. Forecasting census in the Neonatal Intensive Care Unit (NICU) is particularly challenging due to limited ability to control the census and clinical trajectories. The fixed average census approach, using average census from previous year, is a forecasting alternative used in clinical practice, but has limitations due to census variations. Our objectives are to: (i) analyze the daily NICU census at a single health care facility and develop census forecasting models, (ii) explore models with and without patient data characteristics obtained at the time of admission, and (iii) evaluate accuracy of the models compared with the fixed average census approach. We used five years of retrospective daily NICU census data for model development (January 2008 - December 2012, N=1827 observations) and one year of data for validation (January - December 2013, N=365 observations). Best-fitting models of ARIMA and linear regression were applied to various 7-day prediction periods and compared using error statistics. The census showed a slightly increasing linear trend. Best fitting models included a non-seasonal model, ARIMA(1,0,0), seasonal ARIMA models, ARIMA(1,0,0)x(1,1,2)7 and ARIMA(2,1,4)x(1,1,2)14, as well as a seasonal linear regression model. Proposed forecasting models resulted on average in 36.49% improvement in forecasting accuracy compared with the fixed average census approach. Time series models provide higher prediction accuracy under different census conditions compared with the fixed average census approach. Presented methodology is easily applicable in clinical practice, can be generalized to other care settings, support short- and long-term census forecasting, and inform staff resource planning.

Classification of drug molecules considering their IC50 values using mixed-integer linear programming based hyper-boxes method.

PubMed

Armutlu, Pelin; Ozdemir, Muhittin E; Uney-Yuksektepe, Fadime; Kavakli, I Halil; Turkay, Metin

2008-10-03

A priori analysis of the activity of drugs on the target protein by computational approaches can be useful in narrowing down drug candidates for further experimental tests. Currently, there are a large number of computational methods that predict the activity of drugs on proteins. In this study, we approach the activity prediction problem as a classification problem and, we aim to improve the classification accuracy by introducing an algorithm that combines partial least squares regression with mixed-integer programming based hyper-boxes classification method, where drug molecules are classified as low active or high active regarding their binding activity (IC50 values) on target proteins. We also aim to determine the most significant molecular descriptors for the drug molecules. We first apply our approach by analyzing the activities of widely known inhibitor datasets including Acetylcholinesterase (ACHE), Benzodiazepine Receptor (BZR), Dihydrofolate Reductase (DHFR), Cyclooxygenase-2 (COX-2) with known IC50 values. The results at this stage proved that our approach consistently gives better classification accuracies compared to 63 other reported classification methods such as SVM, Naïve Bayes, where we were able to predict the experimentally determined IC50 values with a worst case accuracy of 96%. To further test applicability of this approach we first created dataset for Cytochrome P450 C17 inhibitors and then predicted their activities with 100% accuracy. Our results indicate that this approach can be utilized to predict the inhibitory effects of inhibitors based on their molecular descriptors. This approach will not only enhance drug discovery process, but also save time and resources committed.

The advantages of the surface Laplacian in brain-computer interface research.

PubMed

McFarland, Dennis J

2015-09-01

Brain-computer interface (BCI) systems frequently use signal processing methods, such as spatial filtering, to enhance performance. The surface Laplacian can reduce spatial noise and aid in identification of sources. In BCI research, these two functions of the surface Laplacian correspond to prediction accuracy and signal orthogonality. In the present study, an off-line analysis of data from a sensorimotor rhythm-based BCI task dissociated these functions of the surface Laplacian by comparing nearest-neighbor and next-nearest neighbor Laplacian algorithms. The nearest-neighbor Laplacian produced signals that were more orthogonal while the next-nearest Laplacian produced signals that resulted in better accuracy. Both prediction and signal identification are important for BCI research. Better prediction of user's intent produces increased speed and accuracy of communication and control. Signal identification is important for ruling out the possibility of control by artifacts. Identifying the nature of the control signal is relevant both to understanding exactly what is being studied and in terms of usability for individuals with limited motor control. Copyright © 2014 Elsevier B.V. All rights reserved.

Validating Variational Bayes Linear Regression Method With Multi-Central Datasets.

PubMed

Murata, Hiroshi; Zangwill, Linda M; Fujino, Yuri; Matsuura, Masato; Miki, Atsuya; Hirasawa, Kazunori; Tanito, Masaki; Mizoue, Shiro; Mori, Kazuhiko; Suzuki, Katsuyoshi; Yamashita, Takehiro; Kashiwagi, Kenji; Shoji, Nobuyuki; Asaoka, Ryo

2018-04-01

To validate the prediction accuracy of variational Bayes linear regression (VBLR) with two datasets external to the training dataset. The training dataset consisted of 7268 eyes of 4278 subjects from the University of Tokyo Hospital. The Japanese Archive of Multicentral Databases in Glaucoma (JAMDIG) dataset consisted of 271 eyes of 177 patients, and the Diagnostic Innovations in Glaucoma Study (DIGS) dataset includes 248 eyes of 173 patients, which were used for validation. Prediction accuracy was compared between the VBLR and ordinary least squared linear regression (OLSLR). First, OLSLR and VBLR were carried out using total deviation (TD) values at each of the 52 test points from the second to fourth visual fields (VFs) (VF2-4) to 2nd to 10th VF (VF2-10) of each patient in JAMDIG and DIGS datasets, and the TD values of the 11th VF test were predicted every time. The predictive accuracy of each method was compared through the root mean squared error (RMSE) statistic. OLSLR RMSEs with the JAMDIG and DIGS datasets were between 31 and 4.3 dB, and between 19.5 and 3.9 dB. On the other hand, VBLR RMSEs with JAMDIG and DIGS datasets were between 5.0 and 3.7, and between 4.6 and 3.6 dB. There was statistically significant difference between VBLR and OLSLR for both datasets at every series (VF2-4 to VF2-10) (P < 0.01 for all tests). However, there was no statistically significant difference in VBLR RMSEs between JAMDIG and DIGS datasets at any series of VFs (VF2-2 to VF2-10) (P > 0.05). VBLR outperformed OLSLR to predict future VF progression, and the VBLR has a potential to be a helpful tool at clinical settings.

Combination of Pre-Treatment DWI-Signal Intensity and S-1 Treatment: A Predictor of Survival in Patients with Locally Advanced Pancreatic Cancer Receiving Stereotactic Body Radiation Therapy and Sequential S-1.

PubMed

Zhang, Yu; Zhu, Xiaofei; Liu, Ri; Wang, Xianglian; Sun, Gaofeng; Song, Jiaqi; Lu, Jianping; Zhang, Huojun

2018-04-01

To identify whether the combination of pre-treatment radiological and clinical factors can predict the overall survival (OS) in patients with locally advanced pancreatic cancer (LAPC) treated with stereotactic body radiation and sequential S-1 (a prodrug of 5-FU combined with two modulators) therapy with improved accuracy compared with that of established clinical and radiologic risk models. Patients admitted with LAPC underwent diffusion weighted imaging (DWI) scan at 3.0-T (b = 600 s/mm 2 ). The mean signal intensity (SI b = 600) of region-of-interest (ROI) was measured. The Log-rank test was done for tumor location, biliary stent, S-1, and other treatments and the Cox regression analysis was done to identify independent prognostic factors for OS. Prediction error curves (PEC) were used to assess potential errors in prediction of survival. The accuracy of prediction was evaluated by Integrated Brier Score (IBS) and C index. 41 patients were included in this study. The median OS was 11.7 months (2.8-23.23 months). The 1-year OS was 46%. Multivariate analysis showed that pre-treatment SI b = 600 value and administration of S-1 were independent predictors for OS. The performance of pre-treatment SI b = 600 and S-1 treatment in combination was better than that of SI b = 600 or S-1 treatment alone. The combination of pre-treatment SI b = 600 and S-1 treatment could predict the OS in patients with LAPC undergoing SBRT and sequential S-1 therapy with improved accuracy compared with that of established clinical and radiologic risk models. Copyright © 2018 The Authors. Published by Elsevier Inc. All rights reserved.

Clinical time series prediction: towards a hierarchical dynamical system framework

PubMed Central

Liu, Zitao; Hauskrecht, Milos

2014-01-01

Objective Developing machine learning and data mining algorithms for building temporal models of clinical time series is important for understanding of the patient condition, the dynamics of a disease, effect of various patient management interventions and clinical decision making. In this work, we propose and develop a novel hierarchical framework for modeling clinical time series data of varied length and with irregularly sampled observations. Materials and methods Our hierarchical dynamical system framework for modeling clinical time series combines advantages of the two temporal modeling approaches: the linear dynamical system and the Gaussian process. We model the irregularly sampled clinical time series by using multiple Gaussian process sequences in the lower level of our hierarchical framework and capture the transitions between Gaussian processes by utilizing the linear dynamical system. The experiments are conducted on the complete blood count (CBC) panel data of 1000 post-surgical cardiac patients during their hospitalization. Our framework is evaluated and compared to multiple baseline approaches in terms of the mean absolute prediction error and the absolute percentage error. Results We tested our framework by first learning the time series model from data for the patient in the training set, and then applying the model in order to predict future time series values on the patients in the test set. We show that our model outperforms multiple existing models in terms of its predictive accuracy. Our method achieved a 3.13% average prediction accuracy improvement on ten CBC lab time series when it was compared against the best performing baseline. A 5.25% average accuracy improvement was observed when only short-term predictions were considered. Conclusion A new hierarchical dynamical system framework that lets us model irregularly sampled time series data is a promising new direction for modeling clinical time series and for improving their predictive performance. PMID:25534671

Integrative Chemical-Biological Read-Across Approach for Chemical Hazard Classification

PubMed Central

Low, Yen; Sedykh, Alexander; Fourches, Denis; Golbraikh, Alexander; Whelan, Maurice; Rusyn, Ivan; Tropsha, Alexander

2013-01-01

Traditional read-across approaches typically rely on the chemical similarity principle to predict chemical toxicity; however, the accuracy of such predictions is often inadequate due to the underlying complex mechanisms of toxicity. Here we report on the development of a hazard classification and visualization method that draws upon both chemical structural similarity and comparisons of biological responses to chemicals measured in multiple short-term assays (”biological” similarity). The Chemical-Biological Read-Across (CBRA) approach infers each compound's toxicity from those of both chemical and biological analogs whose similarities are determined by the Tanimoto coefficient. Classification accuracy of CBRA was compared to that of classical RA and other methods using chemical descriptors alone, or in combination with biological data. Different types of adverse effects (hepatotoxicity, hepatocarcinogenicity, mutagenicity, and acute lethality) were classified using several biological data types (gene expression profiling and cytotoxicity screening). CBRA-based hazard classification exhibited consistently high external classification accuracy and applicability to diverse chemicals. Transparency of the CBRA approach is aided by the use of radial plots that show the relative contribution of analogous chemical and biological neighbors. Identification of both chemical and biological features that give rise to the high accuracy of CBRA-based toxicity prediction facilitates mechanistic interpretation of the models. PMID:23848138

Geopositioning with a quadcopter: Extracted feature locations and predicted accuracy without a priori sensor attitude information

NASA Astrophysics Data System (ADS)

Dolloff, John; Hottel, Bryant; Edwards, David; Theiss, Henry; Braun, Aaron

2017-05-01

This paper presents an overview of the Full Motion Video-Geopositioning Test Bed (FMV-GTB) developed to investigate algorithm performance and issues related to the registration of motion imagery and subsequent extraction of feature locations along with predicted accuracy. A case study is included corresponding to a video taken from a quadcopter. Registration of the corresponding video frames is performed without the benefit of a priori sensor attitude (pointing) information. In particular, tie points are automatically measured between adjacent frames using standard optical flow matching techniques from computer vision, an a priori estimate of sensor attitude is then computed based on supplied GPS sensor positions contained in the video metadata and a photogrammetric/search-based structure from motion algorithm, and then a Weighted Least Squares adjustment of all a priori metadata across the frames is performed. Extraction of absolute 3D feature locations, including their predicted accuracy based on the principles of rigorous error propagation, is then performed using a subset of the registered frames. Results are compared to known locations (check points) over a test site. Throughout this entire process, no external control information (e.g. surveyed points) is used other than for evaluation of solution errors and corresponding accuracy.

Study design requirements for RNA sequencing-based breast cancer diagnostics.

PubMed

Mer, Arvind Singh; Klevebring, Daniel; Grönberg, Henrik; Rantalainen, Mattias

2016-02-01

Sequencing-based molecular characterization of tumors provides information required for individualized cancer treatment. There are well-defined molecular subtypes of breast cancer that provide improved prognostication compared to routine biomarkers. However, molecular subtyping is not yet implemented in routine breast cancer care. Clinical translation is dependent on subtype prediction models providing high sensitivity and specificity. In this study we evaluate sample size and RNA-sequencing read requirements for breast cancer subtyping to facilitate rational design of translational studies. We applied subsampling to ascertain the effect of training sample size and the number of RNA sequencing reads on classification accuracy of molecular subtype and routine biomarker prediction models (unsupervised and supervised). Subtype classification accuracy improved with increasing sample size up to N = 750 (accuracy = 0.93), although with a modest improvement beyond N = 350 (accuracy = 0.92). Prediction of routine biomarkers achieved accuracy of 0.94 (ER) and 0.92 (Her2) at N = 200. Subtype classification improved with RNA-sequencing library size up to 5 million reads. Development of molecular subtyping models for cancer diagnostics requires well-designed studies. Sample size and the number of RNA sequencing reads directly influence accuracy of molecular subtyping. Results in this study provide key information for rational design of translational studies aiming to bring sequencing-based diagnostics to the clinic.

Transportation Modes Classification Using Sensors on Smartphones.

PubMed

Fang, Shih-Hau; Liao, Hao-Hsiang; Fei, Yu-Xiang; Chen, Kai-Hsiang; Huang, Jen-Wei; Lu, Yu-Ding; Tsao, Yu

2016-08-19

This paper investigates the transportation and vehicular modes classification by using big data from smartphone sensors. The three types of sensors used in this paper include the accelerometer, magnetometer, and gyroscope. This study proposes improved features and uses three machine learning algorithms including decision trees, K-nearest neighbor, and support vector machine to classify the user's transportation and vehicular modes. In the experiments, we discussed and compared the performance from different perspectives including the accuracy for both modes, the executive time, and the model size. Results show that the proposed features enhance the accuracy, in which the support vector machine provides the best performance in classification accuracy whereas it consumes the largest prediction time. This paper also investigates the vehicle classification mode and compares the results with that of the transportation modes.

Transportation Modes Classification Using Sensors on Smartphones

PubMed Central

Fang, Shih-Hau; Liao, Hao-Hsiang; Fei, Yu-Xiang; Chen, Kai-Hsiang; Huang, Jen-Wei; Lu, Yu-Ding; Tsao, Yu

2016-01-01

This paper investigates the transportation and vehicular modes classification by using big data from smartphone sensors. The three types of sensors used in this paper include the accelerometer, magnetometer, and gyroscope. This study proposes improved features and uses three machine learning algorithms including decision trees, K-nearest neighbor, and support vector machine to classify the user’s transportation and vehicular modes. In the experiments, we discussed and compared the performance from different perspectives including the accuracy for both modes, the executive time, and the model size. Results show that the proposed features enhance the accuracy, in which the support vector machine provides the best performance in classification accuracy whereas it consumes the largest prediction time. This paper also investigates the vehicle classification mode and compares the results with that of the transportation modes. PMID:27548182

The accuracy of Genomic Selection in Norwegian red cattle assessed by cross-validation.

PubMed

Luan, Tu; Woolliams, John A; Lien, Sigbjørn; Kent, Matthew; Svendsen, Morten; Meuwissen, Theo H E

2009-11-01

Genomic Selection (GS) is a newly developed tool for the estimation of breeding values for quantitative traits through the use of dense markers covering the whole genome. For a successful application of GS, accuracy of the prediction of genomewide breeding value (GW-EBV) is a key issue to consider. Here we investigated the accuracy and possible bias of GW-EBV prediction, using real bovine SNP genotyping (18,991 SNPs) and phenotypic data of 500 Norwegian Red bulls. The study was performed on milk yield, fat yield, protein yield, first lactation mastitis traits, and calving ease. Three methods, best linear unbiased prediction (G-BLUP), Bayesian statistics (BayesB), and a mixture model approach (MIXTURE), were used to estimate marker effects, and their accuracy and bias were estimated by using cross-validation. The accuracies of the GW-EBV prediction were found to vary widely between 0.12 and 0.62. G-BLUP gave overall the highest accuracy. We observed a strong relationship between the accuracy of the prediction and the heritability of the trait. GW-EBV prediction for production traits with high heritability achieved higher accuracy and also lower bias than health traits with low heritability. To achieve a similar accuracy for the health traits probably more records will be needed.

Comparison of Space Shuttle Hot Gas Manifold analysis to air flow data

NASA Technical Reports Server (NTRS)

Mcconnaughey, P. K.

1988-01-01

This paper summarizes several recent analyses of the Space Shuttle Main Engine Hot Gas Manifold and compares predicted flow environments to air flow data. Codes used in these analyses include INS3D, PAGE, PHOENICS, and VAST. Both laminar (Re = 250, M = 0.30) and turbulent (Re = 1.9 million, M = 0.30) results are discussed, with the latter being compared to data for system losses, outer wall static pressures, and manifold exit Mach number profiles. Comparison of predicted results for the turbulent case to air flow data shows that the analysis using INS3D predicted system losses within 1 percent error, while the PHOENICS, PAGE, and VAST codes erred by 31, 35, and 47 percent, respectively. The INS3D, PHOENICS, and PAGE codes did a reasonable job of predicting outer wall static pressure, while the PHOENICS code predicted exit Mach number profiles with acceptable accuracy. INS3D was approximately an order of magnitude more efficient than the other codes in terms of code speed and memory requirements. In general, it is seen that complex internal flows in manifold-like geometries can be predicted with a limited degree of confidence, and further development is necessary to improve both efficiency and accuracy of codes if they are to be used as design tools for complex three-dimensional geometries.

The predictive power of SIMION/SDS simulation software for modeling ion mobility spectrometry instruments

NASA Astrophysics Data System (ADS)

Lai, Hanh; McJunkin, Timothy R.; Miller, Carla J.; Scott, Jill R.; Almirall, José R.

2008-09-01

The combined use of SIMION 7.0 and the statistical diffusion simulation (SDS) user program in conjunction with SolidWorks® with COSMSOSFloWorks® fluid dynamics software to model a complete, commercial ion mobility spectrometer (IMS) was demonstrated for the first time and compared to experimental results for tests using compounds of immediate interest in the security industry (e.g., 2,4,6-trinitrotoluene, 2,7-dinitrofluorene, and cocaine). The effort of this research was to evaluate the predictive power of SIMION/SDS for application to IMS instruments. The simulation was evaluated against experimental results in three studies: (1) a drift:carrier gas flow rates study assesses the ability of SIMION/SDS to correctly predict the ion drift times; (2) a drift gas composition study evaluates the accuracy in predicting the resolution; (3) a gate width study compares the simulated peak shape and peak intensity with the experimental values. SIMION/SDS successfully predicted the correct drift time, intensity, and resolution trends for the operating parameters studied. Despite the need for estimations and assumptions in the construction of the simulated instrument, SIMION/SDS was able to predict the resolution between two ion species in air within 3% accuracy. The preliminary success of IMS simulations using SIMION/SDS software holds great promise for the design of future instruments with enhanced performance.

The Predictive Power of SIMION/SDS Simulation Software for Modeling Ion Mobility Spectrometry Instruments

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hanh Lai; Timothy R. McJunkin; Carla J. Miller

2008-09-01

The combined use of SIMION 7.0 and the statistical diffusion simulation (SDS) user program in conjunction with SolidWorks® with COSMSOFloWorks® fluid dynamics software to model a complete, commercial ion mobility spectrometer (IMS) was demonstrated for the first time and compared to experimental results for tests using compounds of immediate interest in the security industry (e.g., 2,4,6-trinitrotoluene and cocaine). The effort of this research was to evaluate the predictive power of SIMION/SDS for application to IMS instruments. The simulation was evaluated against experimental results in three studies: 1) a drift:carrier gas flow rates study assesses the ability of SIMION/SDS to correctlymore » predict the ion drift times; 2) a drift gas composition study evaluates the accuracy in predicting the resolution; and 3) a gate width study compares the simulated peak shape and peak intensity with the experimental values. SIMION/SDS successfully predicted the correct drift time, intensity, and resolution trends for the operating parameters studied. Despite the need for estimations and assumptions in the construction of the simulated instrument, SIMION/SDS was able to predict the resolution between two ion species in air within 3% accuracy. The preliminary success of IMS simulations using SIMION/SDS software holds great promise for the design of future instruments with enhanced performance.« less

Improved Formula for the Stress Intensity Factor of Semi-Elliptical Surface Cracks in Welded Joints under Bending Stress

PubMed Central

Peng, Yang; Wu, Chao; Zheng, Yifu; Dong, Jun

2017-01-01

Welded joints are prone to fatigue cracking with the existence of welding defects and bending stress. Fracture mechanics is a useful approach in which the fatigue life of the welded joint can be predicted. The key challenge of such predictions using fracture mechanics is how to accurately calculate the stress intensity factor (SIF). An empirical formula for calculating the SIF of welded joints under bending stress was developed by Baik, Yamada and Ishikawa based on the hybrid method. However, when calculating the SIF of a semi-elliptical crack, this study found that the accuracy of the Baik-Yamada formula was poor when comparing the benchmark results, experimental data and numerical results. The reasons for the reduced accuracy of the Baik-Yamada formula were identified and discussed in this paper. Furthermore, a new correction factor was developed and added to the Baik-Yamada formula by using theoretical analysis and numerical regression. Finally, the predictions using the modified Baik-Yamada formula were compared with the benchmark results, experimental data and numerical results. It was found that the accuracy of the modified Baik-Yamada formula was greatly improved. Therefore, it is proposed that this modified formula is used to conveniently and accurately calculate the SIF of semi-elliptical cracks in welded joints under bending stress. PMID:28772527

[GSH fermentation process modeling using entropy-criterion based RBF neural network model].

PubMed

Tan, Zuoping; Wang, Shitong; Deng, Zhaohong; Du, Guocheng

2008-05-01

The prediction accuracy and generalization of GSH fermentation process modeling are often deteriorated by noise existing in the corresponding experimental data. In order to avoid this problem, we present a novel RBF neural network modeling approach based on entropy criterion. It considers the whole distribution structure of the training data set in the parameter learning process compared with the traditional MSE-criterion based parameter learning, and thus effectively avoids the weak generalization and over-learning. Then the proposed approach is applied to the GSH fermentation process modeling. Our results demonstrate that this proposed method has better prediction accuracy, generalization and robustness such that it offers a potential application merit for the GSH fermentation process modeling.

Developing an in silico minimum inhibitory concentration panel test for Klebsiella pneumoniae

DOE PAGES

Nguyen, Marcus; Brettin, Thomas; Long, S. Wesley; ...

2018-01-11

Here, antimicrobial resistant infections are a serious public health threat worldwide. Whole genome sequencing approaches to rapidly identify pathogens and predict antibiotic resistance phenotypes are becoming more feasible and may offer a way to reduce clinical test turnaround times compared to conventional culture-based methods, and in turn, improve patient outcomes. In this study, we use whole genome sequence data from 1668 clinical isolates of Klebsiella pneumoniae to develop a XGBoost-based machine learning model that accurately predicts minimum inhibitory concentrations (MICs) for 20 antibiotics. The overall accuracy of the model, within ± 1 two-fold dilution factor, is 92%. Individual accuracies aremore » >= 90% for 15/20 antibiotics. We show that the MICs predicted by the model correlate with known antimicrobial resistance genes. Importantly, the genome-wide approach described in this study offers a way to predict MICs for isolates without knowledge of the underlying gene content. This study shows that machine learning can be used to build a complete in silico MIC prediction panel for K. pneumoniae and provides a framework for building MIC prediction models for other pathogenic bacteria.« less

Developing an in silico minimum inhibitory concentration panel test for Klebsiella pneumoniae

DOE Office of Scientific and Technical Information (OSTI.GOV)

Nguyen, Marcus; Brettin, Thomas; Long, S. Wesley

Here, antimicrobial resistant infections are a serious public health threat worldwide. Whole genome sequencing approaches to rapidly identify pathogens and predict antibiotic resistance phenotypes are becoming more feasible and may offer a way to reduce clinical test turnaround times compared to conventional culture-based methods, and in turn, improve patient outcomes. In this study, we use whole genome sequence data from 1668 clinical isolates of Klebsiella pneumoniae to develop a XGBoost-based machine learning model that accurately predicts minimum inhibitory concentrations (MICs) for 20 antibiotics. The overall accuracy of the model, within ± 1 two-fold dilution factor, is 92%. Individual accuracies aremore » >= 90% for 15/20 antibiotics. We show that the MICs predicted by the model correlate with known antimicrobial resistance genes. Importantly, the genome-wide approach described in this study offers a way to predict MICs for isolates without knowledge of the underlying gene content. This study shows that machine learning can be used to build a complete in silico MIC prediction panel for K. pneumoniae and provides a framework for building MIC prediction models for other pathogenic bacteria.« less

Integrative Approaches for Predicting in vivo Effects of Chemicals from their Structural Descriptors and the Results of Short-term Biological Assays

PubMed Central

Low, Yen S.; Sedykh, Alexander; Rusyn, Ivan; Tropsha, Alexander

2017-01-01

Cheminformatics approaches such as Quantitative Structure Activity Relationship (QSAR) modeling have been used traditionally for predicting chemical toxicity. In recent years, high throughput biological assays have been increasingly employed to elucidate mechanisms of chemical toxicity and predict toxic effects of chemicals in vivo. The data generated in such assays can be considered as biological descriptors of chemicals that can be combined with molecular descriptors and employed in QSAR modeling to improve the accuracy of toxicity prediction. In this review, we discuss several approaches for integrating chemical and biological data for predicting biological effects of chemicals in vivo and compare their performance across several data sets. We conclude that while no method consistently shows superior performance, the integrative approaches rank consistently among the best yet offer enriched interpretation of models over those built with either chemical or biological data alone. We discuss the outlook for such interdisciplinary methods and offer recommendations to further improve the accuracy and interpretability of computational models that predict chemical toxicity. PMID:24805064

Evaluation of in silico tools to predict the skin sensitization potential of chemicals.

