A metabolic fingerprinting approach based on selected ion flow tube mass spectrometry (SIFT-MS) and chemometrics: A reliable tool for Mediterranean origin-labeled olive oils authentication.

PubMed

Bajoub, Aadil; Medina-Rodríguez, Santiago; Ajal, El Amine; Cuadros-Rodríguez, Luis; Monasterio, Romina Paula; Vercammen, Joeri; Fernández-Gutiérrez, Alberto; Carrasco-Pancorbo, Alegría

2018-04-01

Selected Ion flow tube mass spectrometry (SIFT-MS) in combination with chemometrics was used to authenticate the geographical origin of Mediterranean virgin olive oils (VOOs) produced under geographical origin labels. In particular, 130 oil samples from six different Mediterranean regions (Kalamata (Greece); Toscana (Italy); Meknès and Tyout (Morocco); and Priego de Córdoba and Baena (Spain)) were considered. The headspace volatile fingerprints were measured by SIFT-MS in full scan with H 3 O + , NO + and O 2 + as precursor ions and the results were subjected to chemometric treatments. Principal Component Analysis (PCA) was used for preliminary multivariate data analysis and Partial Least Squares-Discriminant Analysis (PLS-DA) was applied to build different models (considering the three reagent ions) to classify samples according to the country of origin and regions (within the same country). The multi-class PLS-DA models showed very good performance in terms of fitting accuracy (98.90-100%) and prediction accuracy (96.70-100% accuracy for cross validation and 97.30-100% accuracy for external validation (test set)). Considering the two-class PLS-DA models, the one for the Spanish samples showed 100% sensitivity, specificity and accuracy in calibration, cross validation and external validation; the model for Moroccan oils also showed very satisfactory results (with perfect scores for almost every parameter in all the cases). Copyright © 2017 Elsevier Ltd. All rights reserved.

Accuracy of genomic selection in European maize elite breeding populations.

PubMed

Zhao, Yusheng; Gowda, Manje; Liu, Wenxin; Würschum, Tobias; Maurer, Hans P; Longin, Friedrich H; Ranc, Nicolas; Reif, Jochen C

2012-03-01

Genomic selection is a promising breeding strategy for rapid improvement of complex traits. The objective of our study was to investigate the prediction accuracy of genomic breeding values through cross validation. The study was based on experimental data of six segregating populations from a half-diallel mating design with 788 testcross progenies from an elite maize breeding program. The plants were intensively phenotyped in multi-location field trials and fingerprinted with 960 SNP markers. We used random regression best linear unbiased prediction in combination with fivefold cross validation. The prediction accuracy across populations was higher for grain moisture (0.90) than for grain yield (0.58). The accuracy of genomic selection realized for grain yield corresponds to the precision of phenotyping at unreplicated field trials in 3-4 locations. As for maize up to three generations are feasible per year, selection gain per unit time is high and, consequently, genomic selection holds great promise for maize breeding programs.

MetaKTSP: a meta-analytic top scoring pair method for robust cross-study validation of omics prediction analysis.

PubMed

Kim, SungHwan; Lin, Chien-Wei; Tseng, George C

2016-07-01

Supervised machine learning is widely applied to transcriptomic data to predict disease diagnosis, prognosis or survival. Robust and interpretable classifiers with high accuracy are usually favored for their clinical and translational potential. The top scoring pair (TSP) algorithm is an example that applies a simple rank-based algorithm to identify rank-altered gene pairs for classifier construction. Although many classification methods perform well in cross-validation of single expression profile, the performance usually greatly reduces in cross-study validation (i.e. the prediction model is established in the training study and applied to an independent test study) for all machine learning methods, including TSP. The failure of cross-study validation has largely diminished the potential translational and clinical values of the models. The purpose of this article is to develop a meta-analytic top scoring pair (MetaKTSP) framework that combines multiple transcriptomic studies and generates a robust prediction model applicable to independent test studies. We proposed two frameworks, by averaging TSP scores or by combining P-values from individual studies, to select the top gene pairs for model construction. We applied the proposed methods in simulated data sets and three large-scale real applications in breast cancer, idiopathic pulmonary fibrosis and pan-cancer methylation. The result showed superior performance of cross-study validation accuracy and biomarker selection for the new meta-analytic framework. In conclusion, combining multiple omics data sets in the public domain increases robustness and accuracy of the classification model that will ultimately improve disease understanding and clinical treatment decisions to benefit patients. An R package MetaKTSP is available online. (http://tsenglab.biostat.pitt.edu/software.htm). ctseng@pitt.edu Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Cross-Validation of Survival Bump Hunting by Recursive Peeling Methods.

PubMed

Dazard, Jean-Eudes; Choe, Michael; LeBlanc, Michael; Rao, J Sunil

2014-08-01

We introduce a survival/risk bump hunting framework to build a bump hunting model with a possibly censored time-to-event type of response and to validate model estimates. First, we describe the use of adequate survival peeling criteria to build a survival/risk bump hunting model based on recursive peeling methods. Our method called "Patient Recursive Survival Peeling" is a rule-induction method that makes use of specific peeling criteria such as hazard ratio or log-rank statistics. Second, to validate our model estimates and improve survival prediction accuracy, we describe a resampling-based validation technique specifically designed for the joint task of decision rule making by recursive peeling (i.e. decision-box) and survival estimation. This alternative technique, called "combined" cross-validation is done by combining test samples over the cross-validation loops, a design allowing for bump hunting by recursive peeling in a survival setting. We provide empirical results showing the importance of cross-validation and replication.

Cross-Validation of Survival Bump Hunting by Recursive Peeling Methods

PubMed Central

Dazard, Jean-Eudes; Choe, Michael; LeBlanc, Michael; Rao, J. Sunil

2015-01-01

We introduce a survival/risk bump hunting framework to build a bump hunting model with a possibly censored time-to-event type of response and to validate model estimates. First, we describe the use of adequate survival peeling criteria to build a survival/risk bump hunting model based on recursive peeling methods. Our method called “Patient Recursive Survival Peeling” is a rule-induction method that makes use of specific peeling criteria such as hazard ratio or log-rank statistics. Second, to validate our model estimates and improve survival prediction accuracy, we describe a resampling-based validation technique specifically designed for the joint task of decision rule making by recursive peeling (i.e. decision-box) and survival estimation. This alternative technique, called “combined” cross-validation is done by combining test samples over the cross-validation loops, a design allowing for bump hunting by recursive peeling in a survival setting. We provide empirical results showing the importance of cross-validation and replication. PMID:26997922

Psychometric Evaluation of the D-Catch, an Instrument to Measure the Accuracy of Nursing Documentation.

PubMed

D'Agostino, Fabio; Barbaranelli, Claudio; Paans, Wolter; Belsito, Romina; Juarez Vela, Raul; Alvaro, Rosaria; Vellone, Ercole

2017-07-01

To evaluate the psychometric properties of the D-Catch instrument. A cross-sectional methodological study. Validity and reliability were estimated with confirmatory factor analysis (CFA) and internal consistency and inter-rater reliability, respectively. A sample of 250 nursing documentations was selected. CFA showed the adequacy of a 1-factor model (chronologically descriptive accuracy) with an outlier item (nursing diagnosis accuracy). Internal consistency and inter-rater reliability were adequate. The D-Catch is a valid and reliable instrument for measuring the accuracy of nursing documentation. Caution is needed when measuring diagnostic accuracy since only one item measures this dimension. The D-Catch can be used as an indicator of the accuracy of nursing documentation and the quality of nursing care. © 2015 NANDA International, Inc.

Validation of Cross Sections for Monte Carlo Simulation of the Photoelectric Effect

NASA Astrophysics Data System (ADS)

Han, Min Cheol; Kim, Han Sung; Pia, Maria Grazia; Basaglia, Tullio; Batič, Matej; Hoff, Gabriela; Kim, Chan Hyeong; Saracco, Paolo

2016-04-01

Several total and partial photoionization cross section calculations, based on both theoretical and empirical approaches, are quantitatively evaluated with statistical analyses using a large collection of experimental data retrieved from the literature to identify the state of the art for modeling the photoelectric effect in Monte Carlo particle transport. Some of the examined cross section models are available in general purpose Monte Carlo systems, while others have been implemented and subjected to validation tests for the first time to estimate whether they could improve the accuracy of particle transport codes. The validation process identifies Scofield's 1973 non-relativistic calculations, tabulated in the Evaluated Photon Data Library (EPDL), as the one best reproducing experimental measurements of total cross sections. Specialized total cross section models, some of which derive from more recent calculations, do not provide significant improvements. Scofield's non-relativistic calculations are not surpassed regarding the compatibility with experiment of K and L shell photoionization cross sections either, although in a few test cases Ebel's parameterization produces more accurate results close to absorption edges. Modifications to Biggs and Lighthill's parameterization implemented in Geant4 significantly reduce the accuracy of total cross sections at low energies with respect to its original formulation. The scarcity of suitable experimental data hinders a similar extensive analysis for the simulation of the photoelectron angular distribution, which is limited to a qualitative appraisal.

A Machine Learning and Cross-Validation Approach for the Discrimination of Vegetation Physiognomic Types Using Satellite Based Multispectral and Multitemporal Data.

PubMed

Sharma, Ram C; Hara, Keitarou; Hirayama, Hidetake

2017-01-01

This paper presents the performance and evaluation of a number of machine learning classifiers for the discrimination between the vegetation physiognomic classes using the satellite based time-series of the surface reflectance data. Discrimination of six vegetation physiognomic classes, Evergreen Coniferous Forest, Evergreen Broadleaf Forest, Deciduous Coniferous Forest, Deciduous Broadleaf Forest, Shrubs, and Herbs, was dealt with in the research. Rich-feature data were prepared from time-series of the satellite data for the discrimination and cross-validation of the vegetation physiognomic types using machine learning approach. A set of machine learning experiments comprised of a number of supervised classifiers with different model parameters was conducted to assess how the discrimination of vegetation physiognomic classes varies with classifiers, input features, and ground truth data size. The performance of each experiment was evaluated by using the 10-fold cross-validation method. Experiment using the Random Forests classifier provided highest overall accuracy (0.81) and kappa coefficient (0.78). However, accuracy metrics did not vary much with experiments. Accuracy metrics were found to be very sensitive to input features and size of ground truth data. The results obtained in the research are expected to be useful for improving the vegetation physiognomic mapping in Japan.

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.

Knowledge discovery by accuracy maximization

PubMed Central

Cacciatore, Stefano; Luchinat, Claudio; Tenori, Leonardo

2014-01-01

Here we describe KODAMA (knowledge discovery by accuracy maximization), an unsupervised and semisupervised learning algorithm that performs feature extraction from noisy and high-dimensional data. Unlike other data mining methods, the peculiarity of KODAMA is that it is driven by an integrated procedure of cross-validation of the results. The discovery of a local manifold’s topology is led by a classifier through a Monte Carlo procedure of maximization of cross-validated predictive accuracy. Briefly, our approach differs from previous methods in that it has an integrated procedure of validation of the results. In this way, the method ensures the highest robustness of the obtained solution. This robustness is demonstrated on experimental datasets of gene expression and metabolomics, where KODAMA compares favorably with other existing feature extraction methods. KODAMA is then applied to an astronomical dataset, revealing unexpected features. Interesting and not easily predictable features are also found in the analysis of the State of the Union speeches by American presidents: KODAMA reveals an abrupt linguistic transition sharply separating all post-Reagan from all pre-Reagan speeches. The transition occurs during Reagan’s presidency and not from its beginning. PMID:24706821

Accuracies of genomic breeding values in American Angus beef cattle using K-means clustering for cross-validation.

PubMed

Saatchi, Mahdi; McClure, Mathew C; McKay, Stephanie D; Rolf, Megan M; Kim, JaeWoo; Decker, Jared E; Taxis, Tasia M; Chapple, Richard H; Ramey, Holly R; Northcutt, Sally L; Bauck, Stewart; Woodward, Brent; Dekkers, Jack C M; Fernando, Rohan L; Schnabel, Robert D; Garrick, Dorian J; Taylor, Jeremy F

2011-11-28

Genomic selection is a recently developed technology that is beginning to revolutionize animal breeding. The objective of this study was to estimate marker effects to derive prediction equations for direct genomic values for 16 routinely recorded traits of American Angus beef cattle and quantify corresponding accuracies of prediction. Deregressed estimated breeding values were used as observations in a weighted analysis to derive direct genomic values for 3570 sires genotyped using the Illumina BovineSNP50 BeadChip. These bulls were clustered into five groups using K-means clustering on pedigree estimates of additive genetic relationships between animals, with the aim of increasing within-group and decreasing between-group relationships. All five combinations of four groups were used for model training, with cross-validation performed in the group not used in training. Bivariate animal models were used for each trait to estimate the genetic correlation between deregressed estimated breeding values and direct genomic values. Accuracies of direct genomic values ranged from 0.22 to 0.69 for the studied traits, with an average of 0.44. Predictions were more accurate when animals within the validation group were more closely related to animals in the training set. When training and validation sets were formed by random allocation, the accuracies of direct genomic values ranged from 0.38 to 0.85, with an average of 0.65, reflecting the greater relationship between animals in training and validation. The accuracies of direct genomic values obtained from training on older animals and validating in younger animals were intermediate to the accuracies obtained from K-means clustering and random clustering for most traits. The genetic correlation between deregressed estimated breeding values and direct genomic values ranged from 0.15 to 0.80 for the traits studied. These results suggest that genomic estimates of genetic merit can be produced in beef cattle at a young age but the recurrent inclusion of genotyped sires in retraining analyses will be necessary to routinely produce for the industry the direct genomic values with the highest accuracy.

Accuracies of genomic breeding values in American Angus beef cattle using K-means clustering for cross-validation

PubMed Central

2011-01-01

Background Genomic selection is a recently developed technology that is beginning to revolutionize animal breeding. The objective of this study was to estimate marker effects to derive prediction equations for direct genomic values for 16 routinely recorded traits of American Angus beef cattle and quantify corresponding accuracies of prediction. Methods Deregressed estimated breeding values were used as observations in a weighted analysis to derive direct genomic values for 3570 sires genotyped using the Illumina BovineSNP50 BeadChip. These bulls were clustered into five groups using K-means clustering on pedigree estimates of additive genetic relationships between animals, with the aim of increasing within-group and decreasing between-group relationships. All five combinations of four groups were used for model training, with cross-validation performed in the group not used in training. Bivariate animal models were used for each trait to estimate the genetic correlation between deregressed estimated breeding values and direct genomic values. Results Accuracies of direct genomic values ranged from 0.22 to 0.69 for the studied traits, with an average of 0.44. Predictions were more accurate when animals within the validation group were more closely related to animals in the training set. When training and validation sets were formed by random allocation, the accuracies of direct genomic values ranged from 0.38 to 0.85, with an average of 0.65, reflecting the greater relationship between animals in training and validation. The accuracies of direct genomic values obtained from training on older animals and validating in younger animals were intermediate to the accuracies obtained from K-means clustering and random clustering for most traits. The genetic correlation between deregressed estimated breeding values and direct genomic values ranged from 0.15 to 0.80 for the traits studied. Conclusions These results suggest that genomic estimates of genetic merit can be produced in beef cattle at a young age but the recurrent inclusion of genotyped sires in retraining analyses will be necessary to routinely produce for the industry the direct genomic values with the highest accuracy. PMID:22122853

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.

Sex estimation from measurements of the first rib in a contemporary Polish population.

PubMed

Kubicka, Anna Maria; Piontek, Janusz

2016-01-01

The aim of this study was to evaluate the accuracy of sex assessment using measurements of the first rib from computed tomography (CT) to develop a discriminant formula. Four discriminant formulae were derived based on CT imaging of the right first rib of 85 female and 91 male Polish patients of known age and sex. In direct discriminant analysis, the first equation consisted of all first rib variables; the second included measurements of the rib body; the third comprised only two measurements of the sternal end of the first rib. The stepwise method selected the four best variables from all measurements. The discriminant function equation was then tested on a cross-validated group consisting of 23 females and 24 males. The direct discriminant analysis showed that sex assessment was possible in 81.5% of cases in the first group and in 91.5% in the cross-validated group when all variables for the first rib were included. The average accuracy for the original group for rib body and sternal end was 80.9 and 67.9%, respectively. The percentages of correctly assigned individuals for the functions based on the rib body and sternal end in the cross-validated group were 76.6 and 85.0%, respectively. Higher average accuracies were obtained for stepwise discriminant analysis: 83.1% for the original group and 91.2% for the cross-validated group. The exterior edge, anterior-posterior of the sternal end, and depth of the arc were the most reliable parameters. Our results suggest that the first rib is dimorphic and that the described method can be used for sex assessment.

Automated detection of exudative age-related macular degeneration in spectral domain optical coherence tomography using deep learning.

PubMed

Treder, Maximilian; Lauermann, Jost Lennart; Eter, Nicole

2018-02-01

Our purpose was to use deep learning for the automated detection of age-related macular degeneration (AMD) in spectral domain optical coherence tomography (SD-OCT). A total of 1112 cross-section SD-OCT images of patients with exudative AMD and a healthy control group were used for this study. In the first step, an open-source multi-layer deep convolutional neural network (DCNN), which was pretrained with 1.2 million images from ImageNet, was trained and validated with 1012 cross-section SD-OCT scans (AMD: 701; healthy: 311). During this procedure training accuracy, validation accuracy and cross-entropy were computed. The open-source deep learning framework TensorFlow™ (Google Inc., Mountain View, CA, USA) was used to accelerate the deep learning process. In the last step, a created DCNN classifier, using the information of the above mentioned deep learning process, was tested in detecting 100 untrained cross-section SD-OCT images (AMD: 50; healthy: 50). Therefore, an AMD testing score was computed: 0.98 or higher was presumed for AMD. After an iteration of 500 training steps, the training accuracy and validation accuracies were 100%, and the cross-entropy was 0.005. The average AMD scores were 0.997 ± 0.003 in the AMD testing group and 0.9203 ± 0.085 in the healthy comparison group. The difference between the two groups was highly significant (p < 0.001). With a deep learning-based approach using TensorFlow™, it is possible to detect AMD in SD-OCT with high sensitivity and specificity. With more image data, an expansion of this classifier for other macular diseases or further details in AMD is possible, suggesting an application for this model as a support in clinical decisions. Another possible future application would involve the individual prediction of the progress and success of therapy for different diseases by automatically detecting hidden image information.

Remote sensing and GIS-based landslide hazard analysis and cross-validation using multivariate logistic regression model on three test areas in Malaysia

NASA Astrophysics Data System (ADS)

Pradhan, Biswajeet

2010-05-01

This paper presents the results of the cross-validation of a multivariate logistic regression model using remote sensing data and GIS for landslide hazard analysis on the Penang, Cameron, and Selangor areas in Malaysia. Landslide locations in the study areas were identified by interpreting aerial photographs and satellite images, supported by field surveys. SPOT 5 and Landsat TM satellite imagery were used to map landcover and vegetation index, respectively. Maps of topography, soil type, lineaments and land cover were constructed from the spatial datasets. Ten factors which influence landslide occurrence, i.e., slope, aspect, curvature, distance from drainage, lithology, distance from lineaments, soil type, landcover, rainfall precipitation, and normalized difference vegetation index (ndvi), were extracted from the spatial database and the logistic regression coefficient of each factor was computed. Then the landslide hazard was analysed using the multivariate logistic regression coefficients derived not only from the data for the respective area but also using the logistic regression coefficients calculated from each of the other two areas (nine hazard maps in all) as a cross-validation of the model. For verification of the model, the results of the analyses were then compared with the field-verified landslide locations. Among the three cases of the application of logistic regression coefficient in the same study area, the case of Selangor based on the Selangor logistic regression coefficients showed the highest accuracy (94%), where as Penang based on the Penang coefficients showed the lowest accuracy (86%). Similarly, among the six cases from the cross application of logistic regression coefficient in other two areas, the case of Selangor based on logistic coefficient of Cameron showed highest (90%) prediction accuracy where as the case of Penang based on the Selangor logistic regression coefficients showed the lowest accuracy (79%). Qualitatively, the cross application model yields reasonable results which can be used for preliminary landslide hazard mapping.

Recommendations for elaboration, transcultural adaptation and validation process of tests in Speech, Hearing and Language Pathology.

PubMed

Pernambuco, Leandro; Espelt, Albert; Magalhães, Hipólito Virgílio; Lima, Kenio Costa de

2017-06-08

to present a guide with recommendations for translation, adaptation, elaboration and process of validation of tests in Speech and Language Pathology. the recommendations were based on international guidelines with a focus on the elaboration, translation, cross-cultural adaptation and validation process of tests. the recommendations were grouped into two Charts, one of them with procedures for translation and transcultural adaptation and the other for obtaining evidence of validity, reliability and measures of accuracy of the tests. a guide with norms for the organization and systematization of the process of elaboration, translation, cross-cultural adaptation and validation process of tests in Speech and Language Pathology was created.

Computer simulation of Cerebral Arteriovenous Malformation-validation analysis of hemodynamics parameters.

PubMed

Kumar, Y Kiran; Mehta, Shashi Bhushan; Ramachandra, Manjunath

2017-01-01

The purpose of this work is to provide some validation methods for evaluating the hemodynamic assessment of Cerebral Arteriovenous Malformation (CAVM). This article emphasizes the importance of validating noninvasive measurements for CAVM patients, which are designed using lumped models for complex vessel structure. The validation of the hemodynamics assessment is based on invasive clinical measurements and cross-validation techniques with the Philips proprietary validated software's Qflow and 2D Perfursion. The modeling results are validated for 30 CAVM patients for 150 vessel locations. Mean flow, diameter, and pressure were compared between modeling results and with clinical/cross validation measurements, using an independent two-tailed Student t test. Exponential regression analysis was used to assess the relationship between blood flow, vessel diameter, and pressure between them. Univariate analysis is used to assess the relationship between vessel diameter, vessel cross-sectional area, AVM volume, AVM pressure, and AVM flow results were performed with linear or exponential regression. Modeling results were compared with clinical measurements from vessel locations of cerebral regions. Also, the model is cross validated with Philips proprietary validated software's Qflow and 2D Perfursion. Our results shows that modeling results and clinical results are nearly matching with a small deviation. In this article, we have validated our modeling results with clinical measurements. The new approach for cross-validation is proposed by demonstrating the accuracy of our results with a validated product in a clinical environment.

An empirical assessment of validation practices for molecular classifiers

PubMed Central

Castaldi, Peter J.; Dahabreh, Issa J.

2011-01-01

Proposed molecular classifiers may be overfit to idiosyncrasies of noisy genomic and proteomic data. Cross-validation methods are often used to obtain estimates of classification accuracy, but both simulations and case studies suggest that, when inappropriate methods are used, bias may ensue. Bias can be bypassed and generalizability can be tested by external (independent) validation. We evaluated 35 studies that have reported on external validation of a molecular classifier. We extracted information on study design and methodological features, and compared the performance of molecular classifiers in internal cross-validation versus external validation for 28 studies where both had been performed. We demonstrate that the majority of studies pursued cross-validation practices that are likely to overestimate classifier performance. Most studies were markedly underpowered to detect a 20% decrease in sensitivity or specificity between internal cross-validation and external validation [median power was 36% (IQR, 21–61%) and 29% (IQR, 15–65%), respectively]. The median reported classification performance for sensitivity and specificity was 94% and 98%, respectively, in cross-validation and 88% and 81% for independent validation. The relative diagnostic odds ratio was 3.26 (95% CI 2.04–5.21) for cross-validation versus independent validation. Finally, we reviewed all studies (n = 758) which cited those in our study sample, and identified only one instance of additional subsequent independent validation of these classifiers. In conclusion, these results document that many cross-validation practices employed in the literature are potentially biased and genuine progress in this field will require adoption of routine external validation of molecular classifiers, preferably in much larger studies than in current practice. PMID:21300697

Scoring and staging systems using cox linear regression modeling and recursive partitioning.

PubMed

Lee, J W; Um, S H; Lee, J B; Mun, J; Cho, H

2006-01-01

Scoring and staging systems are used to determine the order and class of data according to predictors. Systems used for medical data, such as the Child-Turcotte-Pugh scoring and staging systems for ordering and classifying patients with liver disease, are often derived strictly from physicians' experience and intuition. We construct objective and data-based scoring/staging systems using statistical methods. We consider Cox linear regression modeling and recursive partitioning techniques for censored survival data. In particular, to obtain a target number of stages we propose cross-validation and amalgamation algorithms. We also propose an algorithm for constructing scoring and staging systems by integrating local Cox linear regression models into recursive partitioning, so that we can retain the merits of both methods such as superior predictive accuracy, ease of use, and detection of interactions between predictors. The staging system construction algorithms are compared by cross-validation evaluation of real data. The data-based cross-validation comparison shows that Cox linear regression modeling is somewhat better than recursive partitioning when there are only continuous predictors, while recursive partitioning is better when there are significant categorical predictors. The proposed local Cox linear recursive partitioning has better predictive accuracy than Cox linear modeling and simple recursive partitioning. This study indicates that integrating local linear modeling into recursive partitioning can significantly improve prediction accuracy in constructing scoring and staging systems.

Joint use of over- and under-sampling techniques and cross-validation for the development and assessment of prediction models.

PubMed

Blagus, Rok; Lusa, Lara

2015-11-04

Prediction models are used in clinical research to develop rules that can be used to accurately predict the outcome of the patients based on some of their characteristics. They represent a valuable tool in the decision making process of clinicians and health policy makers, as they enable them to estimate the probability that patients have or will develop a disease, will respond to a treatment, or that their disease will recur. The interest devoted to prediction models in the biomedical community has been growing in the last few years. Often the data used to develop the prediction models are class-imbalanced as only few patients experience the event (and therefore belong to minority class). Prediction models developed using class-imbalanced data tend to achieve sub-optimal predictive accuracy in the minority class. This problem can be diminished by using sampling techniques aimed at balancing the class distribution. These techniques include under- and oversampling, where a fraction of the majority class samples are retained in the analysis or new samples from the minority class are generated. The correct assessment of how the prediction model is likely to perform on independent data is of crucial importance; in the absence of an independent data set, cross-validation is normally used. While the importance of correct cross-validation is well documented in the biomedical literature, the challenges posed by the joint use of sampling techniques and cross-validation have not been addressed. We show that care must be taken to ensure that cross-validation is performed correctly on sampled data, and that the risk of overestimating the predictive accuracy is greater when oversampling techniques are used. Examples based on the re-analysis of real datasets and simulation studies are provided. We identify some results from the biomedical literature where the incorrect cross-validation was performed, where we expect that the performance of oversampling techniques was heavily overestimated.

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

Three-Jet Production in Electron-Positron Collisions at Next-to-Next-to-Leading Order Accuracy

NASA Astrophysics Data System (ADS)

Del Duca, Vittorio; Duhr, Claude; Kardos, Adam; Somogyi, Gábor; Trócsányi, Zoltán

2016-10-01

We introduce a completely local subtraction method for fully differential predictions at next-to-next-to-leading order (NNLO) accuracy for jet cross sections and use it to compute event shapes in three-jet production in electron-positron collisions. We validate our method on two event shapes, thrust and C parameter, which are already known in the literature at NNLO accuracy and compute for the first time oblateness and the energy-energy correlation at the same accuracy.

Three-Jet Production in Electron-Positron Collisions at Next-to-Next-to-Leading Order Accuracy.

PubMed

Del Duca, Vittorio; Duhr, Claude; Kardos, Adam; Somogyi, Gábor; Trócsányi, Zoltán

2016-10-07

We introduce a completely local subtraction method for fully differential predictions at next-to-next-to-leading order (NNLO) accuracy for jet cross sections and use it to compute event shapes in three-jet production in electron-positron collisions. We validate our method on two event shapes, thrust and C parameter, which are already known in the literature at NNLO accuracy and compute for the first time oblateness and the energy-energy correlation at the same accuracy.

Photodetachment cross sections of negative ions - The range of validity of the Wigner threshold law

NASA Technical Reports Server (NTRS)

Farley, John W.

1989-01-01

The threshold behavior of the photodetachment cross section of negative ions as a function of photon frequency is usually described by the Wigner law. This paper reports the results of a model calculation using the zero-core-contribution (ZCC) approximation. Theoretical expressions for the leading correction to the Wigner law are developed, giving the range of validity of the Wigner law and the expected accuracy. The results are relevant to extraction of electron affinities from experimental photodetachment data.

A three-dimensional parabolic equation model of sound propagation using higher-order operator splitting and Padé approximants.

PubMed

Lin, Ying-Tsong; Collis, Jon M; Duda, Timothy F

2012-11-01

An alternating direction implicit (ADI) three-dimensional fluid parabolic equation solution method with enhanced accuracy is presented. The method uses a square-root Helmholtz operator splitting algorithm that retains cross-multiplied operator terms that have been previously neglected. With these higher-order cross terms, the valid angular range of the parabolic equation solution is improved. The method is tested for accuracy against an image solution in an idealized wedge problem. Computational efficiency improvements resulting from the ADI discretization are also discussed.

Assessing clinical reasoning (ASCLIRE): Instrument development and validation.

PubMed

Kunina-Habenicht, Olga; Hautz, Wolf E; Knigge, Michel; Spies, Claudia; Ahlers, Olaf

2015-12-01

Clinical reasoning is an essential competency in medical education. This study aimed at developing and validating a test to assess diagnostic accuracy, collected information, and diagnostic decision time in clinical reasoning. A norm-referenced computer-based test for the assessment of clinical reasoning (ASCLIRE) was developed, integrating the entire clinical decision process. In a cross-sectional study participants were asked to choose as many diagnostic measures as they deemed necessary to diagnose the underlying disease of six different cases with acute or sub-acute dyspnea and provide a diagnosis. 283 students and 20 content experts participated. In addition to diagnostic accuracy, respective decision time and number of used relevant diagnostic measures were documented as distinct performance indicators. The empirical structure of the test was investigated using a structural equation modeling approach. Experts showed higher accuracy rates and lower decision times than students. In a cross-sectional comparison, the diagnostic accuracy of students improved with the year of study. Wrong diagnoses provided by our sample were comparable to wrong diagnoses in practice. We found an excellent fit for a model with three latent factors-diagnostic accuracy, decision time, and choice of relevant diagnostic information-with diagnostic accuracy showing no significant correlation with decision time. ASCLIRE considers decision time as an important performance indicator beneath diagnostic accuracy and provides evidence that clinical reasoning is a complex ability comprising diagnostic accuracy, decision time, and choice of relevant diagnostic information as three partly correlated but still distinct aspects.