PubMed

Verheyen, G R; Braeken, E; Van Deun, K; Van Miert, S

2017-01-01

Public domain and commercial in silico tools were compared for their performance in predicting the skin sensitization potential of chemicals. The packages were either statistical based (Vega, CASE Ultra) or rule based (OECD Toolbox, Toxtree, Derek Nexus). In practice, several of these in silico tools are used in gap filling and read-across, but here their use was limited to make predictions based on presence/absence of structural features associated to sensitization. The top 400 ranking substances of the ATSDR 2011 Priority List of Hazardous Substances were selected as a starting point. Experimental information was identified for 160 chemically diverse substances (82 positive and 78 negative). The prediction for skin sensitization potential was compared with the experimental data. Rule-based tools perform slightly better, with accuracies ranging from 0.6 (OECD Toolbox) to 0.78 (Derek Nexus), compared with statistical tools that had accuracies ranging from 0.48 (Vega) to 0.73 (CASE Ultra - LLNA weak model). Combining models increased the performance, with positive and negative predictive values up to 80% and 84%, respectively. However, the number of substances that were predicted positive or negative for skin sensitization in both models was low. Adding more substances to the dataset will increase the confidence in the conclusions reached. The insights obtained in this evaluation are incorporated in a web database www.asopus.weebly.com that provides a potential end user context for the scope and performance of different in silico tools with respect to a common dataset of curated skin sensitization data.

Comparison of Eight Equations That Predict Percent Body Fat Using Skinfolds in American Youth

PubMed Central

Roberts, Amy; Cai, Jianwen; Berge, Jerica M.; Stevens, June

2016-01-01

Abstract Background: Skinfolds are often used in equations to predict percent body fat (PBF) in youth. Although there are numerous such equations published, there is limited information to help researchers determine which equation to use for their sample. Methods: Using data from the 1999–2006 National Health and Nutrition Examination Surveys (NHANES), we compared eight published equations for prediction of PBF. These published equations all included triceps and/or subscapular skinfold measurements. We examined the PBF equations in a nationally representative sample of American youth that was matched by age, sex, and race/ethnicity to the original equation development population and a full sample of 8- to 18-year-olds. We compared the equation-predicted PBF to the dual-emission X-ray absorptiometry (DXA)-measured PBF. The adjusted R2, root mean square error (RMSE), and mean signed difference (MSD) were compared. The MSDs were used to examine accuracy and differential bias by age, sex, and race/ethnicity. Results: When applied to the full range of 8- 18-year-old youth, the R2 values ranged from 0.495 to 0.738. The MSD between predicted and DXA-measured PBF indicated high average accuracy (MSD between −1.0 and 1.0) for only three equations (Bray subscapular equation and Dezenberg equations [with and without race/ethnicity]). The majority of the equations showed differential bias by sex, race/ethnicity, weight status, or age. Conclusions: These findings indicate that investigators should use caution in the selection of an equation to predict PBF in youth given that results may vary systematically in important subgroups. PMID:27045618

Comparison of Eight Equations That Predict Percent Body Fat Using Skinfolds in American Youth.

PubMed

Truesdale, Kimberly P; Roberts, Amy; Cai, Jianwen; Berge, Jerica M; Stevens, June

2016-08-01

Skinfolds are often used in equations to predict percent body fat (PBF) in youth. Although there are numerous such equations published, there is limited information to help researchers determine which equation to use for their sample. Using data from the 1999-2006 National Health and Nutrition Examination Surveys (NHANES), we compared eight published equations for prediction of PBF. These published equations all included triceps and/or subscapular skinfold measurements. We examined the PBF equations in a nationally representative sample of American youth that was matched by age, sex, and race/ethnicity to the original equation development population and a full sample of 8- to 18-year-olds. We compared the equation-predicted PBF to the dual-emission X-ray absorptiometry (DXA)-measured PBF. The adjusted R(2), root mean square error (RMSE), and mean signed difference (MSD) were compared. The MSDs were used to examine accuracy and differential bias by age, sex, and race/ethnicity. When applied to the full range of 8- 18-year-old youth, the R(2) values ranged from 0.495 to 0.738. The MSD between predicted and DXA-measured PBF indicated high average accuracy (MSD between -1.0 and 1.0) for only three equations (Bray subscapular equation and Dezenberg equations [with and without race/ethnicity]). The majority of the equations showed differential bias by sex, race/ethnicity, weight status, or age. These findings indicate that investigators should use caution in the selection of an equation to predict PBF in youth given that results may vary systematically in important subgroups.

Benefit of Hepatitis C Virus Core Antigen Assay in Prediction of Therapeutic Response to Interferon and Ribavirin Combination Therapy

PubMed Central

Takahashi, Masahiko; Saito, Hidetsugu; Higashimoto, Makiko; Atsukawa, Kazuhiro; Ishii, Hiromasa

2005-01-01

A highly sensitive second-generation hepatitis C virus (HCV) core antigen assay has recently been developed. We compared viral disappearance and first-phase kinetics between commercially available core antigen (Ag) assays, Lumipulse Ortho HCV Ag (Lumipulse-Ag), and a quantitative HCV RNA PCR assay, Cobas Amplicor HCV Monitor test, version 2 (Amplicor M), to estimate the predictive benefit of a sustained viral response (SVR) and non-SVR in 44 genotype 1b patients treated with interferon (IFN) and ribavirin. HCV core Ag negativity could predict SVR on day 1 (sensitivity = 100%, specificity = 85.0%, accuracy = 86.4%), whereas RNA negativity could predict SVR on day 7 (sensitivity = 100%, specificity = 87.2%, accuracy = 88.6%). None of the patients who had detectable serum core Ag or RNA on day 14 achieved SVR (specificity = 100%). The predictive accuracy on day 14 was higher by RNA negativity (93.2%) than that by core Ag negativity (75.0%). The combined predictive criterion of both viral load decline during the first 24 h and basal viral load was also predictive for SVR; the sensitivities of Lumipulse-Ag and Amplicor-M were 45.5 and 47.6%, respectively, and the specificity was 100%. Amplicor-M had better predictive accuracy than Lumipulse-Ag in 2-week disappearance tests because it had better sensitivity. On the other hand, estimates of kinetic parameters were similar regardless of the detection method. Although the correlations between Lumipulse-Ag and Amplicor-M were good both before and 24 h after IFN administration, HCV core Ag seemed to be relatively lower 24 h after IFN administration than before administration. Lumipulse-Ag seems to be useful for detecting the HCV concentration during IFN therapy; however, we still need to understand the characteristics of the assay. PMID:15634970

Risk-adjusted capitation based on the Diagnostic Cost Group Model: an empirical evaluation with health survey information.

PubMed Central

Lamers, L M

1999-01-01

OBJECTIVE: To evaluate the predictive accuracy of the Diagnostic Cost Group (DCG) model using health survey information. DATA SOURCES/STUDY SETTING: Longitudinal data collected for a sample of members of a Dutch sickness fund. In the Netherlands the sickness funds provide compulsory health insurance coverage for the 60 percent of the population in the lowest income brackets. STUDY DESIGN: A demographic model and DCG capitation models are estimated by means of ordinary least squares, with an individual's annual healthcare expenditures in 1994 as the dependent variable. For subgroups based on health survey information, costs predicted by the models are compared with actual costs. Using stepwise regression procedures a subset of relevant survey variables that could improve the predictive accuracy of the three-year DCG model was identified. Capitation models were extended with these variables. DATA COLLECTION/EXTRACTION METHODS: For the empirical analysis, panel data of sickness fund members were used that contained demographic information, annual healthcare expenditures, and diagnostic information from hospitalizations for each member. In 1993, a mailed health survey was conducted among a random sample of 15,000 persons in the panel data set, with a 70 percent response rate. PRINCIPAL FINDINGS: The predictive accuracy of the demographic model improves when it is extended with diagnostic information from prior hospitalizations (DCGs). A subset of survey variables further improves the predictive accuracy of the DCG capitation models. The predictable profits and losses based on survey information for the DCG models are smaller than for the demographic model. Most persons with predictable losses based on health survey information were not hospitalized in the preceding year. CONCLUSIONS: The use of diagnostic information from prior hospitalizations is a promising option for improving the demographic capitation payment formula. This study suggests that diagnostic information from outpatient utilization is complementary to DCGs in predicting future costs. PMID:10029506

Artificial Neural Network System to Predict the Postoperative Outcome of Percutaneous Nephrolithotomy.

PubMed

Aminsharifi, Alireza; Irani, Dariush; Pooyesh, Shima; Parvin, Hamid; Dehghani, Sakineh; Yousofi, Khalilolah; Fazel, Ebrahim; Zibaie, Fatemeh

2017-05-01

To construct, train, and apply an artificial neural network (ANN) system for prediction of different outcome variables of percutaneous nephrolithotomy (PCNL). We calculated predictive accuracy, sensitivity, and precision for each outcome variable. During the study period, all adult patients who underwent PCNL at our institute were enrolled in the study. Preoperative and postoperative variables were recorded, and stone-free status was assessed perioperatively with computed tomography scans. MATLAB software was used to design and train the network in a feed forward back-propagation error adjustment scheme. Preoperative and postoperative data from 200 patients (training set) were used to analyze the effect and relative relevance of preoperative values on postoperative parameters. The validated adequately trained ANN was used to predict postoperative outcomes in the subsequent 254 adult patients (test set) whose preoperative values were serially fed into the system. To evaluate system accuracy in predicting each postoperative variable, predicted values were compared with actual outcomes. Two hundred fifty-four patients (155 [61%] males) were considered the test set. Mean stone burden was 6702.86 ± 381.6 mm 3 . Overall stone-free rate was 76.4%. Fifty-four out of 254 patients (21.3%) required ancillary procedures (shockwave lithotripsy 5.9%, transureteral lithotripsy 10.6%, and repeat PCNL 4.7%). The accuracy and sensitivity of the system in predicting different postoperative variables ranged from 81.0% to 98.2%. As a complex nonlinear mathematical model, our ANN system is an interconnected data mining tool, which prospectively analyzes and "learns" the relationships between variables. The accuracy and sensitivity of the system for predicting the stone-free rate, the need for blood transfusion, and post-PCNL ancillary procedures ranged from 81.0% to 98.2%.The stone burden and the stone morphometry were among the most significant preoperative characteristics that affected all postoperative outcome variables and they received the highest relative weight by the ANN system.

Comparison between Frailty Index of Deficit Accumulation and Phenotypic Model to Predict Risk of Falls: Data from the Global Longitudinal Study of Osteoporosis in Women (GLOW) Hamilton Cohort

PubMed Central

Thabane, Lehana; Ioannidis, George; Kennedy, Courtney; Papaioannou, Alexandra

2015-01-01

Objectives To compare the predictive accuracy of the frailty index (FI) of deficit accumulation and the phenotypic frailty (PF) model in predicting risks of future falls, fractures and death in women aged ≥55 years. Methods Based on the data from the Global Longitudinal Study of Osteoporosis in Women (GLOW) 3-year Hamilton cohort (n = 3,985), we compared the predictive accuracy of the FI and PF in risks of falls, fractures and death using three strategies: (1) investigated the relationship with adverse health outcomes by increasing per one-fifth (i.e., 20%) of the FI and PF; (2) trichotomized the FI based on the overlap in the density distribution of the FI by the three groups (robust, pre-frail and frail) which were defined by the PF; (3) categorized the women according to a predicted probability function of falls during the third year of follow-up predicted by the FI. Logistic regression models were used for falls and death, while survival analyses were conducted for fractures. Results The FI and PF agreed with each other at a good level of consensus (correlation coefficients ≥ 0.56) in all the three strategies. Both the FI and PF approaches predicted adverse health outcomes significantly. The FI quantified the risks of future falls, fractures and death more precisely than the PF. Both the FI and PF discriminated risks of adverse outcomes in multivariable models with acceptable and comparable area under the curve (AUCs) for falls (AUCs ≥ 0.68) and death (AUCs ≥ 0.79), and c-indices for fractures (c-indices ≥ 0.69) respectively. Conclusions The FI is comparable with the PF in predicting risks of adverse health outcomes. These findings may indicate the flexibility in the choice of frailty model for the elderly in the population-based settings. PMID:25764521

Comparison between frailty index of deficit accumulation and phenotypic model to predict risk of falls: data from the global longitudinal study of osteoporosis in women (GLOW) Hamilton cohort.

PubMed

Li, Guowei; Thabane, Lehana; Ioannidis, George; Kennedy, Courtney; Papaioannou, Alexandra; Adachi, Jonathan D

2015-01-01

To compare the predictive accuracy of the frailty index (FI) of deficit accumulation and the phenotypic frailty (PF) model in predicting risks of future falls, fractures and death in women aged ≥55 years. Based on the data from the Global Longitudinal Study of Osteoporosis in Women (GLOW) 3-year Hamilton cohort (n = 3,985), we compared the predictive accuracy of the FI and PF in risks of falls, fractures and death using three strategies: (1) investigated the relationship with adverse health outcomes by increasing per one-fifth (i.e., 20%) of the FI and PF; (2) trichotomized the FI based on the overlap in the density distribution of the FI by the three groups (robust, pre-frail and frail) which were defined by the PF; (3) categorized the women according to a predicted probability function of falls during the third year of follow-up predicted by the FI. Logistic regression models were used for falls and death, while survival analyses were conducted for fractures. The FI and PF agreed with each other at a good level of consensus (correlation coefficients ≥ 0.56) in all the three strategies. Both the FI and PF approaches predicted adverse health outcomes significantly. The FI quantified the risks of future falls, fractures and death more precisely than the PF. Both the FI and PF discriminated risks of adverse outcomes in multivariable models with acceptable and comparable area under the curve (AUCs) for falls (AUCs ≥ 0.68) and death (AUCs ≥ 0.79), and c-indices for fractures (c-indices ≥ 0.69) respectively. The FI is comparable with the PF in predicting risks of adverse health outcomes. These findings may indicate the flexibility in the choice of frailty model for the elderly in the population-based settings.

An evidential link prediction method and link predictability based on Shannon entropy

NASA Astrophysics Data System (ADS)

Yin, Likang; Zheng, Haoyang; Bian, Tian; Deng, Yong

2017-09-01

Predicting missing links is of both theoretical value and practical interest in network science. In this paper, we empirically investigate a new link prediction method base on similarity and compare nine well-known local similarity measures on nine real networks. Most of the previous studies focus on the accuracy, however, it is crucial to consider the link predictability as an initial property of networks itself. Hence, this paper has proposed a new link prediction approach called evidential measure (EM) based on Dempster-Shafer theory. Moreover, this paper proposed a new method to measure link predictability via local information and Shannon entropy.

Outcome Prediction in Mathematical Models of Immune Response to Infection.

PubMed

Mai, Manuel; Wang, Kun; Huber, Greg; Kirby, Michael; Shattuck, Mark D; O'Hern, Corey S

2015-01-01

Clinicians need to predict patient outcomes with high accuracy as early as possible after disease inception. In this manuscript, we show that patient-to-patient variability sets a fundamental limit on outcome prediction accuracy for a general class of mathematical models for the immune response to infection. However, accuracy can be increased at the expense of delayed prognosis. We investigate several systems of ordinary differential equations (ODEs) that model the host immune response to a pathogen load. Advantages of systems of ODEs for investigating the immune response to infection include the ability to collect data on large numbers of 'virtual patients', each with a given set of model parameters, and obtain many time points during the course of the infection. We implement patient-to-patient variability v in the ODE models by randomly selecting the model parameters from distributions with coefficients of variation v that are centered on physiological values. We use logistic regression with one-versus-all classification to predict the discrete steady-state outcomes of the system. We find that the prediction algorithm achieves near 100% accuracy for v = 0, and the accuracy decreases with increasing v for all ODE models studied. The fact that multiple steady-state outcomes can be obtained for a given initial condition, i.e. the basins of attraction overlap in the space of initial conditions, limits the prediction accuracy for v > 0. Increasing the elapsed time of the variables used to train and test the classifier, increases the prediction accuracy, while adding explicit external noise to the ODE models decreases the prediction accuracy. Our results quantify the competition between early prognosis and high prediction accuracy that is frequently encountered by clinicians.

Adjusted Clinical Groups: Predictive Accuracy for Medicaid Enrollees in Three States

PubMed Central

Adams, E. Kathleen; Bronstein, Janet M.; Raskind-Hood, Cheryl

2002-01-01

Actuarial split-sample methods were used to assess predictive accuracy of adjusted clinical groups (ACGs) for Medicaid enrollees in Georgia, Mississippi (lagging in managed care penetration), and California. Accuracy for two non-random groups—high-cost and located in urban poor areas—was assessed. Measures for random groups were derived with and without short-term enrollees to assess the effect of turnover on predictive accuracy. ACGs improved predictive accuracy for high-cost conditions in all States, but did so only for those in Georgia's poorest urban areas. Higher and more unpredictable expenses of short-term enrollees moderated the predictive power of ACGs. This limitation was significant in Mississippi due in part, to that State's very high proportion of short-term enrollees. PMID:12545598

Wind Prediction Accuracy for Air Traffic Management Decision Support Tools

NASA Technical Reports Server (NTRS)

Cole, Rod; Green, Steve; Jardin, Matt; Schwartz, Barry; Benjamin, Stan

2000-01-01

The performance of Air Traffic Management and flight deck decision support tools depends in large part on the accuracy of the supporting 4D trajectory predictions. This is particularly relevant to conflict prediction and active advisories for the resolution of conflicts and the conformance with of traffic-flow management flow-rate constraints (e.g., arrival metering / required time of arrival). Flight test results have indicated that wind prediction errors may represent the largest source of trajectory prediction error. The tests also discovered relatively large errors (e.g., greater than 20 knots), existing in pockets of space and time critical to ATM DST performance (one or more sectors, greater than 20 minutes), are inadequately represented by the classic RMS aggregate prediction-accuracy studies of the past. To facilitate the identification and reduction of DST-critical wind-prediction errors, NASA has lead a collaborative research and development activity with MIT Lincoln Laboratories and the Forecast Systems Lab of the National Oceanographic and Atmospheric Administration (NOAA). This activity, begun in 1996, has focussed on the development of key metrics for ATM DST performance, assessment of wind-prediction skill for state of the art systems, and development/validation of system enhancements to improve skill. A 13 month study was conducted for the Denver Center airspace in 1997. Two complementary wind-prediction systems were analyzed and compared to the forecast performance of the then standard 60 km Rapid Update Cycle - version 1 (RUC-1). One system, developed by NOAA, was the prototype 40-km RUC-2 that became operational at NCEP in 1999. RUC-2 introduced a faster cycle (1 hr vs. 3 hr) and improved mesoscale physics. The second system, Augmented Winds (AW), is a prototype en route wind application developed by MITLL based on the Integrated Terminal Wind System (ITWS). AW is run at a local facility (Center) level, and updates RUC predictions based on an optimal interpolation of the latest ACARS reports since the RUC run. This paper presents an overview of the study's results including the identification and use of new large mor wind-prediction accuracy metrics that are key to ATM DST performance.

Optimization of rotamers prior to template minimization improves stability predictions made by computational protein design.

PubMed

Davey, James A; Chica, Roberto A

2015-04-01

Computational protein design (CPD) predictions are highly dependent on the structure of the input template used. However, it is unclear how small differences in template geometry translate to large differences in stability prediction accuracy. Herein, we explored how structural changes to the input template affect the outcome of stability predictions by CPD. To do this, we prepared alternate templates by Rotamer Optimization followed by energy Minimization (ROM) and used them to recapitulate the stability of 84 protein G domain β1 mutant sequences. In the ROM process, side-chain rotamers for wild-type (WT) or mutant sequences are optimized on crystal or nuclear magnetic resonance (NMR) structures prior to template minimization, resulting in alternate structures termed ROM templates. We show that use of ROM templates prepared from sequences known to be stable results predominantly in improved prediction accuracy compared to using the minimized crystal or NMR structures. Conversely, ROM templates prepared from sequences that are less stable than the WT reduce prediction accuracy by increasing the number of false positives. These observed changes in prediction outcomes are attributed to differences in side-chain contacts made by rotamers in ROM templates. Finally, we show that ROM templates prepared from sequences that are unfolded or that adopt a nonnative fold result in the selective enrichment of sequences that are also unfolded or that adopt a nonnative fold, respectively. Our results demonstrate the existence of a rotamer bias caused by the input template that can be harnessed to skew predictions toward sequences displaying desired characteristics. © 2014 The Protein Society.

Personalized Risk Prediction in Clinical Oncology Research: Applications and Practical Issues Using Survival Trees and Random Forests.

PubMed

Hu, Chen; Steingrimsson, Jon Arni

2018-01-01

A crucial component of making individualized treatment decisions is to accurately predict each patient's disease risk. In clinical oncology, disease risks are often measured through time-to-event data, such as overall survival and progression/recurrence-free survival, and are often subject to censoring. Risk prediction models based on recursive partitioning methods are becoming increasingly popular largely due to their ability to handle nonlinear relationships, higher-order interactions, and/or high-dimensional covariates. The most popular recursive partitioning methods are versions of the Classification and Regression Tree (CART) algorithm, which builds a simple interpretable tree structured model. With the aim of increasing prediction accuracy, the random forest algorithm averages multiple CART trees, creating a flexible risk prediction model. Risk prediction models used in clinical oncology commonly use both traditional demographic and tumor pathological factors as well as high-dimensional genetic markers and treatment parameters from multimodality treatments. In this article, we describe the most commonly used extensions of the CART and random forest algorithms to right-censored outcomes. We focus on how they differ from the methods for noncensored outcomes, and how the different splitting rules and methods for cost-complexity pruning impact these algorithms. We demonstrate these algorithms by analyzing a randomized Phase III clinical trial of breast cancer. We also conduct Monte Carlo simulations to compare the prediction accuracy of survival forests with more commonly used regression models under various scenarios. These simulation studies aim to evaluate how sensitive the prediction accuracy is to the underlying model specifications, the choice of tuning parameters, and the degrees of missing covariates.

A multivariate model for predicting segmental body composition.

PubMed

Tian, Simiao; Mioche, Laurence; Denis, Jean-Baptiste; Morio, Béatrice

2013-12-01

The aims of the present study were to propose a multivariate model for predicting simultaneously body, trunk and appendicular fat and lean masses from easily measured variables and to compare its predictive capacity with that of the available univariate models that predict body fat percentage (BF%). The dual-energy X-ray absorptiometry (DXA) dataset (52% men and 48% women) with White, Black and Hispanic ethnicities (1999-2004, National Health and Nutrition Examination Survey) was randomly divided into three sub-datasets: a training dataset (TRD), a test dataset (TED); a validation dataset (VAD), comprising 3835, 1917 and 1917 subjects. For each sex, several multivariate prediction models were fitted from the TRD using age, weight, height and possibly waist circumference. The most accurate model was selected from the TED and then applied to the VAD and a French DXA dataset (French DB) (526 men and 529 women) to assess the prediction accuracy in comparison with that of five published univariate models, for which adjusted formulas were re-estimated using the TRD. Waist circumference was found to improve the prediction accuracy, especially in men. For BF%, the standard error of prediction (SEP) values were 3.26 (3.75) % for men and 3.47 (3.95)% for women in the VAD (French DB), as good as those of the adjusted univariate models. Moreover, the SEP values for the prediction of body and appendicular lean masses ranged from 1.39 to 2.75 kg for both the sexes. The prediction accuracy was best for age < 65 years, BMI < 30 kg/m2 and the Hispanic ethnicity. The application of our multivariate model to large populations could be useful to address various public health issues.