Identifying a predictive model for response to atypical antipsychotic monotherapy treatment in south Indian schizophrenia patients.

PubMed

Gupta, Meenal; Moily, Nagaraj S; Kaur, Harpreet; Jajodia, Ajay; Jain, Sanjeev; Kukreti, Ritushree

2013-08-01

Atypical antipsychotic (AAP) drugs are the preferred choice of treatment for schizophrenia patients. Patients who do not show favorable response to AAP monotherapy are subjected to random prolonged therapeutic treatment with AAP multitherapy, typical antipsychotics or a combination of both. Therefore, prior identification of patients' response to drugs can be an important step in providing efficacious and safe therapeutic treatment. We thus attempted to elucidate a genetic signature which could predict patients' response to AAP monotherapy. Our logistic regression analyses indicated the probability that 76% patients carrying combination of four SNPs will not show favorable response to AAP therapy. The robustness of this prediction model was assessed using repeated 10-fold cross validation method, and the results across n-fold cross-validations (mean accuracy=71.91%; 95%CI=71.47-72.35) suggest high accuracy and reliability of the prediction model. Further validations of these results in large sample sets are likely to establish their clinical applicability. Copyright © 2013 Elsevier Inc. All rights reserved.

Validating LES for Jet Aeroacoustics

NASA Technical Reports Server (NTRS)

Bridges, James

2011-01-01

Engineers charged with making jet aircraft quieter have long dreamed of being able to see exactly how turbulent eddies produce sound and this dream is now coming true with the advent of large eddy simulation (LES). Two obvious challenges remain: validating the LES codes at the resolution required to see the fluid-acoustic coupling, and the interpretation of the massive datasets that result in having dreams come true. This paper primarily addresses the former, the use of advanced experimental techniques such as particle image velocimetry (PIV) and Raman and Rayleigh scattering, to validate the computer codes and procedures used to create LES solutions. It also addresses the latter problem in discussing what are relevant measures critical for aeroacoustics that should be used in validating LES codes. These new diagnostic techniques deliver measurements and flow statistics of increasing sophistication and capability, but what of their accuracy? And what are the measures to be used in validation? This paper argues that the issue of accuracy be addressed by cross-facility and cross-disciplinary examination of modern datasets along with increased reporting of internal quality checks in PIV analysis. Further, it is argued that the appropriate validation metrics for aeroacoustic applications are increasingly complicated statistics that have been shown in aeroacoustic theory to be critical to flow-generated sound.

Dental attrition models predicting temporomandibular joint disease or masticatory muscle pain versus asymptomatic controls.

PubMed

Seligman, D A; Pullinger, A G

2006-11-01

To determine whether patients with temporomandibular joint disease or masticatory muscle pain can be usefully differentiated from asymptomatic controls using multifactorial classification tree models of attrition severity and/or rates. Measures of attrition severity and rates in patients diagnosed with disc displacement (n = 52), osteoarthrosis (n = 74), or masticatory muscle pain only (n = 43) were compared against those in asymptomatic controls (n = 132). Cross-validated classification tree models were tested for fit with sensitivity, specificity, accuracy and log likelihood accountability. The model for identifying asymptomatic controls only required the three measures of attrition severity (anterior, mediotrusive and laterotrusive posterior) to be differentiated from the patients with a 74.2 +/- 3.8% cross-validation accuracy. This compared with cross-validation accuracies of 69.7 +/- 3.7% for differentiating disc displacement using anterior and laterotrusive attrition severity, 68.7 +/- 3.9% for differentiating disc displacement using anterior and laterotrusive attrition rates, 70.9 +/- 3.3% for differentiating osteoarthrosis using anterior attrition severity and rates, 94.6 +/- 2.1% for differentiating myofascial pain using mediotrusive and laterotrusive attrition severity, and 92.0 +/- 2.1% for differentiating myofascial pain using mediotrusive and anterior attrition rates. The myofascial pain models exceeded the > or =75% sensitivity and > or =90% specificity thresholds recommended for diagnostic tests, and the asymptomatic control model approached these thresholds. Multifactorial models using attrition severity and rates may differentiate masticatory muscle pain patients from asymptomatic controls, and have some predictive value for differentiating intracapsular temporomandibular disorder patients as well.

Cross-validation to select Bayesian hierarchical models in phylogenetics.

PubMed

Duchêne, Sebastián; Duchêne, David A; Di Giallonardo, Francesca; Eden, John-Sebastian; Geoghegan, Jemma L; Holt, Kathryn E; Ho, Simon Y W; Holmes, Edward C

2016-05-26

Recent developments in Bayesian phylogenetic models have increased the range of inferences that can be drawn from molecular sequence data. Accordingly, model selection has become an important component of phylogenetic analysis. Methods of model selection generally consider the likelihood of the data under the model in question. In the context of Bayesian phylogenetics, the most common approach involves estimating the marginal likelihood, which is typically done by integrating the likelihood across model parameters, weighted by the prior. Although this method is accurate, it is sensitive to the presence of improper priors. We explored an alternative approach based on cross-validation that is widely used in evolutionary analysis. This involves comparing models according to their predictive performance. We analysed simulated data and a range of viral and bacterial data sets using a cross-validation approach to compare a variety of molecular clock and demographic models. Our results show that cross-validation can be effective in distinguishing between strict- and relaxed-clock models and in identifying demographic models that allow growth in population size over time. In most of our empirical data analyses, the model selected using cross-validation was able to match that selected using marginal-likelihood estimation. The accuracy of cross-validation appears to improve with longer sequence data, particularly when distinguishing between relaxed-clock models. Cross-validation is a useful method for Bayesian phylogenetic model selection. This method can be readily implemented even when considering complex models where selecting an appropriate prior for all parameters may be difficult.

Prediction of functional aerobic capacity without exercise testing

NASA Technical Reports Server (NTRS)

Jackson, A. S.; Blair, S. N.; Mahar, M. T.; Wier, L. T.; Ross, R. M.; Stuteville, J. E.

1990-01-01

The purpose of this study was to develop functional aerobic capacity prediction models without using exercise tests (N-Ex) and to compare the accuracy with Astrand single-stage submaximal prediction methods. The data of 2,009 subjects (9.7% female) were randomly divided into validation (N = 1,543) and cross-validation (N = 466) samples. The validation sample was used to develop two N-Ex models to estimate VO2peak. Gender, age, body composition, and self-report activity were used to develop two N-Ex prediction models. One model estimated percent fat from skinfolds (N-Ex %fat) and the other used body mass index (N-Ex BMI) to represent body composition. The multiple correlations for the developed models were R = 0.81 (SE = 5.3 ml.kg-1.min-1) and R = 0.78 (SE = 5.6 ml.kg-1.min-1). This accuracy was confirmed when applied to the cross-validation sample. The N-Ex models were more accurate than what was obtained from VO2peak estimated from the Astrand prediction models. The SEs of the Astrand models ranged from 5.5-9.7 ml.kg-1.min-1. The N-Ex models were cross-validated on 59 men on hypertensive medication and 71 men who were found to have a positive exercise ECG. The SEs of the N-Ex models ranged from 4.6-5.4 ml.kg-1.min-1 with these subjects.(ABSTRACT TRUNCATED AT 250 WORDS).

Raman fiber-optical method for colon cancer detection: Cross-validation and outlier identification approach

NASA Astrophysics Data System (ADS)

Petersen, D.; Naveed, P.; Ragheb, A.; Niedieker, D.; El-Mashtoly, S. F.; Brechmann, T.; Kötting, C.; Schmiegel, W. H.; Freier, E.; Pox, C.; Gerwert, K.

2017-06-01

Endoscopy plays a major role in early recognition of cancer which is not externally accessible and therewith in increasing the survival rate. Raman spectroscopic fiber-optical approaches can help to decrease the impact on the patient, increase objectivity in tissue characterization, reduce expenses and provide a significant time advantage in endoscopy. In gastroenterology an early recognition of malign and precursor lesions is relevant. Instantaneous and precise differentiation between adenomas as precursor lesions for cancer and hyperplastic polyps on the one hand and between high and low-risk alterations on the other hand is important. Raman fiber-optical measurements of colon biopsy samples taken during colonoscopy were carried out during a clinical study, and samples of adenocarcinoma (22), tubular adenomas (141), hyperplastic polyps (79) and normal tissue (101) from 151 patients were analyzed. This allows us to focus on the bioinformatic analysis and to set stage for Raman endoscopic measurements. Since spectral differences between normal and cancerous biopsy samples are small, special care has to be taken in data analysis. Using a leave-one-patient-out cross-validation scheme, three different outlier identification methods were investigated to decrease the influence of systematic errors, like a residual risk in misplacement of the sample and spectral dilution of marker bands (esp. cancerous tissue) and therewith optimize the experimental design. Furthermore other validations methods like leave-one-sample-out and leave-one-spectrum-out cross-validation schemes were compared with leave-one-patient-out cross-validation. High-risk lesions were differentiated from low-risk lesions with a sensitivity of 79%, specificity of 74% and an accuracy of 77%, cancer and normal tissue with a sensitivity of 79%, specificity of 83% and an accuracy of 81%. Additionally applied outlier identification enabled us to improve the recognition of neoplastic biopsy samples.

Effects of sample survey design on the accuracy of classification tree models in species distribution models

USGS Publications Warehouse

Edwards, T.C.; Cutler, D.R.; Zimmermann, N.E.; Geiser, L.; Moisen, Gretchen G.

2006-01-01

We evaluated the effects of probabilistic (hereafter DESIGN) and non-probabilistic (PURPOSIVE) sample surveys on resultant classification tree models for predicting the presence of four lichen species in the Pacific Northwest, USA. Models derived from both survey forms were assessed using an independent data set (EVALUATION). Measures of accuracy as gauged by resubstitution rates were similar for each lichen species irrespective of the underlying sample survey form. Cross-validation estimates of prediction accuracies were lower than resubstitution accuracies for all species and both design types, and in all cases were closer to the true prediction accuracies based on the EVALUATION data set. We argue that greater emphasis should be placed on calculating and reporting cross-validation accuracy rates rather than simple resubstitution accuracy rates. Evaluation of the DESIGN and PURPOSIVE tree models on the EVALUATION data set shows significantly lower prediction accuracy for the PURPOSIVE tree models relative to the DESIGN models, indicating that non-probabilistic sample surveys may generate models with limited predictive capability. These differences were consistent across all four lichen species, with 11 of the 12 possible species and sample survey type comparisons having significantly lower accuracy rates. Some differences in accuracy were as large as 50%. The classification tree structures also differed considerably both among and within the modelled species, depending on the sample survey form. Overlap in the predictor variables selected by the DESIGN and PURPOSIVE tree models ranged from only 20% to 38%, indicating the classification trees fit the two evaluated survey forms on different sets of predictor variables. The magnitude of these differences in predictor variables throws doubt on ecological interpretation derived from prediction models based on non-probabilistic sample surveys. ?? 2006 Elsevier B.V. All rights reserved.

Predicting protein-binding regions in RNA using nucleotide profiles and compositions.

PubMed

Choi, Daesik; Park, Byungkyu; Chae, Hanju; Lee, Wook; Han, Kyungsook

2017-03-14

Motivated by the increased amount of data on protein-RNA interactions and the availability of complete genome sequences of several organisms, many computational methods have been proposed to predict binding sites in protein-RNA interactions. However, most computational methods are limited to finding RNA-binding sites in proteins instead of protein-binding sites in RNAs. Predicting protein-binding sites in RNA is more challenging than predicting RNA-binding sites in proteins. Recent computational methods for finding protein-binding sites in RNAs have several drawbacks for practical use. We developed a new support vector machine (SVM) model for predicting protein-binding regions in mRNA sequences. The model uses sequence profiles constructed from log-odds scores of mono- and di-nucleotides and nucleotide compositions. The model was evaluated by standard 10-fold cross validation, leave-one-protein-out (LOPO) cross validation and independent testing. Since actual mRNA sequences have more non-binding regions than protein-binding regions, we tested the model on several datasets with different ratios of protein-binding regions to non-binding regions. The best performance of the model was obtained in a balanced dataset of positive and negative instances. 10-fold cross validation with a balanced dataset achieved a sensitivity of 91.6%, a specificity of 92.4%, an accuracy of 92.0%, a positive predictive value (PPV) of 91.7%, a negative predictive value (NPV) of 92.3% and a Matthews correlation coefficient (MCC) of 0.840. LOPO cross validation showed a lower performance than the 10-fold cross validation, but the performance remains high (87.6% accuracy and 0.752 MCC). In testing the model on independent datasets, it achieved an accuracy of 82.2% and an MCC of 0.656. Testing of our model and other state-of-the-art methods on a same dataset showed that our model is better than the others. Sequence profiles of log-odds scores of mono- and di-nucleotides were much more powerful features than nucleotide compositions in finding protein-binding regions in RNA sequences. But, a slight performance gain was obtained when using the sequence profiles along with nucleotide compositions. These are preliminary results of ongoing research, but demonstrate the potential of our approach as a powerful predictor of protein-binding regions in RNA. The program and supporting data are available at http://bclab.inha.ac.kr/RBPbinding .

Parkinson's disease detection based on dysphonia measurements

NASA Astrophysics Data System (ADS)

Lahmiri, Salim

2017-04-01

Assessing dysphonic symptoms is a noninvasive and effective approach to detect Parkinson's disease (PD) in patients. The main purpose of this study is to investigate the effect of different dysphonia measurements on PD detection by support vector machine (SVM). Seven categories of dysphonia measurements are considered. Experimental results from ten-fold cross-validation technique demonstrate that vocal fundamental frequency statistics yield the highest accuracy of 88 % ± 0.04. When all dysphonia measurements are employed, the SVM classifier achieves 94 % ± 0.03 accuracy. A refinement of the original patterns space by removing dysphonia measurements with similar variation across healthy and PD subjects allows achieving 97.03 % ± 0.03 accuracy. The latter performance is larger than what is reported in the literature on the same dataset with ten-fold cross-validation technique. Finally, it was found that measures of ratio of noise to tonal components in the voice are the most suitable dysphonic symptoms to detect PD subjects as they achieve 99.64 % ± 0.01 specificity. This finding is highly promising for understanding PD symptoms.

The SNAQ(RC), an easy traffic light system as a first step in the recognition of undernutrition in residential care.

PubMed

Kruizenga, H M; de Vet, H C W; Van Marissing, C M E; Stassen, E E P M; Strijk, J E; Van Bokhorst-de Van der Schueren, M A E; Horman, J C H; Schols, J M G A; Van Binsbergen, J J; Eliens, A; Knol, D L; Visser, M

2010-02-01

Development and validation of a quick and easy screening tool for the early detection of undernourished residents in nursing homes and residential homes. Multi-center, cross sectional observational study. Nursing homes and residential homes. The screening tool was developed in a total of 308 residents (development sample; sample A) and cross validated in a new sample of 720 residents (validation sample) consisting of 476 nursing home residents (Sample B1) and 244 residential home residents (sample B2). Patients were defined severely undernourished when they met at least one of the following criteria: BMI or= 5% unintentional weight loss in the past month and/or >or= 10% unintentional weight loss in the past 6 months. Patients were defined as moderately undernourished if they met the following criteria: BMI 20.1-22 kg/m2 and/or 5-10% unintentional weight loss in the past six months. The most predictive questions (originally derived from previously developed screening instruments) of undernourishment were selected in sample A and cross validated in sample B. In a second stage BMI was added to the SNAQRC in sample B. The diagnostic accuracy of the screening tool in the development and validation samples was expressed in sensitivity, specificity, and the negative and positive predictive value. The four most predictive questions for undernutrition related to: unintentional weight loss more than 6 kg during the past 6 months and more than 3 kg in the past month, capability of eating and drinking with help, and decreased appetite during the past month. The diagnostic accuracy of these questions alone was insufficient (Se=45%, Sp=87%, PPV=50% and NPV=84%). However, combining the questions with measured BMI sufficiently improved the diagnostic accuracy (Se=87%, Sp=82%, PPV=59% and NPV=95%). Early detection of undernourished nursing- and residential home residents is possible using four screening questions and measured BMI.

[Traceability of Wine Varieties Using Near Infrared Spectroscopy Combined with Cyclic Voltammetry].

PubMed

Li, Meng-hua; Li, Jing-ming; Li, Jun-hui; Zhang, Lu-da; Zhao, Long-lian

2015-06-01

To achieve the traceability of wine varieties, a method was proposed to fuse Near-infrared (NIR) spectra and cyclic voltammograms (CV) which contain different information using D-S evidence theory. NIR spectra and CV curves of three different varieties of wines (cabernet sauvignon, merlot, cabernet gernischt) which come from seven different geographical origins were collected separately. The discriminant models were built using PLS-DA method. Based on this, D-S evidence theory was then applied to achieve the integration of the two kinds of discrimination results. After integrated by D-S evidence theory, the accuracy rate of cross-validation is 95.69% and validation set is 94.12% for wine variety identification. When only considering the wine that come from Yantai, the accuracy rate of cross-validation is 99.46% and validation set is 100%. All the traceability models after fusion achieved better results on classification than individual method. These results suggest that the proposed method combining electrochemical information with spectral information using the D-S evidence combination formula is benefit to the improvement of model discrimination effect, and is a promising tool for discriminating different kinds of wines.

NNvPDB: Neural Network based Protein Secondary Structure Prediction with PDB Validation.

PubMed

Sakthivel, Seethalakshmi; S K M, Habeeb

2015-01-01

The predicted secondary structural states are not cross validated by any of the existing servers. Hence, information on the level of accuracy for every sequence is not reported by the existing servers. This was overcome by NNvPDB, which not only reported greater Q3 but also validates every prediction with the homologous PDB entries. NNvPDB is based on the concept of Neural Network, with a new and different approach of training the network every time with five PDB structures that are similar to query sequence. The average accuracy for helix is 76%, beta sheet is 71% and overall (helix, sheet and coil) is 66%. http://bit.srmuniv.ac.in/cgi-bin/bit/cfpdb/nnsecstruct.pl.

Screening for postdeployment conditions: development and cross-validation of an embedded validity scale in the neurobehavioral symptom inventory.

PubMed

Vanderploeg, Rodney D; Cooper, Douglas B; Belanger, Heather G; Donnell, Alison J; Kennedy, Jan E; Hopewell, Clifford A; Scott, Steven G

2014-01-01

To develop and cross-validate internal validity scales for the Neurobehavioral Symptom Inventory (NSI). Four existing data sets were used: (1) outpatient clinical traumatic brain injury (TBI)/neurorehabilitation database from a military site (n = 403), (2) National Department of Veterans Affairs TBI evaluation database (n = 48 175), (3) Florida National Guard nonclinical TBI survey database (n = 3098), and (4) a cross-validation outpatient clinical TBI/neurorehabilitation database combined across 2 military medical centers (n = 206). Secondary analysis of existing cohort data to develop (study 1) and cross-validate (study 2) internal validity scales for the NSI. The NSI, Mild Brain Injury Atypical Symptoms, and Personality Assessment Inventory scores. Study 1: Three NSI validity scales were developed, composed of 5 unusual items (Negative Impression Management [NIM5]), 6 low-frequency items (LOW6), and the combination of 10 nonoverlapping items (Validity-10). Cut scores maximizing sensitivity and specificity on these measures were determined, using a Mild Brain Injury Atypical Symptoms score of 8 or more as the criterion for invalidity. Study 2: The same validity scale cut scores again resulted in the highest classification accuracy and optimal balance between sensitivity and specificity in the cross-validation sample, using a Personality Assessment Inventory Negative Impression Management scale with a T score of 75 or higher as the criterion for invalidity. The NSI is widely used in the Department of Defense and Veterans Affairs as a symptom-severity assessment following TBI, but is subject to symptom overreporting or exaggeration. This study developed embedded NSI validity scales to facilitate the detection of invalid response styles. The NSI Validity-10 scale appears to hold considerable promise for validity assessment when the NSI is used as a population-screening tool.

Breast cancer detection via Hu moment invariant and feedforward neural network

NASA Astrophysics Data System (ADS)

Zhang, Xiaowei; Yang, Jiquan; Nguyen, Elijah

2018-04-01

One of eight women can get breast cancer during all her life. This study used Hu moment invariant and feedforward neural network to diagnose breast cancer. With the help of K-fold cross validation, we can test the out-of-sample accuracy of our method. Finally, we found that our methods can improve the accuracy of detecting breast cancer and reduce the difficulty of judging.

Ensemble Methods for Classification of Physical Activities from Wrist Accelerometry.

PubMed

Chowdhury, Alok Kumar; Tjondronegoro, Dian; Chandran, Vinod; Trost, Stewart G

2017-09-01

To investigate whether the use of ensemble learning algorithms improve physical activity recognition accuracy compared to the single classifier algorithms, and to compare the classification accuracy achieved by three conventional ensemble machine learning methods (bagging, boosting, random forest) and a custom ensemble model comprising four algorithms commonly used for activity recognition (binary decision tree, k nearest neighbor, support vector machine, and neural network). The study used three independent data sets that included wrist-worn accelerometer data. For each data set, a four-step classification framework consisting of data preprocessing, feature extraction, normalization and feature selection, and classifier training and testing was implemented. For the custom ensemble, decisions from the single classifiers were aggregated using three decision fusion methods: weighted majority vote, naïve Bayes combination, and behavior knowledge space combination. Classifiers were cross-validated using leave-one subject out cross-validation and compared on the basis of average F1 scores. In all three data sets, ensemble learning methods consistently outperformed the individual classifiers. Among the conventional ensemble methods, random forest models provided consistently high activity recognition; however, the custom ensemble model using weighted majority voting demonstrated the highest classification accuracy in two of the three data sets. Combining multiple individual classifiers using conventional or custom ensemble learning methods can improve activity recognition accuracy from wrist-worn accelerometer data.

Computer-aided diagnosis system: a Bayesian hybrid classification method.

PubMed

Calle-Alonso, F; Pérez, C J; Arias-Nicolás, J P; Martín, J

2013-10-01

A novel method to classify multi-class biomedical objects is presented. The method is based on a hybrid approach which combines pairwise comparison, Bayesian regression and the k-nearest neighbor technique. It can be applied in a fully automatic way or in a relevance feedback framework. In the latter case, the information obtained from both an expert and the automatic classification is iteratively used to improve the results until a certain accuracy level is achieved, then, the learning process is finished and new classifications can be automatically performed. The method has been applied in two biomedical contexts by following the same cross-validation schemes as in the original studies. The first one refers to cancer diagnosis, leading to an accuracy of 77.35% versus 66.37%, originally obtained. The second one considers the diagnosis of pathologies of the vertebral column. The original method achieves accuracies ranging from 76.5% to 96.7%, and from 82.3% to 97.1% in two different cross-validation schemes. Even with no supervision, the proposed method reaches 96.71% and 97.32% in these two cases. By using a supervised framework the achieved accuracy is 97.74%. Furthermore, all abnormal cases were correctly classified. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

Individual Patient Diagnosis of AD and FTD via High-Dimensional Pattern Classification of MRI

PubMed Central

Davatzikos, C.; Resnick, S. M.; Wu, X.; Parmpi, P.; Clark, C. M.

2008-01-01

The purpose of this study is to determine the diagnostic accuracy of MRI-based high-dimensional pattern classification in differentiating between patients with Alzheimer’s Disease (AD), Frontotemporal Dementia (FTD), and healthy controls, on an individual patient basis. MRI scans of 37 patients with AD and 37 age-matched cognitively normal elderly individuals, as well as 12 patients with FTD and 12 age-matched cognitively normal elderly individuals, were analyzed using voxel-based analysis and high-dimensional pattern classification. Diagnostic sensitivity and specificity of spatial patterns of regional brain atrophy found to be characteristic of AD and FTD were determined via cross-validation and via split-sample methods. Complex spatial patterns of relatively reduced brain volumes were identified, including temporal, orbitofrontal, parietal and cingulate regions, which were predominantly characteristic of either AD or FTD. These patterns provided 100% diagnostic accuracy, when used to separate AD or FTD from healthy controls. The ability to correctly distinguish AD from FTD averaged 84.3%. All estimates of diagnostic accuracy were determined via cross-validation. In conclusion, AD- and FTD-specific patterns of brain atrophy can be detected with high accuracy using high-dimensional pattern classification of MRI scans obtained in a typical clinical setting. PMID:18474436

How to test validity in orthodontic research: a mixed dentition analysis example.

PubMed

Donatelli, Richard E; Lee, Shin-Jae

2015-02-01

The data used to test the validity of a prediction method should be different from the data used to generate the prediction model. In this study, we explored whether an independent data set is mandatory for testing the validity of a new prediction method and how validity can be tested without independent new data. Several validation methods were compared in an example using the data from a mixed dentition analysis with a regression model. The validation errors of real mixed dentition analysis data and simulation data were analyzed for increasingly large data sets. The validation results of both the real and the simulation studies demonstrated that the leave-1-out cross-validation method had the smallest errors. The largest errors occurred in the traditional simple validation method. The differences between the validation methods diminished as the sample size increased. The leave-1-out cross-validation method seems to be an optimal validation method for improving the prediction accuracy in a data set with limited sample sizes. Copyright © 2015 American Association of Orthodontists. Published by Elsevier Inc. All rights reserved.

Application of Multivariable Analysis and FTIR-ATR Spectroscopy to the Prediction of Properties in Campeche Honey

PubMed Central

Pat, Lucio; Ali, Bassam; Guerrero, Armando; Córdova, Atl V.; Garduza, José P.

2016-01-01

Attenuated total reflectance-Fourier transform infrared spectrometry and chemometrics model was used for determination of physicochemical properties (pH, redox potential, free acidity, electrical conductivity, moisture, total soluble solids (TSS), ash, and HMF) in honey samples. The reference values of 189 honey samples of different botanical origin were determined using Association Official Analytical Chemists, (AOAC), 1990; Codex Alimentarius, 2001, International Honey Commission, 2002, methods. Multivariate calibration models were built using partial least squares (PLS) for the measurands studied. The developed models were validated using cross-validation and external validation; several statistical parameters were obtained to determine the robustness of the calibration models: (PCs) optimum number of components principal, (SECV) standard error of cross-validation, (R 2 cal) coefficient of determination of cross-validation, (SEP) standard error of validation, and (R 2 val) coefficient of determination for external validation and coefficient of variation (CV). The prediction accuracy for pH, redox potential, electrical conductivity, moisture, TSS, and ash was good, while for free acidity and HMF it was poor. The results demonstrate that attenuated total reflectance-Fourier transform infrared spectrometry is a valuable, rapid, and nondestructive tool for the quantification of physicochemical properties of honey. PMID:28070445

Cross-validation of resting metabolic rate prediction equations

USDA-ARS?s Scientific Manuscript database

Background: Knowledge of the resting metabolic rate (RMR) is necessary for determining individual total energy requirements. Measurement of RMR is time consuming and requires specialized equipment. Prediction equations provide an easy method to estimate RMR; however, the accuracy of these equations...

Application of Bayes' to the prediction of referral decisions made by specialist optometrists in relation to chronic open angle glaucoma.

PubMed

Gurney, J C; Ansari, E; Harle, D; O'Kane, N; Sagar, R V; Dunne, M C M

2018-02-09

To determine the accuracy of a Bayesian learning scheme (Bayes') applied to the prediction of clinical decisions made by specialist optometrists in relation to the referral refinement of chronic open angle glaucoma. This cross-sectional observational study involved collection of data from the worst affected or right eyes of a consecutive sample of cases (n = 1,006) referred into the West Kent Clinical Commissioning Group Community Ophthalmology Team (COT) by high street optometrists. Multilevel classification of each case was based on race, sex, age, family history of chronic open angle glaucoma, reason for referral, Goldmann Applanation Tonometry (intraocular pressure and interocular asymmetry), optic nerve head assessment (vertical size, cup disc ratio and interocular asymmetry), central corneal thickness and visual field analysis (Hodapp-Parrish-Anderson classification). Randomised stratified tenfold cross-validation was applied to determine the accuracy of Bayes' by comparing its output to the clinical decisions of three COT specialist optometrists; namely, the decision to discharge, follow-up or refer each case. Outcomes of cross-validation, expressed as means and standard deviations, showed that the accuracy of Bayes' was high (95%, 2.0%) but that it falsely discharged (3.4%, 1.6%) or referred (3.1%, 1.5%) some cases. The results indicate that Bayes' has the potential to augment the decisions of specialist optometrists.

Free kick instead of cross-validation in maximum-likelihood refinement of macromolecular crystal structures

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

Pražnikar, Jure; University of Primorska,; Turk, Dušan, E-mail: dusan.turk@ijs.si

2014-12-01

The maximum-likelihood free-kick target, which calculates model error estimates from the work set and a randomly displaced model, proved superior in the accuracy and consistency of refinement of crystal structures compared with the maximum-likelihood cross-validation target, which calculates error estimates from the test set and the unperturbed model. The refinement of a molecular model is a computational procedure by which the atomic model is fitted to the diffraction data. The commonly used target in the refinement of macromolecular structures is the maximum-likelihood (ML) function, which relies on the assessment of model errors. The current ML functions rely on cross-validation. Theymore » utilize phase-error estimates that are calculated from a small fraction of diffraction data, called the test set, that are not used to fit the model. An approach has been developed that uses the work set to calculate the phase-error estimates in the ML refinement from simulating the model errors via the random displacement of atomic coordinates. It is called ML free-kick refinement as it uses the ML formulation of the target function and is based on the idea of freeing the model from the model bias imposed by the chemical energy restraints used in refinement. This approach for the calculation of error estimates is superior to the cross-validation approach: it reduces the phase error and increases the accuracy of molecular models, is more robust, provides clearer maps and may use a smaller portion of data for the test set for the calculation of R{sub free} or may leave it out completely.« less

Prediction of psychosis across protocols and risk cohorts using automated language analysis.

PubMed

Corcoran, Cheryl M; Carrillo, Facundo; Fernández-Slezak, Diego; Bedi, Gillinder; Klim, Casimir; Javitt, Daniel C; Bearden, Carrie E; Cecchi, Guillermo A

2018-02-01

Language and speech are the primary source of data for psychiatrists to diagnose and treat mental disorders. In psychosis, the very structure of language can be disturbed, including semantic coherence (e.g., derailment and tangentiality) and syntactic complexity (e.g., concreteness). Subtle disturbances in language are evident in schizophrenia even prior to first psychosis onset, during prodromal stages. Using computer-based natural language processing analyses, we previously showed that, among English-speaking clinical (e.g., ultra) high-risk youths, baseline reduction in semantic coherence (the flow of meaning in speech) and in syntactic complexity could predict subsequent psychosis onset with high accuracy. Herein, we aimed to cross-validate these automated linguistic analytic methods in a second larger risk cohort, also English-speaking, and to discriminate speech in psychosis from normal speech. We identified an automated machine-learning speech classifier - comprising decreased semantic coherence, greater variance in that coherence, and reduced usage of possessive pronouns - that had an 83% accuracy in predicting psychosis onset (intra-protocol), a cross-validated accuracy of 79% of psychosis onset prediction in the original risk cohort (cross-protocol), and a 72% accuracy in discriminating the speech of recent-onset psychosis patients from that of healthy individuals. The classifier was highly correlated with previously identified manual linguistic predictors. Our findings support the utility and validity of automated natural language processing methods to characterize disturbances in semantics and syntax across stages of psychotic disorder. The next steps will be to apply these methods in larger risk cohorts to further test reproducibility, also in languages other than English, and identify sources of variability. This technology has the potential to improve prediction of psychosis outcome among at-risk youths and identify linguistic targets for remediation and preventive intervention. More broadly, automated linguistic analysis can be a powerful tool for diagnosis and treatment across neuropsychiatry. © 2018 World Psychiatric Association.

Diagnostic accuracy of eye movements in assessing pedophilia.

PubMed

Fromberger, Peter; Jordan, Kirsten; Steinkrauss, Henrike; von Herder, Jakob; Witzel, Joachim; Stolpmann, Georg; Kröner-Herwig, Birgit; Müller, Jürgen Leo

2012-07-01

Given that recurrent sexual interest in prepubescent children is one of the strongest single predictors for pedosexual offense recidivism, valid and reliable diagnosis of pedophilia is of particular importance. Nevertheless, current assessment methods still fail to fulfill psychometric quality criteria. The aim of the study was to evaluate the diagnostic accuracy of eye-movement parameters in regard to pedophilic sexual preferences. Eye movements were measured while 22 pedophiles (according to ICD-10 F65.4 diagnosis), 8 non-pedophilic forensic controls, and 52 healthy controls simultaneously viewed the picture of a child and the picture of an adult. Fixation latency was assessed as a parameter for automatic attentional processes and relative fixation time to account for controlled attentional processes. Receiver operating characteristic (ROC) analyses, which are based on calculated age-preference indices, were carried out to determine the classifier performance. Cross-validation using the leave-one-out method was used to test the validity of classifiers. Pedophiles showed significantly shorter fixation latencies and significantly longer relative fixation times for child stimuli than either of the control groups. Classifier performance analysis revealed an area under the curve (AUC) = 0.902 for fixation latency and an AUC = 0.828 for relative fixation time. The eye-tracking method based on fixation latency discriminated between pedophiles and non-pedophiles with a sensitivity of 86.4% and a specificity of 90.0%. Cross-validation demonstrated good validity of eye-movement parameters. Despite some methodological limitations, measuring eye movements seems to be a promising approach to assess deviant pedophilic interests. Eye movements, which represent automatic attentional processes, demonstrated high diagnostic accuracy. © 2012 International Society for Sexual Medicine.

Evaluation of MuSyQ land surface albedo based on LAnd surface Parameters VAlidation System (LAPVAS)

NASA Astrophysics Data System (ADS)

Dou, B.; Wen, J.; Xinwen, L.; Zhiming, F.; Wu, S.; Zhang, Y.

2016-12-01

satellite derived Land surface albedo is an essential climate variable which controls the earth energy budget and it can be used in applications such as climate change, hydrology, and numerical weather prediction. However, the accuracy and uncertainty of surface albedo products should be evaluated with a reliable reference truth data prior to applications. A new comprehensive and systemic project of china, called the Remote Sensing Application Network (CRSAN), has been launched recent years. Two subjects of this project is developing a Multi-source data Synergized Quantitative Remote Sensin g Production System ( MuSyQ ) and a Web-based validation system named LAnd surface remote sensing Product VAlidation System (LAPVAS) , which aims to generate a quantitative remote sensing product for ecosystem and environmental monitoring and validate them with a reference validation data and a standard validation system, respectively. Land surface BRDF/albedo is one of product datasets of MuSyQ which has a pentad period with 1km spatial resolution and is derived by Multi-sensor Combined BRDF Inversion ( MCBI ) Model. In this MuSyQ albedo evaluation, a multi-validation strategy is implemented by LAPVAS, including directly and multi-scale validation with field measured albedo and cross validation with MODIS albedo product with different land cover. The results reveal that MuSyQ albedo data with a 5-day temporal resolution is in higher sensibility and accuracy during land cover change period, e.g. snowing. But results without regard to snow or changed land cover, MuSyQ albedo generally is in similar accuracy with MODIS albedo and meet the climate modeling requirement of an absolute accuracy of 0.05.

Proton-nucleus total inelastic cross sections - An empirical formula for E greater than 10 MeV

NASA Technical Reports Server (NTRS)

Letaw, J. R.; Silberberg, R.; Tsao, C. H.

1983-01-01

An empirical formula for the total inelastic cross section of protons on nuclei with charge greater than 1 is presented. The formula is valid with a varying degree of accuracy down to proton energies of 10 MeV. At high energies (equal to or greater than 2 GeV) the formula reproduces experimental data to within reported errors (about 2%).

Genomic estimation of additive and dominance effects and impact of accounting for dominance on accuracy of genomic evaluation in sheep populations.

PubMed

Moghaddar, N; van der Werf, J H J

2017-12-01

The objectives of this study were to estimate the additive and dominance variance component of several weight and ultrasound scanned body composition traits in purebred and combined cross-bred sheep populations based on single nucleotide polymorphism (SNP) marker genotypes and then to investigate the effect of fitting additive and dominance effects on accuracy of genomic evaluation. Additive and dominance variance components were estimated in a mixed model equation based on "average information restricted maximum likelihood" using additive and dominance (co)variances between animals calculated from 48,599 SNP marker genotypes. Genomic prediction was based on genomic best linear unbiased prediction (GBLUP), and the accuracy of prediction was assessed based on a random 10-fold cross-validation. Across different weight and scanned body composition traits, dominance variance ranged from 0.0% to 7.3% of the phenotypic variance in the purebred population and from 7.1% to 19.2% in the combined cross-bred population. In the combined cross-bred population, the range of dominance variance decreased to 3.1% and 9.9% after accounting for heterosis effects. Accounting for dominance effects significantly improved the likelihood of the fitting model in the combined cross-bred population. This study showed a substantial dominance genetic variance for weight and ultrasound scanned body composition traits particularly in cross-bred population; however, improvement in the accuracy of genomic breeding values was small and statistically not significant. Dominance variance estimates in combined cross-bred population could be overestimated if heterosis is not fitted in the model. © 2017 Blackwell Verlag GmbH.

PAIR Comparison between Two Within-Group Conditions of Resting-State fMRI Improves Classification Accuracy

PubMed Central

Zhou, Zhen; Wang, Jian-Bao; Zang, Yu-Feng; Pan, Gang

2018-01-01

Classification approaches have been increasingly applied to differentiate patients and normal controls using resting-state functional magnetic resonance imaging data (RS-fMRI). Although most previous classification studies have reported promising accuracy within individual datasets, achieving high levels of accuracy with multiple datasets remains challenging for two main reasons: high dimensionality, and high variability across subjects. We used two independent RS-fMRI datasets (n = 31, 46, respectively) both with eyes closed (EC) and eyes open (EO) conditions. For each dataset, we first reduced the number of features to a small number of brain regions with paired t-tests, using the amplitude of low frequency fluctuation (ALFF) as a metric. Second, we employed a new method for feature extraction, named the PAIR method, examining EC and EO as paired conditions rather than independent conditions. Specifically, for each dataset, we obtained EC minus EO (EC—EO) maps of ALFF from half of subjects (n = 15 for dataset-1, n = 23 for dataset-2) and obtained EO—EC maps from the other half (n = 16 for dataset-1, n = 23 for dataset-2). A support vector machine (SVM) method was used for classification of EC RS-fMRI mapping and EO mapping. The mean classification accuracy of the PAIR method was 91.40% for dataset-1, and 92.75% for dataset-2 in the conventional frequency band of 0.01–0.08 Hz. For cross-dataset validation, we applied the classifier from dataset-1 directly to dataset-2, and vice versa. The mean accuracy of cross-dataset validation was 94.93% for dataset-1 to dataset-2 and 90.32% for dataset-2 to dataset-1 in the 0.01–0.08 Hz range. For the UNPAIR method, classification accuracy was substantially lower (mean 69.89% for dataset-1 and 82.97% for dataset-2), and was much lower for cross-dataset validation (64.69% for dataset-1 to dataset-2 and 64.98% for dataset-2 to dataset-1) in the 0.01–0.08 Hz range. In conclusion, for within-group design studies (e.g., paired conditions or follow-up studies), we recommend the PAIR method for feature extraction. In addition, dimensionality reduction with strong prior knowledge of specific brain regions should also be considered for feature selection in neuroimaging studies. PMID:29375288

Genomic prediction using different estimation methodology, blending and cross-validation techniques for growth traits and visual scores in Hereford and Braford cattle.

PubMed

Campos, G S; Reimann, F A; Cardoso, L L; Ferreira, C E R; Junqueira, V S; Schmidt, P I; Braccini Neto, J; Yokoo, M J I; Sollero, B P; Boligon, A A; Cardoso, F F

2018-05-07

The objective of the present study was to evaluate the accuracy and bias of direct and blended genomic predictions using different methods and cross-validation techniques for growth traits (weight and weight gains) and visual scores (conformation, precocity, muscling and size) obtained at weaning and at yearling in Hereford and Braford breeds. Phenotypic data contained 126,290 animals belonging to the Delta G Connection genetic improvement program, and a set of 3,545 animals genotyped with the 50K chip and 131 sires with the 777K. After quality control, 41,045 markers remained for all animals. An animal model was used to estimate (co)variances components and to predict breeding values, which were later used to calculate the deregressed estimated breeding values (DEBV). Animals with genotype and phenotype for the traits studied were divided into four or five groups by random and k-means clustering cross-validation strategies. The values of accuracy of the direct genomic values (DGV) were moderate to high magnitude for at weaning and at yearling traits, ranging from 0.19 to 0.45 for the k-means and 0.23 to 0.78 for random clustering among all traits. The greatest gain in relation to the pedigree BLUP (PBLUP) was 9.5% with the BayesB method with both the k-means and the random clustering. Blended genomic value accuracies ranged from 0.19 to 0.56 for k-means and from 0.21 to 0.82 for random clustering. The analyzes using the historical pedigree and phenotypes contributed additional information to calculate the GEBV and in general, the largest gains were for the single-step (ssGBLUP) method in bivariate analyses with a mean increase of 43.00% among all traits measured at weaning and of 46.27% for those evaluated at yearling. The accuracy values for the marker effects estimation methods were lower for k-means clustering, indicating that the training set relationship to the selection candidates is a major factor affecting accuracy of genomic predictions. The gains in accuracy obtained with genomic blending methods, mainly ssGBLUP in bivariate analyses, indicate that genomic predictions should be used as a tool to improve genetic gains in relation to the traditional PBLUP selection.

Protein Secondary Structure Prediction Using AutoEncoder Network and Bayes Classifier

NASA Astrophysics Data System (ADS)

Wang, Leilei; Cheng, Jinyong

2018-03-01

Protein secondary structure prediction is belong to bioinformatics,and it's important in research area. In this paper, we propose a new prediction way of protein using bayes classifier and autoEncoder network. Our experiments show some algorithms including the construction of the model, the classification of parameters and so on. The data set is a typical CB513 data set for protein. In terms of accuracy, the method is the cross validation based on the 3-fold. Then we can get the Q3 accuracy. Paper results illustrate that the autoencoder network improved the prediction accuracy of protein secondary structure.

Cross-trial prediction of treatment outcome in depression: a machine learning approach.

PubMed

Chekroud, Adam Mourad; Zotti, Ryan Joseph; Shehzad, Zarrar; Gueorguieva, Ralitza; Johnson, Marcia K; Trivedi, Madhukar H; Cannon, Tyrone D; Krystal, John Harrison; Corlett, Philip Robert

2016-03-01

Antidepressant treatment efficacy is low, but might be improved by matching patients to interventions. At present, clinicians have no empirically validated mechanisms to assess whether a patient with depression will respond to a specific antidepressant. We aimed to develop an algorithm to assess whether patients will achieve symptomatic remission from a 12-week course of citalopram. We used patient-reported data from patients with depression (n=4041, with 1949 completers) from level 1 of the Sequenced Treatment Alternatives to Relieve Depression (STAR*D; ClinicalTrials.gov, number NCT00021528) to identify variables that were most predictive of treatment outcome, and used these variables to train a machine-learning model to predict clinical remission. We externally validated the model in the escitalopram treatment group (n=151) of an independent clinical trial (Combining Medications to Enhance Depression Outcomes [COMED]; ClinicalTrials.gov, number NCT00590863). We identified 25 variables that were most predictive of treatment outcome from 164 patient-reportable variables, and used these to train the model. The model was internally cross-validated, and predicted outcomes in the STAR*D cohort with accuracy significantly above chance (64·6% [SD 3·2]; p<0·0001). The model was externally validated in the escitalopram treatment group (N=151) of COMED (accuracy 59·6%, p=0.043). The model also performed significantly above chance in a combined escitalopram-buproprion treatment group in COMED (n=134; accuracy 59·7%, p=0·023), but not in a combined venlafaxine-mirtazapine group (n=140; accuracy 51·4%, p=0·53), suggesting specificity of the model to underlying mechanisms. Building statistical models by mining existing clinical trial data can enable prospective identification of patients who are likely to respond to a specific antidepressant. Yale University. Copyright © 2016 Elsevier Ltd. All rights reserved.

Dutch population specific sex estimation formulae using the proximal femur.

PubMed

Colman, K L; Janssen, M C L; Stull, K E; van Rijn, R R; Oostra, R J; de Boer, H H; van der Merwe, A E

2018-05-01

Sex estimation techniques are frequently applied in forensic anthropological analyses of unidentified human skeletal remains. While morphological sex estimation methods are able to endure population differences, the classification accuracy of metric sex estimation methods are population-specific. No metric sex estimation method currently exists for the Dutch population. The purpose of this study is to create Dutch population specific sex estimation formulae by means of osteometric analyses of the proximal femur. Since the Netherlands lacks a representative contemporary skeletal reference population, 2D plane reconstructions, derived from clinical computed tomography (CT) data, were used as an alternative source for a representative reference sample. The first part of this study assesses the intra- and inter-observer error, or reliability, of twelve measurements of the proximal femur. The technical error of measurement (TEM) and relative TEM (%TEM) were calculated using 26 dry adult femora. In addition, the agreement, or accuracy, between the dry bone and CT-based measurements was determined by percent agreement. Only reliable and accurate measurements were retained for the logistic regression sex estimation formulae; a training set (n=86) was used to create the models while an independent testing set (n=28) was used to validate the models. Due to high levels of multicollinearity, only single variable models were created. Cross-validated classification accuracies ranged from 86% to 92%. The high cross-validated classification accuracies indicate that the developed formulae can contribute to the biological profile and specifically in sex estimation of unidentified human skeletal remains in the Netherlands. Furthermore, the results indicate that clinical CT data can be a valuable alternative source of data when representative skeletal collections are unavailable. Copyright © 2017 Elsevier B.V. All rights reserved.

INCLEN Diagnostic Tool for Autism Spectrum Disorder (INDT-ASD): development and validation.

PubMed

Juneja, Monica; Mishra, Devendra; Russell, Paul S S; Gulati, Sheffali; Deshmukh, Vaishali; Tudu, Poma; Sagar, Rajesh; Silberberg, Donald; Bhutani, Vinod K; Pinto, Jennifer M; Durkin, Maureen; Pandey, Ravindra M; Nair, M K C; Arora, Narendra K

2014-05-01

To develop and validate INCLEN Diagnostic Tool for Autism Spectrum Disorder (INDT-ASD). Diagnostic test evaluation by cross sectional design. Four tertiary pediatric neurology centers in Delhi and Thiruvanthapuram, India. Children aged 2-9 years were enrolled in the study. INDT-ASD and Childhood Autism Rating Scale (CARS) were administered in a randomly decided sequence by trained psychologist, followed by an expert evaluation by DSM-IV TR diagnostic criteria (gold standard). Psychometric parameters of diagnostic accuracy, validity (construct, criterion and convergent) and internal consistency. 154 children (110 boys, mean age 64.2 mo) were enrolled. The overall diagnostic accuracy (AUC=0.97, 95% CI 0.93, 0.99; P<0.001) and validity (sensitivity 98%, specificity 95%, positive predictive value 91%, negative predictive value 99%) of INDT-ASD for Autism spectrum disorder were high, taking expert diagnosis using DSM-IV-TR as gold standard. The concordance rate between the INDT-ASD and expert diagnosis for 'ASD group' was 82.52% [Cohen's k=0.89; 95% CI (0.82, 0.97); P=0.001]. The internal consistency of INDT-ASD was 0.96. The convergent validity with CARS (r = 0.73, P= 0.001) and divergent validity with Binet-Kamat Test of intelligence (r = -0.37; P=0.004) were significantly high. INDT-ASD has a 4-factor structure explaining 85.3% of the variance. INDT-ASD has high diagnostic accuracy, adequate content validity, good internal consistency high criterion validity and high to moderate convergent validity and 4-factor construct validity for diagnosis of Autistm spectrum disorder.

Identifying Wrist Fracture Patients with High Accuracy by Automatic Categorization of X-ray Reports

PubMed Central

de Bruijn, Berry; Cranney, Ann; O’Donnell, Siobhan; Martin, Joel D.; Forster, Alan J.

2006-01-01

The authors performed this study to determine the accuracy of several text classification methods to categorize wrist x-ray reports. We randomly sampled 751 textual wrist x-ray reports. Two expert reviewers rated the presence (n = 301) or absence (n = 450) of an acute fracture of wrist. We developed two information retrieval (IR) text classification methods and a machine learning method using a support vector machine (TC-1). In cross-validation on the derivation set (n = 493), TC-1 outperformed the two IR based methods and six benchmark classifiers, including Naive Bayes and a Neural Network. In the validation set (n = 258), TC-1 demonstrated consistent performance with 93.8% accuracy; 95.5% sensitivity; 92.9% specificity; and 87.5% positive predictive value. TC-1 was easy to implement and superior in performance to the other classification methods. PMID:16929046

A Transcription and Translation Protocol for Sensitive Cross-Cultural Team Research.

PubMed

Clark, Lauren; Birkhead, Ana Sanchez; Fernandez, Cecilia; Egger, Marlene J

2017-10-01

Assurance of transcript accuracy and quality in interview-based qualitative research is foundational for data accuracy and study validity. Based on our experience in a cross-cultural ethnographic study of women's pelvic organ prolapse, we provide practical guidance to set up step-by-step interview transcription and translation protocols for team-based research on sensitive topics. Beginning with team decisions about level of detail in transcription, completeness, and accuracy, we operationalize the process of securing vendors to deliver the required quality of transcription and translation. We also share rubrics for assessing transcript quality and the team protocol for managing transcripts (assuring consistency of format, insertion of metadata, anonymization, and file labeling conventions) and procuring an acceptable initial translation of Spanish-language interviews. Accurate, complete, and systematically constructed transcripts in both source and target languages respond to the call for more transparency and reproducibility of scientific methods.

Validating LES for Jet Aeroacoustics

NASA Technical Reports Server (NTRS)

Bridges, James; Wernet, Mark P.

2011-01-01

Engineers charged with making jet aircraft quieter have long dreamed of being able to see exactly how turbulent eddies produce sound and this dream is now coming true with the advent of large eddy simulation (LES). Two obvious challenges remain: validating the LES codes at the resolution required to see the fluid-acoustic coupling, and the interpretation of the massive datasets that are produced. This paper addresses the former, the use of advanced experimental techniques such as particle image velocimetry (PIV) and Raman and Rayleigh scattering, to validate the computer codes and procedures used to create LES solutions. This paper argues that the issue of accuracy of the experimental measurements be addressed by cross-facility and cross-disciplinary examination of modern datasets along with increased reporting of internal quality checks in PIV analysis. Further, it argues that the appropriate validation metrics for aeroacoustic applications are increasingly complicated statistics that have been shown in aeroacoustic theory to be critical to flow-generated sound, such as two-point space-time velocity correlations. A brief review of data sources available is presented along with examples illustrating cross-facility and internal quality checks required of the data before it should be accepted for validation of LES.

Translation and validation of the Brown attention-deficit disorder scale for use in Brazil: identifying cases of attention-deficit/hyperactivity disorder among samples of substance users and non-users. Cross-cultural validation study.

PubMed

Kakubo, Simone Mayumi; Mendez, Mariel; Silveira, Juliana Doering; Maringolo, Leonardo; Nitta, Conrado; Silveira, Dartiu Xavier da; Fidalgo, Thiago Marques

2018-04-23

The Brown Attention-Deficit Disorder Scale (BADDS) was developed as a self-report assessment that was designed to screen for presence of symptoms of attention deficit hyperactivity disorder (ADHD). The objective here was to translate and validate the adult self-report BADDS for use in Brazil. Cross-cultural validation study conducted in an addiction unit at a public university hospital. This study included a control group (n = 100) and a drug-user group (n = 100). Both groups included subjects aged 18 to 60 years old. The control group had no prior diagnosis of drug addiction and the drug-user group included participants with a diagnosis of addiction. Each participant answered Brazilian Portuguese translations of both the BADDS and the Adult Attention Deficit Hyperactivity Disorder Self-Report Scale (ASRS) questionnaires, in paper-and-pencil format. The drug-user group scored higher than the control group on both scales. The mean scores on ASRS were 27.26 (standard deviation, SD: 11.99) and 25.85 (SD: 8.65) respectively (P > 0.05). The mean scores on BADDS were 79.56 (SD: 29.61) and 79.31 (SD: 18.09), respectively (P > 0.05). Cronbach's alpha for BADDS was 0.95. BADDS presented fair sensitivity (72% accuracy) and fair specificity (88% accuracy). This study provides discriminative validity evidence for use of BADDS among Brazilian adults with substance-use disorders.

Blood-based protein biomarkers for diagnosis of Alzheimer disease.

PubMed

Doecke, James D; Laws, Simon M; Faux, Noel G; Wilson, William; Burnham, Samantha C; Lam, Chiou-Peng; Mondal, Alinda; Bedo, Justin; Bush, Ashley I; Brown, Belinda; De Ruyck, Karl; Ellis, Kathryn A; Fowler, Christopher; Gupta, Veer B; Head, Richard; Macaulay, S Lance; Pertile, Kelly; Rowe, Christopher C; Rembach, Alan; Rodrigues, Mark; Rumble, Rebecca; Szoeke, Cassandra; Taddei, Kevin; Taddei, Tania; Trounson, Brett; Ames, David; Masters, Colin L; Martins, Ralph N

2012-10-01

To identify plasma biomarkers for the diagnosis of Alzheimer disease (AD). Baseline plasma screening of 151 multiplexed analytes combined with targeted biomarker and clinical pathology data. General community-based, prospective, longitudinal study of aging. A total of 754 healthy individuals serving as controls and 207 participants with AD from the Australian Imaging Biomarker and Lifestyle study (AIBL) cohort with identified biomarkers that were validated in 58 healthy controls and 112 individuals with AD from the Alzheimer Disease Neuroimaging Initiative (ADNI) cohort. A biomarker panel was identified that included markers significantly increased (cortisol, pancreatic polypeptide, insulinlike growth factor binding protein 2, β(2) microglobulin, vascular cell adhesion molecule 1, carcinoembryonic antigen, matrix metalloprotein 2, CD40, macrophage inflammatory protein 1α, superoxide dismutase, and homocysteine) and decreased (apolipoprotein E, epidermal growth factor receptor, hemoglobin, calcium, zinc, interleukin 17, and albumin) in AD. Cross-validated accuracy measures from the AIBL cohort reached a mean (SD) of 85% (3.0%) for sensitivity and specificity and 93% (3.0) for the area under the receiver operating characteristic curve. A second validation using the ADNI cohort attained accuracy measures of 80% (3.0%) for sensitivity and specificity and 85% (3.0) for area under the receiver operating characteristic curve. This study identified a panel of plasma biomarkers that distinguish individuals with AD from cognitively healthy control subjects with high sensitivity and specificity. Cross-validation within the AIBL cohort and further validation within the ADNI cohort provides strong evidence that the identified biomarkers are important for AD diagnosis.

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.

Classification of THz pulse signals using two-dimensional cross-correlation feature extraction and non-linear classifiers.

PubMed

Siuly; Yin, Xiaoxia; Hadjiloucas, Sillas; Zhang, Yanchun

2016-04-01

This work provides a performance comparison of four different machine learning classifiers: multinomial logistic regression with ridge estimators (MLR) classifier, k-nearest neighbours (KNN), support vector machine (SVM) and naïve Bayes (NB) as applied to terahertz (THz) transient time domain sequences associated with pixelated images of different powder samples. The six substances considered, although have similar optical properties, their complex insertion loss at the THz part of the spectrum is significantly different because of differences in both their frequency dependent THz extinction coefficient as well as differences in their refractive index and scattering properties. As scattering can be unquantifiable in many spectroscopic experiments, classification solely on differences in complex insertion loss can be inconclusive. The problem is addressed using two-dimensional (2-D) cross-correlations between background and sample interferograms, these ensure good noise suppression of the datasets and provide a range of statistical features that are subsequently used as inputs to the above classifiers. A cross-validation procedure is adopted to assess the performance of the classifiers. Firstly the measurements related to samples that had thicknesses of 2mm were classified, then samples at thicknesses of 4mm, and after that 3mm were classified and the success rate and consistency of each classifier was recorded. In addition, mixtures having thicknesses of 2 and 4mm as well as mixtures of 2, 3 and 4mm were presented simultaneously to all classifiers. This approach provided further cross-validation of the classification consistency of each algorithm. The results confirm the superiority in classification accuracy and robustness of the MLR (least accuracy 88.24%) and KNN (least accuracy 90.19%) algorithms which consistently outperformed the SVM (least accuracy 74.51%) and NB (least accuracy 56.86%) classifiers for the same number of feature vectors across all studies. The work establishes a general methodology for assessing the performance of other hyperspectral dataset classifiers on the basis of 2-D cross-correlations in far-infrared spectroscopy or other parts of the electromagnetic spectrum. It also advances the wider proliferation of automated THz imaging systems across new application areas e.g., biomedical imaging, industrial processing and quality control where interpretation of hyperspectral images is still under development. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Temporal variability in estuarine fish otolith elemental fingerprints: Implications for connectivity assessments

NASA Astrophysics Data System (ADS)

Reis-Santos, Patrick; Gillanders, Bronwyn M.; Tanner, Susanne E.; Vasconcelos, Rita P.; Elsdon, Travis S.; Cabral, Henrique N.

2012-10-01

The chemical composition of fish otoliths can provide valuable information for determining the nursery value of estuaries to adult populations of coastal fishes. However, understanding temporal variation in elemental fingerprints at different scales is important as it can potentially confound spatial discrimination among estuaries. Otolith elemental ratios (Li:Ca, Mg:Ca, Mn:Ca, Cu:Ca, Sr:Ca, Ba:Ca and Pb:Ca) of Platichthys flesus and Dicentrarchus labrax, from several estuaries along the Portuguese coast in two years and three seasons (spring, summer and autumn) within a year, were determined via Laser Ablation Inductively Coupled Plasma Mass Spectrometry. Elemental fingerprints varied significantly among years and seasons within a year but we achieved accurate classifications of juvenile fish to estuarine nursery of origin (77-96% overall cross-validated accuracy). Although elemental fingerprints were year-specific, variation among seasons did not hinder spatial discrimination. Estuarine fingerprints of pooled seasonal data were representative of the entire juvenile year class and attained high discrimination (77% and 80% overall cross-validated accuracy for flounder and sea bass, respectively). Incorporating seasonal variation resulted in up to an 11% increase in correct classification of individual estuaries, in comparison to seasons where accuracies were lowest. Overall, understanding the implications of temporal variations in otolith chemistry for spatial discrimination is key to establish baseline data for connectivity studies.

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

Cross-Cultural Applicability of the Montreal Cognitive Assessment (MoCA): A Systematic Review.

PubMed

O'Driscoll, Ciarán; Shaikh, Madiha

2017-01-01

The Montreal Cognitive Assessment (MoCA) is widely used to screen for mild cognitive impairment (MCI). While there are many available versions, the cross-cultural validity of the assessment has not been explored sufficiently. We aimed to interrogate the validity of the MoCA in a cross-cultural context: in differentiating MCI from normal controls (NC); and identifying cut-offs and adjustments for age and education where possible. This review sourced a wide range of studies including case-control studies. In addition, we report findings for differentiating dementias from NC and MCI from dementias, however, these were not considered to be an appropriate use of the MoCA. The subject of the review assumes heterogeneity and therefore meta-analyses was not conducted. Quality ratings, forest plots of validated studies (sensitivity and specificity) with covariates (suggested cut-offs, age, education and country), and summary receiver operating characteristic curve are presented. The results showed a wide range in suggested cutoffs for MCI cross-culturally, with variability in levels of sensitivity and specificity ranging from low to high. Poor methodological rigor appears to have affected reported accuracy and validity of the MoCA. The review highlights the necessity for cross-cultural considerations when using the MoCA, and recognizing it as a screen and not a diagnostic tool. Appropriate cutoffs and point adjustments for education are suggested.