Accuracy of predicting genomic breeding values for residual feed intake in Angus and Charolais beef cattle.

PubMed

Chen, L; Schenkel, F; Vinsky, M; Crews, D H; Li, C

2013-10-01

In beef cattle, phenotypic data that are difficult and/or costly to measure, such as feed efficiency, and DNA marker genotypes are usually available on a small number of animals of different breeds or populations. To achieve a maximal accuracy of genomic prediction using the phenotype and genotype data, strategies for forming a training population to predict genomic breeding values (GEBV) of the selection candidates need to be evaluated. In this study, we examined the accuracy of predicting GEBV for residual feed intake (RFI) based on 522 Angus and 395 Charolais steers genotyped on SNP with the Illumina Bovine SNP50 Beadchip for 3 training population forming strategies: within breed, across breed, and by pooling data from the 2 breeds (i.e., combined). Two other scenarios with the training and validation data split by birth year and by sire family within a breed were also investigated to assess the impact of genetic relationships on the accuracy of genomic prediction. Three statistical methods including the best linear unbiased prediction with the relationship matrix defined based on the pedigree (PBLUP), based on the SNP genotypes (GBLUP), and a Bayesian method (BayesB) were used to predict the GEBV. The results showed that the accuracy of the GEBV prediction was the highest when the prediction was within breed and when the validation population had greater genetic relationships with the training population, with a maximum of 0.58 for Angus and 0.64 for Charolais. The within-breed prediction accuracies dropped to 0.29 and 0.38, respectively, when the validation populations had a minimal pedigree link with the training population. When the training population of a different breed was used to predict the GEBV of the validation population, that is, across-breed genomic prediction, the accuracies were further reduced to 0.10 to 0.22, depending on the prediction method used. Pooling data from the 2 breeds to form the training population resulted in accuracies increased to 0.31 and 0.43, respectively, for the Angus and Charolais validation populations. The results suggested that the genetic relationship of selection candidates with the training population has a greater impact on the accuracy of GEBV using the Illumina Bovine SNP50 Beadchip. Pooling data from different breeds to form the training population will improve the accuracy of across breed genomic prediction for RFI in beef cattle.

Comparing ordinary kriging and inverse distance weighting for soil as pollution in Beijing.

PubMed

Qiao, Pengwei; Lei, Mei; Yang, Sucai; Yang, Jun; Guo, Guanghui; Zhou, Xiaoyong

2018-06-01

Spatial interpolation method is the basis of soil heavy metal pollution assessment and remediation. The existing evaluation index for interpolation accuracy did not combine with actual situation. The selection of interpolation methods needs to be based on specific research purposes and research object characteristics. In this paper, As pollution in soils of Beijing was taken as an example. The prediction accuracy of ordinary kriging (OK) and inverse distance weighted (IDW) were evaluated based on the cross validation results and spatial distribution characteristics of influencing factors. The results showed that, under the condition of specific spatial correlation, the cross validation results of OK and IDW for every soil point and the prediction accuracy of spatial distribution trend are similar. But the prediction accuracy of OK for the maximum and minimum is less than IDW, while the number of high pollution areas identified by OK are less than IDW. It is difficult to identify the high pollution areas fully by OK, which shows that the smoothing effect of OK is obvious. In addition, with increasing of the spatial correlation of As concentration, the cross validation error of OK and IDW decreases, and the high pollution area identified by OK is approaching the result of IDW, which can identify the high pollution areas more comprehensively. However, because the semivariogram constructed by OK interpolation method is more subjective and requires larger number of soil samples, IDW is more suitable for spatial prediction of heavy metal pollution in soils.

The need to approximate the use-case in clinical machine learning

PubMed Central

Saeb, Sohrab; Jayaraman, Arun; Mohr, David C.; Kording, Konrad P.

2017-01-01

Abstract The availability of smartphone and wearable sensor technology is leading to a rapid accumulation of human subject data, and machine learning is emerging as a technique to map those data into clinical predictions. As machine learning algorithms are increasingly used to support clinical decision making, it is vital to reliably quantify their prediction accuracy. Cross-validation (CV) is the standard approach where the accuracy of such algorithms is evaluated on part of the data the algorithm has not seen during training. However, for this procedure to be meaningful, the relationship between the training and the validation set should mimic the relationship between the training set and the dataset expected for the clinical use. Here we compared two popular CV methods: record-wise and subject-wise. While the subject-wise method mirrors the clinically relevant use-case scenario of diagnosis in newly recruited subjects, the record-wise strategy has no such interpretation. Using both a publicly available dataset and a simulation, we found that record-wise CV often massively overestimates the prediction accuracy of the algorithms. We also conducted a systematic review of the relevant literature, and found that this overly optimistic method was used by almost half of the retrieved studies that used accelerometers, wearable sensors, or smartphones to predict clinical outcomes. As we move towards an era of machine learning-based diagnosis and treatment, using proper methods to evaluate their accuracy is crucial, as inaccurate results can mislead both clinicians and data scientists. PMID:28327985

Two level approach to safety planning incorporating the Highway Safety Manual (HSM) network screening.

DOT National Transportation Integrated Search

2014-04-01

Compared to microscopic safety studies, macroscopic-focused research is more efficient at integrating zonal-level features into crash prediction models and identifying hot zones. However, macroscopic screening has accuracy limitations. Thus, this stu...

Comparing the line broadened quasilinear model to Vlasov code

NASA Astrophysics Data System (ADS)

Ghantous, K.; Berk, H. L.; Gorelenkov, N. N.

2014-03-01

The Line Broadened Quasilinear (LBQ) model is revisited to study its predicted saturation level as compared with predictions of a Vlasov solver BOT [Lilley et al., Phys. Rev. Lett. 102, 195003 (2009) and M. Lilley, BOT Manual. The parametric dependencies of the model are modified to achieve more accuracy compared to the results of the Vlasov solver both in regards to a mode amplitude's time evolution to a saturated state and its final steady state amplitude in the parameter space of the model's applicability. However, the regions of stability as predicted by LBQ model and BOT are found to significantly differ from each other. The solutions of the BOT simulations are found to have a larger region of instability than the LBQ simulations.

Research on Improved Depth Belief Network-Based Prediction of Cardiovascular Diseases

PubMed Central

Zhang, Hongpo

2018-01-01

Quantitative analysis and prediction can help to reduce the risk of cardiovascular disease. Quantitative prediction based on traditional model has low accuracy. The variance of model prediction based on shallow neural network is larger. In this paper, cardiovascular disease prediction model based on improved deep belief network (DBN) is proposed. Using the reconstruction error, the network depth is determined independently, and unsupervised training and supervised optimization are combined. It ensures the accuracy of model prediction while guaranteeing stability. Thirty experiments were performed independently on the Statlog (Heart) and Heart Disease Database data sets in the UCI database. Experimental results showed that the mean of prediction accuracy was 91.26% and 89.78%, respectively. The variance of prediction accuracy was 5.78 and 4.46, respectively. PMID:29854369

Artificial Intelligence Systems as Prognostic and Predictive Tools in Ovarian Cancer.

PubMed

Enshaei, A; Robson, C N; Edmondson, R J

2015-11-01

The ability to provide accurate prognostic and predictive information to patients is becoming increasingly important as clinicians enter an era of personalized medicine. For a disease as heterogeneous as epithelial ovarian cancer, conventional algorithms become too complex for routine clinical use. This study therefore investigated the potential for an artificial intelligence model to provide this information and compared it with conventional statistical approaches. The authors created a database comprising 668 cases of epithelial ovarian cancer during a 10-year period and collected data routinely available in a clinical environment. They also collected survival data for all the patients, then constructed an artificial intelligence model capable of comparing a variety of algorithms and classifiers alongside conventional statistical approaches such as logistic regression. The model was used to predict overall survival and demonstrated that an artificial neural network (ANN) algorithm was capable of predicting survival with high accuracy (93 %) and an area under the curve (AUC) of 0.74 and that this outperformed logistic regression. The model also was used to predict the outcome of surgery and again showed that ANN could predict outcome (complete/optimal cytoreduction vs. suboptimal cytoreduction) with 77 % accuracy and an AUC of 0.73. These data are encouraging and demonstrate that artificial intelligence systems may have a role in providing prognostic and predictive data for patients. The performance of these systems likely will improve with increasing data set size, and this needs further investigation.

Comparison of the Mortality Probability Admission Model III, National Quality Forum, and Acute Physiology and Chronic Health Evaluation IV hospital mortality models: implications for national benchmarking*.

PubMed

Kramer, Andrew A; Higgins, Thomas L; Zimmerman, Jack E

2014-03-01

To examine the accuracy of the original Mortality Probability Admission Model III, ICU Outcomes Model/National Quality Forum modification of Mortality Probability Admission Model III, and Acute Physiology and Chronic Health Evaluation IVa models for comparing observed and risk-adjusted hospital mortality predictions. Retrospective paired analyses of day 1 hospital mortality predictions using three prognostic models. Fifty-five ICUs at 38 U.S. hospitals from January 2008 to December 2012. Among 174,001 intensive care admissions, 109,926 met model inclusion criteria and 55,304 had data for mortality prediction using all three models. None. We compared patient exclusions and the discrimination, calibration, and accuracy for each model. Acute Physiology and Chronic Health Evaluation IVa excluded 10.7% of all patients, ICU Outcomes Model/National Quality Forum 20.1%, and Mortality Probability Admission Model III 24.1%. Discrimination of Acute Physiology and Chronic Health Evaluation IVa was superior with area under receiver operating curve (0.88) compared with Mortality Probability Admission Model III (0.81) and ICU Outcomes Model/National Quality Forum (0.80). Acute Physiology and Chronic Health Evaluation IVa was better calibrated (lowest Hosmer-Lemeshow statistic). The accuracy of Acute Physiology and Chronic Health Evaluation IVa was superior (adjusted Brier score = 31.0%) to that for Mortality Probability Admission Model III (16.1%) and ICU Outcomes Model/National Quality Forum (17.8%). Compared with observed mortality, Acute Physiology and Chronic Health Evaluation IVa overpredicted mortality by 1.5% and Mortality Probability Admission Model III by 3.1%; ICU Outcomes Model/National Quality Forum underpredicted mortality by 1.2%. Calibration curves showed that Acute Physiology and Chronic Health Evaluation performed well over the entire risk range, unlike the Mortality Probability Admission Model and ICU Outcomes Model/National Quality Forum models. Acute Physiology and Chronic Health Evaluation IVa had better accuracy within patient subgroups and for specific admission diagnoses. Acute Physiology and Chronic Health Evaluation IVa offered the best discrimination and calibration on a large common dataset and excluded fewer patients than Mortality Probability Admission Model III or ICU Outcomes Model/National Quality Forum. The choice of ICU performance benchmarks should be based on a comparison of model accuracy using data for identical patients.

Predicting susceptibility of white fir during a drought-associated outbreak of the fir engraver, Scolytus centralis, in California

Treesearch

G.T. Ferrell; W.J. Otrosina; C.J. DeMars

1994-01-01

Phenotypic traits were compared with a vigor (growth efficiency) index for accuracy in predicting susceptibility of white fir, Abies concolor (Gord. & Glend.) Lindl., during a drought-associated outbreak of the fir engraver, Scolytus centralis LeC., in the central Sierra Nevada at Lake Tahoe, California.Predictor variables were estimated for 633 firs in six forest...

Building Energy Simulation Test for Existing Homes (BESTEST-EX) (Presentation)

DOE Office of Scientific and Technical Information (OSTI.GOV)

Judkoff, R.; Neymark, J.; Polly, B.

2011-12-01

This presentation discusses the goals of NREL Analysis Accuracy R&D; BESTEST-EX goals; what BESTEST-EX is; how it works; 'Building Physics' cases; 'Building Physics' reference results; 'utility bill calibration' cases; limitations and potential future work. Goals of NREL Analysis Accuracy R&D are: (1) Provide industry with the tools and technical information needed to improve the accuracy and consistency of analysis methods; (2) Reduce the risks associated with purchasing, financing, and selling energy efficiency upgrades; and (3) Enhance software and input collection methods considering impacts on accuracy, cost, and time of energy assessments. BESTEST-EX Goals are: (1) Test software predictions of retrofitmore » energy savings in existing homes; (2) Ensure building physics calculations and utility bill calibration procedures perform up to a minimum standard; and (3) Quantify impact of uncertainties in input audit data and occupant behavior. BESTEST-EX is a repeatable procedure that tests how well audit software predictions compare to the current state of the art in building energy simulation. There is no direct truth standard. However, reference software have been subjected to validation testing, including comparisons with empirical data.« less

Improving risk prediction accuracy for new soldiers in the U.S. Army by adding self-report survey data to administrative data.

PubMed

Bernecker, Samantha L; Rosellini, Anthony J; Nock, Matthew K; Chiu, Wai Tat; Gutierrez, Peter M; Hwang, Irving; Joiner, Thomas E; Naifeh, James A; Sampson, Nancy A; Zaslavsky, Alan M; Stein, Murray B; Ursano, Robert J; Kessler, Ronald C

2018-04-03

High rates of mental disorders, suicidality, and interpersonal violence early in the military career have raised interest in implementing preventive interventions with high-risk new enlistees. The Army Study to Assess Risk and Resilience in Servicemembers (STARRS) developed risk-targeting systems for these outcomes based on machine learning methods using administrative data predictors. However, administrative data omit many risk factors, raising the question whether risk targeting could be improved by adding self-report survey data to prediction models. If so, the Army may gain from routinely administering surveys that assess additional risk factors. The STARRS New Soldier Survey was administered to 21,790 Regular Army soldiers who agreed to have survey data linked to administrative records. As reported previously, machine learning models using administrative data as predictors found that small proportions of high-risk soldiers accounted for high proportions of negative outcomes. Other machine learning models using self-report survey data as predictors were developed previously for three of these outcomes: major physical violence and sexual violence perpetration among men and sexual violence victimization among women. Here we examined the extent to which this survey information increases prediction accuracy, over models based solely on administrative data, for those three outcomes. We used discrete-time survival analysis to estimate a series of models predicting first occurrence, assessing how model fit improved and concentration of risk increased when adding the predicted risk score based on survey data to the predicted risk score based on administrative data. The addition of survey data improved prediction significantly for all outcomes. In the most extreme case, the percentage of reported sexual violence victimization among the 5% of female soldiers with highest predicted risk increased from 17.5% using only administrative predictors to 29.4% adding survey predictors, a 67.9% proportional increase in prediction accuracy. Other proportional increases in concentration of risk ranged from 4.8% to 49.5% (median = 26.0%). Data from an ongoing New Soldier Survey could substantially improve accuracy of risk models compared to models based exclusively on administrative predictors. Depending upon the characteristics of interventions used, the increase in targeting accuracy from survey data might offset survey administration costs.

Noninvasive scoring algorithm to identify significant liver fibrosis among treatment-naive chronic hepatitis C patients.

PubMed

Koller, Tomas; Kollerova, Jana; Huorka, Martin; Meciarova, Iveta; Payer, Juraj

2014-10-01

Staging for liver fibrosis is recommended in the management of hepatitis C as an argument for treatment priority. Our aim was to construct a noninvasive algorithm to predict the significant liver fibrosis (SLF) using common biochemical markers and compare it with some existing models. The study group included 104 consecutive cases; SLF was defined as Ishak fibrosis stage greater than 2. The patient population was assigned randomly to the training and the validation groups of 52 cases each. The training group was used to construct the algorithm from parameters with the best predictive value. Each parameter was assigned a score that was added to the noninvasive fibrosis score (NFS). The accuracy of NFS in predicting SLF was tested in the validation group and compared with APRI, FIB4, and Forns models. Our algorithm used age, alkaline phosphatase, ferritin, APRI, α2 macroglobulin, and insulin and the NFS ranged from -4 to 5. The probability of SLF was 2.6 versus 77.1% in NFS<0 and NFS>0, leaving NFS=0 in a gray zone (29.8% of cases). The area under the receiver operating curve was 0.895 and 0.886, with a specificity, sensitivity, and diagnostic accuracy of 85.1, 92.3, and 87.5% versus 77.8, 100, and 87.9% for the training and the validation group. In comparison, the area under the receiver operating curve for APRI=0.810, FIB4=0.781, and Forns=0.703 with a diagnostic accuracy of 83.9, 72.3, and 62% and gray zone cases in 46.15, 37.5, and 44.2%. We devised an algorithm to calculate the NFS to predict SLF with good accuracy, fewer cases in the gray zone, and a straightforward clinical interpretation. NFS could be used for the initial evaluation of the treatment priority.

Comparison of [{sup 11}C]choline Positron Emission Tomography With T2- and Diffusion-Weighted Magnetic Resonance Imaging for Delineating Malignant Intraprostatic Lesions

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chang, Joe H.; University of Melbourne, Victoria; Lim Joon, Daryl

2015-06-01

Purpose: The purpose of this study was to compare the accuracy of [{sup 11}C]choline positron emission tomography (CHOL-PET) with that of the combination of T2-weighted and diffusion-weighted (T2W/DW) magnetic resonance imaging (MRI) for delineating malignant intraprostatic lesions (IPLs) for guiding focal therapies and to investigate factors predicting the accuracy of CHOL-PET. Methods and Materials: This study included 21 patients who underwent CHOL-PET and T2W/DW MRI prior to radical prostatectomy. Two observers manually delineated IPL contours for each scan, and automatic IPL contours were generated on CHOL-PET based on varying proportions of the maximum standardized uptake value (SUV). IPLs identified onmore » prostatectomy specimens defined reference standard contours. The imaging-based contours were compared with the reference standard contours using Dice similarity coefficient (DSC), and sensitivity and specificity values. Factors that could potentially predict the DSC of the best contouring method were analyzed using linear models. Results: The best automatic contouring method, 60% of the maximum SUV (SUV{sub 60}) , had similar correlations (DSC: 0.59) with the manual PET contours (DSC: 0.52, P=.127) and significantly better correlations than the manual MRI contours (DSC: 0.37, P<.001). The sensitivity and specificity values were 72% and 71% for SUV{sub 60}; 53% and 86% for PET manual contouring; and 28% and 92% for MRI manual contouring. The tumor volume and transition zone pattern could independently predict the accuracy of CHOL-PET. Conclusions: CHOL-PET is superior to the combination of T2W/DW MRI for delineating IPLs. The accuracy of CHOL-PET is insufficient for gland-sparing focal therapies but may be accurate enough for focal boost therapies. The transition zone pattern is a new classification that may predict how well CHOL-PET delineates IPLs.« less

Optimum location of external markers using feature selection algorithms for real‐time tumor tracking in external‐beam radiotherapy: a virtual phantom study

PubMed Central

Nankali, Saber; Miandoab, Payam Samadi; Baghizadeh, Amin

2016-01-01

In external‐beam radiotherapy, using external markers is one of the most reliable tools to predict tumor position, in clinical applications. The main challenge in this approach is tumor motion tracking with highest accuracy that depends heavily on external markers location, and this issue is the objective of this study. Four commercially available feature selection algorithms entitled 1) Correlation‐based Feature Selection, 2) Classifier, 3) Principal Components, and 4) Relief were proposed to find optimum location of external markers in combination with two “Genetic” and “Ranker” searching procedures. The performance of these algorithms has been evaluated using four‐dimensional extended cardiac‐torso anthropomorphic phantom. Six tumors in lung, three tumors in liver, and 49 points on the thorax surface were taken into account to simulate internal and external motions, respectively. The root mean square error of an adaptive neuro‐fuzzy inference system (ANFIS) as prediction model was considered as metric for quantitatively evaluating the performance of proposed feature selection algorithms. To do this, the thorax surface region was divided into nine smaller segments and predefined tumors motion was predicted by ANFIS using external motion data of given markers at each small segment, separately. Our comparative results showed that all feature selection algorithms can reasonably select specific external markers from those segments where the root mean square error of the ANFIS model is minimum. Moreover, the performance accuracy of proposed feature selection algorithms was compared, separately. For this, each tumor motion was predicted using motion data of those external markers selected by each feature selection algorithm. Duncan statistical test, followed by F‐test, on final results reflected that all proposed feature selection algorithms have the same performance accuracy for lung tumors. But for liver tumors, a correlation‐based feature selection algorithm, in combination with a genetic search algorithm, proved to yield best performance accuracy for selecting optimum markers. PACS numbers: 87.55.km, 87.56.Fc PMID:26894358

Optimum location of external markers using feature selection algorithms for real-time tumor tracking in external-beam radiotherapy: a virtual phantom study.

PubMed

Nankali, Saber; Torshabi, Ahmad Esmaili; Miandoab, Payam Samadi; Baghizadeh, Amin

2016-01-08

In external-beam radiotherapy, using external markers is one of the most reliable tools to predict tumor position, in clinical applications. The main challenge in this approach is tumor motion tracking with highest accuracy that depends heavily on external markers location, and this issue is the objective of this study. Four commercially available feature selection algorithms entitled 1) Correlation-based Feature Selection, 2) Classifier, 3) Principal Components, and 4) Relief were proposed to find optimum location of external markers in combination with two "Genetic" and "Ranker" searching procedures. The performance of these algorithms has been evaluated using four-dimensional extended cardiac-torso anthropomorphic phantom. Six tumors in lung, three tumors in liver, and 49 points on the thorax surface were taken into account to simulate internal and external motions, respectively. The root mean square error of an adaptive neuro-fuzzy inference system (ANFIS) as prediction model was considered as metric for quantitatively evaluating the performance of proposed feature selection algorithms. To do this, the thorax surface region was divided into nine smaller segments and predefined tumors motion was predicted by ANFIS using external motion data of given markers at each small segment, separately. Our comparative results showed that all feature selection algorithms can reasonably select specific external markers from those segments where the root mean square error of the ANFIS model is minimum. Moreover, the performance accuracy of proposed feature selection algorithms was compared, separately. For this, each tumor motion was predicted using motion data of those external markers selected by each feature selection algorithm. Duncan statistical test, followed by F-test, on final results reflected that all proposed feature selection algorithms have the same performance accuracy for lung tumors. But for liver tumors, a correlation-based feature selection algorithm, in combination with a genetic search algorithm, proved to yield best performance accuracy for selecting optimum markers.

Machine Learning Algorithms Outperform Conventional Regression Models in Predicting Development of Hepatocellular Carcinoma

PubMed Central

Singal, Amit G.; Mukherjee, Ashin; Elmunzer, B. Joseph; Higgins, Peter DR; Lok, Anna S.; Zhu, Ji; Marrero, Jorge A; Waljee, Akbar K

2015-01-01

Background Predictive models for hepatocellular carcinoma (HCC) have been limited by modest accuracy and lack of validation. Machine learning algorithms offer a novel methodology, which may improve HCC risk prognostication among patients with cirrhosis. Our study's aim was to develop and compare predictive models for HCC development among cirrhotic patients, using conventional regression analysis and machine learning algorithms. Methods We enrolled 442 patients with Child A or B cirrhosis at the University of Michigan between January 2004 and September 2006 (UM cohort) and prospectively followed them until HCC development, liver transplantation, death, or study termination. Regression analysis and machine learning algorithms were used to construct predictive models for HCC development, which were tested on an independent validation cohort from the Hepatitis C Antiviral Long-term Treatment against Cirrhosis (HALT-C) Trial. Both models were also compared to the previously published HALT-C model. Discrimination was assessed using receiver operating characteristic curve analysis and diagnostic accuracy was assessed with net reclassification improvement and integrated discrimination improvement statistics. Results After a median follow-up of 3.5 years, 41 patients developed HCC. The UM regression model had a c-statistic of 0.61 (95%CI 0.56-0.67), whereas the machine learning algorithm had a c-statistic of 0.64 (95%CI 0.60–0.69) in the validation cohort. The machine learning algorithm had significantly better diagnostic accuracy as assessed by net reclassification improvement (p<0.001) and integrated discrimination improvement (p=0.04). The HALT-C model had a c-statistic of 0.60 (95%CI 0.50-0.70) in the validation cohort and was outperformed by the machine learning algorithm (p=0.047). Conclusion Machine learning algorithms improve the accuracy of risk stratifying patients with cirrhosis and can be used to accurately identify patients at high-risk for developing HCC. PMID:24169273

Genomic prediction in a nuclear population of layers using single-step models.