Electroencephalography as a clinical tool for diagnosing and monitoring attention deficit hyperactivity disorder: a cross-sectional study

PubMed Central

Helgadóttir, Halla; Gudmundsson, Ólafur Ó; Baldursson, Gísli; Magnússon, Páll; Blin, Nicolas; Brynjólfsdóttir, Berglind; Emilsdóttir, Ásdís; Gudmundsdóttir, Gudrún B; Lorange, Málfrídur; Newman, Paula K; Jóhannesson, Gísli H; Johnsen, Kristinn

2015-01-01

Objectives The aim of this study was to develop and test, for the first time, a multivariate diagnostic classifier of attention deficit hyperactivity disorder (ADHD) based on EEG coherence measures and chronological age. Setting The participants were recruited in two specialised centres and three schools in Reykjavik. Participants The data are from a large cross-sectional cohort of 310 patients with ADHD and 351 controls, covering an age range from 5.8 to 14 years. ADHD was diagnosed according to the Diagnostic and Statistical Manual of Mental Disorders fourth edition (DSM-IV) criteria using the K-SADS-PL semistructured interview. Participants in the control group were reported to be free of any mental or developmental disorders by their parents and had a score of less than 1.5 SDs above the age-appropriate norm on the ADHD Rating Scale-IV. Other than moderate or severe intellectual disability, no additional exclusion criteria were applied in order that the cohort reflected the typical cross section of patients with ADHD. Results Diagnostic classifiers were developed using statistical pattern recognition for the entire age range and for specific age ranges and were tested using cross-validation and by application to a separate cohort of recordings not used in the development process. The age-specific classification approach was more accurate (76% accuracy in the independent test cohort; 81% cross-validation accuracy) than the age-independent version (76%; 73%). Chronological age was found to be an important classification feature. Conclusions The novel application of EEG-based classification methods presented here can offer significant benefit to the clinician by improving both the accuracy of initial diagnosis and ongoing monitoring of children and adolescents with ADHD. The most accurate possible diagnosis at a single point in time can be obtained by the age-specific classifiers, but the age-independent classifiers are also useful as they enable longitudinal monitoring of brain function. PMID:25596195

Prediction of individual milk proteins including free amino acids in bovine milk using mid-infrared spectroscopy and their correlations with milk processing characteristics.

PubMed

McDermott, A; Visentin, G; De Marchi, M; Berry, D P; Fenelon, M A; O'Connor, P M; Kenny, O A; McParland, S

2016-04-01

The aim of this study was to evaluate the effectiveness of mid-infrared spectroscopy in predicting milk protein and free amino acid (FAA) composition in bovine milk. Milk samples were collected from 7 Irish research herds and represented cows from a range of breeds, parities, and stages of lactation. Mid-infrared spectral data in the range of 900 to 5,000 cm(-1) were available for 730 milk samples; gold standard methods were used to quantify individual protein fractions and FAA of these samples with a view to predicting these gold standard protein fractions and FAA levels with available mid-infrared spectroscopy data. Separate prediction equations were developed for each trait using partial least squares regression; accuracy of prediction was assessed using both cross validation on a calibration data set (n=400 to 591 samples) and external validation on an independent data set (n=143 to 294 samples). The accuracy of prediction in external validation was the same irrespective of whether undertaken on the entire external validation data set or just within the Holstein-Friesian breed. The strongest coefficient of correlation obtained for protein fractions in external validation was 0.74, 0.69, and 0.67 for total casein, total β-lactoglobulin, and β-casein, respectively. Total proteins (i.e., total casein, total whey, and total lactoglobulin) were predicted with greater accuracy then their respective component traits; prediction accuracy using the infrared spectrum was superior to prediction using just milk protein concentration. Weak to moderate prediction accuracies were observed for FAA. The greatest coefficient of correlation in both cross validation and external validation was for Gly (0.75), indicating a moderate accuracy of prediction. Overall, the FAA prediction models overpredicted the gold standard values. Near-unity correlations existed between total casein and β-casein irrespective of whether the traits were based on the gold standard (0.92) or mid-infrared spectroscopy predictions (0.95). Weaker correlations among FAA were observed than the correlations among the protein fractions. Pearson correlations between gold standard protein fractions and the milk processing characteristics of rennet coagulation time, curd firming time, curd firmness, heat coagulating time, pH, and casein micelle size were weak to moderate and ranged from -0.48 (protein and pH) to 0.50 (total casein and a30). Pearson correlations between gold standard FAA and these milk processing characteristics were also weak to moderate and ranged from -0.60 (Val and pH) to 0.49 (Val and K20). Results from this study indicate that mid-infrared spectroscopy has the potential to predict protein fractions and some FAA in milk at a population level. Copyright © 2016 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Model-Based Collaborative Filtering Analysis of Student Response Data: Machine-Learning Item Response Theory

ERIC Educational Resources Information Center

Bergner, Yoav; Droschler, Stefan; Kortemeyer, Gerd; Rayyan, Saif; Seaton, Daniel; Pritchard, David E.

2012-01-01

We apply collaborative filtering (CF) to dichotomously scored student response data (right, wrong, or no interaction), finding optimal parameters for each student and item based on cross-validated prediction accuracy. The approach is naturally suited to comparing different models, both unidimensional and multidimensional in ability, including a…

Classification of pulmonary pathology from breath sounds using the wavelet packet transform and an extreme learning machine.

PubMed

Palaniappan, Rajkumar; Sundaraj, Kenneth; Sundaraj, Sebastian; Huliraj, N; Revadi, S S

2017-06-08

Auscultation is a medical procedure used for the initial diagnosis and assessment of lung and heart diseases. From this perspective, we propose assessing the performance of the extreme learning machine (ELM) classifiers for the diagnosis of pulmonary pathology using breath sounds. Energy and entropy features were extracted from the breath sound using the wavelet packet transform. The statistical significance of the extracted features was evaluated by one-way analysis of variance (ANOVA). The extracted features were inputted into the ELM classifier. The maximum classification accuracies obtained for the conventional validation (CV) of the energy and entropy features were 97.36% and 98.37%, respectively, whereas the accuracies obtained for the cross validation (CRV) of the energy and entropy features were 96.80% and 97.91%, respectively. In addition, maximum classification accuracies of 98.25% and 99.25% were obtained for the CV and CRV of the ensemble features, respectively. The results indicate that the classification accuracy obtained with the ensemble features was higher than those obtained with the energy and entropy features.

Short communication: Variations in major mineral contents of Mediterranean buffalo milk and application of Fourier-transform infrared spectroscopy for their prediction.

PubMed

Stocco, G; Cipolat-Gotet, C; Bonfatti, V; Schiavon, S; Bittante, G; Cecchinato, A

2016-11-01

The aims of this study were (1) to assess variability in the major mineral components of buffalo milk, (2) to estimate the effect of certain environmental sources of variation on the major minerals during lactation, and (3) to investigate the possibility of using Fourier-transform infrared (FTIR) spectroscopy as an indirect, noninvasive tool for routine prediction of the mineral content of buffalo milk. A total of 173 buffaloes reared in 5 herds were sampled once during the morning milking. Milk samples were analyzed for Ca, P, K, and Mg contents within 3h of sample collection using inductively coupled plasma optical emission spectrometry. A Milkoscan FT2 (Foss, Hillerød, Denmark) was used to acquire milk spectra over the spectral range from 5,000 to 900 wavenumber/cm. Prediction models were built using a partial least square approach, and cross-validation was used to assess the prediction accuracy of FTIR. Prediction models were validated using a 4-fold random cross-validation, thus dividing the calibration-test set in 4 folds, using one of them to check the results (prediction models) and the remaining 3 to develop the calibration models. Buffalo milk minerals averaged 162, 117, 86, and 14.4mg/dL of milk for Ca, P, K, and Mg, respectively. Herd and days in milk were the most important sources of variation in the traits investigated. Parity slightly affected only Ca content. Coefficients of determination of cross-validation between the FTIR-predicted and the measured values were 0.71, 0.70, and 0.72 for Ca, Mg, and P, respectively, whereas prediction accuracy was lower for K (0.55). Our findings reveal FTIR to be an unsuitable tool when milk mineral content needs to be predicted with high accuracy. Predictions may play a role as indicator traits in selective breeding (if the additive genetic correlation between FTIR predictions and measures of milk minerals is high enough) or in monitoring the milk of buffalo populations for dairy industry purposes. Copyright © 2016 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Seeing It All: Evaluating Supervised Machine Learning Methods for the Classification of Diverse Otariid Behaviours

PubMed Central

Slip, David J.; Hocking, David P.; Harcourt, Robert G.

2016-01-01

Constructing activity budgets for marine animals when they are at sea and cannot be directly observed is challenging, but recent advances in bio-logging technology offer solutions to this problem. Accelerometers can potentially identify a wide range of behaviours for animals based on unique patterns of acceleration. However, when analysing data derived from accelerometers, there are many statistical techniques available which when applied to different data sets produce different classification accuracies. We investigated a selection of supervised machine learning methods for interpreting behavioural data from captive otariids (fur seals and sea lions). We conducted controlled experiments with 12 seals, where their behaviours were filmed while they were wearing 3-axis accelerometers. From video we identified 26 behaviours that could be grouped into one of four categories (foraging, resting, travelling and grooming) representing key behaviour states for wild seals. We used data from 10 seals to train four predictive classification models: stochastic gradient boosting (GBM), random forests, support vector machine using four different kernels and a baseline model: penalised logistic regression. We then took the best parameters from each model and cross-validated the results on the two seals unseen so far. We also investigated the influence of feature statistics (describing some characteristic of the seal), testing the models both with and without these. Cross-validation accuracies were lower than training accuracy, but the SVM with a polynomial kernel was still able to classify seal behaviour with high accuracy (>70%). Adding feature statistics improved accuracies across all models tested. Most categories of behaviour -resting, grooming and feeding—were all predicted with reasonable accuracy (52–81%) by the SVM while travelling was poorly categorised (31–41%). These results show that model selection is important when classifying behaviour and that by using animal characteristics we can strengthen the overall accuracy. PMID:28002450

A Decision Tree for Nonmetric Sex Assessment from the Skull.

PubMed

Langley, Natalie R; Dudzik, Beatrix; Cloutier, Alesia

2018-01-01

This study uses five well-documented cranial nonmetric traits (glabella, mastoid process, mental eminence, supraorbital margin, and nuchal crest) and one additional trait (zygomatic extension) to develop a validated decision tree for sex assessment. The decision tree was built and cross-validated on a sample of 293 U.S. White individuals from the William M. Bass Donated Skeletal Collection. Ordinal scores from the six traits were analyzed using the partition modeling option in JMP Pro 12. A holdout sample of 50 skulls was used to test the model. The most accurate decision tree includes three variables: glabella, zygomatic extension, and mastoid process. This decision tree yielded 93.5% accuracy on the training sample, 94% on the cross-validated sample, and 96% on a holdout validation sample. Linear weighted kappa statistics indicate acceptable agreement among observers for these variables. Mental eminence should be avoided, and definitions and figures should be referenced carefully to score nonmetric traits. © 2017 American Academy of Forensic Sciences.

Assessment of EchoMRI-AH versus dual-energy X-ray absorptiometry by iDXA to measure human body composition.

PubMed

Marlatt, K L; Greenway, F L; Ravussin, E

2017-04-01

Comparison of percent fat mass across different body composition analysis devices is important given variation in technology accuracy and precision, as well as the growing need for cross-validation of devices often applied across longitudinal studies. We compared EchoMRI-AH and Lunar iDXA quantification of percent body fat (PBF) in 84 adults (43M, 41F), with the mean age 39.7±15.9 years and body mass index (BMI) 26.2±5.3 kg/m 2 . PBF correlated strongly between devices (r>0.95, P<0.0001). A prediction equation was derived in half of the subjects, and the other half were used to cross-validate the proposed equation (EchoMRI-AH PBF=[(0.94 × iDXA PBF)+(0.14 × Age)+(3.3 × Female)-8.83). The mean PBF difference (predicted-measured) in the validation group was not different from 0 (diff=0.27%, 95% confidence interval: -0.42-0.96, P=0.430). Bland-Altman plots showed a bias with higher measured PBF on EchoMRI-AH versus iDXA in all 84 subjects (β=0.13, P<0.0001). The proposed prediction equation was valid in our cross-validation sample, and it has the potential to be applied across multicenter studies.

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.

Measurement of the $$\\mathrm{Z}\\gamma^{*} \\to \\tau\\tau$$ cross section in pp collisions at $$\\sqrt{s} = $$ 13 TeV and validation of $$\\tau$$ lepton analysis techniques

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

Sirunyan, Albert M; et al.

A measurement is presented of themore » $$\\mathrm{Z}/\\gamma^{*} \\to \\tau\\tau$$ cross section in pp collisions at $$\\sqrt{s} = $$ 13 TeV, using data recorded by the CMS experiment at the LHC, corresponding to an integrated luminosity of 2.3 fb$$^{-1}$$. The product of the inclusive cross section and branching fraction is measured to be $$\\sigma(\\mathrm{pp} \\to \\mathrm{Z}/\\gamma^{*}\\text{+X}) \\, \\mathcal{B}(\\mathrm{Z}/\\gamma^{*} \\to \\tau\\tau) = $$ 1848 $$\\pm$$ 12 (stat) $$\\pm$$ 67 (syst+lumi) pb, in agreement with the standard model expectation, computed at next-to-next-to-leading order accuracy in perturbative quantum chromodynamics. The measurement is used to validate new analysis techniques relevant for future measurements of $$\\tau$$ lepton production. The measurement also provides the reconstruction efficiency and energy scale for $$\\tau$$ decays to hadrons+$$\

Concussion classification via deep learning using whole-brain white matter fiber strains

PubMed Central

Cai, Yunliang; Wu, Shaoju; Zhao, Wei; Li, Zhigang; Wu, Zheyang

2018-01-01

Developing an accurate and reliable injury predictor is central to the biomechanical studies of traumatic brain injury. State-of-the-art efforts continue to rely on empirical, scalar metrics based on kinematics or model-estimated tissue responses explicitly pre-defined in a specific brain region of interest. They could suffer from loss of information. A single training dataset has also been used to evaluate performance but without cross-validation. In this study, we developed a deep learning approach for concussion classification using implicit features of the entire voxel-wise white matter fiber strains. Using reconstructed American National Football League (NFL) injury cases, leave-one-out cross-validation was employed to objectively compare injury prediction performances against two baseline machine learning classifiers (support vector machine (SVM) and random forest (RF)) and four scalar metrics via univariate logistic regression (Brain Injury Criterion (BrIC), cumulative strain damage measure of the whole brain (CSDM-WB) and the corpus callosum (CSDM-CC), and peak fiber strain in the CC). Feature-based machine learning classifiers including deep learning, SVM, and RF consistently outperformed all scalar injury metrics across all performance categories (e.g., leave-one-out accuracy of 0.828–0.862 vs. 0.690–0.776, and .632+ error of 0.148–0.176 vs. 0.207–0.292). Further, deep learning achieved the best cross-validation accuracy, sensitivity, AUC, and .632+ error. These findings demonstrate the superior performances of deep learning in concussion prediction and suggest its promise for future applications in biomechanical investigations of traumatic brain injury. PMID:29795640

Concussion classification via deep learning using whole-brain white matter fiber strains.

PubMed

Cai, Yunliang; Wu, Shaoju; Zhao, Wei; Li, Zhigang; Wu, Zheyang; Ji, Songbai

2018-01-01

Developing an accurate and reliable injury predictor is central to the biomechanical studies of traumatic brain injury. State-of-the-art efforts continue to rely on empirical, scalar metrics based on kinematics or model-estimated tissue responses explicitly pre-defined in a specific brain region of interest. They could suffer from loss of information. A single training dataset has also been used to evaluate performance but without cross-validation. In this study, we developed a deep learning approach for concussion classification using implicit features of the entire voxel-wise white matter fiber strains. Using reconstructed American National Football League (NFL) injury cases, leave-one-out cross-validation was employed to objectively compare injury prediction performances against two baseline machine learning classifiers (support vector machine (SVM) and random forest (RF)) and four scalar metrics via univariate logistic regression (Brain Injury Criterion (BrIC), cumulative strain damage measure of the whole brain (CSDM-WB) and the corpus callosum (CSDM-CC), and peak fiber strain in the CC). Feature-based machine learning classifiers including deep learning, SVM, and RF consistently outperformed all scalar injury metrics across all performance categories (e.g., leave-one-out accuracy of 0.828-0.862 vs. 0.690-0.776, and .632+ error of 0.148-0.176 vs. 0.207-0.292). Further, deep learning achieved the best cross-validation accuracy, sensitivity, AUC, and .632+ error. These findings demonstrate the superior performances of deep learning in concussion prediction and suggest its promise for future applications in biomechanical investigations of traumatic brain injury.

Evaluating model structure adequacy: The case of the Maggia Valley groundwater system, southern Switzerland

USGS Publications Warehouse

Hill, Mary C.; L. Foglia,; S. W. Mehl,; P. Burlando,

2013-01-01

Model adequacy is evaluated with alternative models rated using model selection criteria (AICc, BIC, and KIC) and three other statistics. Model selection criteria are tested with cross-validation experiments and insights for using alternative models to evaluate model structural adequacy are provided. The study is conducted using the computer codes UCODE_2005 and MMA (MultiModel Analysis). One recharge alternative is simulated using the TOPKAPI hydrological model. The predictions evaluated include eight heads and three flows located where ecological consequences and model precision are of concern. Cross-validation is used to obtain measures of prediction accuracy. Sixty-four models were designed deterministically and differ in representation of river, recharge, bedrock topography, and hydraulic conductivity. Results include: (1) What may seem like inconsequential choices in model construction may be important to predictions. Analysis of predictions from alternative models is advised. (2) None of the model selection criteria consistently identified models with more accurate predictions. This is a disturbing result that suggests to reconsider the utility of model selection criteria, and/or the cross-validation measures used in this work to measure model accuracy. (3) KIC displayed poor performance for the present regression problems; theoretical considerations suggest that difficulties are associated with wide variations in the sensitivity term of KIC resulting from the models being nonlinear and the problems being ill-posed due to parameter correlations and insensitivity. The other criteria performed somewhat better, and similarly to each other. (4) Quantities with high leverage are more difficult to predict. The results are expected to be generally applicable to models of environmental systems.

2D-QSAR and 3D-QSAR Analyses for EGFR Inhibitors

PubMed Central

Zhao, Manman; Zheng, Linfeng; Qiu, Chun

2017-01-01

Epidermal growth factor receptor (EGFR) is an important target for cancer therapy. In this study, EGFR inhibitors were investigated to build a two-dimensional quantitative structure-activity relationship (2D-QSAR) model and a three-dimensional quantitative structure-activity relationship (3D-QSAR) model. In the 2D-QSAR model, the support vector machine (SVM) classifier combined with the feature selection method was applied to predict whether a compound was an EGFR inhibitor. As a result, the prediction accuracy of the 2D-QSAR model was 98.99% by using tenfold cross-validation test and 97.67% by using independent set test. Then, in the 3D-QSAR model, the model with q2 = 0.565 (cross-validated correlation coefficient) and r2 = 0.888 (non-cross-validated correlation coefficient) was built to predict the activity of EGFR inhibitors. The mean absolute error (MAE) of the training set and test set was 0.308 log units and 0.526 log units, respectively. In addition, molecular docking was also employed to investigate the interaction between EGFR inhibitors and EGFR. PMID:28630865

The French Version of the Autism-Spectrum Quotient in Adolescents: A Cross-Cultural Validation Study

ERIC Educational Resources Information Center

Sonie, Sandrine; Kassai, Behrouz; Pirat, Elodie; Bain, Paul; Robinson, Janine; Gomot, Marie; Barthelemy, Catherine; Charvet, Dorothee; Rochet, Thierry; Tatou, Mohamed; Assouline, Brigitte; Cabrol, Stephane; Chabane, Nadia; Arnaud, Valerie; Faure, Patricia; Manificat, Sabine

2013-01-01

We assessed the accuracy of the French version of the "Autism Spectrum Quotient" ("AQ") in adolescents with Asperger syndrome (AS) and high-functioning autism (HFA) compared to healthy controls and adolescents with psychiatric disorders (PDs). Three groups of adolescents, aged 11-18, were assessed: 116 with AS/HFA (93 with IQ…

Estimating unconsolidated sediment cover thickness by using the horizontal distance to a bedrock outcrop as secondary information

NASA Astrophysics Data System (ADS)

Kitterød, Nils-Otto

2017-08-01

Unconsolidated sediment cover thickness (D) above bedrock was estimated by using a publicly available well database from Norway, GRANADA. General challenges associated with such databases typically involve clustering and bias. However, if information about the horizontal distance to the nearest bedrock outcrop (L) is included, does the spatial estimation of D improve? This idea was tested by comparing two cross-validation results: ordinary kriging (OK) where L was disregarded; and co-kriging (CK) where cross-covariance between D and L was included. The analysis showed only minor differences between OK and CK with respect to differences between estimation and true values. However, the CK results gave in general less estimation variance compared to the OK results. All observations were declustered and transformed to standard normal probability density functions before estimation and back-transformed for the cross-validation analysis. The semivariogram analysis gave correlation lengths for D and L of approx. 10 and 6 km. These correlations reduce the estimation variance in the cross-validation analysis because more than 50 % of the data material had two or more observations within a radius of 5 km. The small-scale variance of D, however, was about 50 % of the total variance, which gave an accuracy of less than 60 % for most of the cross-validation cases. Despite the noisy character of the observations, the analysis demonstrated that L can be used as secondary information to reduce the estimation variance of D.

Empirical evaluation of data normalization methods for molecular classification.

PubMed

Huang, Huei-Chung; Qin, Li-Xuan

2018-01-01

Data artifacts due to variations in experimental handling are ubiquitous in microarray studies, and they can lead to biased and irreproducible findings. A popular approach to correct for such artifacts is through post hoc data adjustment such as data normalization. Statistical methods for data normalization have been developed and evaluated primarily for the discovery of individual molecular biomarkers. Their performance has rarely been studied for the development of multi-marker molecular classifiers-an increasingly important application of microarrays in the era of personalized medicine. In this study, we set out to evaluate the performance of three commonly used methods for data normalization in the context of molecular classification, using extensive simulations based on re-sampling from a unique pair of microRNA microarray datasets for the same set of samples. The data and code for our simulations are freely available as R packages at GitHub. In the presence of confounding handling effects, all three normalization methods tended to improve the accuracy of the classifier when evaluated in an independent test data. The level of improvement and the relative performance among the normalization methods depended on the relative level of molecular signal, the distributional pattern of handling effects (e.g., location shift vs scale change), and the statistical method used for building the classifier. In addition, cross-validation was associated with biased estimation of classification accuracy in the over-optimistic direction for all three normalization methods. Normalization may improve the accuracy of molecular classification for data with confounding handling effects; however, it cannot circumvent the over-optimistic findings associated with cross-validation for assessing classification accuracy.

In-vitro Equilibrium Phosphate Binding Study of Sevelamer Carbonate by UV-Vis Spectrophotometry.

PubMed

Prasaja, Budi; Syabani, M Maulana; Sari, Endah; Chilmi, Uci; Cahyaningsih, Prawitasari; Kosasih, Theresia Weliana

2018-06-12

Sevelamer carbonate is a cross-linked polymeric amine; it is the active ingredient in Renvela ® tablets. US FDA provides recommendation for demonstrating bioequivalence for the development of a generic product of sevelamer carbonte using in-vitro equilibrium binding study. A simple UV-vis spectrophotometry method was developed and validated for quantification of free phosphate to determine the binding parameter constant of sevelamer. The method validation demonstrated the specificity, limit of quantification, accuracy and precision of measurements. The validated method has been successfully used to analyze samples in in-vitro equilibrium binding study for demonstrating bioequivalence. © Georg Thieme Verlag KG Stuttgart · New York.

Development of estrogen receptor beta binding prediction model using large sets of chemicals.

PubMed

Sakkiah, Sugunadevi; Selvaraj, Chandrabose; Gong, Ping; Zhang, Chaoyang; Tong, Weida; Hong, Huixiao

2017-11-03

We developed an ER β binding prediction model to facilitate identification of chemicals specifically bind ER β or ER α together with our previously developed ER α binding model. Decision Forest was used to train ER β binding prediction model based on a large set of compounds obtained from EADB. Model performance was estimated through 1000 iterations of 5-fold cross validations. Prediction confidence was analyzed using predictions from the cross validations. Informative chemical features for ER β binding were identified through analysis of the frequency data of chemical descriptors used in the models in the 5-fold cross validations. 1000 permutations were conducted to assess the chance correlation. The average accuracy of 5-fold cross validations was 93.14% with a standard deviation of 0.64%. Prediction confidence analysis indicated that the higher the prediction confidence the more accurate the predictions. Permutation testing results revealed that the prediction model is unlikely generated by chance. Eighteen informative descriptors were identified to be important to ER β binding prediction. Application of the prediction model to the data from ToxCast project yielded very high sensitivity of 90-92%. Our results demonstrated ER β binding of chemicals could be accurately predicted using the developed model. Coupling with our previously developed ER α prediction model, this model could be expected to facilitate drug development through identification of chemicals that specifically bind ER β or ER α .

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.

Improved method for predicting protein fold patterns with ensemble classifiers.

PubMed

Chen, W; Liu, X; Huang, Y; Jiang, Y; Zou, Q; Lin, C

2012-01-27

Protein folding is recognized as a critical problem in the field of biophysics in the 21st century. Predicting protein-folding patterns is challenging due to the complex structure of proteins. In an attempt to solve this problem, we employed ensemble classifiers to improve prediction accuracy. In our experiments, 188-dimensional features were extracted based on the composition and physical-chemical property of proteins and 20-dimensional features were selected using a coupled position-specific scoring matrix. Compared with traditional prediction methods, these methods were superior in terms of prediction accuracy. The 188-dimensional feature-based method achieved 71.2% accuracy in five cross-validations. The accuracy rose to 77% when we used a 20-dimensional feature vector. These methods were used on recent data, with 54.2% accuracy. Source codes and dataset, together with web server and software tools for prediction, are available at: http://datamining.xmu.edu.cn/main/~cwc/ProteinPredict.html.

Recalibration of the Klales et al. (2012) method of sexing the human innominate for Mexican populations.

PubMed

Gómez-Valdés, Jorge A; Menéndez Garmendia, Antinea; García-Barzola, Lizbeth; Sánchez-Mejorada, Gabriela; Karam, Carlos; Baraybar, José Pablo; Klales, Alexandra

2017-03-01

The aim of this study was to test the accuracy of the Klales et al. (2012) equation for sex estimation in contemporary Mexican population. Our investigation was carried out on a sample of 203 left innominates of identified adult skeletons from the UNAM-Collection and the Santa María Xigui Cemetery, in Central Mexico. The Klales' original equation produces a sex bias in sex estimation against males (86-92% accuracy versus 100% accuracy in females). Based on these results, the Klales et al. (2012) method was recalibrated for a new cutt-of-point for sex estimation in contemporary Mexican populations. The results show cross-validated classification accuracy rates as high as 100% after recalibrating the original logistic regression equation. Recalibration improved classification accuracy and eliminated sex bias. This new formula will improve sex estimation for Mexican contemporary populations. © 2017 Wiley Periodicals, Inc.

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

Anastasiou, Charalampos; Duhr, Claude; Dulat, Falko

In this study, we compute the gluon fusion Higgs boson cross-section at N 3LO through the second term in the threshold expansion. This calculation constitutes a major milestone towards the full N 3LO cross section. Our result has the best formal accuracy in the threshold expansion currently available, and includes contributions from collinear regions besides subleading corrections from soft and hard regions, as well as certain logarithmically enhanced contributions for general kinematics. We use our results to perform a critical appraisal of the validity of the threshold approximation at N 3LO in perturbative QCD.

Summarising and validating test accuracy results across multiple studies for use in clinical practice.

PubMed

Riley, Richard D; Ahmed, Ikhlaaq; Debray, Thomas P A; Willis, Brian H; Noordzij, J Pieter; Higgins, Julian P T; Deeks, Jonathan J

2015-06-15

Following a meta-analysis of test accuracy studies, the translation of summary results into clinical practice is potentially problematic. The sensitivity, specificity and positive (PPV) and negative (NPV) predictive values of a test may differ substantially from the average meta-analysis findings, because of heterogeneity. Clinicians thus need more guidance: given the meta-analysis, is a test likely to be useful in new populations, and if so, how should test results inform the probability of existing disease (for a diagnostic test) or future adverse outcome (for a prognostic test)? We propose ways to address this. Firstly, following a meta-analysis, we suggest deriving prediction intervals and probability statements about the potential accuracy of a test in a new population. Secondly, we suggest strategies on how clinicians should derive post-test probabilities (PPV and NPV) in a new population based on existing meta-analysis results and propose a cross-validation approach for examining and comparing their calibration performance. Application is made to two clinical examples. In the first example, the joint probability that both sensitivity and specificity will be >80% in a new population is just 0.19, because of a low sensitivity. However, the summary PPV of 0.97 is high and calibrates well in new populations, with a probability of 0.78 that the true PPV will be at least 0.95. In the second example, post-test probabilities calibrate better when tailored to the prevalence in the new population, with cross-validation revealing a probability of 0.97 that the observed NPV will be within 10% of the predicted NPV. © 2015 The Authors. Statistics in Medicine Published by John Wiley & Sons Ltd.

Ethical considerations and potential threats to validity for three methods commonly used to collect geographic information in studies among people who use drugs.

PubMed

Rudolph, Abby E; Bazzi, Angela Robertson; Fish, Sue

2016-10-01

Analyses with geographic data can be used to identify "hot spots" and "health service deserts", examine associations between proximity to services and their use, and link contextual factors with individual-level data to better understand how environmental factors influence behaviors. Technological advancements in methods for collecting this information can improve the accuracy of contextually-relevant information; however, they have outpaced the development of ethical standards and guidance, particularly for research involving populations engaging in illicit/stigmatized behaviors. Thematic analysis identified ethical considerations for collecting geographic data using different methods and the extent to which these concerns could influence study compliance and data validity. In-depth interviews with 15 Baltimore residents (6 recruited via flyers and 9 via peer-referral) reporting recent drug use explored comfort with and ethics of three methods for collecting geographic information: (1) surveys collecting self-reported addresses/cross-streets, (2) surveys using web-based maps to find/confirm locations, and (3) geographical momentary assessments (GMA), which collect spatiotemporally referenced behavioral data. Survey methods for collecting geographic data (i.e., addresses/cross-streets and web-based maps) were generally acceptable; however, participants raised confidentiality concerns regarding exact addresses for illicit/stigmatized behaviors. Concerns specific to GMA included burden of carrying/safeguarding phones and responding to survey prompts, confidentiality, discomfort with being tracked, and noncompliance with study procedures. Overall, many felt that confidentiality concerns could influence the accuracy of location information collected for sensitive behaviors and study compliance. Concerns raised by participants could result in differential study participation and/or study compliance and questionable accuracy/validity of location data for sensitive behaviors. Copyright © 2016 Elsevier Ltd. All rights reserved.