PubMed

Yan, Yiyuan; Wu, Guiqin; Liu, Aiqiao; Sun, Congjiao; Han, Wenpeng; Li, Guangqi; Yang, Ning

2018-02-01

Single-step genomic prediction method has been proposed to improve the accuracy of genomic prediction by incorporating information of both genotyped and ungenotyped animals. The objective of this study is to compare the prediction performance of single-step model with a 2-step models and the pedigree-based models in a nuclear population of layers. A total of 1,344 chickens across 4 generations were genotyped by a 600 K SNP chip. Four traits were analyzed, i.e., body weight at 28 wk (BW28), egg weight at 28 wk (EW28), laying rate at 38 wk (LR38), and Haugh unit at 36 wk (HU36). In predicting offsprings, individuals from generation 1 to 3 were used as training data and females from generation 4 were used as validation set. The accuracies of predicted breeding values by pedigree BLUP (PBLUP), genomic BLUP (GBLUP), SSGBLUP and single-step blending (SSBlending) were compared for both genotyped and ungenotyped individuals. For genotyped females, GBLUP performed no better than PBLUP because of the small size of training data, while the 2 single-step models predicted more accurately than the PBLUP model. The average predictive ability of SSGBLUP and SSBlending were 16.0% and 10.8% higher than the PBLUP model across traits, respectively. Furthermore, the predictive abilities for ungenotyped individuals were also enhanced. The average improvements of prediction abilities were 5.9% and 1.5% for SSGBLUP and SSBlending model, respectively. It was concluded that single-step models, especially the SSGBLUP model, can yield more accurate prediction of genetic merits and are preferable for practical implementation of genomic selection in layers. © 2017 Poultry Science Association Inc.

The accuracy of new wheelchair users' predictions about their future wheelchair use.

PubMed

Hoenig, Helen; Griffiths, Patricia; Ganesh, Shanti; Caves, Kevin; Harris, Frances

2012-06-01

This study examined the accuracy of new wheelchair user predictions about their future wheelchair use. This was a prospective cohort study of 84 community-dwelling veterans provided a new manual wheelchair. The association between predicted and actual wheelchair use was strong at 3 mos (ϕ coefficient = 0.56), with 90% of those who anticipated using the wheelchair at 3 mos still using it (i.e., positive predictive value = 0.96) and 60% of those who anticipated not using it indeed no longer using the wheelchair (i.e., negative predictive value = 0.60, overall accuracy = 0.92). Predictive accuracy diminished over time, with overall accuracy declining from 0.92 at 3 mos to 0.66 at 6 mos. At all time points, and for all types of use, patients better predicted use as opposed to disuse, with correspondingly higher positive than negative predictive values. Accuracy of prediction of use in specific indoor and outdoor locations varied according to location. This study demonstrates the importance of better understanding the potential mismatch between the anticipated and actual patterns of wheelchair use. The findings suggest that users can be relied upon to accurately predict their basic wheelchair-related needs in the short-term. Further exploration is needed to identify characteristics that will aid users and their providers in more accurately predicting mobility needs for the long-term.

Prediction of the spectral reflectance of laser-generated color prints by combination of an optical model and learning methods.

PubMed

Nébouy, David; Hébert, Mathieu; Fournel, Thierry; Larina, Nina; Lesur, Jean-Luc

2015-09-01

Recent color printing technologies based on the principle of revealing colors on pre-functionalized achromatic supports by laser irradiation offer advanced functionalities, especially for security applications. However, for such technologies, the color prediction is challenging, compared to classic ink-transfer printing systems. The spectral properties of the coloring materials modified by the lasers are not precisely known and may strongly vary, depending on the laser settings, in a nonlinear manner. We show in this study, through the example of the color laser marking (CLM) technology, based on laser bleaching of a mixture of pigments, that the combination of an adapted optical reflectance model and learning methods to get the model's parameters enables prediction of the spectral reflectance of any printable color with rather good accuracy. Even though the pigment mixture is formulated from three colored pigments, an analysis of the dimensionality of the spectral space generated by CLM printing, thanks to a principal component analysis decomposition, shows that at least four spectral primaries are needed for accurate spectral reflectance predictions. A polynomial interpolation is then used to relate RGB laser intensities with virtual coordinates of new basis vectors. By studying the influence of the number of calibration patches on the prediction accuracy, we can conclude that a reasonable number of 130 patches are enough to achieve good accuracy in this application.

An evaluation of the accuracy of the Federal Transit Administration approved, groundborne noise and vibration prediction model for rail transit systems; a case study for a new subway line using post construction, transit operation measurements

NASA Astrophysics Data System (ADS)

Carman, Richard A.; Reyes, Carlos H.

2005-09-01

The groundborne noise and vibration model developed by Nelson and Saurenman in 1984, now recognized by the Federal Transit Administration as the approved model for new transit system facilities, is entering its third decade of use by engineers and consultants in the transit industry. The accuracy of the model has been explored in the past (e.g., Carman and Wolfe). New data obtained for a recently completed extension to a major heavy rail transit system provides an opportunity to evaluate the accuracy of the model once more. During the engineering design phase of the project, noise and vibration predictions were performed for numerous buildings adjacent to the new subway line. The values predicted by the model were used to determine the need for and type of noise and/or vibration control measures. After the start of transit operations on the new line, noise and vibration measurements were made inside several of the buildings to determine whether the criteria were in fact achieved. The measurement results are compared with the values predicted by the model. The predicted and measured, overall noise and vibration levels show very good agreement, whereas the spectral comparisons indicate some differences. Possible reasons for these differences are offered.

Accuracy of three-dimensional multislice view Doppler in diagnosis of morbid adherent placenta

PubMed Central

Abdel Moniem, Alaa M.; Ibrahim, Ahmed; Akl, Sherif A.; Aboul-Enen, Loay; Abdelazim, Ibrahim A.

2015-01-01

Objective To detect the accuracy of the three-dimensional multislice view (3D MSV) Doppler in the diagnosis of morbid adherent placenta (MAP). Material and Methods Fifty pregnant women at ≥28 weeks gestation with suspected MAP were included in this prospective study. Two dimensional (2D) trans-abdominal gray-scale ultrasound scan was performed for the subjects to confirm the gestational age, placental location, and findings suggestive of MAP, followed by the 3D power Doppler and then the 3D MSV Doppler to confirm the diagnosis of MAP. Intraoperative findings and histopathology results of removed uteri in cases managed by emergency hysterectomy were compared with preoperative sonographic findings to detect the accuracy of the 3D MSV Doppler in the diagnosis of MAP. Results The 3D MSV Doppler increased the accuracy and predictive values of the diagnostic criteria of MAP compared with the 3D power Doppler. The sensitivity and negative predictive value (NPV) (79.6% and 82.2%, respectively) of crowded vessels over the peripheral sub-placental zone to detect difficult placental separation and considerable intraoperative blood loss in cases of MAP using the 3D power Doppler was increased to 82.6% and 84%, respectively, using the 3D MSV Doppler. In addition, the sensitivity, specificity, and positive predictive value (PPV) (90.9%, 68.8%, and 47%, respectively) of the disruption of the uterine serosa-bladder interface for the detection of emergency hysterectomy in cases of MAP using the 3D power Doppler was increased to 100%, 71.8%, and 50%, respectively, using the 3D MSV Doppler. Conclusion The 3D MSV Doppler is a useful adjunctive tool to the 3D power Doppler or color Doppler to refine the diagnosis of MAP. PMID:26401104

Meta-analytical prognostic accuracy of the Comprehensive Assessment of at Risk Mental States (CAARMS): The need for refined prediction.

PubMed

Oliver, D; Kotlicka-Antczak, M; Minichino, A; Spada, G; McGuire, P; Fusar-Poli, P

2018-03-01

Primary indicated prevention is reliant on accurate tools to predict the onset of psychosis. The gold standard assessment for detecting individuals at clinical high risk (CHR-P) for psychosis in the UK and many other countries is the Comprehensive Assessment for At Risk Mental States (CAARMS). While the prognostic accuracy of CHR-P instruments has been assessed in general, this is the first study to specifically analyse that of the CAARMS. As such, the CAARMS was used as the index test, with the reference index being psychosis onset within 2 years. Six independent studies were analysed using MIDAS (STATA 14), with a total of 1876 help-seeking subjects referred to high risk services (CHR-P+: n=892; CHR-P-: n=984). Area under the curve (AUC), summary receiver operating characteristic curves (SROC), quality assessment, likelihood ratios, and probability modified plots were computed, along with sensitivity analyses and meta-regressions. The current meta-analysis confirmed that the 2-year prognostic accuracy of the CAARMS is only acceptable (AUC=0.79 95% CI: 0.75-0.83) and not outstanding as previously reported. In particular, specificity was poor. Sensitivity of the CAARMS is inferior compared to the SIPS, while specificity is comparably low. However, due to the difficulties in performing these types of studies, power in this meta-analysis was low. These results indicate that refining and improving the prognostic accuracy of the CAARMS should be the mainstream area of research for the next era. Avenues of prediction improvement are critically discussed and presented to better benefit patients and improve outcomes of first episode psychosis. Copyright © 2017 The Authors. Published by Elsevier Masson SAS.. All rights reserved.

Using artificial intelligence to predict the risk for posterior capsule opacification after phacoemulsification.

PubMed

Mohammadi, Seyed-Farzad; Sabbaghi, Mostafa; Z-Mehrjardi, Hadi; Hashemi, Hassan; Alizadeh, Somayeh; Majdi, Mercede; Taee, Farough

2012-03-01

To apply artificial intelligence models to predict the occurrence of posterior capsule opacification (PCO) after phacoemulsification. Farabi Eye Hospital, Tehran, Iran. Clinical-based cross-sectional study. The posterior capsule status of eyes operated on for age-related cataract and the need for laser capsulotomy were determined. After a literature review, data polishing, and expert consultation, 10 input variables were selected. The QUEST algorithm was used to develop a decision tree. Three back-propagation artificial neural networks were constructed with 4, 20, and 40 neurons in 2 hidden layers and trained with the same transfer functions (log-sigmoid and linear transfer) and training protocol with randomly selected eyes. They were then tested on the remaining eyes and the networks compared for their performance. Performance indices were used to compare resultant models with the results of logistic regression analysis. The models were trained using 282 randomly selected eyes and then tested using 70 eyes. Laser capsulotomy for clinically significant PCO was indicated or had been performed 2 years postoperatively in 40 eyes. A sample decision tree was produced with accuracy of 50% (likelihood ratio 0.8). The best artificial neural network, which showed 87% accuracy and a positive likelihood ratio of 8, was achieved with 40 neurons. The area under the receiver-operating-characteristic curve was 0.71. In comparison, logistic regression reached accuracy of 80%; however, the likelihood ratio was not measurable because the sensitivity was zero. A prototype artificial neural network was developed that predicted posterior capsule status (requiring capsulotomy) with reasonable accuracy. No author has a financial or proprietary interest in any material or method mentioned. Copyright © 2012 ASCRS and ESCRS. Published by Elsevier Inc. All rights reserved.

Direct comparison of the hygroscopic properties of ammonium sulfate and sodium chloride aerosol at relative humidities approaching saturation.

PubMed

Walker, Jim S; Wills, Jon B; Reid, Jonathan P; Wang, Liangyu; Topping, David O; Butler, Jason R; Zhang, Yun-Hong

2010-12-09

Holographic optical tweezers are used to make comparative measurements of the hygroscopic properties of single component aqueous aerosol containing sodium chloride and ammonium sulfate over a range of relative humidity from 84% to 96%. The change in RH over the course of the experiment is monitored precisely using a sodium chloride probe droplet with accuracy better than ±0.09%. The measurements are used to assess the accuracy of thermodynamic treatments of the relationship between water activity and solute mass fraction with particular attention focused on the dilute solute limit approaching saturation vapor pressure. The consistency of the frequently used Clegg-Brimblecombe-Wexler (CBW) treatment for predicting the hygroscopic properties of sodium chloride and ammonium sulfate aerosol is confirmed. Measurements of the equilibrium size of ammonium sulfate aerosol are found to agree with predictions to within an uncertainty of ±0.2%. Given the accuracy of treating equilibrium composition, the inconsistencies highlighted in recent calibration measurements of critical supersaturations of sodium chloride and ammonium sulfate aerosol cannot be attributed to uncertainties associated with the thermodynamic predictions and must have an alternative origin. It is concluded that the CBW treatment can allow the critical supersaturation to be estimated for sodium chloride and ammonium sulfate aerosol with an accuracy of better than ±0.002% in RH. This corresponds to an uncertainty of ≤1% in the critical supersaturation for typical supersaturations of 0.2% and above. This supports the view that these systems can be used to accurately calibrate instruments that measure cloud condensation nuclei concentrations at selected supersaturations. These measurements represent the first study in which the equilibrium properties of two particles of chemically distinct composition have been compared simultaneously and directly alongside each other in the same environment.

Comparison of Adjacency and Distance-Based Approaches for Spatial Analysis of Multimodal Traffic Crash Data

NASA Astrophysics Data System (ADS)

Gill, G.; Sakrani, T.; Cheng, W.; Zhou, J.

2017-09-01

Many studies have utilized the spatial correlations among traffic crash data to develop crash prediction models with the aim to investigate the influential factors or predict crash counts at different sites. The spatial correlation have been observed to account for heterogeneity in different forms of weight matrices which improves the estimation performance of models. But very rarely have the weight matrices been compared for the prediction accuracy for estimation of crash counts. This study was targeted at the comparison of two different approaches for modelling the spatial correlations among crash data at macro-level (County). Multivariate Full Bayesian crash prediction models were developed using Decay-50 (distance-based) and Queen-1 (adjacency-based) weight matrices for simultaneous estimation crash counts of four different modes: vehicle, motorcycle, bike, and pedestrian. The goodness-of-fit and different criteria for accuracy at prediction of crash count reveled the superiority of Decay-50 over Queen-1. Decay-50 was essentially different from Queen-1 with the selection of neighbors and more robust spatial weight structure which rendered the flexibility to accommodate the spatially correlated crash data. The consistently better performance of Decay-50 at prediction accuracy further bolstered its superiority. Although the data collection efforts to gather centroid distance among counties for Decay-50 may appear to be a downside, but the model has a significant edge to fit the crash data without losing the simplicity of computation of estimated crash count.

Application and analysis of debris-flow early warning system in Wenchuan earthquake-affected area

NASA Astrophysics Data System (ADS)

Liu, D. L.; Zhang, S. J.; Yang, H. J.; Zhao, L. Q.; Jiang, Y. H.; Tang, D.; Leng, X. P.

2016-02-01

The activities of debris flow (DF) in the Wenchuan earthquake-affected area significantly increased after the earthquake on 12 May 2008. The safety of the lives and property of local people is threatened by DFs. A physics-based early warning system (EWS) for DF forecasting was developed and applied in this earthquake area. This paper introduces an application of the system in the Wenchuan earthquake-affected area and analyzes the prediction results via a comparison to the DF events triggered by the strong rainfall events reported by the local government. The prediction accuracy and efficiency was first compared with a contribution-factor-based system currently used by the weather bureau of Sichuan province. The storm on 17 August 2012 was used as a case study for this comparison. The comparison shows that the false negative rate and false positive rate of the new system is, respectively, 19 and 21 % lower than the system based on the contribution factors. Consequently, the prediction accuracy is obviously higher than the system based on the contribution factors with a higher operational efficiency. On the invitation of the weather bureau of Sichuan province, the authors upgraded their prediction system of DF by using this new system before the monsoon of Wenchuan earthquake-affected area in 2013. Two prediction cases on 9 July 2013 and 10 July 2014 were chosen to further demonstrate that the new EWS has high stability, efficiency, and prediction accuracy.

Mortality, morbidity and refractoriness prediction in status epilepticus: Comparison of STESS and EMSE scores.

PubMed

Giovannini, Giada; Monti, Giulia; Tondelli, Manuela; Marudi, Andrea; Valzania, Franco; Leitinger, Markus; Trinka, Eugen; Meletti, Stefano

2017-03-01

Status epilepticus (SE) is a neurological emergency, characterized by high short-term morbidity and mortality. We evaluated and compared two scores that have been developed to evaluate status epilepticus prognosis: STESS (Status Epilepticus Severity Score) and EMSE (Epidemiology based Mortality score in Status Epilepticus). A prospective observational study was performed on consecutive patients with SE admitted between September 2013 and August 2015. Demographics, clinical variables, STESS-3 and -4, and EMSE-64 scores were calculated for each patient at baseline. SE drug response, 30-day mortality and morbidity were the outcomes measure. 162 episodes of SE were observed: 69% had a STESS ≥3; 34% had a STESS ≥4; 51% patients had an EMSE ≥64. The 30-days mortality was 31.5%: EMSE-64 showed greater negative predictive value (NPV) (97.5%), positive predictive value (PPV) (59.8%) and accuracy in the prediction of death than STESS-3 and STESS-4 (p<0.001). At 30 days, the clinical condition had deteriorated in 59% of the cases: EMSE-64 showed greater NPV (71.3%), PPV (87.8%) and accuracy than STESS-3 and STESS-4 (p<0.001) in the prediction of this outcome. In 23% of all cases, status epilepticus proved refractory to non-anaesthetic treatment. All three scales showed a high NPV (EMSE-64: 87.3%; STESS-4: 89.4%; STESS-3: 87.5%) but a low PPV (EMSE-64: 40.9%; STESS-4: 52.9%; STESS-3: 32%) for the prediction of refractoriness to first and second line drugs. This means that accuracy for the prediction of refractoriness was equally poor for all scales. EMSE-64 appears superior to STESS-3 and STESS-4 in the prediction of 30-days mortality and morbidity. All scales showed poor accuracy in the prediction of response to first and second line antiepileptic drugs. At present, there are no reliable scores capable of predicting treatment responsiveness. Copyright © 2017 British Epilepsy Association. Published by Elsevier Ltd. All rights reserved.

Decoding the Traumatic Memory among Women with PTSD: Implications for Neurocircuitry Models of PTSD and Real-Time fMRI Neurofeedback

PubMed Central

Cisler, Josh M.; Bush, Keith; James, G. Andrew; Smitherman, Sonet; Kilts, Clinton D.

2015-01-01

Posttraumatic Stress Disorder (PTSD) is characterized by intrusive recall of the traumatic memory. While numerous studies have investigated the neural processing mechanisms engaged during trauma memory recall in PTSD, these analyses have only focused on group-level contrasts that reveal little about the predictive validity of the identified brain regions. By contrast, a multivariate pattern analysis (MVPA) approach towards identifying the neural mechanisms engaged during trauma memory recall would entail testing whether a multivariate set of brain regions is reliably predictive of (i.e., discriminates) whether an individual is engaging in trauma or non-trauma memory recall. Here, we use a MVPA approach to test 1) whether trauma memory vs neutral memory recall can be predicted reliably using a multivariate set of brain regions among women with PTSD related to assaultive violence exposure (N=16), 2) the methodological parameters (e.g., spatial smoothing, number of memory recall repetitions, etc.) that optimize classification accuracy and reproducibility of the feature weight spatial maps, and 3) the correspondence between brain regions that discriminate trauma memory recall and the brain regions predicted by neurocircuitry models of PTSD. Cross-validation classification accuracy was significantly above chance for all methodological permutations tested; mean accuracy across participants was 76% for the methodological parameters selected as optimal for both efficiency and accuracy. Classification accuracy was significantly better for a voxel-wise approach relative to voxels within restricted regions-of-interest (ROIs); classification accuracy did not differ when using PTSD-related ROIs compared to randomly generated ROIs. ROI-based analyses suggested the reliable involvement of the left hippocampus in discriminating memory recall across participants and that the contribution of the left amygdala to the decision function was dependent upon PTSD symptom severity. These results have methodological implications for real-time fMRI neurofeedback of the trauma memory in PTSD and conceptual implications for neurocircuitry models of PTSD that attempt to explain core neural processing mechanisms mediating PTSD. PMID:26241958

Decoding the Traumatic Memory among Women with PTSD: Implications for Neurocircuitry Models of PTSD and Real-Time fMRI Neurofeedback.

PubMed

Cisler, Josh M; Bush, Keith; James, G Andrew; Smitherman, Sonet; Kilts, Clinton D

2015-01-01

Posttraumatic Stress Disorder (PTSD) is characterized by intrusive recall of the traumatic memory. While numerous studies have investigated the neural processing mechanisms engaged during trauma memory recall in PTSD, these analyses have only focused on group-level contrasts that reveal little about the predictive validity of the identified brain regions. By contrast, a multivariate pattern analysis (MVPA) approach towards identifying the neural mechanisms engaged during trauma memory recall would entail testing whether a multivariate set of brain regions is reliably predictive of (i.e., discriminates) whether an individual is engaging in trauma or non-trauma memory recall. Here, we use a MVPA approach to test 1) whether trauma memory vs neutral memory recall can be predicted reliably using a multivariate set of brain regions among women with PTSD related to assaultive violence exposure (N=16), 2) the methodological parameters (e.g., spatial smoothing, number of memory recall repetitions, etc.) that optimize classification accuracy and reproducibility of the feature weight spatial maps, and 3) the correspondence between brain regions that discriminate trauma memory recall and the brain regions predicted by neurocircuitry models of PTSD. Cross-validation classification accuracy was significantly above chance for all methodological permutations tested; mean accuracy across participants was 76% for the methodological parameters selected as optimal for both efficiency and accuracy. Classification accuracy was significantly better for a voxel-wise approach relative to voxels within restricted regions-of-interest (ROIs); classification accuracy did not differ when using PTSD-related ROIs compared to randomly generated ROIs. ROI-based analyses suggested the reliable involvement of the left hippocampus in discriminating memory recall across participants and that the contribution of the left amygdala to the decision function was dependent upon PTSD symptom severity. These results have methodological implications for real-time fMRI neurofeedback of the trauma memory in PTSD and conceptual implications for neurocircuitry models of PTSD that attempt to explain core neural processing mechanisms mediating PTSD.

Spindle Thermal Error Optimization Modeling of a Five-axis Machine Tool

NASA Astrophysics Data System (ADS)

Guo, Qianjian; Fan, Shuo; Xu, Rufeng; Cheng, Xiang; Zhao, Guoyong; Yang, Jianguo

2017-05-01

Aiming at the problem of low machining accuracy and uncontrollable thermal errors of NC machine tools, spindle thermal error measurement, modeling and compensation of a two turntable five-axis machine tool are researched. Measurement experiment of heat sources and thermal errors are carried out, and GRA(grey relational analysis) method is introduced into the selection of temperature variables used for thermal error modeling. In order to analyze the influence of different heat sources on spindle thermal errors, an ANN (artificial neural network) model is presented, and ABC(artificial bee colony) algorithm is introduced to train the link weights of ANN, a new ABC-NN(Artificial bee colony-based neural network) modeling method is proposed and used in the prediction of spindle thermal errors. In order to test the prediction performance of ABC-NN model, an experiment system is developed, the prediction results of LSR (least squares regression), ANN and ABC-NN are compared with the measurement results of spindle thermal errors. Experiment results show that the prediction accuracy of ABC-NN model is higher than LSR and ANN, and the residual error is smaller than 3 μm, the new modeling method is feasible. The proposed research provides instruction to compensate thermal errors and improve machining accuracy of NC machine tools.

Experimental comparison between speech transmission index, rapid speech transmission index, and speech intelligibility index.

PubMed

Larm, Petra; Hongisto, Valtteri

2006-02-01

During the acoustical design of, e.g., auditoria or open-plan offices, it is important to know how speech can be perceived in various parts of the room. Different objective methods have been developed to measure and predict speech intelligibility, and these have been extensively used in various spaces. In this study, two such methods were compared, the speech transmission index (STI) and the speech intelligibility index (SII). Also the simplification of the STI, the room acoustics speech transmission index (RASTI), was considered. These quantities are all based on determining an apparent speech-to-noise ratio on selected frequency bands and summing them using a specific weighting. For comparison, some data were needed on the possible differences of these methods resulting from the calculation scheme and also measuring equipment. Their prediction accuracy was also of interest. Measurements were made in a laboratory having adjustable noise level and absorption, and in a real auditorium. It was found that the measurement equipment, especially the selection of the loudspeaker, can greatly affect the accuracy of the results. The prediction accuracy of the RASTI was found acceptable, if the input values for the prediction are accurately known, even though the studied space was not ideally diffuse.

Improving Genomic Prediction in Cassava Field Experiments Using Spatial Analysis.

PubMed

Elias, Ani A; Rabbi, Ismail; Kulakow, Peter; Jannink, Jean-Luc

2018-01-04

Cassava ( Manihot esculenta Crantz) is an important staple food in sub-Saharan Africa. Breeding experiments were conducted at the International Institute of Tropical Agriculture in cassava to select elite parents. Taking into account the heterogeneity in the field while evaluating these trials can increase the accuracy in estimation of breeding values. We used an exploratory approach using the parametric spatial kernels Power, Spherical, and Gaussian to determine the best kernel for a given scenario. The spatial kernel was fit simultaneously with a genomic kernel in a genomic selection model. Predictability of these models was tested through a 10-fold cross-validation method repeated five times. The best model was chosen as the one with the lowest prediction root mean squared error compared to that of the base model having no spatial kernel. Results from our real and simulated data studies indicated that predictability can be increased by accounting for spatial variation irrespective of the heritability of the trait. In real data scenarios we observed that the accuracy can be increased by a median value of 3.4%. Through simulations, we showed that a 21% increase in accuracy can be achieved. We also found that Range (row) directional spatial kernels, mostly Gaussian, explained the spatial variance in 71% of the scenarios when spatial correlation was significant. Copyright © 2018 Elias et al.

Mapping water table depth using geophysical and environmental variables.

PubMed

Buchanan, S; Triantafilis, J

2009-01-01

Despite its importance, accurate representation of the spatial distribution of water table depth remains one of the greatest deficiencies in many hydrological investigations. Historically, both inverse distance weighting (IDW) and ordinary kriging (OK) have been used to interpolate depths. These methods, however, have major limitations: namely they require large numbers of measurements to represent the spatial variability of water table depth and they do not represent the variation between measurement points. We address this issue by assessing the benefits of using stepwise multiple linear regression (MLR) with three different ancillary data sets to predict the water table depth at 100-m intervals. The ancillary data sets used are Electromagnetic (EM34 and EM38), gamma radiometric: potassium (K), uranium (eU), thorium (eTh), total count (TC), and morphometric data. Results show that MLR offers significant precision and accuracy benefits over OK and IDW. Inclusion of the morphometric data set yielded the greatest (16%) improvement in prediction accuracy compared with IDW, followed by the electromagnetic data set (5%). Use of the gamma radiometric data set showed no improvement. The greatest improvement, however, resulted when all data sets were combined (37% increase in prediction accuracy over IDW). Significantly, however, the use of MLR also allows for prediction in variations in water table depth between measurement points, which is crucial for land management.

Family-Based Benchmarking of Copy Number Variation Detection Software.

PubMed

Nutsua, Marcel Elie; Fischer, Annegret; Nebel, Almut; Hofmann, Sylvia; Schreiber, Stefan; Krawczak, Michael; Nothnagel, Michael

2015-01-01

The analysis of structural variants, in particular of copy-number variations (CNVs), has proven valuable in unraveling the genetic basis of human diseases. Hence, a large number of algorithms have been developed for the detection of CNVs in SNP array signal intensity data. Using the European and African HapMap trio data, we undertook a comparative evaluation of six commonly used CNV detection software tools, namely Affymetrix Power Tools (APT), QuantiSNP, PennCNV, GLAD, R-gada and VEGA, and assessed their level of pair-wise prediction concordance. The tool-specific CNV prediction accuracy was assessed in silico by way of intra-familial validation. Software tools differed greatly in terms of the number and length of the CNVs predicted as well as the number of markers included in a CNV. All software tools predicted substantially more deletions than duplications. Intra-familial validation revealed consistently low levels of prediction accuracy as measured by the proportion of validated CNVs (34-60%). Moreover, up to 20% of apparent family-based validations were found to be due to chance alone. Software using Hidden Markov models (HMM) showed a trend to predict fewer CNVs than segmentation-based algorithms albeit with greater validity. PennCNV yielded the highest prediction accuracy (60.9%). Finally, the pairwise concordance of CNV prediction was found to vary widely with the software tools involved. We recommend HMM-based software, in particular PennCNV, rather than segmentation-based algorithms when validity is the primary concern of CNV detection. QuantiSNP may be used as an additional tool to detect sets of CNVs not detectable by the other tools. Our study also reemphasizes the need for laboratory-based validation, such as qPCR, of CNVs predicted in silico.

Performance of genomic prediction within and across generations in maritime pine.

PubMed

Bartholomé, Jérôme; Van Heerwaarden, Joost; Isik, Fikret; Boury, Christophe; Vidal, Marjorie; Plomion, Christophe; Bouffier, Laurent

2016-08-11

Genomic selection (GS) is a promising approach for decreasing breeding cycle length in forest trees. Assessment of progeny performance and of the prediction accuracy of GS models over generations is therefore a key issue. A reference population of maritime pine (Pinus pinaster) with an estimated effective inbreeding population size (status number) of 25 was first selected with simulated data. This reference population (n = 818) covered three generations (G0, G1 and G2) and was genotyped with 4436 single-nucleotide polymorphism (SNP) markers. We evaluated the effects on prediction accuracy of both the relatedness between the calibration and validation sets and validation on the basis of progeny performance. Pedigree-based (best linear unbiased prediction, ABLUP) and marker-based (genomic BLUP and Bayesian LASSO) models were used to predict breeding values for three different traits: circumference, height and stem straightness. On average, the ABLUP model outperformed genomic prediction models, with a maximum difference in prediction accuracies of 0.12, depending on the trait and the validation method. A mean difference in prediction accuracy of 0.17 was found between validation methods differing in terms of relatedness. Including the progenitors in the calibration set reduced this difference in prediction accuracy to 0.03. When only genotypes from the G0 and G1 generations were used in the calibration set and genotypes from G2 were used in the validation set (progeny validation), prediction accuracies ranged from 0.70 to 0.85. This study suggests that the training of prediction models on parental populations can predict the genetic merit of the progeny with high accuracy: an encouraging result for the implementation of GS in the maritime pine breeding program.

Assessing the accuracy and stability of variable selection methods for random forest modeling in ecology.

PubMed

Fox, Eric W; Hill, Ryan A; Leibowitz, Scott G; Olsen, Anthony R; Thornbrugh, Darren J; Weber, Marc H

2017-07-01

Random forest (RF) modeling has emerged as an important statistical learning method in ecology due to its exceptional predictive performance. However, for large and complex ecological data sets, there is limited guidance on variable selection methods for RF modeling. Typically, either a preselected set of predictor variables are used or stepwise procedures are employed which iteratively remove variables according to their importance measures. This paper investigates the application of variable selection methods to RF models for predicting probable biological stream condition. Our motivating data set consists of the good/poor condition of n = 1365 stream survey sites from the 2008/2009 National Rivers and Stream Assessment, and a large set (p = 212) of landscape features from the StreamCat data set as potential predictors. We compare two types of RF models: a full variable set model with all 212 predictors and a reduced variable set model selected using a backward elimination approach. We assess model accuracy using RF's internal out-of-bag estimate, and a cross-validation procedure with validation folds external to the variable selection process. We also assess the stability of the spatial predictions generated by the RF models to changes in the number of predictors and argue that model selection needs to consider both accuracy and stability. The results suggest that RF modeling is robust to the inclusion of many variables of moderate to low importance. We found no substantial improvement in cross-validated accuracy as a result of variable reduction. Moreover, the backward elimination procedure tended to select too few variables and exhibited numerous issues such as upwardly biased out-of-bag accuracy estimates and instabilities in the spatial predictions. We use simulations to further support and generalize results from the analysis of real data. A main purpose of this work is to elucidate issues of model selection bias and instability to ecologists interested in using RF to develop predictive models with large environmental data sets.

Determination of heat capacity of ionic liquid based nanofluids using group method of data handling technique

NASA Astrophysics Data System (ADS)

Sadi, Maryam

2018-01-01

In this study a group method of data handling model has been successfully developed to predict heat capacity of ionic liquid based nanofluids by considering reduced temperature, acentric factor and molecular weight of ionic liquids, and nanoparticle concentration as input parameters. In order to accomplish modeling, 528 experimental data points extracted from the literature have been divided into training and testing subsets. The training set has been used to predict model coefficients and the testing set has been applied for model validation. The ability and accuracy of developed model, has been evaluated by comparison of model predictions with experimental values using different statistical parameters such as coefficient of determination, mean square error and mean absolute percentage error. The mean absolute percentage error of developed model for training and testing sets are 1.38% and 1.66%, respectively, which indicate excellent agreement between model predictions and experimental data. Also, the results estimated by the developed GMDH model exhibit a higher accuracy when compared to the available theoretical correlations.

Theoretical prediction of welding distortion in large and complex structures

NASA Astrophysics Data System (ADS)

Deng, De-An

2010-06-01

Welding technology is widely used to assemble large thin plate structures such as ships, automobiles, and passenger trains because of its high productivity. However, it is impossible to avoid welding-induced distortion during the assembly process. Welding distortion not only reduces the fabrication accuracy of a weldment, but also decreases the productivity due to correction work. If welding distortion can be predicted using a practical method beforehand, the prediction will be useful for taking appropriate measures to control the dimensional accuracy to an acceptable limit. In this study, a two-step computational approach, which is a combination of a thermoelastic-plastic finite element method (FEM) and an elastic finite element with consideration for large deformation, is developed to estimate welding distortion for large and complex welded structures. Welding distortions in several representative large complex structures, which are often used in shipbuilding, are simulated using the proposed method. By comparing the predictions and the measurements, the effectiveness of the two-step computational approach is verified.

Electrophysiological evidence for preserved primacy of lexical prediction in aging.

PubMed

Dave, Shruti; Brothers, Trevor A; Traxler, Matthew J; Ferreira, Fernanda; Henderson, John M; Swaab, Tamara Y

2018-05-28

Young adults show consistent neural benefits of predictable contexts when processing upcoming words, but these benefits are less clear-cut in older adults. Here we disentangle the neural correlates of prediction accuracy and contextual support during word processing, in order to test current theories that suggest that neural mechanisms underlying predictive processing are specifically impaired in older adults. During a sentence comprehension task, older and younger readers were asked to predict passage-final words and report the accuracy of these predictions. Age-related reductions were observed for N250 and N400 effects of prediction accuracy, as well as for N400 effects of contextual support independent of prediction accuracy. Furthermore, temporal primacy of predictive processing (i.e., earlier facilitation for successful predictions) was preserved across the lifespan, suggesting that predictive mechanisms are unlikely to be uniquely impaired in older adults. In addition, older adults showed prediction effects on frontal post-N400 positivities (PNPs) that were similar in amplitude to PNPs in young adults. Previous research has shown correlations between verbal fluency and lexical prediction in older adult readers, suggesting that the production system may be linked to capacity for lexical prediction, especially in aging. The current study suggests that verbal fluency modulates PNP effects of contextual support, but not prediction accuracy. Taken together, our findings suggest that aging does not result in specific declines in lexical prediction. Copyright © 2018 Elsevier Ltd. All rights reserved.

Are foetal ultrasonographic and maternal blood progesterone measurements near parturition reliable predictors of the time of birth in the domestic cat?

PubMed

Keiser, R; Reichler, I M; Balogh, O

2017-06-01

In cats, accuracy of parturition day prediction by ultrasonographic measurement of foetal structures is decreasing towards the end of gestation. Foetal measurements during the last days of pregnancy are scarce. We determined foetal biparietal, abdominal and eye diameter (BPD, AD and ED, respectively) by ultrasonography as well as maternal blood progesterone (P4) within five days of delivery to predict parturition date and calculate accuracy of prediction. Foetal BPD at birth was compared with newborn kitten head diameter (HD). Kitten HD, crown-rump length (CRL) and body weight were compared by breed and gender. Ultrasonography measurements were carried out on the day of parturition in 14 queens, and on days 62-63 after the first mating and repeated 24-72 hr later in ten other cats. Accuracy of parturition day prediction using BPD and AD was determined based on the equations of Beccaglia et al. (2008) Veterinary Research Communications, 32(Suppl 1), S99 and Garcia Mitacek et al. (2015) Theriogenology, 84, 1131. Progesterone was measured at the time of presentation and repeated 24-72 hr later if parturition did not occur. Data were analysed with linear regression, t test, Mann-Whitney U test, one-way anova and Kruskal-Wallis test. There was a moderate relationship between BPD, days before birth (DBB) and litter size. AD and DBB had a low agreement, and ED was not associated with DBB. BPD at birth was significantly related to HD. The accuracy of parturition day prediction using BPD and AD was 27-53% and 17-35%, respectively. Kitten HD was associated with body weight, and both were inversely related to litter size. Newborn biometric measurements differed by breed but not by gender. Progesterone decreased towards parturition and reached 3.18 ± 1.68 ng/ml on the day of delivery. In conclusion, close to birth, the combination of foetal ultrasonography and maternal blood P4 rather than each as a sole predictor of parturition is recommended. © 2017 Blackwell Verlag GmbH.

Accuracy of refractive outcomes in myopic and hyperopic laser in situ keratomileusis: Manifest versus aberrometric refraction.

PubMed

Reinstein, Dan Z; Morral, Merce; Gobbe, Marine; Archer, Timothy J

2012-11-01

To compare the achieved refractive accuracy of laser in situ keratomileusis (LASIK) performed based on manifest refraction with the predicted accuracy that would have been achieved using WASCA aberrometric refraction with and without Seidel correction factor for sphere. London Vision Clinic, London, United Kingdom. Comparative case series. Myopic eyes and hyperopic eyes had LASIK based on manifest refraction. Two aberrometric refractions were obtained preoperatively: Seidel, which includes spherical aberration in the sphere calculation, and non-Seidel. Bland-Altman plots were used to show the agreement between aberrometric and manifest refractions. Predicted LASIK outcomes had aberrometric refraction been used were modeled by shifting the postoperative manifest refraction by the vector difference between the preoperative manifest and aberrometric refractions. This study included 869 myopic eyes and 413 hyperopic eyes. The mean differences (manifest minus aberrometric) in spherical equivalent were +0.03 diopters (D) ± 0.48 (SD) (Seidel aberrometric) and +0.45 ± 0.42 D (non-Seidel aberrometric) for myopia and -0.20 ± 0.39 D and +0.39 ± 0.34 D, respectively, for hyperopia. The mean differences in cylinder magnitude were -0.10 ± 0.27 D and 0.00 ± 0.25 D, respectively. The percentage of eyes within ±0.50 D of the attempted correction was 81% (manifest), 70% (Seidel), and 67% (non-Seidel) for myopia and 71% (manifest), 61% (Seidel), and 64% (non-Seidel) for hyperopia. The achieved refractive accuracy by manifest refraction was better than the predicted accuracy had Seidel or non-Seidel aberrometric refractions been used for surgical planning. Using the Seidel method improved the accuracy in myopic eyes but not in hyperopic eyes. Dr. Reinstein is a consultant to Carl Zeiss Meditec AG and has a proprietary interest in the Artemis technology (Arcscan Inc., Morrison, Colorado, USA) through patents administered by the Cornell Center for Technology Enterprise and Commercialization, Ithaca, New York. No other author has a financial or proprietary interest in any material or method mentioned. Copyright © 2012 ASCRS and ESCRS. Published by Elsevier Inc. All rights reserved.

Synthetic Stromgren photometry for F dwarf stars

NASA Technical Reports Server (NTRS)

Bell, R. A.

1988-01-01

Recent synthetic spectrum and color calculations for cool dwarf star models are tested by comparison with observation. The accuracy of the computed dependence of the thermal colors B-V and b-y on effective temperature is examined, and H-beta indices are presented and compared with observed values. The accuracy of the predictions of the Stromgren uvby system metal-abundance indicator m1 and luminosity indicator c1 are tested. A new calibration of the c1, b-y diagram in terms of absolute magnitudes is given, making use of recent calculations of stellar isochrones. Observations of very metal-poor subdwarfs are used to study the accuracy of the isochrones. The c1, b-y diagram of the subdwarfs is compared with that of the turnoff-region stars in the very metal-poor globular cluster NGC 6397.

Utilizing multiple scale models to improve predictions of extra-axial hemorrhage in the immature piglet.

PubMed

Scott, Gregory G; Margulies, Susan S; Coats, Brittany

2016-10-01

Traumatic brain injury (TBI) is a leading cause of death and disability in the USA. To help understand and better predict TBI, researchers have developed complex finite element (FE) models of the head which incorporate many biological structures such as scalp, skull, meninges, brain (with gray/white matter differentiation), and vasculature. However, most models drastically simplify the membranes and substructures between the pia and arachnoid membranes. We hypothesize that substructures in the pia-arachnoid complex (PAC) contribute substantially to brain deformation following head rotation, and that when included in FE models accuracy of extra-axial hemorrhage prediction improves. To test these hypotheses, microscale FE models of the PAC were developed to span the variability of PAC substructure anatomy and regional density. The constitutive response of these models were then integrated into an existing macroscale FE model of the immature piglet brain to identify changes in cortical stress distribution and predictions of extra-axial hemorrhage (EAH). Incorporating regional variability of PAC substructures substantially altered the distribution of principal stress on the cortical surface of the brain compared to a uniform representation of the PAC. Simulations of 24 non-impact rapid head rotations in an immature piglet animal model resulted in improved accuracy of EAH prediction (to 94 % sensitivity, 100 % specificity), as well as a high accuracy in regional hemorrhage prediction (to 82-100 % sensitivity, 100 % specificity). We conclude that including a biofidelic PAC substructure variability in FE models of the head is essential for improved predictions of hemorrhage at the brain/skull interface.

A novel method for landslide displacement prediction by integrating advanced computational intelligence algorithms.

PubMed

Zhou, Chao; Yin, Kunlong; Cao, Ying; Ahmed, Bayes; Fu, Xiaolin

2018-05-08

Landslide displacement prediction is considered as an essential component for developing early warning systems. The modelling of conventional forecast methods requires enormous monitoring data that limit its application. To conduct accurate displacement prediction with limited data, a novel method is proposed and applied by integrating three computational intelligence algorithms namely: the wavelet transform (WT), the artificial bees colony (ABC), and the kernel-based extreme learning machine (KELM). At first, the total displacement was decomposed into several sub-sequences with different frequencies using the WT. Next each sub-sequence was predicted separately by the KELM whose parameters were optimized by the ABC. Finally the predicted total displacement was obtained by adding all the predicted sub-sequences. The Shuping landslide in the Three Gorges Reservoir area in China was taken as a case study. The performance of the new method was compared with the WT-ELM, ABC-KELM, ELM, and the support vector machine (SVM) methods. Results show that the prediction accuracy can be improved by decomposing the total displacement into sub-sequences with various frequencies and by predicting them separately. The ABC-KELM algorithm shows the highest prediction capacity followed by the ELM and SVM. Overall, the proposed method achieved excellent performance both in terms of accuracy and stability.

Paroxysmal atrial fibrillation prediction method with shorter HRV sequences.

PubMed

Boon, K H; Khalil-Hani, M; Malarvili, M B; Sia, C W

2016-10-01

This paper proposes a method that predicts the onset of paroxysmal atrial fibrillation (PAF), using heart rate variability (HRV) segments that are shorter than those applied in existing methods, while maintaining good prediction accuracy. PAF is a common cardiac arrhythmia that increases the health risk of a patient, and the development of an accurate predictor of the onset of PAF is clinical important because it increases the possibility to stabilize (electrically) and prevent the onset of atrial arrhythmias with different pacing techniques. We investigate the effect of HRV features extracted from different lengths of HRV segments prior to PAF onset with the proposed PAF prediction method. The pre-processing stage of the predictor includes QRS detection, HRV quantification and ectopic beat correction. Time-domain, frequency-domain, non-linear and bispectrum features are then extracted from the quantified HRV. In the feature selection, the HRV feature set and classifier parameters are optimized simultaneously using an optimization procedure based on genetic algorithm (GA). Both full feature set and statistically significant feature subset are optimized by GA respectively. For the statistically significant feature subset, Mann-Whitney U test is used to filter non-statistical significance features that cannot pass the statistical test at 20% significant level. The final stage of our predictor is the classifier that is based on support vector machine (SVM). A 10-fold cross-validation is applied in performance evaluation, and the proposed method achieves 79.3% prediction accuracy using 15-minutes HRV segment. This accuracy is comparable to that achieved by existing methods that use 30-minutes HRV segments, most of which achieves accuracy of around 80%. More importantly, our method significantly outperforms those that applied segments shorter than 30 minutes. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Predictors of Mortality in the Critically Ill Cirrhotic Patient: Is the Model for End-Stage Liver Disease Enough?

PubMed

Annamalai, Alagappan; Harada, Megan Y; Chen, Melissa; Tran, Tram; Ko, Ara; Ley, Eric J; Nuno, Miriam; Klein, Andrew; Nissen, Nicholas; Noureddin, Mazen

2017-03-01

Critically ill cirrhotics require liver transplantation urgently, but are at high risk for perioperative mortality. The Model for End-stage Liver Disease (MELD) score, recently updated to incorporate serum sodium, estimates survival probability in patients with cirrhosis, but needs additional evaluation in the critically ill. The purpose of this study was to evaluate the predictive power of ICU admission MELD scores and identify clinical risk factors associated with increased mortality. This was a retrospective review of cirrhotic patients admitted to the ICU between January 2011 and December 2014. Patients who were discharged or underwent transplantation (survivors) were compared with those who died (nonsurvivors). Demographic characteristics, admission MELD scores, and clinical risk factors were recorded. Multivariate regression was used to identify independent predictors of mortality, and measures of model performance were assessed to determine predictive accuracy. Of 276 patients who met inclusion criteria, 153 were considered survivors and 123 were nonsurvivors. Survivor and nonsurvivor cohorts had similar demographic characteristics. Nonsurvivors had increased MELD, gastrointestinal bleeding, infection, mechanical ventilation, encephalopathy, vasopressors, dialysis, renal replacement therapy, requirement of blood products, and ICU length of stay. The MELD demonstrated low predictive power (c-statistic 0.73). Multivariate analysis identified MELD score (adjusted odds ratio [AOR] = 1.05), mechanical ventilation (AOR = 4.55), vasopressors (AOR = 3.87), and continuous renal replacement therapy (AOR = 2.43) as independent predictors of mortality, with stronger predictive accuracy (c-statistic 0.87). The MELD demonstrated relatively poor predictive accuracy in critically ill patients with cirrhosis and might not be the best indicator for prognosis in the ICU population. Prognostic accuracy is significantly improved when variables indicating organ support (mechanical ventilation, vasopressors, and continuous renal replacement therapy) are included in the model. Copyright © 2016. Published by Elsevier Inc.

Accuracy of Body Mass Index Versus Lean Mass Index for Prediction of Sarcopenia in Older Women.

PubMed

Benton, M J; Silva-Smith, A L

2018-01-01

We compared accuracy of body mass index (BMI) versus lean mass index (LMI) to predict sarcopenia in 58 community-dwelling women (74.1±0.9 years). Lean mass was measured with multi-frequency bioelectrical impedance analysis, and strength was measured with Arm Curl test, Chair Stand test, and handgrip dynamometry. Sarcopenia was defined as low LMI. When categorized by BMI, normal women had less absolute lean mass (37.6±1.0 vs. 42.6±0.9 kg; P<0.001) and less relative lean mass (14.1±0.2 vs. 16.1±0.2 kg/m2; P<0.001) compared to overweight/obese women, but no differences in strength. When categorized by LMI, normal women had more absolute lean mass (44.0±0.7 vs. 35.7±0.7 kg; P<0.001), more relative lean mass (16.2±0.2 vs. 13.8±0.2 kg/m2; P<0.001), and greater upper body strength (16.7±0.9 vs. 14.2±0.6 arm curls; P<0.05) compared to women with low LMI. BMI failed to accurately predict low values of lean mass and strength. For clinical assessment, calculation of LMI rather than BMI is appropriate.

Evaluation of image features and classification methods for Barrett's cancer detection using VLE imaging

NASA Astrophysics Data System (ADS)

Klomp, Sander; van der Sommen, Fons; Swager, Anne-Fré; Zinger, Svitlana; Schoon, Erik J.; Curvers, Wouter L.; Bergman, Jacques J.; de With, Peter H. N.

2017-03-01

Volumetric Laser Endomicroscopy (VLE) is a promising technique for the detection of early neoplasia in Barrett's Esophagus (BE). VLE generates hundreds of high resolution, grayscale, cross-sectional images of the esophagus. However, at present, classifying these images is a time consuming and cumbersome effort performed by an expert using a clinical prediction model. This paper explores the feasibility of using computer vision techniques to accurately predict the presence of dysplastic tissue in VLE BE images. Our contribution is threefold. First, a benchmarking is performed for widely applied machine learning techniques and feature extraction methods. Second, three new features based on the clinical detection model are proposed, having superior classification accuracy and speed, compared to earlier work. Third, we evaluate automated parameter tuning by applying simple grid search and feature selection methods. The results are evaluated on a clinically validated dataset of 30 dysplastic and 30 non-dysplastic VLE images. Optimal classification accuracy is obtained by applying a support vector machine and using our modified Haralick features and optimal image cropping, obtaining an area under the receiver operating characteristic of 0.95 compared to the clinical prediction model at 0.81. Optimal execution time is achieved using a proposed mean and median feature, which is extracted at least factor 2.5 faster than alternative features with comparable performance.