A QSAR Model for Thyroperoxidase Inhibition and Screening ...

EPA Pesticide Factsheets

Thyroid hormones (THs) are critical modulators of a wide range of biological processes from neurodevelopment to metabolism. Well regulated levels of THs are critical during development and even moderate changes in maternal or fetal TH levels produce irreversible neurological deficits in children. The enzyme thyroperoxidase (TPO) plays a key role in the synthesis of THs. Inhibition of TPO by xenobiotics leads to decreased TH synthesis and, depending on the degree of synthesis inhibition, may result in adverse developmental outcomes. Recently, a high-throughput screening assay for TPO inhibition (AUR-TPO) was developed and used to screen the ToxCast Phase I and II chemicals. In the present study, we used the results from the AUR-TPO screening to develop a Quantitative Structure-Activity Relationship (QSAR) model for TPO inhibition in Leadscope®. The training set consisted of 898 discrete organic chemicals: 134 positive and 764 negative for TPO inhibition. A 10 times two-fold 50% cross-validation of the model was performed, yielding a balanced accuracy of 78.7% within its defined applicability domain. More recently, an additional ~800 chemicals from the US EPA Endocrine Disruption Screening Program (EDSP21) were screened using the AUR-TPO assay. This data was used for external validation of the QSAR model, demonstrating a balanced accuracy of 85.7% within its applicability domain. Overall, the cross- and external validations indicate a model with a high predictiv

Optimal Combinations of Diagnostic Tests Based on AUC.

PubMed

Huang, Xin; Qin, Gengsheng; Fang, Yixin

2011-06-01

When several diagnostic tests are available, one can combine them to achieve better diagnostic accuracy. This article considers the optimal linear combination that maximizes the area under the receiver operating characteristic curve (AUC); the estimates of the combination's coefficients can be obtained via a nonparametric procedure. However, for estimating the AUC associated with the estimated coefficients, the apparent estimation by re-substitution is too optimistic. To adjust for the upward bias, several methods are proposed. Among them the cross-validation approach is especially advocated, and an approximated cross-validation is developed to reduce the computational cost. Furthermore, these proposed methods can be applied for variable selection to select important diagnostic tests. The proposed methods are examined through simulation studies and applications to three real examples. © 2010, The International Biometric Society.

A Multiplexed Serum Biomarker Immunoassay Panel Discriminates Clinical Lung Cancer Patients from High-Risk Individuals Found to be Cancer-Free by CT Screening

PubMed Central

Bigbee, William L.; Gopalakrishnan, Vanathi; Weissfeld, Joel L.; Wilson, David O.; Dacic, Sanja; Lokshin, Anna E.; Siegfried, Jill M.

2012-01-01

Introduction Clinical decision-making in the setting of CT screening could benefit from accessible biomarkers that help predict the level of lung cancer risk in high-risk individuals with indeterminate pulmonary nodules. Methods To identify candidate serum biomarkers, we measured 70 cancer-related proteins by Luminex xMAP® multiplexed immunoassays in a training set of sera from 56 patients with biopsy-proven primary non small cell lung cancer and 56 age-, sex- and smoking-matched CT-screened controls. Results We identified a panel of 10 serum biomarkers – prolactin, transthyretin, thrombospondin-1, E-selectin, C-C motif chemokine 5, macrophage migration inhibitory factor, plasminogen activator inhibitor, receptor tyrosine-protein kinase, Cyfra 21.1, and serum amyloid A – that distinguished lung cancer from controls with an estimated balanced accuracy (average of sensitivity and specificity) of 76.0%±3.8% from 20-fold internal cross-validation. We then iteratively evaluated this model in independent test and verification case/control studies confirming the initial classification performance of the panel. The classification performance of the 10-biomarker panel was also analytically validated using ELISAs in a second independent case/control population further validating the robustness of the panel. Conclusions The performance of this 10-biomarker panel based model was 77.1% sensitivity/76.2% specificity in cross-validation in the expanded training set, 73.3% sensitivity/93.3% specificity (balanced accuracy 83.3%) in the blinded verification set with the best discriminative performance in Stage I/II cases: 85% sensitivity (balanced accuracy 89.2%). Importantly, the rate of misclassification of CT-screened controls was not different in most control subgroups with or without airflow obstruction or emphysema or pulmonary nodules. These biomarkers have potential to aid in the early detection of lung cancer and more accurate interpretation of indeterminate pulmonary nodules detected by screening CT. PMID:22425918

Validation of the Economic and Health Outcomes Model of Type 2 Diabetes Mellitus (ECHO-T2DM).

PubMed

Willis, Michael; Johansen, Pierre; Nilsson, Andreas; Asseburg, Christian

2017-03-01

The Economic and Health Outcomes Model of Type 2 Diabetes Mellitus (ECHO-T2DM) was developed to address study questions pertaining to the cost-effectiveness of treatment alternatives in the care of patients with type 2 diabetes mellitus (T2DM). Naturally, the usefulness of a model is determined by the accuracy of its predictions. A previous version of ECHO-T2DM was validated against actual trial outcomes and the model predictions were generally accurate. However, there have been recent upgrades to the model, which modify model predictions and necessitate an update of the validation exercises. The objectives of this study were to extend the methods available for evaluating model validity, to conduct a formal model validation of ECHO-T2DM (version 2.3.0) in accordance with the principles espoused by the International Society for Pharmacoeconomics and Outcomes Research (ISPOR) and the Society for Medical Decision Making (SMDM), and secondarily to evaluate the relative accuracy of four sets of macrovascular risk equations included in ECHO-T2DM. We followed the ISPOR/SMDM guidelines on model validation, evaluating face validity, verification, cross-validation, and external validation. Model verification involved 297 'stress tests', in which specific model inputs were modified systematically to ascertain correct model implementation. Cross-validation consisted of a comparison between ECHO-T2DM predictions and those of the seminal National Institutes of Health model. In external validation, study characteristics were entered into ECHO-T2DM to replicate the clinical results of 12 studies (including 17 patient populations), and model predictions were compared to observed values using established statistical techniques as well as measures of average prediction error, separately for the four sets of macrovascular risk equations supported in ECHO-T2DM. Sub-group analyses were conducted for dependent vs. independent outcomes and for microvascular vs. macrovascular vs. mortality endpoints. All stress tests were passed. ECHO-T2DM replicated the National Institutes of Health cost-effectiveness application with numerically similar results. In external validation of ECHO-T2DM, model predictions agreed well with observed clinical outcomes. For all sets of macrovascular risk equations, the results were close to the intercept and slope coefficients corresponding to a perfect match, resulting in high R 2 and failure to reject concordance using an F test. The results were similar for sub-groups of dependent and independent validation, with some degree of under-prediction of macrovascular events. ECHO-T2DM continues to match health outcomes in clinical trials in T2DM, with prediction accuracy similar to other leading models of T2DM.

Validation of diffuse optical tomography using a bi-functional optical-MRI contrast agent and a hybrid MRI-DOT system

NASA Astrophysics Data System (ADS)

Luk, Alex T.; Lin, Yuting; Grimmond, Brian; Sood, Anup; Uzgiris, Egidijus E.; Nalcioglu, Orhan; Gulsen, Gultekin

2013-03-01

Since diffuse optical tomography (DOT) is a low spatial resolution modality, it is desirable to validate its quantitative accuracy with another well-established imaging modality, such as magnetic resonance imaging (MRI). In this work, we have used a polymer based bi-functional MRI-optical contrast agent (Gd-DTPA-polylysine-IR800) in collaboration with GE Global Research. This multi-modality contrast agent provided not only co-localization but also the same kinetics, to cross-validate two imaging modalities. Bi-functional agents are injected to the rats and pharmacokinetics at the bladder are recovered using both optical and MR imaging. DOT results are validated using MRI results as "gold standard"

Scaling Cross Sections for Ion-atom Impact Ionization

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

Igor D. Kaganovich; Edward Startsev; Ronald C. Davidson

2003-06-06

The values of ion-atom ionization cross sections are frequently needed for many applications that utilize the propagation of fast ions through matter. When experimental data and theoretical calculations are not available, approximate formulas are frequently used. This paper briefly summarizes the most important theoretical results and approaches to cross section calculations in order to place the discussion in historical perspective and offer a concise introduction to the topic. Based on experimental data and theoretical predictions, a new fit for ionization cross sections is proposed. The range of validity and accuracy of several frequently used approximations (classical trajectory, the Born approximation,more » and so forth) are discussed using, as examples, the ionization cross sections of hydrogen and helium atoms by various fully stripped ions.« less

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.

Evaluation of gene expression classification studies: factors associated with classification performance.

PubMed

Novianti, Putri W; Roes, Kit C B; Eijkemans, Marinus J C

2014-01-01

Classification methods used in microarray studies for gene expression are diverse in the way they deal with the underlying complexity of the data, as well as in the technique used to build the classification model. The MAQC II study on cancer classification problems has found that performance was affected by factors such as the classification algorithm, cross validation method, number of genes, and gene selection method. In this paper, we study the hypothesis that the disease under study significantly determines which method is optimal, and that additionally sample size, class imbalance, type of medical question (diagnostic, prognostic or treatment response), and microarray platform are potentially influential. A systematic literature review was used to extract the information from 48 published articles on non-cancer microarray classification studies. The impact of the various factors on the reported classification accuracy was analyzed through random-intercept logistic regression. The type of medical question and method of cross validation dominated the explained variation in accuracy among studies, followed by disease category and microarray platform. In total, 42% of the between study variation was explained by all the study specific and problem specific factors that we studied together.

Physiological Differences in the Follicular, Luteal, and Menstrual Phases in Healthy Women Determined by Electrovestibulography: Depression, Anxiety, or Other Associations?

PubMed

Lithgow, Brian J; Moussavi, Zahra

2018-06-05

Electrovestibulography (EVestG) recordings have been previously applied toward classifying and/or measuring the severity of several neurological disorders including depression with and without anxiety. This study's objectives were to: (1) extract EVestG features representing physiological differences of healthy women during their menses, and follicular and luteal phases of their menstrual cycle, and (2) compare these features to those observed in previous studies for depression with and without anxiety. Three EVestG recordings were made on 15 young healthy menstruating females during menses, and follicular and luteal phases. Three features were extracted, using the shape and timing of the detected spontaneously evoked vestibulo-acoustic field potentials. Using these features, a 3-way separation of the 3 phases was achieved, with a leave-one-out cross-validation, resulting in accuracy of > 72%. Using an EVestG shape feature, separation of the follicular and luteal phases was achieved with a leave-one-out cross-validation accuracy of > 93%. The mechanism of separation was not like that in previous depression analyses, and is postulated to be more akin to a form of anxiety and/or progesterone sensitivity. © 2018 S. Karger AG, Basel.

Genomic selection in sugar beet breeding populations.

PubMed

Würschum, Tobias; Reif, Jochen C; Kraft, Thomas; Janssen, Geert; Zhao, Yusheng

2013-09-18

Genomic selection exploits dense genome-wide marker data to predict breeding values. In this study we used a large sugar beet population of 924 lines representing different germplasm types present in breeding populations: unselected segregating families and diverse lines from more advanced stages of selection. All lines have been intensively phenotyped in multi-location field trials for six agronomically important traits and genotyped with 677 SNP markers. We used ridge regression best linear unbiased prediction in combination with fivefold cross-validation and obtained high prediction accuracies for all except one trait. In addition, we investigated whether a calibration developed based on a training population composed of diverse lines is suited to predict the phenotypic performance within families. Our results show that the prediction accuracy is lower than that obtained within the diverse set of lines, but comparable to that obtained by cross-validation within the respective families. The results presented in this study suggest that a training population derived from intensively phenotyped and genotyped diverse lines from a breeding program does hold potential to build up robust calibration models for genomic selection. Taken together, our results indicate that genomic selection is a valuable tool and can thus complement the genomics toolbox in sugar beet breeding.

Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms.

PubMed

Ellis, Katherine; Godbole, Suneeta; Marshall, Simon; Lanckriet, Gert; Staudenmayer, John; Kerr, Jacqueline

2014-01-01

Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper, we present a supervised machine learning method for transportation mode prediction from global positioning system (GPS) and accelerometer data. We collected a dataset of about 150 h of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-min windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time. The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%. Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel.

Inflammatory Asthma Phenotype Discrimination Using an Electronic Nose Breath Analyzer.

PubMed

Plaza, V; Crespo, A; Giner, J; Merino, J L; Ramos-Barbón, D; Mateus, E F; Torrego, A; Cosio, B G; Agustí, A; Sibila, O

2015-01-01

Patients with persistent asthma have different inflammatory phenotypes. The electronic nose is a new technology capable of distinguishing volatile organic compound (VOC) breath-prints in exhaled breath. The aim of the study was to investigate the capacity of electronic nose breath-print analysis to discriminate between different inflammatory asthma phenotypes (eosinophilic, neutrophilic, paucigranulocytic) determined by induced sputum in patients with persistent asthma. Fifty-two patients with persistent asthma were consecutively included in a cross-sectional proof-of-concept study. Inflammatory asthma phenotypes (eosinophilic, neutrophilic and paucigranulocytic) were recognized by inflammatory cell counts in induced sputum. VOC breath-prints were analyzed using the electronic nose Cyranose 320 and assessed by discriminant analysis on principal component reduction, resulting in cross-validated accuracy values. Receiver operating characteristic (ROC) curves were calculated. VOC breath-prints were different in eosinophilic asthmatics compared with both neutrophilic asthmatics (accuracy 73%; P=.008; area under ROC, 0.92) and paucigranulocytic asthmatics (accuracy 74%; P=.004; area under ROC, 0.79). Likewise, neutrophilic and paucigranulocytic breath-prints were also different (accuracy 89%; P=.001; area under ROC, 0.88). An electronic nose can discriminate inflammatory phenotypes in patients with persistent asthma in a regular clinical setting. ClinicalTrials.gov identifier: NCT02026336.

Sequence-based prediction of protein-binding sites in DNA: comparative study of two SVM models.

PubMed

Park, Byungkyu; Im, Jinyong; Tuvshinjargal, Narankhuu; Lee, Wook; Han, Kyungsook

2014-11-01

As many structures of protein-DNA complexes have been known in the past years, several computational methods have been developed to predict DNA-binding sites in proteins. However, its inverse problem (i.e., predicting protein-binding sites in DNA) has received much less attention. One of the reasons is that the differences between the interaction propensities of nucleotides are much smaller than those between amino acids. Another reason is that DNA exhibits less diverse sequence patterns than protein. Therefore, predicting protein-binding DNA nucleotides is much harder than predicting DNA-binding amino acids. We computed the interaction propensity (IP) of nucleotide triplets with amino acids using an extensive dataset of protein-DNA complexes, and developed two support vector machine (SVM) models that predict protein-binding nucleotides from sequence data alone. One SVM model predicts protein-binding nucleotides using DNA sequence data alone, and the other SVM model predicts protein-binding nucleotides using both DNA and protein sequences. In a 10-fold cross-validation with 1519 DNA sequences, the SVM model that uses DNA sequence data only predicted protein-binding nucleotides with an accuracy of 67.0%, an F-measure of 67.1%, and a Matthews correlation coefficient (MCC) of 0.340. With an independent dataset of 181 DNAs that were not used in training, it achieved an accuracy of 66.2%, an F-measure 66.3% and a MCC of 0.324. Another SVM model that uses both DNA and protein sequences achieved an accuracy of 69.6%, an F-measure of 69.6%, and a MCC of 0.383 in a 10-fold cross-validation with 1519 DNA sequences and 859 protein sequences. With an independent dataset of 181 DNAs and 143 proteins, it showed an accuracy of 67.3%, an F-measure of 66.5% and a MCC of 0.329. Both in cross-validation and independent testing, the second SVM model that used both DNA and protein sequence data showed better performance than the first model that used DNA sequence data. To the best of our knowledge, this is the first attempt to predict protein-binding nucleotides in a given DNA sequence from the sequence data alone. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

German translation, cross-cultural adaptation and diagnostic test accuracy of three frailty screening tools : PRISMA-7, FRAIL scale and Groningen Frailty Indicator.

PubMed

Braun, Tobias; Grüneberg, Christian; Thiel, Christian

2018-04-01

Routine screening for frailty could be used to timely identify older people with increased vulnerability und corresponding medical needs. The aim of this study was the translation and cross-cultural adaptation of the PRISMA-7 questionnaire, the FRAIL scale and the Groningen Frailty Indicator (GFI) into the German language as well as a preliminary analysis of the diagnostic test accuracy of these instruments used to screen for frailty. A diagnostic cross-sectional study was performed. The instrument translation into German followed a standardized process. Prefinal versions were clinically tested on older adults who gave structured in-depth feedback on the scales in order to compile a final revision of the German language scale versions. For the analysis of diagnostic test accuracy (criterion validity), PRISMA-7, FRAIL scale and GFI were considered the index tests. Two reference tests were applied to assess frailty, either based on Fried's model of a Physical Frailty Phenotype or on the model of deficit accumulation, expressed in a Frailty Index. Prefinal versions of the German translations of each instrument were produced and completed by 52 older participants (mean age: 73 ± 6 years). Some minor issues concerning comprehensibility and semantics of the scales were identified and resolved. Using the Physical Frailty Phenotype (frailty prevalence: 4%) criteria as a reference standard, the accuracy of the instruments was excellent (area under the curve AUC >0.90). Taking the Frailty Index (frailty prevalence: 23%) as the reference standard, the accuracy was good (AUC between 0.73 and 0.88). German language versions of PRISMA-7, FRAIL scale and GFI have been established and preliminary results indicate sufficient diagnostic test accuracy that needs to be further established.

Machine Learning Interface for Medical Image Analysis.

PubMed

Zhang, Yi C; Kagen, Alexander C

2017-10-01

TensorFlow is a second-generation open-source machine learning software library with a built-in framework for implementing neural networks in wide variety of perceptual tasks. Although TensorFlow usage is well established with computer vision datasets, the TensorFlow interface with DICOM formats for medical imaging remains to be established. Our goal is to extend the TensorFlow API to accept raw DICOM images as input; 1513 DaTscan DICOM images were obtained from the Parkinson's Progression Markers Initiative (PPMI) database. DICOM pixel intensities were extracted and shaped into tensors, or n-dimensional arrays, to populate the training, validation, and test input datasets for machine learning. A simple neural network was constructed in TensorFlow to classify images into normal or Parkinson's disease groups. Training was executed over 1000 iterations for each cross-validation set. The gradient descent optimization and Adagrad optimization algorithms were used to minimize cross-entropy between the predicted and ground-truth labels. Cross-validation was performed ten times to produce a mean accuracy of 0.938 ± 0.047 (95 % CI 0.908-0.967). The mean sensitivity was 0.974 ± 0.043 (95 % CI 0.947-1.00) and mean specificity was 0.822 ± 0.207 (95 % CI 0.694-0.950). We extended the TensorFlow API to enable DICOM compatibility in the context of DaTscan image analysis. We implemented a neural network classifier that produces diagnostic accuracies on par with excellent results from previous machine learning models. These results indicate the potential role of TensorFlow as a useful adjunct diagnostic tool in the clinical setting.

Prediction and visualization of redox conditions in the groundwater of Central Valley, California

NASA Astrophysics Data System (ADS)

Rosecrans, Celia Z.; Nolan, Bernard T.; Gronberg, JoAnn M.

2017-03-01

Regional-scale, three-dimensional continuous probability models, were constructed for aspects of redox conditions in the groundwater system of the Central Valley, California. These models yield grids depicting the probability that groundwater in a particular location will have dissolved oxygen (DO) concentrations less than selected threshold values representing anoxic groundwater conditions, or will have dissolved manganese (Mn) concentrations greater than selected threshold values representing secondary drinking water-quality contaminant levels (SMCL) and health-based screening levels (HBSL). The probability models were constrained by the alluvial boundary of the Central Valley to a depth of approximately 300 m. Probability distribution grids can be extracted from the 3-D models at any desired depth, and are of interest to water-resource managers, water-quality researchers, and groundwater modelers concerned with the occurrence of natural and anthropogenic contaminants related to anoxic conditions. Models were constructed using a Boosted Regression Trees (BRT) machine learning technique that produces many trees as part of an additive model and has the ability to handle many variables, automatically incorporate interactions, and is resistant to collinearity. Machine learning methods for statistical prediction are becoming increasing popular in that they do not require assumptions associated with traditional hypothesis testing. Models were constructed using measured dissolved oxygen and manganese concentrations sampled from 2767 wells within the alluvial boundary of the Central Valley, and over 60 explanatory variables representing regional-scale soil properties, soil chemistry, land use, aquifer textures, and aquifer hydrologic properties. Models were trained on a USGS dataset of 932 wells, and evaluated on an independent hold-out dataset of 1835 wells from the California Division of Drinking Water. We used cross-validation to assess the predictive performance of models of varying complexity, as a basis for selecting final models. Trained models were applied to cross-validation testing data and a separate hold-out dataset to evaluate model predictive performance by emphasizing three model metrics of fit: Kappa; accuracy; and the area under the receiver operator characteristic curve (ROC). The final trained models were used for mapping predictions at discrete depths to a depth of 304.8 m. Trained DO and Mn models had accuracies of 86-100%, Kappa values of 0.69-0.99, and ROC values of 0.92-1.0. Model accuracies for cross-validation testing datasets were 82-95% and ROC values were 0.87-0.91, indicating good predictive performance. Kappas for the cross-validation testing dataset were 0.30-0.69, indicating fair to substantial agreement between testing observations and model predictions. Hold-out data were available for the manganese model only and indicated accuracies of 89-97%, ROC values of 0.73-0.75, and Kappa values of 0.06-0.30. The predictive performance of both the DO and Mn models was reasonable, considering all three of these fit metrics and the low percentages of low-DO and high-Mn events in the data.

SU-G-BRC-13: Model Based Classification for Optimal Position Selection for Left-Sided Breast Radiotherapy: Free Breathing, DIBH, Or Prone

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

Lin, H; Liu, T; Xu, X

Purpose: There are clinical decision challenges to select optimal treatment positions for left-sided breast cancer patients—supine free breathing (FB), supine Deep Inspiration Breath Hold (DIBH) and prone free breathing (prone). Physicians often make the decision based on experiences and trials, which might not always result optimal OAR doses. We herein propose a mathematical model to predict the lowest OAR doses among these three positions, providing a quantitative tool for corresponding clinical decision. Methods: Patients were scanned in FB, DIBH, and prone positions under an IRB approved protocol. Tangential beam plans were generated for each position, and OAR doses were calculated.more » The position with least OAR doses is defined as the optimal position. The following features were extracted from each scan to build the model: heart, ipsilateral lung, breast volume, in-field heart, ipsilateral lung volume, distance between heart and target, laterality of heart, and dose to heart and ipsilateral lung. Principal Components Analysis (PCA) was applied to remove the co-linearity of the input data and also to lower the data dimensionality. Feature selection, another method to reduce dimensionality, was applied as a comparison. Support Vector Machine (SVM) was then used for classification. Thirtyseven patient data were acquired; up to now, five patient plans were available. K-fold cross validation was used to validate the accuracy of the classifier model with small training size. Results: The classification results and K-fold cross validation demonstrated the model is capable of predicting the optimal position for patients. The accuracy of K-fold cross validations has reached 80%. Compared to PCA, feature selection allows causal features of dose to be determined. This provides more clinical insights. Conclusion: The proposed classification system appeared to be feasible. We are generating plans for the rest of the 37 patient images, and more statistically significant results are to be presented.« less

An SVM-Based Classifier for Estimating the State of Various Rotating Components in Agro-Industrial Machinery with a Vibration Signal Acquired from a Single Point on the Machine Chassis

PubMed Central

Ruiz-Gonzalez, Ruben; Gomez-Gil, Jaime; Gomez-Gil, Francisco Javier; Martínez-Martínez, Víctor

2014-01-01

The goal of this article is to assess the feasibility of estimating the state of various rotating components in agro-industrial machinery by employing just one vibration signal acquired from a single point on the machine chassis. To do so, a Support Vector Machine (SVM)-based system is employed. Experimental tests evaluated this system by acquiring vibration data from a single point of an agricultural harvester, while varying several of its working conditions. The whole process included two major steps. Initially, the vibration data were preprocessed through twelve feature extraction algorithms, after which the Exhaustive Search method selected the most suitable features. Secondly, the SVM-based system accuracy was evaluated by using Leave-One-Out cross-validation, with the selected features as the input data. The results of this study provide evidence that (i) accurate estimation of the status of various rotating components in agro-industrial machinery is possible by processing the vibration signal acquired from a single point on the machine structure; (ii) the vibration signal can be acquired with a uniaxial accelerometer, the orientation of which does not significantly affect the classification accuracy; and, (iii) when using an SVM classifier, an 85% mean cross-validation accuracy can be reached, which only requires a maximum of seven features as its input, and no significant improvements are noted between the use of either nonlinear or linear kernels. PMID:25372618

An SVM-based classifier for estimating the state of various rotating components in agro-industrial machinery with a vibration signal acquired from a single point on the machine chassis.

PubMed

Ruiz-Gonzalez, Ruben; Gomez-Gil, Jaime; Gomez-Gil, Francisco Javier; Martínez-Martínez, Víctor

2014-11-03

The goal of this article is to assess the feasibility of estimating the state of various rotating components in agro-industrial machinery by employing just one vibration signal acquired from a single point on the machine chassis. To do so, a Support Vector Machine (SVM)-based system is employed. Experimental tests evaluated this system by acquiring vibration data from a single point of an agricultural harvester, while varying several of its working conditions. The whole process included two major steps. Initially, the vibration data were preprocessed through twelve feature extraction algorithms, after which the Exhaustive Search method selected the most suitable features. Secondly, the SVM-based system accuracy was evaluated by using Leave-One-Out cross-validation, with the selected features as the input data. The results of this study provide evidence that (i) accurate estimation of the status of various rotating components in agro-industrial machinery is possible by processing the vibration signal acquired from a single point on the machine structure; (ii) the vibration signal can be acquired with a uniaxial accelerometer, the orientation of which does not significantly affect the classification accuracy; and, (iii) when using an SVM classifier, an 85% mean cross-validation accuracy can be reached, which only requires a maximum of seven features as its input, and no significant improvements are noted between the use of either nonlinear or linear kernels.

Empirical evaluation of data normalization methods for molecular classification

PubMed Central

Huang, Huei-Chung

2018-01-01

Background Data artifacts due to variations in experimental handling are ubiquitous in microarray studies, and they can lead to biased and irreproducible findings. A popular approach to correct for such artifacts is through post hoc data adjustment such as data normalization. Statistical methods for data normalization have been developed and evaluated primarily for the discovery of individual molecular biomarkers. Their performance has rarely been studied for the development of multi-marker molecular classifiers—an increasingly important application of microarrays in the era of personalized medicine. Methods In this study, we set out to evaluate the performance of three commonly used methods for data normalization in the context of molecular classification, using extensive simulations based on re-sampling from a unique pair of microRNA microarray datasets for the same set of samples. The data and code for our simulations are freely available as R packages at GitHub. Results In the presence of confounding handling effects, all three normalization methods tended to improve the accuracy of the classifier when evaluated in an independent test data. The level of improvement and the relative performance among the normalization methods depended on the relative level of molecular signal, the distributional pattern of handling effects (e.g., location shift vs scale change), and the statistical method used for building the classifier. In addition, cross-validation was associated with biased estimation of classification accuracy in the over-optimistic direction for all three normalization methods. Conclusion Normalization may improve the accuracy of molecular classification for data with confounding handling effects; however, it cannot circumvent the over-optimistic findings associated with cross-validation for assessing classification accuracy. PMID:29666754

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.

Perception Accuracy of Affiliative Relationships in Elementary School Children and Young Adolescents

PubMed Central

Daniel, João R.; Silva, Rita R.; Santos, António J.; Cardoso, Jordana; Coelho, Leandra; Freitas, Miguel; Ribeiro, Olívia

2017-01-01

There has been a rapid growth of studies focused on selection and socialization processes of peer groups, mostly due to the development of stochastic actor-based models to analyze longitudinal social network data. One of the core assumptions of these models is that individuals have an accurate knowledge of the dyadic relationships within their network (i.e., who is and is not connected to whom). Recent cross-sectional findings suggest that elementary school children are very inaccurate in perceiving their classmates’ dyadic relationships. These findings question the validity of stochastic actor-based models to study the developmental dynamics of children and carry implications for future research as well as for the interpretation of past findings. The goal of the present study was thus to further explore the adequacy of the accuracy assumption, analysing data from three longitudinal samples of different age groups (elementary school children and adolescents). Our results support the validity of stochastic actor-based models to study the network of adolescents and suggest that the violation of the accuracy assumption for elementary school children is not as severe as previously thought. PMID:29163310

Predicting drug-induced liver injury using ensemble learning methods and molecular fingerprints.

PubMed

Ai, Haixin; Chen, Wen; Zhang, Li; Huang, Liangchao; Yin, Zimo; Hu, Huan; Zhao, Qi; Zhao, Jian; Liu, Hongsheng

2018-05-21

Drug-induced liver injury (DILI) is a major safety concern in the drug-development process, and various methods have been proposed to predict the hepatotoxicity of compounds during the early stages of drug trials. In this study, we developed an ensemble model using three machine learning algorithms and 12 molecular fingerprints from a dataset containing 1,241 diverse compounds. The ensemble model achieved an average accuracy of 71.1±2.6%, sensitivity of 79.9±3.6%, specificity of 60.3±4.8%, and area under the receiver operating characteristic curve (AUC) of 0.764±0.026 in five-fold cross-validation and an accuracy of 84.3%, sensitivity of 86.9%, specificity of 75.4%, and AUC of 0.904 in an external validation dataset of 286 compounds collected from the Liver Toxicity Knowledge Base (LTKB). Compared with previous methods, the ensemble model achieved relatively high accuracy and sensitivity. We also identified several substructures related to DILI. In addition, we provide a web server offering access to our models (http://ccsipb.lnu.edu.cn/toxicity/HepatoPred-EL/).

Automated Deep Learning-Based System to Identify Endothelial Cells Derived from Induced Pluripotent Stem Cells.