Comparative evaluation of Indian Diabetes Risk Score and Finnish Diabetes Risk Score for predicting risk of diabetes mellitus type II: A teaching hospital-based survey in Maharashtra.

PubMed

Pawar, Shivshakti D; Naik, Jayashri D; Prabhu, Priya; Jatti, Gajanan M; Jadhav, Sachin B; Radhe, B K

2017-01-01

India is currently becoming capital for diabetes mellitus. This significantly increasing incidence of diabetes putting an additional burden on health care in India. Unfortunately, half of diabetic individuals are unknown about their diabetic status. Hence, there is an emergent need of effective screening instrument to identify "diabetes risk" individuals. The aim is to evaluate and compare the diagnostic accuracy and clinical utility of Indian Diabetes Risk Score (IDRS) and Finnish Diabetes Risk Score (FINDRISC). This is retrospective, record-based study of diabetes detection camp organized by a teaching hospital. Out of 780 people attended this camp voluntarily only 763 fulfilled inclusion criteria of the study. In this camp, pro forma included the World Health Organization STEP guidelines for surveillance of noncommunicable diseases. Included primary sociodemographic characters, physical measurements, and clinical examination. After that followed the random blood glucose estimation of each individual. Diagnostic accuracy of IDRS and FINDRISC compared by using receiver operative characteristic curve (ROC). Sensitivity, specificity, likelihood ratio, positive predictive and negative predictive values were compared. Clinical utility index (CUI) of each score also compared. SPSS version 22, Stata 13, R3.2.9 used. Out of 763 individuals, 38 were new diabetics. By IDRS 347 and by FINDRISC 96 people were included in high-risk category for diabetes. Odds ratio for high-risk people in FINDRISC for getting affected by diabetes was 10.70. Similarly, it was 4.79 for IDRS. Area under curves of ROCs of both scores were indifferent ( P = 0.98). Sensitivity and specificity of IDRS was 78.95% and 56.14%; whereas for FINDRISC it was 55.26% and 89.66%, respectively. CUI was excellent (0.86) for FINDRISC while IDRS it was "satisfactory" (0.54). Bland-Altman plot and Cohen's Kappa suggested fair agreement between these score in measuring diabetes risk. Diagnostic accuracy and clinical utility of FINDRISC is fairly good than IDRS.

Electroencephalogram-based decoding cognitive states using convolutional neural network and likelihood ratio based score fusion.

PubMed

Zafar, Raheel; Dass, Sarat C; Malik, Aamir Saeed

2017-01-01

Electroencephalogram (EEG)-based decoding human brain activity is challenging, owing to the low spatial resolution of EEG. However, EEG is an important technique, especially for brain-computer interface applications. In this study, a novel algorithm is proposed to decode brain activity associated with different types of images. In this hybrid algorithm, convolutional neural network is modified for the extraction of features, a t-test is used for the selection of significant features and likelihood ratio-based score fusion is used for the prediction of brain activity. The proposed algorithm takes input data from multichannel EEG time-series, which is also known as multivariate pattern analysis. Comprehensive analysis was conducted using data from 30 participants. The results from the proposed method are compared with current recognized feature extraction and classification/prediction techniques. The wavelet transform-support vector machine method is the most popular currently used feature extraction and prediction method. This method showed an accuracy of 65.7%. However, the proposed method predicts the novel data with improved accuracy of 79.9%. In conclusion, the proposed algorithm outperformed the current feature extraction and prediction method.

Development of a Nonequilibrium Radiative Heating Prediction Method for Coupled Flowfield Solutions

NASA Technical Reports Server (NTRS)

Hartung, Lin C.

1991-01-01

A method for predicting radiative heating and coupling effects in nonequilibrium flow-fields has been developed. The method resolves atomic lines with a minimum number of spectral points, and treats molecular radiation using the smeared band approximation. To further minimize computational time, the calculation is performed on an optimized spectrum, which is computed for each flow condition to enhance spectral resolution. Additional time savings are obtained by performing the radiation calculation on a subgrid optimally selected for accuracy. Representative results from the new method are compared to previous work to demonstrate that the speedup does not cause a loss of accuracy and is sufficient to make coupled solutions practical. The method is found to be a useful tool for studies of nonequilibrium flows.

The effects of divided attention at study and reporting procedure on regulation and monitoring for episodic recall.

PubMed

Sauer, James; Hope, Lorraine

2016-09-01

Eyewitnesses regulate the level of detail (grain size) reported to balance competing demands for informativeness and accuracy. However, research to date has predominantly examined metacognitive monitoring for semantic memory tasks, and used relatively artificial phased reporting procedures. Further, although the established role of confidence in this regulation process may affect the confidence-accuracy relation for volunteered responses in predictable ways, previous investigations of the confidence-accuracy relation for eyewitness recall have largely overlooked the regulation of response granularity. Using a non-phased paradigm, Experiment 1 compared reporting and monitoring following optimal and sub-optimal (divided attention) encoding conditions. Participants showed evidence of sacrificing accuracy for informativeness, even when memory quality was relatively weak. Participants in the divided (cf. full) attention condition showed reduced accuracy for fine- but not coarse-grained responses. However, indices of discrimination and confidence diagnosticity showed no effect of divided attention. Experiment 2 compared the effects of divided attention at encoding on reporting and monitoring using both non-phased and 2-phase procedures. Divided attention effects were consistent with Experiment 1. However, compared to those in the non-phased condition, participants in the 2-phase condition displayed a more conservative control strategy, and confidence ratings were less diagnostic of accuracy. When memory quality was reduced, although attempts to balance informativeness and accuracy increased the chance of fine-grained response errors, confidence provided an index of the likely accuracy of volunteered fine-grained responses for both condition. Copyright © 2016 Elsevier B.V. All rights reserved.

An Innovative Model to Predict Pediatric Emergency Department Return Visits.

PubMed

Bergese, Ilaria; Frigerio, Simona; Clari, Marco; Castagno, Emanuele; De Clemente, Antonietta; Ponticelli, Elena; Scavino, Enrica; Berchialla, Paola

2016-10-06

Return visit (RV) to the emergency department (ED) is considered a benchmarking clinical indicator for health care quality. The purpose of this study was to develop a predictive model for early readmission risk in pediatric EDs comparing the performances of 2 learning machine algorithms. A retrospective study based on all children younger than 15 years spontaneously returning within 120 hours after discharge was conducted in an Italian university children's hospital between October 2012 and April 2013. Two predictive models, artificial neural network (ANN) and classification tree (CT), were used. Accuracy, specificity, and sensitivity were assessed. A total of 28,341 patient records were evaluated. Among them, 626 patients returned to the ED within 120 hours after their initial visit. Comparing ANN and CT, our analysis has shown that CT is the best model to predict RVs. The CT model showed an overall accuracy of 81%, slightly lower than the one achieved by the ANN (91.3%), but CT outperformed ANN with regard to sensitivity (79.8% vs 6.9%, respectively). The specificity was similar for the 2 models (CT, 97% vs ANN, 98.3%). In addition, the time of arrival and discharge along with the priority code assigned in triage, age, and diagnosis play a pivotal role to identify patients at high risk of RVs. These models provide a promising predictive tool for supporting the ED staff in preventing unnecessary RVs.

The impact of training strategies on the accuracy of genomic predictors in United States Red Angus cattle.

PubMed

Lee, J; Kachman, S D; Spangler, M L

2017-08-01

Genomic selection (GS) has become an integral part of genetic evaluation methodology and has been applied to all major livestock species, including beef and dairy cattle, pigs, and chickens. Significant contributions in increased accuracy of selection decisions have been clearly illustrated in dairy cattle after practical application of GS. In the majority of U.S. beef cattle breeds, similar efforts have also been made to increase the accuracy of genetic merit estimates through the inclusion of genomic information into routine genetic evaluations using a variety of methods. However, prediction accuracies can vary relative to panel density, the number of folds used for folds cross-validation, and the choice of dependent variables (e.g., EBV, deregressed EBV, adjusted phenotypes). The aim of this study was to evaluate the accuracy of genomic predictors for Red Angus beef cattle with different strategies used in training and evaluation. The reference population consisted of 9,776 Red Angus animals whose genotypes were imputed to 2 medium-density panels consisting of over 50,000 (50K) and approximately 80,000 (80K) SNP. Using the imputed panels, we determined the influence of marker density, exclusion (deregressed EPD adjusting for parental information [DEPD-PA]) or inclusion (deregressed EPD without adjusting for parental information [DEPD]) of parental information in the deregressed EPD used as the dependent variable, and the number of clusters used to partition training animals (3, 5, or 10). A BayesC model with π set to 0.99 was used to predict molecular breeding values (MBV) for 13 traits for which EPD existed. The prediction accuracies were measured as genetic correlations between MBV and weighted deregressed EPD. The average accuracies across all traits were 0.540 and 0.552 when using the 50K and 80K SNP panels, respectively, and 0.538, 0.541, and 0.561 when using 3, 5, and 10 folds, respectively, for cross-validation. Using DEPD-PA as the response variable resulted in higher accuracies of MBV than those obtained by DEPD for growth and carcass traits. When DEPD were used as the response variable, accuracies were greater for threshold traits and those that are sex limited, likely due to the fact that these traits suffer from a lack of information content and excluding animals in training with only parental information substantially decreases the training population size. It is recommended that the contribution of parental average to deregressed EPD should be removed in the construction of genomic prediction equations. The difference in terms of prediction accuracies between the 2 SNP panels or the number of folds compared herein was negligible.

Genomic prediction of piglet response to infection with one of two porcine reproductive and respiratory syndrome virus isolates.

PubMed

Waide, Emily H; Tuggle, Christopher K; Serão, Nick V L; Schroyen, Martine; Hess, Andrew; Rowland, Raymond R R; Lunney, Joan K; Plastow, Graham; Dekkers, Jack C M

2018-02-01

Genomic prediction of the pig's response to the porcine reproductive and respiratory syndrome (PRRS) virus (PRRSV) would be a useful tool in the swine industry. This study investigated the accuracy of genomic prediction based on porcine SNP60 Beadchip data using training and validation datasets from populations with different genetic backgrounds that were challenged with different PRRSV isolates. Genomic prediction accuracy averaged 0.34 for viral load (VL) and 0.23 for weight gain (WG) following experimental PRRSV challenge, which demonstrates that genomic selection could be used to improve response to PRRSV infection. Training on WG data during infection with a less virulent PRRSV, KS06, resulted in poor accuracy of prediction for WG during infection with a more virulent PRRSV, NVSL. Inclusion of single nucleotide polymorphisms (SNPs) that are in linkage disequilibrium with a major quantitative trait locus (QTL) on chromosome 4 was vital for accurate prediction of VL. Overall, SNPs that were significantly associated with either trait in single SNP genome-wide association analysis were unable to predict the phenotypes with an accuracy as high as that obtained by using all genotyped SNPs across the genome. Inclusion of data from close relatives into the training population increased whole genome prediction accuracy by 33% for VL and by 37% for WG but did not affect the accuracy of prediction when using only SNPs in the major QTL region. Results show that genomic prediction of response to PRRSV infection is moderately accurate and, when using all SNPs on the porcine SNP60 Beadchip, is not very sensitive to differences in virulence of the PRRSV in training and validation populations. Including close relatives in the training population increased prediction accuracy when using the whole genome or SNPs other than those near a major QTL.

A Novel Method for Accurate Operon Predictions in All SequencedProkaryotes

DOE Office of Scientific and Technical Information (OSTI.GOV)

Price, Morgan N.; Huang, Katherine H.; Alm, Eric J.

2004-12-01

We combine comparative genomic measures and the distance separating adjacent genes to predict operons in 124 completely sequenced prokaryotic genomes. Our method automatically tailors itself to each genome using sequence information alone, and thus can be applied to any prokaryote. For Escherichia coli K12 and Bacillus subtilis, our method is 85 and 83% accurate, respectively, which is similar to the accuracy of methods that use the same features but are trained on experimentally characterized transcripts. In Halobacterium NRC-1 and in Helicobacterpylori, our method correctly infers that genes in operons are separated by shorter distances than they are in E.coli, andmore » its predictions using distance alone are more accurate than distance-only predictions trained on a database of E.coli transcripts. We use microarray data from sixphylogenetically diverse prokaryotes to show that combining intergenic distance with comparative genomic measures further improves accuracy and that our method is broadly effective. Finally, we survey operon structure across 124 genomes, and find several surprises: H.pylori has many operons, contrary to previous reports; Bacillus anthracis has an unusual number of pseudogenes within conserved operons; and Synechocystis PCC6803 has many operons even though it has unusually wide spacings between conserved adjacent genes.« less

GHS additivity formula: can it predict the acute systemic toxicity of agrochemical formulations that contain acutely toxic ingredients?

PubMed

Van Cott, Andrew; Hastings, Charles E; Landsiedel, Robert; Kolle, Susanne; Stinchcombe, Stefan

2018-02-01

In vivo acute systemic testing is a regulatory requirement for agrochemical formulations. GHS specifies an alternative computational approach (GHS additivity formula) for calculating the acute toxicity of mixtures. We collected acute systemic toxicity data from formulations that contained one of several acutely-toxic active ingredients. The resulting acute data set includes 210 formulations tested for oral toxicity, 128 formulations tested for inhalation toxicity and 31 formulations tested for dermal toxicity. The GHS additivity formula was applied to each of these formulations and compared with the experimental in vivo result. In the acute oral assay, the GHS additivity formula misclassified 110 formulations using the GHS classification criteria (48% accuracy) and 119 formulations using the USEPA classification criteria (43% accuracy). With acute inhalation, the GHS additivity formula misclassified 50 formulations using the GHS classification criteria (61% accuracy) and 34 formulations using the USEPA classification criteria (73% accuracy). For acute dermal toxicity, the GHS additivity formula misclassified 16 formulations using the GHS classification criteria (48% accuracy) and 20 formulations using the USEPA classification criteria (36% accuracy). This data indicates the acute systemic toxicity of many formulations is not the sum of the ingredients' toxicity (additivity); but rather, ingredients in a formulation can interact to result in lower or higher toxicity than predicted by the GHS additivity formula. Copyright © 2018 Elsevier Inc. All rights reserved.

Genomic prediction based on data from three layer lines using non-linear regression models.

PubMed

Huang, Heyun; Windig, Jack J; Vereijken, Addie; Calus, Mario P L

2014-11-06

Most studies on genomic prediction with reference populations that include multiple lines or breeds have used linear models. Data heterogeneity due to using multiple populations may conflict with model assumptions used in linear regression methods. In an attempt to alleviate potential discrepancies between assumptions of linear models and multi-population data, two types of alternative models were used: (1) a multi-trait genomic best linear unbiased prediction (GBLUP) model that modelled trait by line combinations as separate but correlated traits and (2) non-linear models based on kernel learning. These models were compared to conventional linear models for genomic prediction for two lines of brown layer hens (B1 and B2) and one line of white hens (W1). The three lines each had 1004 to 1023 training and 238 to 240 validation animals. Prediction accuracy was evaluated by estimating the correlation between observed phenotypes and predicted breeding values. When the training dataset included only data from the evaluated line, non-linear models yielded at best a similar accuracy as linear models. In some cases, when adding a distantly related line, the linear models showed a slight decrease in performance, while non-linear models generally showed no change in accuracy. When only information from a closely related line was used for training, linear models and non-linear radial basis function (RBF) kernel models performed similarly. The multi-trait GBLUP model took advantage of the estimated genetic correlations between the lines. Combining linear and non-linear models improved the accuracy of multi-line genomic prediction. Linear models and non-linear RBF models performed very similarly for genomic prediction, despite the expectation that non-linear models could deal better with the heterogeneous multi-population data. This heterogeneity of the data can be overcome by modelling trait by line combinations as separate but correlated traits, which avoids the occasional occurrence of large negative accuracies when the evaluated line was not included in the training dataset. Furthermore, when using a multi-line training dataset, non-linear models provided information on the genotype data that was complementary to the linear models, which indicates that the underlying data distributions of the three studied lines were indeed heterogeneous.

Comparing the accuracy of perturbative and variational calculations for predicting fundamental vibrational frequencies of dihalomethanes

NASA Astrophysics Data System (ADS)

Krasnoshchekov, Sergey V.; Schutski, Roman S.; Craig, Norman C.; Sibaev, Marat; Crittenden, Deborah L.

2018-02-01

Three dihalogenated methane derivatives (CH2F2, CH2FCl, and CH2Cl2) were used as model systems to compare and assess the accuracy of two different approaches for predicting observed fundamental frequencies: canonical operator Van Vleck vibrational perturbation theory (CVPT) and vibrational configuration interaction (VCI). For convenience and consistency, both methods employ the Watson Hamiltonian in rectilinear normal coordinates, expanding the potential energy surface (PES) as a Taylor series about equilibrium and constructing the wavefunction from a harmonic oscillator product basis. At the highest levels of theory considered here, fourth-order CVPT and VCI in a harmonic oscillator basis with up to 10 quanta of vibrational excitation in conjunction with a 4-mode representation sextic force field (SFF-4MR) computed at MP2/cc-pVTZ with replacement CCSD(T)/aug-cc-pVQZ harmonic force constants, the agreement between computed fundamentals is closer to 0.3 cm-1 on average, with a maximum difference of 1.7 cm-1. The major remaining accuracy-limiting factors are the accuracy of the underlying electronic structure model, followed by the incompleteness of the PES expansion. Nonetheless, computed and experimental fundamentals agree to within 5 cm-1, with an average difference of 2 cm-1, confirming the utility and accuracy of both theoretical models. One exception to this rule is the formally IR-inactive but weakly allowed through Coriolis-coupling H-C-H out-of-plane twisting mode of dichloromethane, whose spectrum we therefore revisit and reassign. We also investigate convergence with respect to order of CVPT, VCI excitation level, and order of PES expansion, concluding that premature truncation substantially decreases accuracy, although VCI(6)/SFF-4MR results are still of acceptable accuracy, and some error cancellation is observed with CVPT2 using a quartic force field.

In-class didactic versus self-directed teaching of the probe-based confocal laser endomicroscopy (pCLE) criteria for Barrett's esophagus.

PubMed

Rzouq, Fadi; Vennalaganti, Prashanth; Pakseresht, Kavous; Kanakadandi, Vijay; Parasa, Sravanthi; Mathur, Sharad C; Alsop, Benjamin R; Hornung, Benjamin; Gupta, Neil; Sharma, Prateek

2016-02-01

Optimal teaching methods for disease recognition using probe-based confocal laser endomicroscopy (pCLE) have not been developed. Our aim was to compare in-class didactic teaching vs. self-directed teaching of Barrett's neoplasia diagnosis using pCLE. This randomized controlled trial was conducted at a tertiary academic center. Study participants with no prior pCLE experience were randomized to in-class didactic (group 1) or self-directed teaching groups (group 2). For group 1, an expert conducted a classroom teaching session using standardized educational material. Participants in group 2 were provided with the same material on an audio PowerPoint. After initial training, all participants graded an initial set of 20 pCLE videos and reviewed correct responses with the expert (group 1) or on audio PowerPoint (group 2). Finally, all participants completed interpretations of a further 40 videos. Eighteen trainees (8 medical students, 10 gastroenterology trainees) participated in the study. Overall diagnostic accuracy for neoplasia prediction by pCLE was 77 % (95 % confidence interval [CI] 74.0 % - 79.2 %); of predictions made with high confidence (53 %), the accuracy was 85 % (95 %CI 81.8 % - 87.8 %). The overall accuracy and interobserver agreement was significantly higher in group 1 than in group 2 for all predictions (80.4 % vs. 73 %; P = 0.005) and for high confidence predictions (90 % vs. 80 %; P < 0.001). Following feedback (after the initial 20 videos), the overall accuracy improved from 73 % to 79 % (P = 0.04), mainly driven by a significant improvement in group 1 (74 % to 84 %; P < 0.01). Accuracy of prediction significantly improved with time in endoscopy training (72 % students, 77 % FY1, 82 % FY2, and 85 % FY3; P = 0.003). For novice trainees, in-class didactic teaching enables significantly better recognition of the pCLE features of Barrett's esophagus than self-directed teaching. The in-class didactic group had a shorter learning curve and were able to achieve 90 % accuracy for their high confidence predictions. © Georg Thieme Verlag KG Stuttgart · New York.

Prehospital Acute Stroke Severity Scale to Predict Large Artery Occlusion: Design and Comparison With Other Scales.

PubMed

Hastrup, Sidsel; Damgaard, Dorte; Johnsen, Søren Paaske; Andersen, Grethe

2016-07-01

We designed and validated a simple prehospital stroke scale to identify emergent large vessel occlusion (ELVO) in patients with acute ischemic stroke and compared the scale to other published scales for prediction of ELVO. A national historical test cohort of 3127 patients with information on intracranial vessel status (angiography) before reperfusion therapy was identified. National Institutes of Health Stroke Scale (NIHSS) items with the highest predictive value of occlusion of a large intracranial artery were identified, and the most optimal combination meeting predefined criteria to ensure usefulness in the prehospital phase was determined. The predictive performance of Prehospital Acute Stroke Severity (PASS) scale was compared with other published scales for ELVO. The PASS scale was composed of 3 NIHSS scores: level of consciousness (month/age), gaze palsy/deviation, and arm weakness. In derivation of PASS 2/3 of the test cohort was used and showed accuracy (area under the curve) of 0.76 for detecting large arterial occlusion. Optimal cut point ≥2 abnormal scores showed: sensitivity=0.66 (95% CI, 0.62-0.69), specificity=0.83 (0.81-0.85), and area under the curve=0.74 (0.72-0.76). Validation on 1/3 of the test cohort showed similar performance. Patients with a large artery occlusion on angiography with PASS ≥2 had a median NIHSS score of 17 (interquartile range=6) as opposed to PASS <2 with a median NIHSS score of 6 (interquartile range=5). The PASS scale showed equal performance although more simple when compared with other scales predicting ELVO. The PASS scale is simple and has promising accuracy for prediction of ELVO in the field. © 2016 American Heart Association, Inc.

Effect of obesity on preterm delivery prediction by transabdominal recording of uterine electromyography.

PubMed

Lucovnik, Miha; Chambliss, Linda R; Blumrick, Richard; Balducci, James; Gersak, Ksenija; Garfield, Robert E

2016-10-01

It has been shown that noninvasive uterine electromyography (EMG) can identify true preterm labor more accurately than methods available to clinicians today. The objective of this study was to evaluate the effect of body mass index (BMI) on the accuracy of uterine EMG in predicting preterm delivery. Predictive values of uterine EMG for preterm delivery were compared in obese versus overweight/normal BMI patients. Hanley-McNeil test was used to compare receiver operator characteristics curves in these groups. Previously reported EMG cutoffs were used to determine groups with false positive/false negative and true positive/true negative EMG results. BMI in these groups was compared with Student t test (p < 0.05 significant). A total of 88 patients were included: 20 obese, 64 overweight, and four with normal BMI. EMG predicted preterm delivery within 7 days with area under the curve = 0.95 in the normal/overweight group, and with area under the curve = 1.00 in the obese group (p = 0.08). Six patients in true preterm labor (delivering within 7 days from EMG measurement) had low EMG values (false negative group). There were no false positive results. No significant differences in patient's BMI were noted between false negative group patients and preterm labor patients with high EMG values (true positive group) and nonlabor patients with low EMG values (true negative group; p = 0.32). Accuracy of noninvasive uterine EMG monitoring and its predictive value for preterm delivery are not affected by obesity. Copyright © 2016. Published by Elsevier B.V.

Percutaneous transhepatic cholangiographic endobiliary forceps biopsy versus endoscopic ultrasound fine needle aspiration for proximal biliary strictures: a single-centre experience.

PubMed

Mohkam, Kayvan; Malik, Yaseen; Derosas, Carlos; Isaac, John; Marudanayagam, Ravi; Mehrzad, Homoyoon; Mirza, Darius F; Muiesan, Paolo; Roberts, Keith J; Sutcliffe, Robert P

2017-06-01

Endoscopic ultrasound fine needle aspiration (EUS-FNA) and percutaneous transhepatic cholangiographic endobiliary forceps biopsy (PTC-EFB) are valid procedures for histological assessment of proximal biliary strictures (PBS), but their performances have never been compared. This study aimed to compare the diagnostic performance of these two techniques. The diagnostic performances of EUS-FNA and PTC-EFB were compared in a retrospective cohort of patients assessed for PBS from 2011 to 2015 at a single tertiary centre. An inverse probability of treatment weighting (IPTW) was performed to adjust for covariate imbalance. A total of 102 EUS-FNAs and 75 PTC-EFBs (performed in 137 patients) were compared. Patients in the PTC-EFB group had higher preoperative bilirubin (243 versus 169 μmol/l, p = 0.005) and a higher incidence of malignancy (87% versus 67%, p = 0.008). Both techniques showed specificity and positive predictive value of 100%, and similar sensitivity (69% versus 75%, p = 0.45), negative predictive value (58% versus 38%, p = 0.15) and accuracy (78% versus 79%, p = 1.00). After IPTW, the diagnostic performance of the two techniques remained similar. Compared to EUS-FNA, PTC-EFB provides similar sensitivity, negative predictive value and accuracy. It should therefore be considered as the preferred tissue-sampling procedure, if biliary drainage is indicated. Crown Copyright © 2017. Published by Elsevier Ltd. All rights reserved.