PubMed

Kusumoto, Dai; Lachmann, Mark; Kunihiro, Takeshi; Yuasa, Shinsuke; Kishino, Yoshikazu; Kimura, Mai; Katsuki, Toshiomi; Itoh, Shogo; Seki, Tomohisa; Fukuda, Keiichi

2018-06-05

Deep learning technology is rapidly advancing and is now used to solve complex problems. Here, we used deep learning in convolutional neural networks to establish an automated method to identify endothelial cells derived from induced pluripotent stem cells (iPSCs), without the need for immunostaining or lineage tracing. Networks were trained to predict whether phase-contrast images contain endothelial cells based on morphology only. Predictions were validated by comparison to immunofluorescence staining for CD31, a marker of endothelial cells. Method parameters were then automatically and iteratively optimized to increase prediction accuracy. We found that prediction accuracy was correlated with network depth and pixel size of images to be analyzed. Finally, K-fold cross-validation confirmed that optimized convolutional neural networks can identify endothelial cells with high performance, based only on morphology. Copyright © 2018 The Author(s). Published by Elsevier Inc. All rights reserved.

Validating Remotely Sensed Land Surface Evapotranspiration Based on Multi-scale Field Measurements

NASA Astrophysics Data System (ADS)

Jia, Z.; Liu, S.; Ziwei, X.; Liang, S.

2012-12-01

The land surface evapotranspiration plays an important role in the surface energy balance and the water cycle. There have been significant technical and theoretical advances in our knowledge of evapotranspiration over the past two decades. Acquisition of the temporally and spatially continuous distribution of evapotranspiration using remote sensing technology has attracted the widespread attention of researchers and managers. However, remote sensing technology still has many uncertainties coming from model mechanism, model inputs, parameterization schemes, and scaling issue in the regional estimation. Achieving remotely sensed evapotranspiration (RS_ET) with confident certainty is required but difficult. As a result, it is indispensable to develop the validation methods to quantitatively assess the accuracy and error sources of the regional RS_ET estimations. This study proposes an innovative validation method based on multi-scale evapotranspiration acquired from field measurements, with the validation results including the accuracy assessment, error source analysis, and uncertainty analysis of the validation process. It is a potentially useful approach to evaluate the accuracy and analyze the spatio-temporal properties of RS_ET at both the basin and local scales, and is appropriate to validate RS_ET in diverse resolutions at different time-scales. An independent RS_ET validation using this method was presented over the Hai River Basin, China in 2002-2009 as a case study. Validation at the basin scale showed good agreements between the 1 km annual RS_ET and the validation data such as the water balanced evapotranspiration, MODIS evapotranspiration products, precipitation, and landuse types. Validation at the local scale also had good results for monthly, daily RS_ET at 30 m and 1 km resolutions, comparing to the multi-scale evapotranspiration measurements from the EC and LAS, respectively, with the footprint model over three typical landscapes. Although some validation experiments demonstrated that the models yield accurate estimates at flux measurement sites, the question remains whether they are performing well over the broader landscape. Moreover, a large number of RS_ET products have been released in recent years. Thus, we also pay attention to the cross-validation method of RS_ET derived from multi-source models. "The Multi-scale Observation Experiment on Evapotranspiration over Heterogeneous Land Surfaces: Flux Observation Matrix" campaign is carried out at the middle reaches of the Heihe River Basin, China in 2012. Flux measurements from an observation matrix composed of 22 EC and 4 LAS are acquired to investigate the cross-validation of multi-source models over different landscapes. In this case, six remote sensing models, including the empirical statistical model, the one-source and two-source models, the Penman-Monteith equation based model, the Priestley-Taylor equation based model, and the complementary relationship based model, are used to perform an intercomparison. All the results from the two cases of RS_ET validation showed that the proposed validation methods are reasonable and feasible.

Global mapping of highly pathogenic avian influenza H5N1 and H5Nx clade 2.3.4.4 viruses with spatial cross-validation

PubMed Central

Dhingra, Madhur S; Artois, Jean; Robinson, Timothy P; Linard, Catherine; Chaiban, Celia; Xenarios, Ioannis; Engler, Robin; Liechti, Robin; Kuznetsov, Dmitri; Xiao, Xiangming; Dobschuetz, Sophie Von; Claes, Filip; Newman, Scott H; Dauphin, Gwenaëlle; Gilbert, Marius

2016-01-01

Global disease suitability models are essential tools to inform surveillance systems and enable early detection. We present the first global suitability model of highly pathogenic avian influenza (HPAI) H5N1 and demonstrate that reliable predictions can be obtained at global scale. Best predictions are obtained using spatial predictor variables describing host distributions, rather than land use or eco-climatic spatial predictor variables, with a strong association with domestic duck and extensively raised chicken densities. Our results also support a more systematic use of spatial cross-validation in large-scale disease suitability modelling compared to standard random cross-validation that can lead to unreliable measure of extrapolation accuracy. A global suitability model of the H5 clade 2.3.4.4 viruses, a group of viruses that recently spread extensively in Asia and the US, shows in comparison a lower spatial extrapolation capacity than the HPAI H5N1 models, with a stronger association with intensively raised chicken densities and anthropogenic factors. DOI: http://dx.doi.org/10.7554/eLife.19571.001 PMID:27885988

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

A comparison of five methods to predict genomic breeding values of dairy bulls from genome-wide SNP markers

PubMed Central

2009-01-01

Background Genomic selection (GS) uses molecular breeding values (MBV) derived from dense markers across the entire genome for selection of young animals. The accuracy of MBV prediction is important for a successful application of GS. Recently, several methods have been proposed to estimate MBV. Initial simulation studies have shown that these methods can accurately predict MBV. In this study we compared the accuracies and possible bias of five different regression methods in an empirical application in dairy cattle. Methods Genotypes of 7,372 SNP and highly accurate EBV of 1,945 dairy bulls were used to predict MBV for protein percentage (PPT) and a profit index (Australian Selection Index, ASI). Marker effects were estimated by least squares regression (FR-LS), Bayesian regression (Bayes-R), random regression best linear unbiased prediction (RR-BLUP), partial least squares regression (PLSR) and nonparametric support vector regression (SVR) in a training set of 1,239 bulls. Accuracy and bias of MBV prediction were calculated from cross-validation of the training set and tested against a test team of 706 young bulls. Results For both traits, FR-LS using a subset of SNP was significantly less accurate than all other methods which used all SNP. Accuracies obtained by Bayes-R, RR-BLUP, PLSR and SVR were very similar for ASI (0.39-0.45) and for PPT (0.55-0.61). Overall, SVR gave the highest accuracy. All methods resulted in biased MBV predictions for ASI, for PPT only RR-BLUP and SVR predictions were unbiased. A significant decrease in accuracy of prediction of ASI was seen in young test cohorts of bulls compared to the accuracy derived from cross-validation of the training set. This reduction was not apparent for PPT. Combining MBV predictions with pedigree based predictions gave 1.05 - 1.34 times higher accuracies compared to predictions based on pedigree alone. Some methods have largely different computational requirements, with PLSR and RR-BLUP requiring the least computing time. Conclusions The four methods which use information from all SNP namely RR-BLUP, Bayes-R, PLSR and SVR generate similar accuracies of MBV prediction for genomic selection, and their use in the selection of immediate future generations in dairy cattle will be comparable. The use of FR-LS in genomic selection is not recommended. PMID:20043835

Cross-cultural feigning assessment: A systematic review of feigning instruments used with linguistically, ethnically, and culturally diverse samples.

PubMed

Nijdam-Jones, Alicia; Rosenfeld, Barry

2017-11-01

The cross-cultural validity of feigning instruments and cut-scores is a critical concern for forensic mental health clinicians. This systematic review evaluated feigning classification accuracy and effect sizes across instruments and languages by summarizing 45 published peer-reviewed articles and unpublished doctoral dissertations conducted in Europe, Asia, and North America using linguistically, ethnically, and culturally diverse samples. The most common psychiatric symptom measures used with linguistically, ethnically, and culturally diverse samples included the Structured Inventory of Malingered Symptomatology, the Miller Forensic Assessment of Symptoms Test, and the Minnesota Multiphasic Personality Inventory (MMPI). The most frequently studied cognitive effort measures included the Word Recognition Test, the Test of Memory Malingering, and the Rey 15-item Memory test. The classification accuracy of these measures is compared and the implications of this research literature are discussed. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

The development of a probabilistic approach to forecast coastal change

USGS Publications Warehouse

Lentz, Erika E.; Hapke, Cheryl J.; Rosati, Julie D.; Wang, Ping; Roberts, Tiffany M.

2011-01-01

This study demonstrates the applicability of a Bayesian probabilistic model as an effective tool in predicting post-storm beach changes along sandy coastlines. Volume change and net shoreline movement are modeled for two study sites at Fire Island, New York in response to two extratropical storms in 2007 and 2009. Both study areas include modified areas adjacent to unmodified areas in morphologically different segments of coast. Predicted outcomes are evaluated against observed changes to test model accuracy and uncertainty along 163 cross-shore transects. Results show strong agreement in the cross validation of predictions vs. observations, with 70-82% accuracies reported. Although no consistent spatial pattern in inaccurate predictions could be determined, the highest prediction uncertainties appeared in locations that had been recently replenished. Further testing and model refinement are needed; however, these initial results show that Bayesian networks have the potential to serve as important decision-support tools in forecasting coastal change.

Zebra Crossing Spotter: Automatic Population of Spatial Databases for Increased Safety of Blind Travelers

PubMed Central

Ahmetovic, Dragan; Manduchi, Roberto; Coughlan, James M.; Mascetti, Sergio

2016-01-01

In this paper we propose a computer vision-based technique that mines existing spatial image databases for discovery of zebra crosswalks in urban settings. Knowing the location of crosswalks is critical for a blind person planning a trip that includes street crossing. By augmenting existing spatial databases (such as Google Maps or OpenStreetMap) with this information, a blind traveler may make more informed routing decisions, resulting in greater safety during independent travel. Our algorithm first searches for zebra crosswalks in satellite images; all candidates thus found are validated against spatially registered Google Street View images. This cascaded approach enables fast and reliable discovery and localization of zebra crosswalks in large image datasets. While fully automatic, our algorithm could also be complemented by a final crowdsourcing validation stage for increased accuracy. PMID:26824080

Three dimensional X-ray Diffraction Contrast Tomography Reconstruction of Polycrystalline Strontium Titanate during Sintering and Electron Backscatter Diffraction Validation

NASA Astrophysics Data System (ADS)

Syha, M.; Rheinheimer, W.; Loedermann, B.; Graff, A.; Trenkle, A.; Baeurer, M.; Weygand, D.; Ludwig, W.; Gumbsch, P.

The microstructural evolution of polycrystalline strontium titanate was investigated in three dimensions (3D) using X-ray diffraction contrast tomography (DCT) before and after ex-situ annealing at 1600°C. Post-annealing, the specimen was additionally subjected to phase contrast tomography (PCT) in order to finely resolve the porosities. The resulting microstructure reconstructions were studied with special emphasis on morphology and interface orientation during microstructure evolution. Subsequently, cross-sections of the specimen were studied using electron backscatter diffraction (EBSD). Corresponding cross-sections through the 3D reconstruction were identified and the quality of the reconstruction is validated with special emphasis on the spatial resolution at the grain boundaries, the size and location of pores contained in the material and the accuracy of the orientation determination.

Brief Report: Checklist for Autism Spectrum Disorder--Most Discriminating Items for Diagnosing Autism

ERIC Educational Resources Information Center

Mayes, Susan D.

2018-01-01

The smallest subset of items from the 30-item Checklist for Autism Spectrum Disorder (CASD) that differentiated 607 referred children (3-17 years) with and without autism with 100% accuracy was identified. This 6-item subset (CASD-Short Form) was cross-validated on an independent sample of 397 referred children (1-18 years) with and without autism…

[Validation of three screening tests used for early detection of cervical cancer].

PubMed

Rodriguez-Reyes, Esperanza Rosalba; Cerda-Flores, Ricardo M; Quiñones-Pérez, Juan M; Cortés-Gutiérrez, Elva I

2008-01-01

to evaluate the validity (sensitivity, specificity, and accuracy) of three screening methods used in the early detection of the cervical carcinoma versus the histopathology diagnosis. a selected sample of 107 women attended in the Opportune Detection of Cervicouterine Cancer Program in the Hospital de Zona 46, Instituto Mexicano del Seguro Social in Durango, during the 2003 was included. The application of Papa-nicolaou, acetic acid test, and molecular detection of human papillomavirus, and histopatholgy diagnosis were performed in all the patients at the time of the gynecological exam. The detection and tipification of the human papillomavirus was performed by polymerase chain reaction (PCR) and analysis of polymorphisms of length of restriction fragments (RFLP). Histopathology diagnosis was considered the gold standard. The evaluation of the validity was carried out by the Bayesian method for diagnosis test. the positive cases for acetic acid test, Papanicolaou, and PCR were 47, 22, and 19. The accuracy values were 0.70, 0.80 and 0.99, respectively. since the molecular method showed a greater validity in the early detection of the cervical carcinoma we considered of vital importance its implementation in suitable programs of Opportune Detection of Cervicouterino Cancer Program in Mexico. However, in order to validate this conclusion, cross-sectional studies in different region of country must be carried out.

Computer-aided Assessment of Regional Abdominal Fat with Food Residue Removal in CT

PubMed Central

Makrogiannis, Sokratis; Caturegli, Giorgio; Davatzikos, Christos; Ferrucci, Luigi

2014-01-01

Rationale and Objectives Separate quantification of abdominal subcutaneous and visceral fat regions is essential to understand the role of regional adiposity as risk factor in epidemiological studies. Fat quantification is often based on computed tomography (CT) because fat density is distinct from other tissue densities in the abdomen. However, the presence of intestinal food residues with densities similar to fat may reduce fat quantification accuracy. We introduce an abdominal fat quantification method in CT with interest in food residue removal. Materials and Methods Total fat was identified in the feature space of Hounsfield units and divided into subcutaneous and visceral components using model-based segmentation. Regions of food residues were identified and removed from visceral fat using a machine learning method integrating intensity, texture, and spatial information. Cost-weighting and bagging techniques were investigated to address class imbalance. Results We validated our automated food residue removal technique against semimanual quantifications. Our feature selection experiments indicated that joint intensity and texture features produce the highest classification accuracy at 95%. We explored generalization capability using k-fold cross-validation and receiver operating characteristic (ROC) analysis with variable k. Losses in accuracy and area under ROC curve between maximum and minimum k were limited to 0.1% and 0.3%. We validated tissue segmentation against reference semimanual delineations. The Dice similarity scores were as high as 93.1 for subcutaneous fat and 85.6 for visceral fat. Conclusions Computer-aided regional abdominal fat quantification is a reliable computational tool for large-scale epidemiological studies. Our proposed intestinal food residue reduction scheme is an original contribution of this work. Validation experiments indicate very good accuracy and generalization capability. PMID:24119354

Computer-aided assessment of regional abdominal fat with food residue removal in CT.

PubMed

Makrogiannis, Sokratis; Caturegli, Giorgio; Davatzikos, Christos; Ferrucci, Luigi

2013-11-01

Separate quantification of abdominal subcutaneous and visceral fat regions is essential to understand the role of regional adiposity as risk factor in epidemiological studies. Fat quantification is often based on computed tomography (CT) because fat density is distinct from other tissue densities in the abdomen. However, the presence of intestinal food residues with densities similar to fat may reduce fat quantification accuracy. We introduce an abdominal fat quantification method in CT with interest in food residue removal. Total fat was identified in the feature space of Hounsfield units and divided into subcutaneous and visceral components using model-based segmentation. Regions of food residues were identified and removed from visceral fat using a machine learning method integrating intensity, texture, and spatial information. Cost-weighting and bagging techniques were investigated to address class imbalance. We validated our automated food residue removal technique against semimanual quantifications. Our feature selection experiments indicated that joint intensity and texture features produce the highest classification accuracy at 95%. We explored generalization capability using k-fold cross-validation and receiver operating characteristic (ROC) analysis with variable k. Losses in accuracy and area under ROC curve between maximum and minimum k were limited to 0.1% and 0.3%. We validated tissue segmentation against reference semimanual delineations. The Dice similarity scores were as high as 93.1 for subcutaneous fat and 85.6 for visceral fat. Computer-aided regional abdominal fat quantification is a reliable computational tool for large-scale epidemiological studies. Our proposed intestinal food residue reduction scheme is an original contribution of this work. Validation experiments indicate very good accuracy and generalization capability. Published by Elsevier Inc.

Higgs boson gluon-fusion production beyond threshold in N 3LO QCD

DOE PAGES

Anastasiou, Charalampos; Duhr, Claude; Dulat, Falko; ...

2015-03-18

In this study, we compute the gluon fusion Higgs boson cross-section at N 3LO through the second term in the threshold expansion. This calculation constitutes a major milestone towards the full N 3LO cross section. Our result has the best formal accuracy in the threshold expansion currently available, and includes contributions from collinear regions besides subleading corrections from soft and hard regions, as well as certain logarithmically enhanced contributions for general kinematics. We use our results to perform a critical appraisal of the validity of the threshold approximation at N 3LO in perturbative QCD.

Development of a QSAR Model for Thyroperoxidase Inhbition ...

EPA Pesticide Factsheets

hyroid hormones (THs) are involved in multiple biological processes and are critical modulators of fetal development. Even moderate changes in maternal or fetal TH levels can produce irreversible neurological deficits in children, such as lower IQ. The enzyme thyroperoxidase (TPO) plays a key role in the synthesis of THs, and inhibition of TPO by xenobiotics results in decreased TH synthesis. Recently, a high-throughput screening assay for TPO inhibition (AUR-TPO) was developed and used to test the ToxCast Phase I and II chemicals. In the present study, we used the results from AUR-TPO to develop a Quantitative Structure-Activity Relationship (QSAR) model for TPO inhibition. The training set consisted of 898 discrete organic chemicals: 134 inhibitors and 764 non-inhibitors. A five times two-fold cross-validation of the model was performed, yielding a balanced accuracy of 78.7%. More recently, an additional ~800 chemicals were tested in the AUR-TPO assay. These data were used for a blinded external validation of the QSAR model, demonstrating a balanced accuracy of 85.7%. Overall, the cross- and external validation indicate a robust model with high predictive performance. Next, we used the QSAR model to predict 72,526 REACH pre-registered substances. The model could predict 49.5% (35,925) of the substances in its applicability domain and of these, 8,863 (24.7%) were predicted to be TPO inhibitors. Predictions from this screening can be used in a tiered approach to

Anticancer drug sensitivity prediction in cell lines from baseline gene expression through recursive feature selection.

PubMed

Dong, Zuoli; Zhang, Naiqian; Li, Chun; Wang, Haiyun; Fang, Yun; Wang, Jun; Zheng, Xiaoqi

2015-06-30

An enduring challenge in personalized medicine is to select right drug for individual patients. Testing drugs on patients in large clinical trials is one way to assess their efficacy and toxicity, but it is impractical to test hundreds of drugs currently under development. Therefore the preclinical prediction model is highly expected as it enables prediction of drug response to hundreds of cell lines in parallel. Recently, two large-scale pharmacogenomic studies screened multiple anticancer drugs on over 1000 cell lines in an effort to elucidate the response mechanism of anticancer drugs. To this aim, we here used gene expression features and drug sensitivity data in Cancer Cell Line Encyclopedia (CCLE) to build a predictor based on Support Vector Machine (SVM) and a recursive feature selection tool. Robustness of our model was validated by cross-validation and an independent dataset, the Cancer Genome Project (CGP). Our model achieved good cross validation performance for most drugs in the Cancer Cell Line Encyclopedia (≥80% accuracy for 10 drugs, ≥75% accuracy for 19 drugs). Independent tests on eleven common drugs between CCLE and CGP achieved satisfactory performance for three of them, i.e., AZD6244, Erlotinib and PD-0325901, using expression levels of only twelve, six and seven genes, respectively. These results suggest that drug response could be effectively predicted from genomic features. Our model could be applied to predict drug response for some certain drugs and potentially play a complementary role in personalized medicine.

Automatic Identification of Subtechniques in Skating-Style Roller Skiing Using Inertial Sensors

PubMed Central

Sakurai, Yoshihisa; Fujita, Zenya; Ishige, Yusuke

2016-01-01

This study aims to develop and validate an automated system for identifying skating-style cross-country subtechniques using inertial sensors. In the first experiment, the performance of a male cross-country skier was used to develop an automated identification system. In the second, eight male and seven female college cross-country skiers participated to validate the developed identification system. Each subject wore inertial sensors on both wrists and both roller skis, and a small video camera on a backpack. All subjects skied through a 3450 m roller ski course using a skating style at their maximum speed. The adopted subtechniques were identified by the automated method based on the data obtained from the sensors, as well as by visual observations from a video recording of the same ski run. The system correctly identified 6418 subtechniques from a total of 6768 cycles, which indicates an accuracy of 94.8%. The precisions of the automatic system for identifying the V1R, V1L, V2R, V2L, V2AR, and V2AL subtechniques were 87.6%, 87.0%, 97.5%, 97.8%, 92.1%, and 92.0%, respectively. Most incorrect identification cases occurred during a subtechnique identification that included a transition and turn event. Identification accuracy can be improved by separately identifying transition and turn events. This system could be used to evaluate each skier’s subtechniques in course conditions. PMID:27049388

An experimental study of interstitial lung tissue classification in HRCT images using ANN and role of cost functions

NASA Astrophysics Data System (ADS)

Dash, Jatindra K.; Kale, Mandar; Mukhopadhyay, Sudipta; Khandelwal, Niranjan; Prabhakar, Nidhi; Garg, Mandeep; Kalra, Naveen

2017-03-01

In this paper, we investigate the effect of the error criteria used during a training phase of the artificial neural network (ANN) on the accuracy of the classifier for classification of lung tissues affected with Interstitial Lung Diseases (ILD). Mean square error (MSE) and the cross-entropy (CE) criteria are chosen being most popular choice in state-of-the-art implementations. The classification experiment performed on the six interstitial lung disease (ILD) patterns viz. Consolidation, Emphysema, Ground Glass Opacity, Micronodules, Fibrosis and Healthy from MedGIFT database. The texture features from an arbitrary region of interest (AROI) are extracted using Gabor filter. Two different neural networks are trained with the scaled conjugate gradient back propagation algorithm with MSE and CE error criteria function respectively for weight updation. Performance is evaluated in terms of average accuracy of these classifiers using 4 fold cross-validation. Each network is trained for five times for each fold with randomly initialized weight vectors and accuracies are computed. Significant improvement in classification accuracy is observed when ANN is trained by using CE (67.27%) as error function compared to MSE (63.60%). Moreover, standard deviation of the classification accuracy for the network trained with CE (6.69) error criteria is found less as compared to network trained with MSE (10.32) criteria.

Individualized adjustments to reference phantom internal organ dosimetry—scaling factors given knowledge of patient internal anatomy

NASA Astrophysics Data System (ADS)

Wayson, Michael B.; Bolch, Wesley E.

2018-04-01

Various computational tools are currently available that facilitate patient organ dosimetry in diagnostic nuclear medicine, yet they are typically restricted to reporting organ doses to ICRP-defined reference phantoms. The present study, while remaining computational phantom based, provides straightforward tools to adjust reference phantom organ dose for both internal photon and electron sources. A wide variety of monoenergetic specific absorbed fractions were computed using radiation transport simulations for tissue spheres of varying size and separation distance. Scaling methods were then constructed for both photon and electron self-dose and cross-dose, with data validation provided from patient-specific voxel phantom simulations, as well as via comparison to the scaling methodology given in MIRD Pamphlet No. 11. Photon and electron self-dose was found to be dependent on both radiation energy and sphere size. Photon cross-dose was found to be mostly independent of sphere size. Electron cross-dose was found to be dependent on sphere size when the spheres were in close proximity, owing to differences in electron range. The validation studies showed that this dataset was more effective than the MIRD 11 method at predicting patient-specific photon doses for at both high and low energies, but gave similar results at photon energies between 100 keV and 1 MeV. The MIRD 11 method for electron self-dose scaling was accurate for lower energies but began to break down at higher energies. The photon cross-dose scaling methodology developed in this study showed gains in accuracy of up to 9% for actual patient studies, and the electron cross-dose scaling methodology showed gains in accuracy up to 9% as well when only the bremsstrahlung component of the cross-dose was scaled. These dose scaling methods are readily available for incorporation into internal dosimetry software for diagnostic phantom-based organ dosimetry.

Individualized adjustments to reference phantom internal organ dosimetry-scaling factors given knowledge of patient internal anatomy.

PubMed

Wayson, Michael B; Bolch, Wesley E

2018-04-13

Various computational tools are currently available that facilitate patient organ dosimetry in diagnostic nuclear medicine, yet they are typically restricted to reporting organ doses to ICRP-defined reference phantoms. The present study, while remaining computational phantom based, provides straightforward tools to adjust reference phantom organ dose for both internal photon and electron sources. A wide variety of monoenergetic specific absorbed fractions were computed using radiation transport simulations for tissue spheres of varying size and separation distance. Scaling methods were then constructed for both photon and electron self-dose and cross-dose, with data validation provided from patient-specific voxel phantom simulations, as well as via comparison to the scaling methodology given in MIRD Pamphlet No. 11. Photon and electron self-dose was found to be dependent on both radiation energy and sphere size. Photon cross-dose was found to be mostly independent of sphere size. Electron cross-dose was found to be dependent on sphere size when the spheres were in close proximity, owing to differences in electron range. The validation studies showed that this dataset was more effective than the MIRD 11 method at predicting patient-specific photon doses for at both high and low energies, but gave similar results at photon energies between 100 keV and 1 MeV. The MIRD 11 method for electron self-dose scaling was accurate for lower energies but began to break down at higher energies. The photon cross-dose scaling methodology developed in this study showed gains in accuracy of up to 9% for actual patient studies, and the electron cross-dose scaling methodology showed gains in accuracy up to 9% as well when only the bremsstrahlung component of the cross-dose was scaled. These dose scaling methods are readily available for incorporation into internal dosimetry software for diagnostic phantom-based organ dosimetry.

A Comparison of Artificial Intelligence Methods on Determining Coronary Artery Disease

NASA Astrophysics Data System (ADS)

Babaoğlu, Ismail; Baykan, Ömer Kaan; Aygül, Nazif; Özdemir, Kurtuluş; Bayrak, Mehmet

The aim of this study is to show a comparison of multi-layered perceptron neural network (MLPNN) and support vector machine (SVM) on determination of coronary artery disease existence upon exercise stress testing (EST) data. EST and coronary angiography were performed on 480 patients with acquiring 23 verifying features from each. The robustness of the proposed methods is examined using classification accuracy, k-fold cross-validation method and Cohen's kappa coefficient. The obtained classification accuracies are approximately 78% and 79% for MLPNN and SVM respectively. Both MLPNN and SVM methods are rather satisfactory than human-based method looking to Cohen's kappa coefficients. Besides, SVM is slightly better than MLPNN when looking to the diagnostic accuracy, average of sensitivity and specificity, and also Cohen's kappa coefficient.

Development and validation of classifiers and variable subsets for predicting nursing home admission.

PubMed

Nuutinen, Mikko; Leskelä, Riikka-Leena; Suojalehto, Ella; Tirronen, Anniina; Komssi, Vesa

2017-04-13

In previous years a substantial number of studies have identified statistically important predictors of nursing home admission (NHA). However, as far as we know, the analyses have been done at the population-level. No prior research has analysed the prediction accuracy of a NHA model for individuals. This study is an analysis of 3056 longer-term home care customers in the city of Tampere, Finland. Data were collected from the records of social and health service usage and RAI-HC (Resident Assessment Instrument - Home Care) assessment system during January 2011 and September 2015. The aim was to find out the most efficient variable subsets to predict NHA for individuals and validate the accuracy. The variable subsets of predicting NHA were searched by sequential forward selection (SFS) method, a variable ranking metric and the classifiers of logistic regression (LR), support vector machine (SVM) and Gaussian naive Bayes (GNB). The validation of the results was guaranteed using randomly balanced data sets and cross-validation. The primary performance metrics for the classifiers were the prediction accuracy and AUC (average area under the curve). The LR and GNB classifiers achieved 78% accuracy for predicting NHA. The most important variables were RAI MAPLE (Method for Assigning Priority Levels), functional impairment (RAI IADL, Activities of Daily Living), cognitive impairment (RAI CPS, Cognitive Performance Scale), memory disorders (diagnoses G30-G32 and F00-F03) and the use of community-based health-service and prior hospital use (emergency visits and periods of care). The accuracy of the classifier for individuals was high enough to convince the officials of the city of Tampere to integrate the predictive model based on the findings of this study as a part of home care information system. Further work need to be done to evaluate variables that are modifiable and responsive to interventions.

Using Near-Infrared Spectroscopy to Resolve the Species, Gender, Age, and the Presence of Wolbachia Infection in Laboratory-Reared Drosophila

PubMed Central

Aw, Wen C.; Dowell, Floyd E.; Ballard, J. William O.

2012-01-01

The aim of the study was to determine the accuracy of near-infrared spectroscopy (NIRS) in determining species, gender, age, and the presence of the common endosymbiont Wolbachia in laboratory-reared Drosophila. NIRS measures the absorption of light by organic molecules. Initially, a calibration model was developed for each study. An independent set with flies not involved in initial cross-validation was then used to validate the accuracy of each calibration model. Flies from the independent sets were correctly classified into Drosophila melanogaster and Drosophila simulans with 94% and 82% accuracy, respectively, whereas flies were successfully classified by gender with accuracy greater than 90%. In the age grading test, correlation plots of the actual and predicted age for males and females of D. melanogaster and D. simulans were shown to be overlapping between the adjacent age groups. It is, however, possible to predict the age of flies as less than 9 days of age with 62–88% accuracy and flies that are equal to or older than 9 days of age with 91–98% accuracy. Finally, we used NIRS to detect the presence of Wolbachia in flies. Flies from the independent sets were successfully identified as infected or not infected with Wolbachia with approximately 90% accuracy. These results suggest that NIRS has the potential to quantify the species, gender, and presence of Wolbachia in fly populations. However, additional optimization of the protocol may be necessary before the technique can reliably estimate fly age. PMID:22973543

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

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

Genomic Prediction of Single Crosses in the Early Stages of a Maize Hybrid Breeding Pipeline.