Iodine-123 metaiodobenzylguanidine scintigraphy and iodine-123 ioflupane single photon emission computed tomography in Lewy body diseases: complementary or alternative techniques?

PubMed

Treglia, Giorgio; Cason, Ernesto; Cortelli, Pietro; Gabellini, Anna; Liguori, Rocco; Bagnato, Antonio; Giordano, Alessandro; Fagioli, Giorgio

2014-01-01

To compare myocardial sympathetic imaging using (123)I-Metaiodobenzylguanidine (MIBG) scintigraphy and striatal dopaminergic imaging using (123)I-Ioflupane (FP-CIT) single photon emission computed tomography (SPECT) in patients with suspected Lewy body diseases (LBD). Ninety-nine patients who performed both methods within 2 months for differential diagnosis between Parkinson's disease (PD) and other parkinsonism (n = 68) or between dementia with Lewy bodies (DLB) and other dementia (n = 31) were enrolled. Sensitivity, specificity, accuracy, positive and negative predictive values of both methods were calculated. For (123) I-MIBG scintigraphy, the overall sensitivity, specificity, accuracy, positive and negative predictive values in LBD were 83%, 79%, 82%, 86%, and 76%, respectively. For (123)I-FP-CIT SPECT, the overall sensitivity, specificity, accuracy, positive and negative predictive values in LBD were 93%, 41%, 73%, 71%, and 80%, respectively. There was a statistically significant difference between these two methods in patients without LBD, but not in patients with LBD. LBD usually present both myocardial sympathetic and striatal dopaminergic impairments. (123)I-FP-CIT SPECT presents high sensitivity in the diagnosis of LBD; (123)I-MIBG scintigraphy may have a complementary role in differential diagnosis between PD and other parkinsonism. These scintigraphic methods showed similar diagnostic accuracy in differential diagnosis between DLB and other dementia. Copyright © 2012 by the American Society of Neuroimaging.

Tendon-driven continuum robot for neuroendoscopy: validation of extended kinematic mapping for hysteresis operation.

PubMed

Kato, Takahisa; Okumura, Ichiro; Kose, Hidekazu; Takagi, Kiyoshi; Hata, Nobuhiko

2016-04-01

The hysteresis operation is an outstanding issue in tendon-driven actuation--which is used in robot-assisted surgery--as it is incompatible with kinematic mapping for control and trajectory planning. Here, a new tendon-driven continuum robot, designed to fit existing neuroendoscopes, is presented with kinematic mapping for hysteresis operation. With attention to tension in tendons as a salient factor of the hysteresis operation, extended forward kinematic mapping (FKM) has been developed. In the experiment, the significance of every component in the robot for the hysteresis operation has been investigated. Moreover, the prediction accuracy of postures by the extended FKM has been determined experimentally and compared with piecewise constant curvature assumption. The tendons were the most predominant factor affecting the hysteresis operation of the robot. The extended FKM including friction in tendons predicted the postures in the hysteresis operation with improved accuracy (2.89 and 3.87 mm for the single and the antagonistic-tendons layouts, respectively). The measured accuracy was within the target value of 5 mm for planning of neuroendoscopic resection of intraventricle tumors. The friction in tendons was the most predominant factor for the hysteresis operation in the robot. The extended FKM including this factor can improve prediction accuracy of the postures in the hysteresis operation. The trajectory of the new robot can be planned within target value for the neuroendoscopic procedure by using the extended FKM.

Use of the HR index to predict maximal oxygen uptake during different exercise protocols.

PubMed

Haller, Jeannie M; Fehling, Patricia C; Barr, David A; Storer, Thomas W; Cooper, Christopher B; Smith, Denise L

2013-10-01

This study examined the ability of the HRindex model to accurately predict maximal oxygen uptake ([Formula: see text]O2max) across a variety of incremental exercise protocols. Ten men completed five incremental protocols to volitional exhaustion. Protocols included three treadmill (Bruce, UCLA running, Wellness Fitness Initiative [WFI]), one cycle, and one field (shuttle) test. The HRindex prediction equation (METs = 6 × HRindex - 5, where HRindex = HRmax/HRrest) was used to generate estimates of energy expenditure, which were converted to body mass-specific estimates of [Formula: see text]O2max. Estimated [Formula: see text]O2max was compared with measured [Formula: see text]O2max. Across all protocols, the HRindex model significantly underestimated [Formula: see text]O2max by 5.1 mL·kg(-1)·min(-1) (95% CI: -7.4, -2.7) and the standard error of the estimate (SEE) was 6.7 mL·kg(-1)·min(-1). Accuracy of the model was protocol-dependent, with [Formula: see text]O2max significantly underestimated for the Bruce and WFI protocols but not the UCLA, Cycle, or Shuttle protocols. Although no significant differences in [Formula: see text]O2max estimates were identified for these three protocols, predictive accuracy among them was not high, with root mean squared errors and SEEs ranging from 7.6 to 10.3 mL·kg(-1)·min(-1) and from 4.5 to 8.0 mL·kg(-1)·min(-1), respectively. Correlations between measured and predicted [Formula: see text]O2max were between 0.27 and 0.53. Individual prediction errors indicated that prediction accuracy varied considerably within protocols and among participants. In conclusion, across various protocols the HRindex model significantly underestimated [Formula: see text]O2max in a group of aerobically fit young men. Estimates generated using the model did not differ from measured [Formula: see text]O2max for three of the five protocols studied; nevertheless, some individual prediction errors were large. The lack of precision among estimates may limit the utility of the HRindex model; however, further investigation to establish the model's predictive accuracy is warranted.

Multistix 10 SG Leukocyte Esterage Dipstick Testing in Rapid Bedside Diagnosis of Spontaneous Bacterial Peritonitis: A Prospective Study.

PubMed

Jha, Ashish K; Kumawat, Dal C; Bolya, Yasvant K; Goenka, Mahesh K

2012-09-01

Spontaneous bacterial peritonitis (SBP) requires rapid diagnosis and the initiation of antibiotics. Diagnosis of SBP is usually based on cytobacteriological examination of ascitic fluid. These tests require good laboratory facilities and reporting time of few hours to 1-2 day. However, the 24 h laboratory facilities not widely available in country like India. We evaluated the diagnostic utility of reagent strip (Multistix 10 SG(®)) for rapid diagnosis of SBP. The study was prospectively carried out on patients of cirrhosis with ascites. Bedside leukocyte esterase reagent strip testing was performed on ascitic fluid. Cell count as determined by colorimetric scale of reagent strip was compared with counting chamber method. Sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were calculated. Out of 100 patients with cirrhotic ascites, [72 males: 28 female; mean age 44.34 (SD 13.03) years] 18 patients were diagnosed to have SBP by counting chamber method as compared to 14 patients detected to have SBP by reagent strip test ≥++ positive. The sensitivity, specificity, positive predictive value, negative predictive value and accuracy of reagent strip ≥++ positive were 77.77%, 95.12%, 77.77%, 95.12% and 92% respectively compared to counting chamber method. Reagent strip to diagnose SBP is very specific but less sensitive as compared to counting chamber method. This can be performed rapidly, easily and efficiently even in remote area of developing countries. This bedside test could be a useful tool for the diagnosis of SBP in country like India.

Patterns of neural activity associated with honest and dishonest moral decisions

PubMed Central

Greene, Joshua D.; Paxton, Joseph M.

2009-01-01

What makes people behave honestly when confronted with opportunities for dishonest gain? Research on the interplay between controlled and automatic processes in decision making suggests 2 hypotheses: According to the “Will” hypothesis, honesty results from the active resistance of temptation, comparable to the controlled cognitive processes that enable the delay of reward. According to the “Grace” hypothesis, honesty results from the absence of temptation, consistent with research emphasizing the determination of behavior by the presence or absence of automatic processes. To test these hypotheses, we examined neural activity in individuals confronted with opportunities for dishonest gain. Subjects undergoing functional magnetic resonance imaging (fMRI) gained money by accurately predicting the outcomes of computerized coin-flips. In some trials, subjects recorded their predictions in advance. In other trials, subjects were rewarded based on self-reported accuracy, allowing them to gain money dishonestly by lying about the accuracy of their predictions. Many subjects behaved dishonestly, as indicated by improbable levels of “accuracy.” Our findings support the Grace hypothesis. Individuals who behaved honestly exhibited no additional control-related activity (or other kind of activity) when choosing to behave honestly, as compared with a control condition in which there was no opportunity for dishonest gain. In contrast, individuals who behaved dishonestly exhibited increased activity in control-related regions of prefrontal cortex, both when choosing to behave dishonestly and on occasions when they refrained from dishonesty. Levels of activity in these regions correlated with the frequency of dishonesty in individuals. PMID:19622733

Spatially distributed modeling of soil organic carbon across China with improved accuracy

NASA Astrophysics Data System (ADS)

Li, Qi-quan; Zhang, Hao; Jiang, Xin-ye; Luo, Youlin; Wang, Chang-quan; Yue, Tian-xiang; Li, Bing; Gao, Xue-song

2017-06-01

There is a need for more detailed spatial information on soil organic carbon (SOC) for the accurate estimation of SOC stock and earth system models. As it is effective to use environmental factors as auxiliary variables to improve the prediction accuracy of spatially distributed modeling, a combined method (HASM_EF) was developed to predict the spatial pattern of SOC across China using high accuracy surface modeling (HASM), artificial neural network (ANN), and principal component analysis (PCA) to introduce land uses, soil types, climatic factors, topographic attributes, and vegetation cover as predictors. The performance of HASM_EF was compared with ordinary kriging (OK), OK, and HASM combined, respectively, with land uses and soil types (OK_LS and HASM_LS), and regression kriging combined with land uses and soil types (RK_LS). Results showed that HASM_EF obtained the lowest prediction errors and the ratio of performance to deviation (RPD) presented the relative improvements of 89.91%, 63.77%, 55.86%, and 42.14%, respectively, compared to the other four methods. Furthermore, HASM_EF generated more details and more realistic spatial information on SOC. The improved performance of HASM_EF can be attributed to the introduction of more environmental factors, to explicit consideration of the multicollinearity of selected factors and the spatial nonstationarity and nonlinearity of relationships between SOC and selected factors, and to the performance of HASM and ANN. This method may play a useful tool in providing more precise spatial information on soil parameters for global modeling across large areas.

Short-term prediction of solar energy in Saudi Arabia using automated-design fuzzy logic systems

PubMed Central

2017-01-01

Solar energy is considered as one of the main sources for renewable energy in the near future. However, solar energy and other renewable energy sources have a drawback related to the difficulty in predicting their availability in the near future. This problem affects optimal exploitation of solar energy, especially in connection with other resources. Therefore, reliable solar energy prediction models are essential to solar energy management and economics. This paper presents work aimed at designing reliable models to predict the global horizontal irradiance (GHI) for the next day in 8 stations in Saudi Arabia. The designed models are based on computational intelligence methods of automated-design fuzzy logic systems. The fuzzy logic systems are designed and optimized with two models using fuzzy c-means clustering (FCM) and simulated annealing (SA) algorithms. The first model uses FCM based on the subtractive clustering algorithm to automatically design the predictor fuzzy rules from data. The second model is using FCM followed by simulated annealing algorithm to enhance the prediction accuracy of the fuzzy logic system. The objective of the predictor is to accurately predict next-day global horizontal irradiance (GHI) using previous-day meteorological and solar radiation observations. The proposed models use observations of 10 variables of measured meteorological and solar radiation data to build the model. The experimentation and results of the prediction are detailed where the root mean square error of the prediction was approximately 88% for the second model tuned by simulated annealing compared to 79.75% accuracy using the first model. This results demonstrate a good modeling accuracy of the second model despite that the training and testing of the proposed models were carried out using spatially and temporally independent data. PMID:28806754

QSAR Modeling of Rat Acute Toxicity by Oral Exposure

PubMed Central

Zhu, Hao; Martin, Todd M.; Ye, Lin; Sedykh, Alexander; Young, Douglas M.; Tropsha, Alexander

2009-01-01

Few Quantitative Structure-Activity Relationship (QSAR) studies have successfully modeled large, diverse rodent toxicity endpoints. In this study, a comprehensive dataset of 7,385 compounds with their most conservative lethal dose (LD50) values has been compiled. A combinatorial QSAR approach has been employed to develop robust and predictive models of acute toxicity in rats caused by oral exposure to chemicals. To enable fair comparison between the predictive power of models generated in this study versus a commercial toxicity predictor, TOPKAT (Toxicity Prediction by Komputer Assisted Technology), a modeling subset of the entire dataset was selected that included all 3,472 compounds used in the TOPKAT’s training set. The remaining 3,913 compounds, which were not present in the TOPKAT training set, were used as the external validation set. QSAR models of five different types were developed for the modeling set. The prediction accuracy for the external validation set was estimated by determination coefficient R2 of linear regression between actual and predicted LD50 values. The use of the applicability domain threshold implemented in most models generally improved the external prediction accuracy but expectedly led to the decrease in chemical space coverage; depending on the applicability domain threshold, R2 ranged from 0.24 to 0.70. Ultimately, several consensus models were developed by averaging the predicted LD50 for every compound using all 5 models. The consensus models afforded higher prediction accuracy for the external validation dataset with the higher coverage as compared to individual constituent models. The validated consensus LD50 models developed in this study can be used as reliable computational predictors of in vivo acute toxicity. PMID:19845371

Short-term prediction of solar energy in Saudi Arabia using automated-design fuzzy logic systems.

PubMed

Almaraashi, Majid

2017-01-01

Solar energy is considered as one of the main sources for renewable energy in the near future. However, solar energy and other renewable energy sources have a drawback related to the difficulty in predicting their availability in the near future. This problem affects optimal exploitation of solar energy, especially in connection with other resources. Therefore, reliable solar energy prediction models are essential to solar energy management and economics. This paper presents work aimed at designing reliable models to predict the global horizontal irradiance (GHI) for the next day in 8 stations in Saudi Arabia. The designed models are based on computational intelligence methods of automated-design fuzzy logic systems. The fuzzy logic systems are designed and optimized with two models using fuzzy c-means clustering (FCM) and simulated annealing (SA) algorithms. The first model uses FCM based on the subtractive clustering algorithm to automatically design the predictor fuzzy rules from data. The second model is using FCM followed by simulated annealing algorithm to enhance the prediction accuracy of the fuzzy logic system. The objective of the predictor is to accurately predict next-day global horizontal irradiance (GHI) using previous-day meteorological and solar radiation observations. The proposed models use observations of 10 variables of measured meteorological and solar radiation data to build the model. The experimentation and results of the prediction are detailed where the root mean square error of the prediction was approximately 88% for the second model tuned by simulated annealing compared to 79.75% accuracy using the first model. This results demonstrate a good modeling accuracy of the second model despite that the training and testing of the proposed models were carried out using spatially and temporally independent data.

Quantitative structure-activity relationship modeling of rat acute toxicity by oral exposure.

PubMed

Zhu, Hao; Martin, Todd M; Ye, Lin; Sedykh, Alexander; Young, Douglas M; Tropsha, Alexander

2009-12-01

Few quantitative structure-activity relationship (QSAR) studies have successfully modeled large, diverse rodent toxicity end points. In this study, a comprehensive data set of 7385 compounds with their most conservative lethal dose (LD(50)) values has been compiled. A combinatorial QSAR approach has been employed to develop robust and predictive models of acute toxicity in rats caused by oral exposure to chemicals. To enable fair comparison between the predictive power of models generated in this study versus a commercial toxicity predictor, TOPKAT (Toxicity Prediction by Komputer Assisted Technology), a modeling subset of the entire data set was selected that included all 3472 compounds used in TOPKAT's training set. The remaining 3913 compounds, which were not present in the TOPKAT training set, were used as the external validation set. QSAR models of five different types were developed for the modeling set. The prediction accuracy for the external validation set was estimated by determination coefficient R(2) of linear regression between actual and predicted LD(50) values. The use of the applicability domain threshold implemented in most models generally improved the external prediction accuracy but expectedly led to the decrease in chemical space coverage; depending on the applicability domain threshold, R(2) ranged from 0.24 to 0.70. Ultimately, several consensus models were developed by averaging the predicted LD(50) for every compound using all five models. The consensus models afforded higher prediction accuracy for the external validation data set with the higher coverage as compared to individual constituent models. The validated consensus LD(50) models developed in this study can be used as reliable computational predictors of in vivo acute toxicity.

The RAPIDD ebola forecasting challenge: Synthesis and lessons learnt.

PubMed

Viboud, Cécile; Sun, Kaiyuan; Gaffey, Robert; Ajelli, Marco; Fumanelli, Laura; Merler, Stefano; Zhang, Qian; Chowell, Gerardo; Simonsen, Lone; Vespignani, Alessandro

2018-03-01

Infectious disease forecasting is gaining traction in the public health community; however, limited systematic comparisons of model performance exist. Here we present the results of a synthetic forecasting challenge inspired by the West African Ebola crisis in 2014-2015 and involving 16 international academic teams and US government agencies, and compare the predictive performance of 8 independent modeling approaches. Challenge participants were invited to predict 140 epidemiological targets across 5 different time points of 4 synthetic Ebola outbreaks, each involving different levels of interventions and "fog of war" in outbreak data made available for predictions. Prediction targets included 1-4 week-ahead case incidences, outbreak size, peak timing, and several natural history parameters. With respect to weekly case incidence targets, ensemble predictions based on a Bayesian average of the 8 participating models outperformed any individual model and did substantially better than a null auto-regressive model. There was no relationship between model complexity and prediction accuracy; however, the top performing models for short-term weekly incidence were reactive models with few parameters, fitted to a short and recent part of the outbreak. Individual model outputs and ensemble predictions improved with data accuracy and availability; by the second time point, just before the peak of the epidemic, estimates of final size were within 20% of the target. The 4th challenge scenario - mirroring an uncontrolled Ebola outbreak with substantial data reporting noise - was poorly predicted by all modeling teams. Overall, this synthetic forecasting challenge provided a deep understanding of model performance under controlled data and epidemiological conditions. We recommend such "peace time" forecasting challenges as key elements to improve coordination and inspire collaboration between modeling groups ahead of the next pandemic threat, and to assess model forecasting accuracy for a variety of known and hypothetical pathogens. Published by Elsevier B.V.

Prediction of the binding affinities of peptides to class II MHC using a regularized thermodynamic model

PubMed Central

2010-01-01

Background The binding of peptide fragments of extracellular peptides to class II MHC is a crucial event in the adaptive immune response. Each MHC allotype generally binds a distinct subset of peptides and the enormous number of possible peptide epitopes prevents their complete experimental characterization. Computational methods can utilize the limited experimental data to predict the binding affinities of peptides to class II MHC. Results We have developed the Regularized Thermodynamic Average, or RTA, method for predicting the affinities of peptides binding to class II MHC. RTA accounts for all possible peptide binding conformations using a thermodynamic average and includes a parameter constraint for regularization to improve accuracy on novel data. RTA was shown to achieve higher accuracy, as measured by AUC, than SMM-align on the same data for all 17 MHC allotypes examined. RTA also gave the highest accuracy on all but three allotypes when compared with results from 9 different prediction methods applied to the same data. In addition, the method correctly predicted the peptide binding register of 17 out of 18 peptide-MHC complexes. Finally, we found that suboptimal peptide binding registers, which are often ignored in other prediction methods, made significant contributions of at least 50% of the total binding energy for approximately 20% of the peptides. Conclusions The RTA method accurately predicts peptide binding affinities to class II MHC and accounts for multiple peptide binding registers while reducing overfitting through regularization. The method has potential applications in vaccine design and in understanding autoimmune disorders. A web server implementing the RTA prediction method is available at http://bordnerlab.org/RTA/. PMID:20089173

Cow genotyping strategies for genomic selection in a small dairy cattle population.

PubMed

Jenko, J; Wiggans, G R; Cooper, T A; Eaglen, S A E; Luff, W G de L; Bichard, M; Pong-Wong, R; Woolliams, J A

2017-01-01

This study compares how different cow genotyping strategies increase the accuracy of genomic estimated breeding values (EBV) in dairy cattle breeds with low numbers. In these breeds, few sires have progeny records, and genotyping cows can improve the accuracy of genomic EBV. The Guernsey breed is a small dairy cattle breed with approximately 14,000 recorded individuals worldwide. Predictions of phenotypes of milk yield, fat yield, protein yield, and calving interval were made for Guernsey cows from England and Guernsey Island using genomic EBV, with training sets including 197 de-regressed proofs of genotyped bulls, with cows selected from among 1,440 genotyped cows using different genotyping strategies. Accuracies of predictions were tested using 10-fold cross-validation among the cows. Genomic EBV were predicted using 4 different methods: (1) pedigree BLUP, (2) genomic BLUP using only bulls, (3) univariate genomic BLUP using bulls and cows, and (4) bivariate genomic BLUP. Genotyping cows with phenotypes and using their data for the prediction of single nucleotide polymorphism effects increased the correlation between genomic EBV and phenotypes compared with using only bulls by 0.163±0.022 for milk yield, 0.111±0.021 for fat yield, and 0.113±0.018 for protein yield; a decrease of 0.014±0.010 for calving interval from a low base was the only exception. Genetic correlation between phenotypes from bulls and cows were approximately 0.6 for all yield traits and significantly different from 1. Only a very small change occurred in correlation between genomic EBV and phenotypes when using the bivariate model. It was always better to genotype all the cows, but when only half of the cows were genotyped, a divergent selection strategy was better compared with the random or directional selection approach. Divergent selection of 30% of the cows remained superior for the yield traits in 8 of 10 folds. Copyright © 2017 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Comparison between fine needle aspiration cytology (FNAC) and core needle biopsy (CNB) in the diagnosis of breast lesions.

PubMed

Moschetta, M; Telegrafo, M; Carluccio, D A; Jablonska, J P; Rella, L; Serio, Gabriella; Carrozzo, M; Stabile Ianora, A A; Angelelli, G

2014-01-01

To compare the diagnostic accuracy of fine-needle aspiration cytology (FNAC) and core needle biopsy (CNB) in patients with USdetected breast lesions. Between September 2011 and May 2013, 3469 consecutive breast US examinations were performed. 400 breast nodules were detected in 398 patients. 210 FNACs and 190 CNBs were performed. 183 out of 400 (46%) lesions were surgically removed within 30 days form diagnosis; in the remaining cases, a six month follow up US examination was performed. Sensitivity, specificity, diagnostic accuracy, positive predictive (PPV) and negative predictive (NPV) values were calculated for FNAC and CNB. 174 out of 400 (43%) malignant lesions were found while the remaining 226 resulted to be benign lesions. 166 out of 210 (79%) FNACs and 154 out of 190 (81%) CNBs provided diagnostic specimens. Sensitivity, specificity, diagnostic accuracy, PPV and NPV of 97%, 94%, 95%, 91% and 98% were found for FNAC, and values of 92%, 82%, 89%, 92% and 82% were obtained for CNB. Sensitivity, specificity, diagnostic accuracy, PPV and NPV of 97%, 96%, 96%, 97% and 96% were found for FNAC, and values of 97%, 96%, 96%, 97% and 96% were obtained for CNB. FNAC and CNB provide similar values of diagnostic accuracy.

On-line analysis of algae in water by discrete three-dimensional fluorescence spectroscopy.

PubMed

Zhao, Nanjing; Zhang, Xiaoling; Yin, Gaofang; Yang, Ruifang; Hu, Li; Chen, Shuang; Liu, Jianguo; Liu, Wenqing

2018-03-19

In view of the problem of the on-line measurement of algae classification, a method of algae classification and concentration determination based on the discrete three-dimensional fluorescence spectra was studied in this work. The discrete three-dimensional fluorescence spectra of twelve common species of algae belonging to five categories were analyzed, the discrete three-dimensional standard spectra of five categories were built, and the recognition, classification and concentration prediction of algae categories were realized by the discrete three-dimensional fluorescence spectra coupled with non-negative weighted least squares linear regression analysis. The results show that similarities between discrete three-dimensional standard spectra of different categories were reduced and the accuracies of recognition, classification and concentration prediction of the algae categories were significantly improved. By comparing with that of the chlorophyll a fluorescence excitation spectra method, the recognition accuracy rate in pure samples by discrete three-dimensional fluorescence spectra is improved 1.38%, and the recovery rate and classification accuracy in pure diatom samples 34.1% and 46.8%, respectively; the recognition accuracy rate of mixed samples by discrete-three dimensional fluorescence spectra is enhanced by 26.1%, the recovery rate of mixed samples with Chlorophyta 37.8%, and the classification accuracy of mixed samples with diatoms 54.6%.

Genomic selection accuracies within and between environments and small breeding groups in white spruce.

PubMed

Beaulieu, Jean; Doerksen, Trevor K; MacKay, John; Rainville, André; Bousquet, Jean

2014-12-02

Genomic selection (GS) may improve selection response over conventional pedigree-based selection if markers capture more detailed information than pedigrees in recently domesticated tree species and/or make it more cost effective. Genomic prediction accuracies using 1748 trees and 6932 SNPs representative of as many distinct gene loci were determined for growth and wood traits in white spruce, within and between environments and breeding groups (BG), each with an effective size of Ne ≈ 20. Marker subsets were also tested. Model fits and/or cross-validation (CV) prediction accuracies for ridge regression (RR) and the least absolute shrinkage and selection operator models approached those of pedigree-based models. With strong relatedness between CV sets, prediction accuracies for RR within environment and BG were high for wood (r = 0.71-0.79) and moderately high for growth (r = 0.52-0.69) traits, in line with trends in heritabilities. For both classes of traits, these accuracies achieved between 83% and 92% of those obtained with phenotypes and pedigree information. Prediction into untested environments remained moderately high for wood (r ≥ 0.61) but dropped significantly for growth (r ≥ 0.24) traits, emphasizing the need to phenotype in all test environments and model genotype-by-environment interactions for growth traits. Removing relatedness between CV sets sharply decreased prediction accuracies for all traits and subpopulations, falling near zero between BGs with no known shared ancestry. For marker subsets, similar patterns were observed but with lower prediction accuracies. Given the need for high relatedness between CV sets to obtain good prediction accuracies, we recommend to build GS models for prediction within the same breeding population only. Breeding groups could be merged to build genomic prediction models as long as the total effective population size does not exceed 50 individuals in order to obtain high prediction accuracy such as that obtained in the present study. A number of markers limited to a few hundred would not negatively impact prediction accuracies, but these could decrease more rapidly over generations. The most promising short-term approach for genomic selection would likely be the selection of superior individuals within large full-sib families vegetatively propagated to implement multiclonal forestry.

An alternative data filling approach for prediction of missing data in soft sets (ADFIS).

PubMed

Sadiq Khan, Muhammad; Al-Garadi, Mohammed Ali; Wahab, Ainuddin Wahid Abdul; Herawan, Tutut

2016-01-01

Soft set theory is a mathematical approach that provides solution for dealing with uncertain data. As a standard soft set, it can be represented as a Boolean-valued information system, and hence it has been used in hundreds of useful applications. Meanwhile, these applications become worthless if the Boolean information system contains missing data due to error, security or mishandling. Few researches exist that focused on handling partially incomplete soft set and none of them has high accuracy rate in prediction performance of handling missing data. It is shown that the data filling approach for incomplete soft set (DFIS) has the best performance among all previous approaches. However, in reviewing DFIS, accuracy is still its main problem. In this paper, we propose an alternative data filling approach for prediction of missing data in soft sets, namely ADFIS. The novelty of ADFIS is that, unlike the previous approach that used probability, we focus more on reliability of association among parameters in soft set. Experimental results on small, 04 UCI benchmark data and causality workbench lung cancer (LUCAP2) data shows that ADFIS performs better accuracy as compared to DFIS.

Kalman/Map filtering-aided fast normalized cross correlation-based Wi-Fi fingerprinting location sensing.

PubMed

Sun, Yongliang; Xu, Yubin; Li, Cheng; Ma, Lin

2013-11-13

A Kalman/map filtering (KMF)-aided fast normalized cross correlation (FNCC)-based Wi-Fi fingerprinting location sensing system is proposed in this paper. Compared with conventional neighbor selection algorithms that calculate localization results with received signal strength (RSS) mean samples, the proposed FNCC algorithm makes use of all the on-line RSS samples and reference point RSS variations to achieve higher fingerprinting accuracy. The FNCC computes efficiently while maintaining the same accuracy as the basic normalized cross correlation. Additionally, a KMF is also proposed to process fingerprinting localization results. It employs a new map matching algorithm to nonlinearize the linear location prediction process of Kalman filtering (KF) that takes advantage of spatial proximities of consecutive localization results. With a calibration model integrated into an indoor map, the map matching algorithm corrects unreasonable prediction locations of the KF according to the building interior structure. Thus, more accurate prediction locations are obtained. Using these locations, the KMF considerably improves fingerprinting algorithm performance. Experimental results demonstrate that the FNCC algorithm with reduced computational complexity outperforms other neighbor selection algorithms and the KMF effectively improves location sensing accuracy by using indoor map information and spatial proximities of consecutive localization results.

Kalman/Map Filtering-Aided Fast Normalized Cross Correlation-Based Wi-Fi Fingerprinting Location Sensing

PubMed Central

Sun, Yongliang; Xu, Yubin; Li, Cheng; Ma, Lin

2013-01-01

A Kalman/map filtering (KMF)-aided fast normalized cross correlation (FNCC)-based Wi-Fi fingerprinting location sensing system is proposed in this paper. Compared with conventional neighbor selection algorithms that calculate localization results with received signal strength (RSS) mean samples, the proposed FNCC algorithm makes use of all the on-line RSS samples and reference point RSS variations to achieve higher fingerprinting accuracy. The FNCC computes efficiently while maintaining the same accuracy as the basic normalized cross correlation. Additionally, a KMF is also proposed to process fingerprinting localization results. It employs a new map matching algorithm to nonlinearize the linear location prediction process of Kalman filtering (KF) that takes advantage of spatial proximities of consecutive localization results. With a calibration model integrated into an indoor map, the map matching algorithm corrects unreasonable prediction locations of the KF according to the building interior structure. Thus, more accurate prediction locations are obtained. Using these locations, the KMF considerably improves fingerprinting algorithm performance. Experimental results demonstrate that the FNCC algorithm with reduced computational complexity outperforms other neighbor selection algorithms and the KMF effectively improves location sensing accuracy by using indoor map information and spatial proximities of consecutive localization results. PMID:24233027

Clinical application of the basic definition of malnutrition proposed by the European Society for Clinical Nutrition and Metabolism (ESPEN): Comparison with classical tools in geriatric care.

PubMed

Sánchez-Rodríguez, Dolores; Annweiler, Cédric; Ronquillo-Moreno, Natalia; Tortosa-Rodríguez, Andrea; Guillén-Solà, Anna; Vázquez-Ibar, Olga; Escalada, Ferran; Muniesa, Josep M; Marco, Ester

Malnutrition is a prevalent condition related to adverse outcomes in older people. Our aim was to compare the diagnostic capacity of the malnutrition criteria of the European Society of Parenteral and Enteral Nutrition (ESPEN) with other classical diagnostic tools. Cohort study of 102 consecutive in-patients ≥70 years admitted for postacute rehabilitation. Patients were considered malnourished if their Mini-Nutritional Assessment-Short Form (MNA-SF) score was ≤11 and serum albumin <3 mg/dL or MNA-SF ≤ 11, serum albumin <3 mg/dL, and usual clinical signs and symptoms of malnutrition. Sensitivity, specificity, positive and negative predictive values, accuracy likelihood ratios, and kappa values were calculated for both methods: and compared with ESPEN consensus. Of 102 eligible in-patients, 88 fulfilled inclusion criteria and were identified as "at risk" by MNA-SF. Malnutrition diagnosis was confirmed in 11.6% and 10.5% of the patients using classical methods,whereas 19.3% were malnourished according to the ESPEN criteria. Combined with low albumin levels, the diagnosis showed 57.9% sensitivity, 64.5% specificity, 85.9% negative predictive value,0.63 accuracy (fair validity, low range), and kappa index of 0.163 (poor ESPEN agreement). The combination of MNA-SF, low albumin, and clinical malnutrition showed 52.6% sensitivity, 88.3% specificity, 88.3%negative predictive value, and 0.82 accuracy (fair validity, low range), and kappa index of 0.43 (fair ESPEN agreement). Malnutrition was almost twice as prevalent when diagnosed by the ESPEN consensus, compared to classical assessment methods: Classical methods: showed fair validity and poor agreement with the ESPEN consensus in assessing malnutrition in geriatric postacute care. Copyright © 2018 Elsevier B.V. All rights reserved.

Neural Network Prediction of ICU Length of Stay Following Cardiac Surgery Based on Pre-Incision Variables

PubMed Central

Pothula, Venu M.; Yuan, Stanley C.; Maerz, David A.; Montes, Lucresia; Oleszkiewicz, Stephen M.; Yusupov, Albert; Perline, Richard

2015-01-01

Background Advanced predictive analytical techniques are being increasingly applied to clinical risk assessment. This study compared a neural network model to several other models in predicting the length of stay (LOS) in the cardiac surgical intensive care unit (ICU) based on pre-incision patient characteristics. Methods Thirty six variables collected from 185 cardiac surgical patients were analyzed for contribution to ICU LOS. The Automatic Linear Modeling (ALM) module of IBM-SPSS software identified 8 factors with statistically significant associations with ICU LOS; these factors were also analyzed with the Artificial Neural Network (ANN) module of the same software. The weighted contributions of each factor (“trained” data) were then applied to data for a “new” patient to predict ICU LOS for that individual. Results Factors identified in the ALM model were: use of an intra-aortic balloon pump; O2 delivery index; age; use of positive cardiac inotropic agents; hematocrit; serum creatinine ≥ 1.3 mg/deciliter; gender; arterial pCO2. The r2 value for ALM prediction of ICU LOS in the initial (training) model was 0.356, p <0.0001. Cross validation in prediction of a “new” patient yielded r2 = 0.200, p <0.0001. The same 8 factors analyzed with ANN yielded a training prediction r2 of 0.535 (p <0.0001) and a cross validation prediction r2 of 0.410, p <0.0001. Two additional predictive algorithms were studied, but they had lower prediction accuracies. Our validated neural network model identified the upper quartile of ICU LOS with an odds ratio of 9.8(p <0.0001). Conclusions ANN demonstrated a 2-fold greater accuracy than ALM in prediction of observed ICU LOS. This greater accuracy would be presumed to result from the capacity of ANN to capture nonlinear effects and higher order interactions. Predictive modeling may be of value in early anticipation of risks of post-operative morbidity and utilization of ICU facilities. PMID:26710254

Predictive value of Tokuhashi scoring systems in spinal metastases, focusing on various primary tumor groups: evaluation of 448 patients in the Aarhus spinal metastases database.

PubMed

Wang, Miao; Bünger, Cody Eric; Li, Haisheng; Wu, Chunsen; Høy, Kristian; Niedermann, Bent; Helmig, Peter; Wang, Yu; Jensen, Anders Bonde; Schättiger, Katrin; Hansen, Ebbe Stender

2012-04-01

We conducted a prospective cohort study of 448 patients with spinal metastases from a variety of cancer groups. To determine the specific predictive value of the Tokuhashi scoring system (T12) and its revised version (T15) in spinal metastases of various primary tumors. The life expectancy of patients with spinal metastases is one of the most important factors in selecting the treatment modality. Tokuhashi et al formulated a prognostic scoring system with a total sum of 12 points for preoperative prediction of life expectancy in 1990 and revised it in 2005 to a total sum of 15 points. There is a lack of knowledge about the specific predictive value of those scoring systems in patients with spinal metastases from a variety of cancer groups. We included 448 patients with vertebral metastases who underwent surgical treatment during November 1992 to November 2009 in Aarhus University Hospital NBG. Data were retrieved from Aarhus Metastases Database. Scores based on T12 and T15 were calculated prospectively for each patient. We divided all the patients into different groups dictated by the site of their primary tumor. Predictive value and accuracy rate of the 2 scoring systems were compared in each cancer group. Both the T12 and T15 scoring systems showed statistically significant predictive value when the 448 patients were analyzed in total (T12, P < 0.0001; T15, P < 0.0001). The accuracy rate was significantly higher in T15 (P < 0.0001) than in T12. The further analyses by primary cancer groups showed that the predictive value of T12 and T15 was primarily determined by the prostate (P = 0.0003) and breast group (P = 0.0385). Only T12 displayed predictive value in the colon group (P = 0.0011). Neither of the scoring systems showed significant predictive value in the lung (P > 0.05), renal (P > 0.05), or miscellaneous primary tumor groups (P > 0.05). The accuracy rate of prognosis in T15 was significantly improved in the prostate (P = 0.0032) and breast group (P < 0.0001). Both T12 and T15 showed significant predictive value in patients with spinal metastases. T15 has a statistically higher accuracy rate than T12. Among the various cancer groups, the 2 scoring systems are especially reliable in prostate and breast metastases groups. T15 is recommended as superior to T12 because of its higher accuracy rate.

The need to approximate the use-case in clinical machine learning.

PubMed

Saeb, Sohrab; Lonini, Luca; Jayaraman, Arun; Mohr, David C; Kording, Konrad P

2017-05-01

The availability of smartphone and wearable sensor technology is leading to a rapid accumulation of human subject data, and machine learning is emerging as a technique to map those data into clinical predictions. As machine learning algorithms are increasingly used to support clinical decision making, it is vital to reliably quantify their prediction accuracy. Cross-validation (CV) is the standard approach where the accuracy of such algorithms is evaluated on part of the data the algorithm has not seen during training. However, for this procedure to be meaningful, the relationship between the training and the validation set should mimic the relationship between the training set and the dataset expected for the clinical use. Here we compared two popular CV methods: record-wise and subject-wise. While the subject-wise method mirrors the clinically relevant use-case scenario of diagnosis in newly recruited subjects, the record-wise strategy has no such interpretation. Using both a publicly available dataset and a simulation, we found that record-wise CV often massively overestimates the prediction accuracy of the algorithms. We also conducted a systematic review of the relevant literature, and found that this overly optimistic method was used by almost half of the retrieved studies that used accelerometers, wearable sensors, or smartphones to predict clinical outcomes. As we move towards an era of machine learning-based diagnosis and treatment, using proper methods to evaluate their accuracy is crucial, as inaccurate results can mislead both clinicians and data scientists. © The Author 2017. Published by Oxford University Press.

The Pandolf equation under-predicts the metabolic rate of contemporary military load carriage.

PubMed

Drain, Jace R; Aisbett, Brad; Lewis, Michael; Billing, Daniel C

2017-11-01

This investigation assessed the accuracy of error of the Pandolf load carriage energy expenditure equation when simulating contemporary military conditions (load distribution, external load and walking speed). Within-participant design. Sixteen male participants completed 10 trials comprised of five walking speeds (2.5, 3.5, 4.5, 5.5 and 6.5km·h -1 ) and two external loads (22.7 and 38.4kg). The Pandolf equation demonstrated poor predictive precision, with a mean bias of 124.9W and -48.7 to 298.5W 95% limits of agreement. Furthermore, the Pandolf equation systematically under-predicted metabolic rate (p<0.05) across the 10 speed-load combinations. Predicted metabolic rate error ranged from 12-33% across all conditions with the 'moderate' walking speeds (i.e. 4.5-5.5km·h -1 ) yielding less prediction error (12-17%) when compared to the slower and faster walking speeds (21-33%). Factors such as mechanical efficiency and load distribution contribute to the impaired predictive accuracy. The authors suggest the Pandolf equation should be applied to military load carriage with caution. Copyright © 2017 Sports Medicine Australia. All rights reserved.

Adjustment of regional regression models of urban-runoff quality using data for Chattanooga, Knoxville, and Nashville, Tennessee

USGS Publications Warehouse

Hoos, Anne B.; Patel, Anant R.

1996-01-01

Model-adjustment procedures were applied to the combined data bases of storm-runoff quality for Chattanooga, Knoxville, and Nashville, Tennessee, to improve predictive accuracy for storm-runoff quality for urban watersheds in these three cities and throughout Middle and East Tennessee. Data for 45 storms at 15 different sites (five sites in each city) constitute the data base. Comparison of observed values of storm-runoff load and event-mean concentration to the predicted values from the regional regression models for 10 constituents shows prediction errors, as large as 806,000 percent. Model-adjustment procedures, which combine the regional model predictions with local data, are applied to improve predictive accuracy. Standard error of estimate after model adjustment ranges from 67 to 322 percent. Calibration results may be biased due to sampling error in the Tennessee data base. The relatively large values of standard error of estimate for some of the constituent models, although representing significant reduction (at least 50 percent) in prediction error compared to estimation with unadjusted regional models, may be unacceptable for some applications. The user may wish to collect additional local data for these constituents and repeat the analysis, or calibrate an independent local regression model.

Impacts of Satellite Orbit and Clock on Real-Time GPS Point and Relative Positioning.

PubMed

Shi, Junbo; Wang, Gaojing; Han, Xianquan; Guo, Jiming

2017-06-12

Satellite orbit and clock corrections are always treated as known quantities in GPS positioning models. Therefore, any error in the satellite orbit and clock products will probably cause significant consequences for GPS positioning, especially for real-time applications. Currently three types of satellite products have been made available for real-time positioning, including the broadcast ephemeris, the International GNSS Service (IGS) predicted ultra-rapid product, and the real-time product. In this study, these three predicted/real-time satellite orbit and clock products are first evaluated with respect to the post-mission IGS final product, which demonstrates cm to m level orbit accuracies and sub-ns to ns level clock accuracies. Impacts of real-time satellite orbit and clock products on GPS point and relative positioning are then investigated using the P3 and GAMIT software packages, respectively. Numerical results show that the real-time satellite clock corrections affect the point positioning more significantly than the orbit corrections. On the contrary, only the real-time orbit corrections impact the relative positioning. Compared with the positioning solution using the IGS final product with the nominal orbit accuracy of ~2.5 cm, the real-time broadcast ephemeris with ~2 m orbit accuracy provided <2 cm relative positioning error for baselines no longer than 216 km. As for the baselines ranging from 574 to 2982 km, the cm-dm level positioning error was identified for the relative positioning solution using the broadcast ephemeris. The real-time product could result in <5 mm relative positioning accuracy for baselines within 2982 km, slightly better than the predicted ultra-rapid product.

An interpolation method for stream habitat assessments

USGS Publications Warehouse

Sheehan, Kenneth R.; Welsh, Stuart A.

2015-01-01

Interpolation of stream habitat can be very useful for habitat assessment. Using a small number of habitat samples to predict the habitat of larger areas can reduce time and labor costs as long as it provides accurate estimates of habitat. The spatial correlation of stream habitat variables such as substrate and depth improves the accuracy of interpolated data. Several geographical information system interpolation methods (natural neighbor, inverse distance weighted, ordinary kriging, spline, and universal kriging) were used to predict substrate and depth within a 210.7-m2 section of a second-order stream based on 2.5% and 5.0% sampling of the total area. Depth and substrate were recorded for the entire study site and compared with the interpolated values to determine the accuracy of the predictions. In all instances, the 5% interpolations were more accurate for both depth and substrate than the 2.5% interpolations, which achieved accuracies up to 95% and 92%, respectively. Interpolations of depth based on 2.5% sampling attained accuracies of 49–92%, whereas those based on 5% percent sampling attained accuracies of 57–95%. Natural neighbor interpolation was more accurate than that using the inverse distance weighted, ordinary kriging, spline, and universal kriging approaches. Our findings demonstrate the effective use of minimal amounts of small-scale data for the interpolation of habitat over large areas of a stream channel. Use of this method will provide time and cost savings in the assessment of large sections of rivers as well as functional maps to aid the habitat-based management of aquatic species.

Genomic selection across multiple breeding cycles in applied bread wheat breeding.

PubMed

Michel, Sebastian; Ametz, Christian; Gungor, Huseyin; Epure, Doru; Grausgruber, Heinrich; Löschenberger, Franziska; Buerstmayr, Hermann

2016-06-01

We evaluated genomic selection across five breeding cycles of bread wheat breeding. Bias of within-cycle cross-validation and methods for improving the prediction accuracy were assessed. The prospect of genomic selection has been frequently shown by cross-validation studies using the same genetic material across multiple environments, but studies investigating genomic selection across multiple breeding cycles in applied bread wheat breeding are lacking. We estimated the prediction accuracy of grain yield, protein content and protein yield of 659 inbred lines across five independent breeding cycles and assessed the bias of within-cycle cross-validation. We investigated the influence of outliers on the prediction accuracy and predicted protein yield by its components traits. A high average heritability was estimated for protein content, followed by grain yield and protein yield. The bias of the prediction accuracy using populations from individual cycles using fivefold cross-validation was accordingly substantial for protein yield (17-712 %) and less pronounced for protein content (8-86 %). Cross-validation using the cycles as folds aimed to avoid this bias and reached a maximum prediction accuracy of [Formula: see text] = 0.51 for protein content, [Formula: see text] = 0.38 for grain yield and [Formula: see text] = 0.16 for protein yield. Dropping outlier cycles increased the prediction accuracy of grain yield to [Formula: see text] = 0.41 as estimated by cross-validation, while dropping outlier environments did not have a significant effect on the prediction accuracy. Independent validation suggests, on the other hand, that careful consideration is necessary before an outlier correction is undertaken, which removes lines from the training population. Predicting protein yield by multiplying genomic estimated breeding values of grain yield and protein content raised the prediction accuracy to [Formula: see text] = 0.19 for this derived trait.

Machine Learning and Neurosurgical Outcome Prediction: A Systematic Review.

PubMed

Senders, Joeky T; Staples, Patrick C; Karhade, Aditya V; Zaki, Mark M; Gormley, William B; Broekman, Marike L D; Smith, Timothy R; Arnaout, Omar

2018-01-01

Accurate measurement of surgical outcomes is highly desirable to optimize surgical decision-making. An important element of surgical decision making is identification of the patient cohort that will benefit from surgery before the intervention. Machine learning (ML) enables computers to learn from previous data to make accurate predictions on new data. In this systematic review, we evaluate the potential of ML for neurosurgical outcome prediction. A systematic search in the PubMed and Embase databases was performed to identify all potential relevant studies up to January 1, 2017. Thirty studies were identified that evaluated ML algorithms used as prediction models for survival, recurrence, symptom improvement, and adverse events in patients undergoing surgery for epilepsy, brain tumor, spinal lesions, neurovascular disease, movement disorders, traumatic brain injury, and hydrocephalus. Depending on the specific prediction task evaluated and the type of input features included, ML models predicted outcomes after neurosurgery with a median accuracy and area under the receiver operating curve of 94.5% and 0.83, respectively. Compared with logistic regression, ML models performed significantly better and showed a median absolute improvement in accuracy and area under the receiver operating curve of 15% and 0.06, respectively. Some studies also demonstrated a better performance in ML models compared with established prognostic indices and clinical experts. In the research setting, ML has been studied extensively, demonstrating an excellent performance in outcome prediction for a wide range of neurosurgical conditions. However, future studies should investigate how ML can be implemented as a practical tool supporting neurosurgical care. Copyright © 2017 Elsevier Inc. All rights reserved.

Training set selection for the prediction of essential genes.

PubMed

Cheng, Jian; Xu, Zhao; Wu, Wenwu; Zhao, Li; Li, Xiangchen; Liu, Yanlin; Tao, Shiheng

2014-01-01

Various computational models have been developed to transfer annotations of gene essentiality between organisms. However, despite the increasing number of microorganisms with well-characterized sets of essential genes, selection of appropriate training sets for predicting the essential genes of poorly-studied or newly sequenced organisms remains challenging. In this study, a machine learning approach was applied reciprocally to predict the essential genes in 21 microorganisms. Results showed that training set selection greatly influenced predictive accuracy. We determined four criteria for training set selection: (1) essential genes in the selected training set should be reliable; (2) the growth conditions in which essential genes are defined should be consistent in training and prediction sets; (3) species used as training set should be closely related to the target organism; and (4) organisms used as training and prediction sets should exhibit similar phenotypes or lifestyles. We then analyzed the performance of an incomplete training set and an integrated training set with multiple organisms. We found that the size of the training set should be at least 10% of the total genes to yield accurate predictions. Additionally, the integrated training sets exhibited remarkable increase in stability and accuracy compared with single sets. Finally, we compared the performance of the integrated training sets with the four criteria and with random selection. The results revealed that a rational selection of training sets based on our criteria yields better performance than random selection. Thus, our results provide empirical guidance on training set selection for the identification of essential genes on a genome-wide scale.