PubMed

Kadam, Dnyaneshwar C; Potts, Sarah M; Bohn, Martin O; Lipka, Alexander E; Lorenz, Aaron J

2016-09-19

Prediction of single-cross performance has been a major goal of plant breeders since the beginning of hybrid breeding. Recently, genomic prediction has shown to be a promising approach, but only limited studies have examined the accuracy of predicting single-cross performance. Moreover, no studies have examined the potential of predicting single crosses among random inbreds derived from a series of biparental families, which resembles the structure of germplasm comprising the initial stages of a hybrid maize breeding pipeline. The main objectives of this study were to evaluate the potential of genomic prediction for identifying superior single crosses early in the hybrid breeding pipeline and optimize its application. To accomplish these objectives, we designed and analyzed a novel population of single crosses representing the Iowa Stiff Stalk Synthetic/Non-Stiff Stalk heterotic pattern commonly used in the development of North American commercial maize hybrids. The performance of single crosses was predicted using parental combining ability and covariance among single crosses. Prediction accuracies were estimated using cross-validation and ranged from 0.28 to 0.77 for grain yield, 0.53 to 0.91 for plant height, and 0.49 to 0.94 for staygreen, depending on the number of tested parents of the single cross and genomic prediction method used. The genomic estimated general and specific combining abilities showed an advantage over genomic covariances among single crosses when one or both parents of the single cross were untested. Overall, our results suggest that genomic prediction of single crosses in the early stages of a hybrid breeding pipeline holds great potential to re-design hybrid breeding and increase its efficiency. Copyright © 2016 Author et al.

Bias correction for selecting the minimal-error classifier from many machine learning models.

PubMed

Ding, Ying; Tang, Shaowu; Liao, Serena G; Jia, Jia; Oesterreich, Steffi; Lin, Yan; Tseng, George C

2014-11-15

Supervised machine learning is commonly applied in genomic research to construct a classifier from the training data that is generalizable to predict independent testing data. When test datasets are not available, cross-validation is commonly used to estimate the error rate. Many machine learning methods are available, and it is well known that no universally best method exists in general. It has been a common practice to apply many machine learning methods and report the method that produces the smallest cross-validation error rate. Theoretically, such a procedure produces a selection bias. Consequently, many clinical studies with moderate sample sizes (e.g. n = 30-60) risk reporting a falsely small cross-validation error rate that could not be validated later in independent cohorts. In this article, we illustrated the probabilistic framework of the problem and explored the statistical and asymptotic properties. We proposed a new bias correction method based on learning curve fitting by inverse power law (IPL) and compared it with three existing methods: nested cross-validation, weighted mean correction and Tibshirani-Tibshirani procedure. All methods were compared in simulation datasets, five moderate size real datasets and two large breast cancer datasets. The result showed that IPL outperforms the other methods in bias correction with smaller variance, and it has an additional advantage to extrapolate error estimates for larger sample sizes, a practical feature to recommend whether more samples should be recruited to improve the classifier and accuracy. An R package 'MLbias' and all source files are publicly available. tsenglab.biostat.pitt.edu/software.htm. ctseng@pitt.edu Supplementary data are available at Bioinformatics online. © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

The Work Disability Functional Assessment Battery (WD-FAB): Feasibility and Psychometric Properties

PubMed Central

Meterko, Mark; Marfeo, Elizabeth E.; McDonough, Christine M.; Jette, Alan M.; Ni, Pengsheng; Bogusz, Kara; Rasch, Elizabeth K; Brandt, Diane E.; Chan, Leighton

2015-01-01

Objectives To assess the feasibility and psychometric properties of eight scales covering two domains of the newly developed Work Disability Functional Assessment Battery (WD-FAB): physical function (PF) and behavioral health (BH) function. Design Cross-sectional. Setting Community. Participants Adults unable to work due to a physical (n=497) or mental (n=476) disability. Interventions None. Main Outcome Measures Each disability group responded to a survey consisting of the relevant WD-FAB scales and existing measures of established validity. The WD-FAB scales were evaluated with regard to data quality (score distribution; percent “I don’t know” responses), efficiency of administration (number of items required to achieve reliability criterion; time required to complete the scale) by computerized adaptive testing (CAT), and measurement accuracy as tested by person fit. Construct validity was assessed by examining both convergent and discriminant correlations between the WD-FAB scales and scores on same-domain and cross-domain established measures. Results Data quality was good and CAT efficiency was high across both WD-FAB domains. Measurement accuracy was very good for the PF scales; BH scales demonstrated more variability. Construct validity correlations, both convergent and divergent, between all WD-FAB scales and established measures were in the expected direction and range of magnitude. Conclusions The data quality, CAT efficacy, person fit and construct validity of the WD-FAB scales were well supported and suggest that the WD-FAB could be used to assess physical and behavioral health function related to work disability. Variation in scale performance suggests the need for future work on item replenishment and refinement, particularly regarding the Self-Efficacy scale. PMID:25528263

CrossTalk: The Journal of Defense Software Engineering. Volume 19, Number 7

DTIC Science & Technology

2006-07-01

public key certificates and cryptographic keys for crypto - graphic devices. In an environment where enterprise protection relies on an array of IA-enabled...allowing for greater accuracy, currency , and relevance of the information con- tained in the satellite communications data- base will be evaluated...JWPO). The purpose of the JWPO is to define, develop, validate, and evolve the JTRS SCA; acquire wave- form software applications; acquire Crypto

Exploring the color feature power for psoriasis risk stratification and classification: A data mining paradigm.

PubMed

Shrivastava, Vimal K; Londhe, Narendra D; Sonawane, Rajendra S; Suri, Jasjit S

2015-10-01

A large percentage of dermatologist׳s decision in psoriasis disease assessment is based on color. The current computer-aided diagnosis systems for psoriasis risk stratification and classification lack the vigor of color paradigm. The paper presents an automated psoriasis computer-aided diagnosis (pCAD) system for classification of psoriasis skin images into psoriatic lesion and healthy skin, which solves the two major challenges: (i) fulfills the color feature requirements and (ii) selects the powerful dominant color features while retaining high classification accuracy. Fourteen color spaces are discovered for psoriasis disease analysis leading to 86 color features. The pCAD system is implemented in a support vector-based machine learning framework where the offline image data set is used for computing machine learning offline color machine learning parameters. These are then used for transformation of the online color features to predict the class labels for healthy vs. diseased cases. The above paradigm uses principal component analysis for color feature selection of dominant features, keeping the original color feature unaltered. Using the cross-validation protocol, the above machine learning protocol is compared against the standalone grayscale features with 60 features and against the combined grayscale and color feature set of 146. Using a fixed data size of 540 images with equal number of healthy and diseased, 10 fold cross-validation protocol, and SVM of polynomial kernel of type two, pCAD system shows an accuracy of 99.94% with sensitivity and specificity of 99.93% and 99.96%. Using a varying data size protocol, the mean classification accuracies for color, grayscale, and combined scenarios are: 92.85%, 93.83% and 93.99%, respectively. The reliability of the system in these three scenarios are: 94.42%, 97.39% and 96.00%, respectively. We conclude that pCAD system using color space alone is compatible to grayscale space or combined color and grayscale spaces. We validated our pCAD system against facial color databases and the results are consistent in accuracy and reliability. Copyright © 2015 Elsevier Ltd. All rights reserved.

Identification of DNA-Binding Proteins Using Mixed Feature Representation Methods.

PubMed

Qu, Kaiyang; Han, Ke; Wu, Song; Wang, Guohua; Wei, Leyi

2017-09-22

DNA-binding proteins play vital roles in cellular processes, such as DNA packaging, replication, transcription, regulation, and other DNA-associated activities. The current main prediction method is based on machine learning, and its accuracy mainly depends on the features extraction method. Therefore, using an efficient feature representation method is important to enhance the classification accuracy. However, existing feature representation methods cannot efficiently distinguish DNA-binding proteins from non-DNA-binding proteins. In this paper, a multi-feature representation method, which combines three feature representation methods, namely, K-Skip-N-Grams, Information theory, and Sequential and structural features (SSF), is used to represent the protein sequences and improve feature representation ability. In addition, the classifier is a support vector machine. The mixed-feature representation method is evaluated using 10-fold cross-validation and a test set. Feature vectors, which are obtained from a combination of three feature extractions, show the best performance in 10-fold cross-validation both under non-dimensional reduction and dimensional reduction by max-relevance-max-distance. Moreover, the reduced mixed feature method performs better than the non-reduced mixed feature technique. The feature vectors, which are a combination of SSF and K-Skip-N-Grams, show the best performance in the test set. Among these methods, mixed features exhibit superiority over the single features.

Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms

PubMed Central

Ellis, Katherine; Godbole, Suneeta; Marshall, Simon; Lanckriet, Gert; Staudenmayer, John; Kerr, Jacqueline

2014-01-01

Background: Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper, we present a supervised machine learning method for transportation mode prediction from global positioning system (GPS) and accelerometer data. Methods: We collected a dataset of about 150 h of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-min windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time. Results: The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%. Conclusion: Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel. PMID:24795875

Genomic selection in sugar beet breeding populations

PubMed Central

2013-01-01

Background Genomic selection exploits dense genome-wide marker data to predict breeding values. In this study we used a large sugar beet population of 924 lines representing different germplasm types present in breeding populations: unselected segregating families and diverse lines from more advanced stages of selection. All lines have been intensively phenotyped in multi-location field trials for six agronomically important traits and genotyped with 677 SNP markers. Results We used ridge regression best linear unbiased prediction in combination with fivefold cross-validation and obtained high prediction accuracies for all except one trait. In addition, we investigated whether a calibration developed based on a training population composed of diverse lines is suited to predict the phenotypic performance within families. Our results show that the prediction accuracy is lower than that obtained within the diverse set of lines, but comparable to that obtained by cross-validation within the respective families. Conclusions The results presented in this study suggest that a training population derived from intensively phenotyped and genotyped diverse lines from a breeding program does hold potential to build up robust calibration models for genomic selection. Taken together, our results indicate that genomic selection is a valuable tool and can thus complement the genomics toolbox in sugar beet breeding. PMID:24047500

Quantitative Analysis of Clopidogrel Bisulphate and Aspirin by First Derivative Spectrophotometric Method in Tablets

PubMed Central

Game, Madhuri D.; Gabhane, K. B.; Sakarkar, D. M.

2010-01-01

A simple, accurate and precise spectrophotometric method has been developed for simultaneous estimation of clopidogrel bisulphate and aspirin by employing first order derivative zero crossing method. The first order derivative absorption at 232.5 nm (zero cross point of aspirin) was used for clopidogrel bisulphate and 211.3 nm (zero cross point of clopidogrel bisulphate) for aspirin.Both the drugs obeyed linearity in the concentration range of 5.0 μg/ml to 25.0 μg/ml (correlation coefficient r2<1). No interference was found between both determined constituents and those of matrix. The method was validated statistically and recovery studies were carried out to confirm the accuracy of the method. PMID:21969765

Measuring and Validating Neutron Capture Cross Sections Using a Lead Slowing-Down Spectrometer

NASA Astrophysics Data System (ADS)

Thompson, Nicholas

Accurate nuclear data is essential for the modeling, design, and operation of nuclear systems. In this work, the Rensselaer Polytechnic Institute (RPI) Lead Slowing-Down Spectrometer (LSDS) at the Gaerttner Linear Accelerator Center (LINAC) was used to measure neutron capture cross sections and validate capture cross sections in cross section libraries. The RPI LINAC was used to create a fast burst of neutrons in the center of the LSDS, a large cube of high purity lead. A sample and YAP:Ce scintillator were placed in the LSDS, and as neutrons lost energy through scattering interactions with the lead, the scintillator detected capture gammas resulting from neutron capture events in the sample. Samples of silver, gold, cobalt, iron, indium, molybdenum, niobium, nickel, tin, tantalum, and zirconium were measured. Data was collected as a function of time after neutron pulse, or slowing-down time, which is correlated to average neutron energy. An analog and a digital data acquisition system collected data simultaneously, allowing for collection of pulse shape information as well as timing. Collection of digital data allowed for pulse shape analysis after the experiment. This data was then analyzed and compared to Monte Carlo simulations to validate the accuracy of neutron capture cross section libraries. These measurements represent the first time that neutron capture cross sections have been measured using an LSDS in the United States, and the first time tools such as coincidence measurements and pulse height weighting have been applied to measurements of neutron capture cross sections using an LSDS. Significant differences between measurement results and simulation results were found in multiple materials, and some errors in nuclear data libraries have already been identified due to these measurements.

Validated spectrophotometric methods for simultaneous determination of Omeprazole, Tinidazole and Doxycycline in their ternary mixture

NASA Astrophysics Data System (ADS)

Lotfy, Hayam M.; Hegazy, Maha A.; Mowaka, Shereen; Mohamed, Ekram Hany

2016-01-01

A comparative study of smart spectrophotometric techniques for the simultaneous determination of Omeprazole (OMP), Tinidazole (TIN) and Doxycycline (DOX) without prior separation steps is developed. These techniques consist of several consecutive steps utilizing zero/or ratio/or derivative spectra. The proposed techniques adopt nine simple different methods, namely direct spectrophotometry, dual wavelength, first derivative-zero crossing, amplitude factor, spectrum subtraction, ratio subtraction, derivative ratio-zero crossing, constant center, and successive derivative ratio method. The calibration graphs are linear over the concentration range of 1-20 μg/mL, 5-40 μg/mL and 2-30 μg/mL for OMP, TIN and DOX, respectively. These methods are tested by analyzing synthetic mixtures of the above drugs and successfully applied to commercial pharmaceutical preparation. The methods that are validated according to the ICH guidelines, accuracy, precision, and repeatability, were found to be within the acceptable limits.

First SNPP Cal/Val Campaign: Satellite and Aircraft Sounding Retrieval Intercomparison

NASA Technical Reports Server (NTRS)

Zhou, Daniel K.; Liu, Xu; Larar, Allen M.; Tian, Jialin; Smith, William L.; Wu, Wan; Kizer, Susan; Goldberg, Mitch; Liu, Q.

2015-01-01

Satellite ultraspectral infrared sensors provide key data records essential for weather forecasting and climate change science. The Suomi National Polar-orbiting Partnership (SNPP) satellite Environmental Data Record (EDR) is retrieved from calibrated ultraspectral radiance so called Sensor Data Record (SDR). It is critical to understand the accuracy of retrieved EDRs, which mainly depends on SDR accuracy (e.g., instrument random noise and absolute accuracy), an ill-posed retrieval system, and radiative transfer model errors. There are few approaches to validate EDR products, e.g., some common methods are to rely on radiosonde measurements, ground-based measurements, and dedicated aircraft campaign providing in-situ measurements of atmosphere and/or employing similar ultraspectral interferometer sounders. Ultraspectral interferometer sounder aboard aircraft measures SDR to retrieve EDR, which is often used to validate satellite measurements of SDR and EDR. The SNPP Calibration/Validation Campaign was conducted during May 2013. The NASA high-altitude aircraft ER-2 that carried ultraspectral interferometer sounders such as the NASA Atmospheric Sounder Testbed-Interferometer (NAST-I) flew under the SNPP satellite that carries the Cross-track Infrared Sounder (CrIS). Here we inter-compare the EDRs produced with different retrieval algorithms from SDRs measured by the sensors from satellite and aircraft. The available dropsonde and radiosonde measurements together with the European Centre for Medium-Range Weather Forecasts (ECMWF) analysis were also used to draw the conclusion from this experiment.

A comparative evaluation of Raman and fluorescence spectroscopy for optical diagnosis of oral neoplasia

NASA Astrophysics Data System (ADS)

Majumder, S. K.; Krishna, H.; Sidramesh, M.; Chaturvedi, P.; Gupta, P. K.

2011-08-01

We report the results of a comparative evaluation of in vivo fluorescence and Raman spectroscopy for diagnosis of oral neoplasia. The study carried out at Tata Memorial Hospital, Mumbai, involved 26 healthy volunteers and 138 patients being screened for neoplasm of oral cavity. Spectral measurements were taken from multiple sites of abnormal as well as apparently uninvolved contra-lateral regions of the oral cavity in each patient. The different tissue sites investigated belonged to one of the four histopathology categories: 1) squamous cell carcinoma (SCC), 2) oral sub-mucous fibrosis (OSMF), 3) leukoplakia (LP) and 4) normal squamous tissue. A probability based multivariate statistical algorithm utilizing nonlinear Maximum Representation and Discrimination Feature for feature extraction and Sparse Multinomial Logistic Regression for classification was developed for direct multi-class classification in a leave-one-patient-out cross validation mode. The results reveal that the performance of Raman spectroscopy is considerably superior to that of fluorescence in stratifying the oral tissues into respective histopathologic categories. The best classification accuracy was observed to be 90%, 93%, 94%, and 89% for SCC, SMF, leukoplakia, and normal oral tissues, respectively, on the basis of leave-one-patient-out cross-validation, with an overall accuracy of 91%. However, when a binary classification was employed to distinguish spectra from all the SCC, SMF and leukoplakik tissue sites together from normal, fluorescence and Raman spectroscopy were seen to have almost comparable performances with Raman yielding marginally better classification accuracy of 98.5% as compared to 94% of fluorescence.

Real-Time Food Authentication Using a Miniature Mass Spectrometer.

PubMed

Gerbig, Stefanie; Neese, Stephan; Penner, Alexander; Spengler, Bernhard; Schulz, Sabine

2017-10-17

Food adulteration is a threat to public health and the economy. In order to determine food adulteration efficiently, rapid and easy-to-use on-site analytical methods are needed. In this study, a miniaturized mass spectrometer in combination with three ambient ionization methods was used for food authentication. The chemical fingerprints of three milk types, five fish species, and two coffee types were measured using electrospray ionization, desorption electrospray ionization, and low temperature plasma ionization. Minimum sample preparation was needed for the analysis of liquid and solid food samples. Mass spectrometric data was processed using the laboratory-built software MS food classifier, which allows for the definition of specific food profiles from reference data sets using multivariate statistical methods and the subsequent classification of unknown data. Applicability of the obtained mass spectrometric fingerprints for food authentication was evaluated using different data processing methods, leave-10%-out cross-validation, and real-time classification of new data. Classification accuracy of 100% was achieved for the differentiation of milk types and fish species, and a classification accuracy of 96.4% was achieved for coffee types in cross-validation experiments. Measurement of two milk mixtures yielded correct classification of >94%. For real-time classification, the accuracies were comparable. Functionality of the software program and its performance is described. Processing time for a reference data set and a newly acquired spectrum was found to be 12 s and 2 s, respectively. These proof-of-principle experiments show that the combination of a miniaturized mass spectrometer, ambient ionization, and statistical analysis is suitable for on-site real-time food authentication.

Classification of Focal and Non Focal Epileptic Seizures Using Multi-Features and SVM Classifier.

PubMed

Sriraam, N; Raghu, S

2017-09-02

Identifying epileptogenic zones prior to surgery is an essential and crucial step in treating patients having pharmacoresistant focal epilepsy. Electroencephalogram (EEG) is a significant measurement benchmark to assess patients suffering from epilepsy. This paper investigates the application of multi-features derived from different domains to recognize the focal and non focal epileptic seizures obtained from pharmacoresistant focal epilepsy patients from Bern Barcelona database. From the dataset, five different classification tasks were formed. Total 26 features were extracted from focal and non focal EEG. Significant features were selected using Wilcoxon rank sum test by setting p-value (p < 0.05) and z-score (-1.96 > z > 1.96) at 95% significance interval. Hypothesis was made that the effect of removing outliers improves the classification accuracy. Turkey's range test was adopted for pruning outliers from feature set. Finally, 21 features were classified using optimized support vector machine (SVM) classifier with 10-fold cross validation. Bayesian optimization technique was adopted to minimize the cross-validation loss. From the simulation results, it was inferred that the highest sensitivity, specificity, and classification accuracy of 94.56%, 89.74%, and 92.15% achieved respectively and found to be better than the state-of-the-art approaches. Further, it was observed that the classification accuracy improved from 80.2% with outliers to 92.15% without outliers. The classifier performance metrics ensures the suitability of the proposed multi-features with optimized SVM classifier. It can be concluded that the proposed approach can be applied for recognition of focal EEG signals to localize epileptogenic zones.

Methods for converting continuous shrubland ecosystem component values to thematic National Land Cover Database classes

USGS Publications Warehouse

Rigge, Matthew B.; Gass, Leila; Homer, Collin G.; Xian, George Z.

2017-10-26

The National Land Cover Database (NLCD) provides thematic land cover and land cover change data at 30-meter spatial resolution for the United States. Although the NLCD is considered to be the leading thematic land cover/land use product and overall classification accuracy across the NLCD is high, performance and consistency in the vast shrub and grasslands of the Western United States is lower than desired. To address these issues and fulfill the needs of stakeholders requiring more accurate rangeland data, the USGS has developed a method to quantify these areas in terms of the continuous cover of several cover components. These components include the cover of shrub, sagebrush (Artemisia spp), big sagebrush (Artemisia tridentata spp.), herbaceous, annual herbaceous, litter, and bare ground, and shrub and sagebrush height. To produce maps of component cover, we collected field data that were then associated with spectral values in WorldView-2 and Landsat imagery using regression tree models. The current report outlines the procedures and results of converting these continuous cover components to three thematic NLCD classes: barren, shrubland, and grassland. To accomplish this, we developed a series of indices and conditional models using continuous cover of shrub, bare ground, herbaceous, and litter as inputs. The continuous cover data are currently available for two large regions in the Western United States. Accuracy of the “cross-walked” product was assessed relative to that of NLCD 2011 at independent validation points (n=787) across these two regions. Overall thematic accuracy of the “cross-walked” product was 0.70, compared to 0.63 for NLCD 2011. The kappa value was considerably higher for the “cross-walked” product at 0.41 compared to 0.28 for NLCD 2011. Accuracy was also evaluated relative to the values of training points (n=75,000) used in the development of the continuous cover components. Again, the “cross-walked” product outperformed NLCD 2011, with an overall accuracy of 0.81, compared to 0.66 for NLCD 2011. These results demonstrated that our continuous cover predictions and models were successful in increasing thematic classification accuracy in Western United States shrublands. We plan to directly use the “cross-walked” product, where available, in the NLCD 2016 product.

Prediction and visualization of redox conditions in the groundwater of Central Valley, California

USGS Publications Warehouse

Rosecrans, Celia Z.; Nolan, Bernard T.; Gronberg, JoAnn M.

2017-01-01

Regional-scale, three-dimensional continuous probability models, were constructed for aspects of redox conditions in the groundwater system of the Central Valley, California. These models yield grids depicting the probability that groundwater in a particular location will have dissolved oxygen (DO) concentrations less than selected threshold values representing anoxic groundwater conditions, or will have dissolved manganese (Mn) concentrations greater than selected threshold values representing secondary drinking water-quality contaminant levels (SMCL) and health-based screening levels (HBSL). The probability models were constrained by the alluvial boundary of the Central Valley to a depth of approximately 300 m. Probability distribution grids can be extracted from the 3-D models at any desired depth, and are of interest to water-resource managers, water-quality researchers, and groundwater modelers concerned with the occurrence of natural and anthropogenic contaminants related to anoxic conditions.Models were constructed using a Boosted Regression Trees (BRT) machine learning technique that produces many trees as part of an additive model and has the ability to handle many variables, automatically incorporate interactions, and is resistant to collinearity. Machine learning methods for statistical prediction are becoming increasing popular in that they do not require assumptions associated with traditional hypothesis testing. Models were constructed using measured dissolved oxygen and manganese concentrations sampled from 2767 wells within the alluvial boundary of the Central Valley, and over 60 explanatory variables representing regional-scale soil properties, soil chemistry, land use, aquifer textures, and aquifer hydrologic properties. Models were trained on a USGS dataset of 932 wells, and evaluated on an independent hold-out dataset of 1835 wells from the California Division of Drinking Water. We used cross-validation to assess the predictive performance of models of varying complexity, as a basis for selecting final models. Trained models were applied to cross-validation testing data and a separate hold-out dataset to evaluate model predictive performance by emphasizing three model metrics of fit: Kappa; accuracy; and the area under the receiver operator characteristic curve (ROC). The final trained models were used for mapping predictions at discrete depths to a depth of 304.8 m. Trained DO and Mn models had accuracies of 86–100%, Kappa values of 0.69–0.99, and ROC values of 0.92–1.0. Model accuracies for cross-validation testing datasets were 82–95% and ROC values were 0.87–0.91, indicating good predictive performance. Kappas for the cross-validation testing dataset were 0.30–0.69, indicating fair to substantial agreement between testing observations and model predictions. Hold-out data were available for the manganese model only and indicated accuracies of 89–97%, ROC values of 0.73–0.75, and Kappa values of 0.06–0.30. The predictive performance of both the DO and Mn models was reasonable, considering all three of these fit metrics and the low percentages of low-DO and high-Mn events in the data.

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.

Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma.

PubMed

Hu, Leland S; Ning, Shuluo; Eschbacher, Jennifer M; Gaw, Nathan; Dueck, Amylou C; Smith, Kris A; Nakaji, Peter; Plasencia, Jonathan; Ranjbar, Sara; Price, Stephen J; Tran, Nhan; Loftus, Joseph; Jenkins, Robert; O'Neill, Brian P; Elmquist, William; Baxter, Leslie C; Gao, Fei; Frakes, David; Karis, John P; Zwart, Christine; Swanson, Kristin R; Sarkaria, Jann; Wu, Teresa; Mitchell, J Ross; Li, Jing

2015-01-01

Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM). Contrast-enhanced MRI (CE-MRI) targets enhancing core (ENH) but yields adequate tumor in only ~60% of cases. Further, CE-MRI poorly localizes infiltrative tumor within surrounding non-enhancing parenchyma, or brain-around-tumor (BAT), despite the importance of characterizing this tumor segment, which universally recurs. In this study, we use multiple texture analysis and machine learning (ML) algorithms to analyze multi-parametric MRI, and produce new images indicating tumor-rich targets in GBM. We recruited primary GBM patients undergoing image-guided biopsies and acquired pre-operative MRI: CE-MRI, Dynamic-Susceptibility-weighted-Contrast-enhanced-MRI, and Diffusion Tensor Imaging. Following image coregistration and region of interest placement at biopsy locations, we compared MRI metrics and regional texture with histologic diagnoses of high- vs low-tumor content (≥80% vs <80% tumor nuclei) for corresponding samples. In a training set, we used three texture analysis algorithms and three ML methods to identify MRI-texture features that optimized model accuracy to distinguish tumor content. We confirmed model accuracy in a separate validation set. We collected 82 biopsies from 18 GBMs throughout ENH and BAT. The MRI-based model achieved 85% cross-validated accuracy to diagnose high- vs low-tumor in the training set (60 biopsies, 11 patients). The model achieved 81.8% accuracy in the validation set (22 biopsies, 7 patients). Multi-parametric MRI and texture analysis can help characterize and visualize GBM's spatial histologic heterogeneity to identify regional tumor-rich biopsy targets.

A machine learning approach to multi-level ECG signal quality classification.

PubMed

Li, Qiao; Rajagopalan, Cadathur; Clifford, Gari D

2014-12-01

Current electrocardiogram (ECG) signal quality assessment studies have aimed to provide a two-level classification: clean or noisy. However, clinical usage demands more specific noise level classification for varying applications. This work outlines a five-level ECG signal quality classification algorithm. A total of 13 signal quality metrics were derived from segments of ECG waveforms, which were labeled by experts. A support vector machine (SVM) was trained to perform the classification and tested on a simulated dataset and was validated using data from the MIT-BIH arrhythmia database (MITDB). The simulated training and test datasets were created by selecting clean segments of the ECG in the 2011 PhysioNet/Computing in Cardiology Challenge database, and adding three types of real ECG noise at different signal-to-noise ratio (SNR) levels from the MIT-BIH Noise Stress Test Database (NSTDB). The MITDB was re-annotated for five levels of signal quality. Different combinations of the 13 metrics were trained and tested on the simulated datasets and the best combination that produced the highest classification accuracy was selected and validated on the MITDB. Performance was assessed using classification accuracy (Ac), and a single class overlap accuracy (OAc), which assumes that an individual type classified into an adjacent class is acceptable. An Ac of 80.26% and an OAc of 98.60% on the test set were obtained by selecting 10 metrics while 57.26% (Ac) and 94.23% (OAc) were the numbers for the unseen MITDB validation data without retraining. By performing the fivefold cross validation, an Ac of 88.07±0.32% and OAc of 99.34±0.07% were gained on the validation fold of MITDB. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

Geometrical accuracy improvement in flexible roll forming lines

NASA Astrophysics Data System (ADS)

Larrañaga, J.; Berner, S.; Galdos, L.; Groche, P.

2011-01-01

The general interest to produce profiles with variable cross section in a cost-effective way has increased in the last few years. The flexible roll forming process allows producing profiles with variable cross section lengthwise in a continuous way. Until now, only a few flexible roll forming lines were developed and built up. Apart from the flange wrinkling along the transition zone of u-profiles with variable cross section, the process limits have not been investigated and solutions for shape deviations are unknown. During the PROFOM project a flexible roll forming machine has been developed with the objective of producing high technological components for automotive body structures. In order to investigate the limits of the process, different profile geometries and steel grades including high strength steels have been applied. During the first experimental tests, several errors have been identified, as a result of the complex stress states generated during the forming process. In order to improve the accuracy of the target profiles and to meet the tolerance demands of the automotive industry, a thermo-mechanical solution has been proposed. Additional mechanical devices, supporting flexible the roll forming process, have been implemented in the roll forming line together with local heating techniques. The combination of both methods shows a significant increase of the accuracy. In the present investigation, the experimental results of the validation process are presented.

An improved method of early diagnosis of smoking-induced respiratory changes using machine learning algorithms.

PubMed

Amaral, Jorge L M; Lopes, Agnaldo J; Jansen, José M; Faria, Alvaro C D; Melo, Pedro L

2013-12-01

The purpose of this study was to develop an automatic classifier to increase the accuracy of the forced oscillation technique (FOT) for diagnosing early respiratory abnormalities in smoking patients. The data consisted of FOT parameters obtained from 56 volunteers, 28 healthy and 28 smokers with low tobacco consumption. Many supervised learning techniques were investigated, including logistic linear classifiers, k nearest neighbor (KNN), neural networks and support vector machines (SVM). To evaluate performance, the ROC curve of the most accurate parameter was established as baseline. To determine the best input features and classifier parameters, we used genetic algorithms and a 10-fold cross-validation using the average area under the ROC curve (AUC). In the first experiment, the original FOT parameters were used as input. We observed a significant improvement in accuracy (KNN=0.89 and SVM=0.87) compared with the baseline (0.77). The second experiment performed a feature selection on the original FOT parameters. This selection did not cause any significant improvement in accuracy, but it was useful in identifying more adequate FOT parameters. In the third experiment, we performed a feature selection on the cross products of the FOT parameters. This selection resulted in a further increase in AUC (KNN=SVM=0.91), which allows for high diagnostic accuracy. In conclusion, machine learning classifiers can help identify early smoking-induced respiratory alterations. The use of FOT cross products and the search for the best features and classifier parameters can markedly improve the performance of machine learning classifiers. Copyright © 2013 Elsevier Ireland Ltd. 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

High wavenumber Raman spectroscopy in the characterization of urinary metabolites of normal subjects, oral premalignant and malignant patients

NASA Astrophysics Data System (ADS)

Brindha, Elumalai; Rajasekaran, Ramu; Aruna, Prakasarao; Koteeswaran, Dornadula; Ganesan, Singaravelu

2017-01-01

Urine has emerged as one of the diagnostically potential bio fluids, as it has many metabolites. As the concentration and the physiochemical properties of the urinary metabolites may vary under pathological transformation, Raman spectroscopic characterization of urine has been exploited as a significant tool in identifying several diseased conditions, including cancers. In the present study, an attempt was made to study the high wavenumber (HWVN) Raman spectroscopic characterization of urine samples of normal subjects, oral premalignant and malignant patients. It is concluded that the urinary metabolites flavoproteins, tryptophan and phenylalanine are responsible for the observed spectral variations between the normal and abnormal groups. Principal component analysis-based linear discriminant analysis was carried out to verify the diagnostic potentiality of the present technique. The discriminant analysis performed across normal and oral premalignant subjects classifies 95.6% of the original and 94.9% of the cross-validated grouped cases correctly. In the second analysis performed across normal and oral malignant groups, the accuracy of the original and cross-validated grouped cases was 96.4% and 92.1% respectively. Similarly, the third analysis performed across three groups, normal, oral premalignant and malignant groups, classifies 93.3% and 91.2% of the original and cross-validated grouped cases correctly.

Jet production in the CoLoRFulNNLO method: Event shapes in electron-positron collisions

NASA Astrophysics Data System (ADS)

Del Duca, Vittorio; Duhr, Claude; Kardos, Adam; Somogyi, Gábor; Szőr, Zoltán; Trócsányi, Zoltán; Tulipánt, Zoltán

2016-10-01

We present the CoLoRFulNNLO method to compute higher order radiative corrections to jet cross sections in perturbative QCD. We apply our method to the computation of event shape observables in electron-positron collisions at NNLO accuracy and validate our code by comparing our predictions to previous results in the literature. We also calculate for the first time jet cone energy fraction at NNLO.

Development and Validation of Decision Forest Model for Estrogen Receptor Binding Prediction of Chemicals Using Large Data Sets.

PubMed

Ng, Hui Wen; Doughty, Stephen W; Luo, Heng; Ye, Hao; Ge, Weigong; Tong, Weida; Hong, Huixiao

2015-12-21

Some chemicals in the environment possess the potential to interact with the endocrine system in the human body. Multiple receptors are involved in the endocrine system; estrogen receptor α (ERα) plays very important roles in endocrine activity and is the most studied receptor. Understanding and predicting estrogenic activity of chemicals facilitates the evaluation of their endocrine activity. Hence, we have developed a decision forest classification model to predict chemical binding to ERα using a large training data set of 3308 chemicals obtained from the U.S. Food and Drug Administration's Estrogenic Activity Database. We tested the model using cross validations and external data sets of 1641 chemicals obtained from the U.S. Environmental Protection Agency's ToxCast project. The model showed good performance in both internal (92% accuracy) and external validations (∼ 70-89% relative balanced accuracies), where the latter involved the validations of the model across different ER pathway-related assays in ToxCast. The important features that contribute to the prediction ability of the model were identified through informative descriptor analysis and were related to current knowledge of ER binding. Prediction confidence analysis revealed that the model had both high prediction confidence and accuracy for most predicted chemicals. The results demonstrated that the model constructed based on the large training data set is more accurate and robust for predicting ER binding of chemicals than the published models that have been developed using much smaller data sets. The model could be useful for the evaluation of ERα-mediated endocrine activity potential of environmental chemicals.

On accuracy of the wave finite element predictions of wavenumbers and power flow: A benchmark problem

NASA Astrophysics Data System (ADS)

Søe-Knudsen, Alf; Sorokin, Sergey

2011-06-01

This rapid communication is concerned with justification of the 'rule of thumb', which is well known to the community of users of the finite element (FE) method in dynamics, for the accuracy assessment of the wave finite element (WFE) method. An explicit formula linking the size of a window in the dispersion diagram, where the WFE method is trustworthy, with the coarseness of a FE mesh employed is derived. It is obtained by the comparison of the exact Pochhammer-Chree solution for an elastic rod having the circular cross-section with its WFE approximations. It is shown that the WFE power flow predictions are also valid within this window.

Doubly stochastic radial basis function methods

NASA Astrophysics Data System (ADS)

Yang, Fenglian; Yan, Liang; Ling, Leevan

2018-06-01

We propose a doubly stochastic radial basis function (DSRBF) method for function recoveries. Instead of a constant, we treat the RBF shape parameters as stochastic variables whose distribution were determined by a stochastic leave-one-out cross validation (LOOCV) estimation. A careful operation count is provided in order to determine the ranges of all the parameters in our methods. The overhead cost for setting up the proposed DSRBF method is O (n2) for function recovery problems with n basis. Numerical experiments confirm that the proposed method not only outperforms constant shape parameter formulation (in terms of accuracy with comparable computational cost) but also the optimal LOOCV formulation (in terms of both accuracy and computational cost).

Automated brain volumetrics in multiple sclerosis: a step closer to clinical application

PubMed Central

Beadnall, H N; Hatton, S N; Bader, G; Tomic, D; Silva, D G

2016-01-01

Background Whole brain volume (WBV) estimates in patients with multiple sclerosis (MS) correlate more robustly with clinical disability than traditional, lesion-based metrics. Numerous algorithms to measure WBV have been developed over the past two decades. We compare Structural Image Evaluation using Normalisation of Atrophy-Cross-sectional (SIENAX) to NeuroQuant and MSmetrix, for assessment of cross-sectional WBV in patients with MS. Methods MRIs from 61 patients with relapsing-remitting MS and 2 patients with clinically isolated syndrome were analysed. WBV measurements were calculated using SIENAX, NeuroQuant and MSmetrix. Statistical agreement between the methods was evaluated using linear regression and Bland-Altman plots. Precision and accuracy of WBV measurement was calculated for (1) NeuroQuant versus SIENAX and (2) MSmetrix versus SIENAX. Results Precision (Pearson's r) of WBV estimation for NeuroQuant and MSmetrix versus SIENAX was 0.983 and 0.992, respectively. Accuracy (Cb) was 0.871 and 0.994, respectively. NeuroQuant and MSmetrix showed a 5.5% and 1.0% volume difference compared with SIENAX, respectively, that was consistent across low and high values. Conclusions In the analysed population, NeuroQuant and MSmetrix both quantified cross-sectional WBV with comparable statistical agreement to SIENAX, a well-validated cross-sectional tool that has been used extensively in MS clinical studies. PMID:27071647

Detection of Airway Colonization by Aspergillus fumigatus by Use of Electronic Nose Technology in Patients with Cystic Fibrosis.

PubMed

de Heer, K; Kok, M G M; Fens, N; Weersink, E J M; Zwinderman, A H; van der Schee, M P C; Visser, C E; van Oers, M H J; Sterk, P J

2016-03-01

Currently, there is no noninvasive test that can reliably diagnose early invasive pulmonary aspergillosis (IA). An electronic nose (eNose) can discriminate various lung diseases through an analysis of exhaled volatile organic compounds. We recently published a proof-of-principle study showing that patients with prolonged chemotherapy-induced neutropenia and IA have a distinct exhaled breath profile (or breathprint) that can be discriminated with an eNose. An eNose is cheap and noninvasive, and it yields results within minutes. We determined whether Aspergillus fumigatus colonization may also be detected with an eNose in cystic fibrosis (CF) patients. Exhaled breath samples of 27 CF patients were analyzed with a Cyranose 320. Culture of sputum samples defined the A. fumigatus colonization status. eNose data were classified using canonical discriminant analysis after principal component reduction. Our primary outcome was cross-validated accuracy, defined as the percentage of correctly classified subjects using the leave-one-out method. The P value was calculated by the generation of 100,000 random alternative classifications. Nine of the 27 subjects were colonized by A. fumigatus. In total, 3 subjects were misclassified, resulting in a cross-validated accuracy of the Cyranose detecting IA of 89% (P = 0.004; sensitivity, 78%; specificity, 94%). Receiver operating characteristic (ROC) curve analysis showed an area under the curve (AUC) of 0.89. The results indicate that A. fumigatus colonization leads to a distinctive breathprint in CF patients. The present proof-of-concept data merit external validation and monitoring studies. Copyright © 2016, American Society for Microbiology. All Rights Reserved.

Attribute Weighting Based K-Nearest Neighbor Using Gain Ratio

NASA Astrophysics Data System (ADS)

Nababan, A. A.; Sitompul, O. S.; Tulus

2018-04-01

K- Nearest Neighbor (KNN) is a good classifier, but from several studies, the result performance accuracy of KNN still lower than other methods. One of the causes of the low accuracy produced, because each attribute has the same effect on the classification process, while some less relevant characteristics lead to miss-classification of the class assignment for new data. In this research, we proposed Attribute Weighting Based K-Nearest Neighbor Using Gain Ratio as a parameter to see the correlation between each attribute in the data and the Gain Ratio also will be used as the basis for weighting each attribute of the dataset. The accuracy of results is compared to the accuracy acquired from the original KNN method using 10-fold Cross-Validation with several datasets from the UCI Machine Learning repository and KEEL-Dataset Repository, such as abalone, glass identification, haberman, hayes-roth and water quality status. Based on the result of the test, the proposed method was able to increase the classification accuracy of KNN, where the highest difference of accuracy obtained hayes-roth dataset is worth 12.73%, and the lowest difference of accuracy obtained in the abalone dataset of 0.07%. The average result of the accuracy of all dataset increases the accuracy by 5.33%.

Body Dysmorphic Symptoms Scale for patients seeking esthetic surgery: cross-cultural validation study.

PubMed

Ramos, Tatiana Dalpasquale; Brito, Maria José Azevedo de; Piccolo, Mônica Sarto; Rosella, Maria Fernanda Normanha da Silva Martins; Sabino, Miguel; Ferreira, Lydia Masako

2016-07-21

Rhinoplasty is one of the most sought-after esthetic operations among individuals with body dysmorphic disorder. The aim of this study was to cross-culturally adapt and validate the Body Dysmorphic Symptoms Scale. Cross-cultural validation study conducted in a plastic surgery outpatient clinic of a public university hospital. Between February 2014 and March 2015, 80 consecutive patients of both sexes seeking rhinoplasty were selected. Thirty of them participated in the phase of cultural adaptation of the instrument. Reproducibility was tested on 20 patients and construct validity was assessed on 50 patients, with correlation against the Yale-Brown Obsessive Compulsive Scale for Body Dysmorphic Disorder. The Brazilian version of the instrument showed Cronbach's alpha of 0.805 and excellent inter-rater reproducibility (intraclass correlation coefficient, ICC = 0.873; P < 0.001) and intra-rater reproducibility (ICC = 0.939; P < 0.001). Significant differences in total scores were found between patients with and without symptoms (P < 0.001). A strong correlation (r = 0.841; P < 0.001) was observed between the Yale-Brown Obsessive Compulsive Scale for Body Dysmorphic Disorder and the Body Dysmorphic Symptoms Scale. The area under the receiver operating characteristic curve was 0.981, thus showing good accuracy for discriminating between presence and absence of symptoms of body dysmorphic disorder. Forty-six percent of the patients had body dysmorphic symptoms and 54% had moderate to severe appearance-related obsessive-compulsive symptoms. The Brazilian version of the Body Dysmorphic Symptoms Scale is a reproducible instrument that presents face, content and construct validity.

Body Dysmorphic Symptoms Scale for patients seeking esthetic surgery: cross-cultural validation study.

PubMed

Ramos, Tatiana Dalpasquale; Brito, Maria José Azevedo de; Piccolo, Mônica Sarto; Rosella, Maria Fernanda Normanha da Silva Martins; Sabino, Miguel; Ferreira, Lydia Masako

2016-01-01

Rhinoplasty is one of the most sought-after esthetic operations among individuals with body dysmorphic disorder. The aim of this study was to cross-culturally adapt and validate the Body Dysmorphic Symptoms Scale. Cross-cultural validation study conducted in a plastic surgery outpatient clinic of a public university hospital. Between February 2014 and March 2015, 80 consecutive patients of both sexes seeking rhinoplasty were selected. Thirty of them participated in the phase of cultural adaptation of the instrument. Reproducibility was tested on 20 patients and construct validity was assessed on 50 patients, with correlation against the Yale-Brown Obsessive Compulsive Scale for Body Dysmorphic Disorder. The Brazilian version of the instrument showed Cronbach's alpha of 0.805 and excellent inter-rater reproducibility (intraclass correlation coefficient, ICC = 0.873; P < 0.001) and intra-rater reproducibility (ICC = 0.939; P < 0.001). Significant differences in total scores were found between patients with and without symptoms (P < 0.001). A strong correlation (r = 0.841; P < 0.001) was observed between the Yale-Brown Obsessive Compulsive Scale for Body Dysmorphic Disorder and the Body Dysmorphic Symptoms Scale. The area under the receiver operating characteristic curve was 0.981, thus showing good accuracy for discriminating between presence and absence of symptoms of body dysmorphic disorder. Forty-six percent of the patients had body dysmorphic symptoms and 54% had moderate to severe appearance-related obsessive-compulsive symptoms. The Brazilian version of the Body Dysmorphic Symptoms Scale is a reproducible instrument that presents face, content and construct validity.

Comparison of machine-learning algorithms to build a predictive model for detecting undiagnosed diabetes - ELSA-Brasil: accuracy study.

PubMed

Olivera, André Rodrigues; Roesler, Valter; Iochpe, Cirano; Schmidt, Maria Inês; Vigo, Álvaro; Barreto, Sandhi Maria; Duncan, Bruce Bartholow

2017-01-01

Type 2 diabetes is a chronic disease associated with a wide range of serious health complications that have a major impact on overall health. The aims here were to develop and validate predictive models for detecting undiagnosed diabetes using data from the Longitudinal Study of Adult Health (ELSA-Brasil) and to compare the performance of different machine-learning algorithms in this task. Comparison of machine-learning algorithms to develop predictive models using data from ELSA-Brasil. After selecting a subset of 27 candidate variables from the literature, models were built and validated in four sequential steps: (i) parameter tuning with tenfold cross-validation, repeated three times; (ii) automatic variable selection using forward selection, a wrapper strategy with four different machine-learning algorithms and tenfold cross-validation (repeated three times), to evaluate each subset of variables; (iii) error estimation of model parameters with tenfold cross-validation, repeated ten times; and (iv) generalization testing on an independent dataset. The models were created with the following machine-learning algorithms: logistic regression, artificial neural network, naïve Bayes, K-nearest neighbor and random forest. The best models were created using artificial neural networks and logistic regression. -These achieved mean areas under the curve of, respectively, 75.24% and 74.98% in the error estimation step and 74.17% and 74.41% in the generalization testing step. Most of the predictive models produced similar results, and demonstrated the feasibility of identifying individuals with highest probability of having undiagnosed diabetes, through easily-obtained clinical data.

Primary central nervous system lymphoma and glioblastoma differentiation based on conventional magnetic resonance imaging by high-throughput SIFT features.

PubMed

Chen, Yinsheng; Li, Zeju; Wu, Guoqing; Yu, Jinhua; Wang, Yuanyuan; Lv, Xiaofei; Ju, Xue; Chen, Zhongping

2018-07-01

Due to the totally different therapeutic regimens needed for primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM), accurate differentiation of the two diseases by noninvasive imaging techniques is important for clinical decision-making. Thirty cases of PCNSL and 66 cases of GBM with conventional T1-contrast magnetic resonance imaging (MRI) were analyzed in this study. Convolutional neural networks was used to segment tumor automatically. A modified scale invariant feature transform (SIFT) method was utilized to extract three-dimensional local voxel arrangement information from segmented tumors. Fisher vector was proposed to normalize the dimension of SIFT features. An improved genetic algorithm (GA) was used to extract SIFT features with PCNSL and GBM discrimination ability. The data-set was divided into a cross-validation cohort and an independent validation cohort by the ratio of 2:1. Support vector machine with the leave-one-out cross-validation based on 20 cases of PCNSL and 44 cases of GBM was employed to build and validate the differentiation model. Among 16,384 high-throughput features, 1356 features show significant differences between PCNSL and GBM with p < 0.05 and 420 features with p < 0.001. A total of 496 features were finally chosen by improved GA algorithm. The proposed method produces PCNSL vs. GBM differentiation with an area under the curve (AUC) curve of 99.1% (98.2%), accuracy 95.3% (90.6%), sensitivity 85.0% (80.0%) and specificity 100% (95.5%) on the cross-validation cohort (and independent validation cohort). Since the local voxel arrangement characterization provided by SIFT features, proposed method produced more competitive PCNSL and GBM differentiation performance by using conventional MRI than methods based on advanced MRI.

Validation of bioelectrical impedance analysis for total body water assessment against the deuterium dilution technique in Asian children.

PubMed

Liu, A; Byrne, N M; Ma, G; Nasreddine, L; Trinidad, T P; Kijboonchoo, K; Ismail, M N; Kagawa, M; Poh, B K; Hills, A P

2011-12-01

To develop and cross-validate bioelectrical impedance analysis (BIA) prediction equations of total body water (TBW) and fat-free mass (FFM) for Asian pre-pubertal children from China, Lebanon, Malaysia, Philippines and Thailand. Height, weight, age, gender, resistance and reactance measured by BIA were collected from 948 Asian children (492 boys and 456 girls) aged 8-10 years from the five countries. The deuterium dilution technique was used as the criterion method for the estimation of TBW and FFM. The BIA equations were developed using stepwise multiple regression analysis and cross-validated using the Bland-Altman approach. The BIA prediction equation for the estimation of TBW was as follows: TBW=0.231 × height(2)/resistance+0.066 × height+0.188 × weight+0.128 × age+0.500 × sex-0.316 × Thais-4.574 (R (2)=88.0%, root mean square error (RMSE)=1.3 kg), and for the estimation of FFM was as follows: FFM=0.299 × height(2)/resistance+0.086 × height+0.245 × weight+0.260 × age+0.901 × sex-0.415 × ethnicity (Thai ethnicity =1, others = 0)-6.952 (R (2)=88.3%, RMSE=1.7 kg). No significant difference between measured and predicted values for the whole cross-validation sample was found. However, the prediction equation for estimation of TBW/FFM tended to overestimate TBW/FFM at lower levels whereas underestimate at higher levels of TBW/FFM. Accuracy of the general equation for TBW and FFM was also valid at each body mass index category. Ethnicity influences the relationship between BIA and body composition in Asian pre-pubertal children. The newly developed BIA prediction equations are valid for use in Asian pre-pubertal children.

Automated peroperative assessment of stents apposition from OCT pullbacks.

PubMed

Dubuisson, Florian; Péry, Emilie; Ouchchane, Lemlih; Combaret, Nicolas; Kauffmann, Claude; Souteyrand, Géraud; Motreff, Pascal; Sarry, Laurent

2015-04-01

This study's aim was to control the stents apposition by automatically analyzing endovascular optical coherence tomography (OCT) sequences. Lumen is detected using threshold, morphological and gradient operators to run a Dijkstra algorithm. Wrong detection tagged by the user and caused by bifurcation, struts'presence, thrombotic lesions or dissections can be corrected using a morphing algorithm. Struts are also segmented by computing symmetrical and morphological operators. Euclidian distance between detected struts and wall artery initializes a stent's complete distance map and missing data are interpolated with thin-plate spline functions. Rejection of detected outliers, regularization of parameters by generalized cross-validation and using the one-side cyclic property of the map also optimize accuracy. Several indices computed from the map provide quantitative values of malapposition. Algorithm was run on four in-vivo OCT sequences including different incomplete stent apposition's cases. Comparison with manual expert measurements validates the segmentation׳s accuracy and shows an almost perfect concordance of automated results. Copyright © 2014 Elsevier Ltd. All rights reserved.

Breast Cancer Detection with Reduced Feature Set.

PubMed

Mert, Ahmet; Kılıç, Niyazi; Bilgili, Erdem; Akan, Aydin

2015-01-01

This paper explores feature reduction properties of independent component analysis (ICA) on breast cancer decision support system. Wisconsin diagnostic breast cancer (WDBC) dataset is reduced to one-dimensional feature vector computing an independent component (IC). The original data with 30 features and reduced one feature (IC) are used to evaluate diagnostic accuracy of the classifiers such as k-nearest neighbor (k-NN), artificial neural network (ANN), radial basis function neural network (RBFNN), and support vector machine (SVM). The comparison of the proposed classification using the IC with original feature set is also tested on different validation (5/10-fold cross-validations) and partitioning (20%-40%) methods. These classifiers are evaluated how to effectively categorize tumors as benign and malignant in terms of specificity, sensitivity, accuracy, F-score, Youden's index, discriminant power, and the receiver operating characteristic (ROC) curve with its criterion values including area under curve (AUC) and 95% confidential interval (CI). This represents an improvement in diagnostic decision support system, while reducing computational complexity.

Mapping the Transmission Risk of Zika Virus using Machine Learning Models.

PubMed

Jiang, Dong; Hao, Mengmeng; Ding, Fangyu; Fu, Jingying; Li, Meng

2018-06-19

Zika virus, which has been linked to severe congenital abnormalities, is exacerbating global public health problems with its rapid transnational expansion fueled by increased global travel and trade. Suitability mapping of the transmission risk of Zika virus is essential for drafting public health plans and disease control strategies, which are especially important in areas where medical resources are relatively scarce. Predicting the risk of Zika virus outbreak has been studied in recent years, but the published literature rarely includes multiple model comparisons or predictive uncertainty analysis. Here, three relatively popular machine learning models including backward propagation neural network (BPNN), gradient boosting machine (GBM) and random forest (RF) were adopted to map the probability of Zika epidemic outbreak at the global level, pairing high-dimensional multidisciplinary covariate layers with comprehensive location data on recorded Zika virus infection in humans. The results show that the predicted high-risk areas for Zika transmission are concentrated in four regions: Southeastern North America, Eastern South America, Central Africa and Eastern Asia. To evaluate the performance of machine learning models, the 50 modeling processes were conducted based on a training dataset. The BPNN model obtained the highest predictive accuracy with a 10-fold cross-validation area under the curve (AUC) of 0.966 [95% confidence interval (CI) 0.965-0.967], followed by the GBM model (10-fold cross-validation AUC = 0.964[0.963-0.965]) and the RF model (10-fold cross-validation AUC = 0.963[0.962-0.964]). Based on training samples, compared with the BPNN-based model, we find that significant differences (p = 0.0258* and p = 0.0001***, respectively) are observed for prediction accuracies achieved by the GBM and RF models. Importantly, the prediction uncertainty introduced by the selection of absence data was quantified and could provide more accurate fundamental and scientific information for further study on disease transmission prediction and risk assessment. Copyright © 2018. Published by Elsevier B.V.

Automated characterisation of ultrasound images of ovarian tumours: the diagnostic accuracy of a support vector machine and image processing with a local binary pattern operator.

PubMed

Khazendar, S; Sayasneh, A; Al-Assam, H; Du, H; Kaijser, J; Ferrara, L; Timmerman, D; Jassim, S; Bourne, T

2015-01-01

Preoperative characterisation of ovarian masses into benign or malignant is of paramount importance to optimise patient management. In this study, we developed and validated a computerised model to characterise ovarian masses as benign or malignant. Transvaginal 2D B mode static ultrasound images of 187 ovarian masses with known histological diagnosis were included. Images were first pre-processed and enhanced, and Local Binary Pattern Histograms were then extracted from 2 × 2 blocks of each image. A Support Vector Machine (SVM) was trained using stratified cross validation with randomised sampling. The process was repeated 15 times and in each round 100 images were randomly selected. The SVM classified the original non-treated static images as benign or malignant masses with an average accuracy of 0.62 (95% CI: 0.59-0.65). This performance significantly improved to an average accuracy of 0.77 (95% CI: 0.75-0.79) when images were pre-processed, enhanced and treated with a Local Binary Pattern operator (mean difference 0.15: 95% 0.11-0.19, p < 0.0001, two-tailed t test). We have shown that an SVM can classify static 2D B mode ultrasound images of ovarian masses into benign and malignant categories. The accuracy improves if texture related LBP features extracted from the images are considered.

Classification of breast cancer cytological specimen using convolutional neural network

NASA Astrophysics Data System (ADS)

Żejmo, Michał; Kowal, Marek; Korbicz, Józef; Monczak, Roman

2017-01-01

The paper presents a deep learning approach for automatic classification of breast tumors based on fine needle cytology. The main aim of the system is to distinguish benign from malignant cases based on microscopic images. Experiment was carried out on cytological samples derived from 50 patients (25 benign cases + 25 malignant cases) diagnosed in Regional Hospital in Zielona Góra. To classify microscopic images, we used convolutional neural networks (CNN) of two types: GoogLeNet and AlexNet. Due to the very large size of images of cytological specimen (on average 200000 × 100000 pixels), they were divided into smaller patches of size 256 × 256 pixels. Breast cancer classification usually is based on morphometric features of nuclei. Therefore, training and validation patches were selected using Support Vector Machine (SVM) so that suitable amount of cell material was depicted. Neural classifiers were tuned using GPU accelerated implementation of gradient descent algorithm. Training error was defined as a cross-entropy classification loss. Classification accuracy was defined as the percentage ratio of successfully classified validation patches to the total number of validation patches. The best accuracy rate of 83% was obtained by GoogLeNet model. We observed that more misclassified patches belong to malignant cases.

Cross-modal face recognition using multi-matcher face scores

NASA Astrophysics Data System (ADS)

Zheng, Yufeng; Blasch, Erik

2015-05-01

The performance of face recognition can be improved using information fusion of multimodal images and/or multiple algorithms. When multimodal face images are available, cross-modal recognition is meaningful for security and surveillance applications. For example, a probe face is a thermal image (especially at nighttime), while only visible face images are available in the gallery database. Matching a thermal probe face onto the visible gallery faces requires crossmodal matching approaches. A few such studies were implemented in facial feature space with medium recognition performance. In this paper, we propose a cross-modal recognition approach, where multimodal faces are cross-matched in feature space and the recognition performance is enhanced with stereo fusion at image, feature and/or score level. In the proposed scenario, there are two cameras for stereo imaging, two face imagers (visible and thermal images) in each camera, and three recognition algorithms (circular Gaussian filter, face pattern byte, linear discriminant analysis). A score vector is formed with three cross-matched face scores from the aforementioned three algorithms. A classifier (e.g., k-nearest neighbor, support vector machine, binomial logical regression [BLR]) is trained then tested with the score vectors by using 10-fold cross validations. The proposed approach was validated with a multispectral stereo face dataset from 105 subjects. Our experiments show very promising results: ACR (accuracy rate) = 97.84%, FAR (false accept rate) = 0.84% when cross-matching the fused thermal faces onto the fused visible faces by using three face scores and the BLR classifier.

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.

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.

Refining Time-Activity Classification of Human Subjects Using the Global Positioning System.

PubMed

Hu, Maogui; Li, Wei; Li, Lianfa; Houston, Douglas; Wu, Jun

2016-01-01

Detailed spatial location information is important in accurately estimating personal exposure to air pollution. Global Position System (GPS) has been widely used in tracking personal paths and activities. Previous researchers have developed time-activity classification models based on GPS data, most of them were developed for specific regions. An adaptive model for time-location classification can be widely applied to air pollution studies that use GPS to track individual level time-activity patterns. Time-activity data were collected for seven days using GPS loggers and accelerometers from thirteen adult participants from Southern California under free living conditions. We developed an automated model based on random forests to classify major time-activity patterns (i.e. indoor, outdoor-static, outdoor-walking, and in-vehicle travel). Sensitivity analysis was conducted to examine the contribution of the accelerometer data and the supplemental spatial data (i.e. roadway and tax parcel data) to the accuracy of time-activity classification. Our model was evaluated using both leave-one-fold-out and leave-one-subject-out methods. Maximum speeds in averaging time intervals of 7 and 5 minutes, and distance to primary highways with limited access were found to be the three most important variables in the classification model. Leave-one-fold-out cross-validation showed an overall accuracy of 99.71%. Sensitivities varied from 84.62% (outdoor walking) to 99.90% (indoor). Specificities varied from 96.33% (indoor) to 99.98% (outdoor static). The exclusion of accelerometer and ambient light sensor variables caused a slight loss in sensitivity for outdoor walking, but little loss in overall accuracy. However, leave-one-subject-out cross-validation showed considerable loss in sensitivity for outdoor static and outdoor walking conditions. The random forests classification model can achieve high accuracy for the four major time-activity categories. The model also performed well with just GPS, road and tax parcel data. However, caution is warranted when generalizing the model developed from a small number of subjects to other populations.

Hierarchical Recognition Scheme for Human Facial Expression Recognition Systems

PubMed Central

Siddiqi, Muhammad Hameed; Lee, Sungyoung; Lee, Young-Koo; Khan, Adil Mehmood; Truc, Phan Tran Ho

2013-01-01

Over the last decade, human facial expressions recognition (FER) has emerged as an important research area. Several factors make FER a challenging research problem. These include varying light conditions in training and test images; need for automatic and accurate face detection before feature extraction; and high similarity among different expressions that makes it difficult to distinguish these expressions with a high accuracy. This work implements a hierarchical linear discriminant analysis-based facial expressions recognition (HL-FER) system to tackle these problems. Unlike the previous systems, the HL-FER uses a pre-processing step to eliminate light effects, incorporates a new automatic face detection scheme, employs methods to extract both global and local features, and utilizes a HL-FER to overcome the problem of high similarity among different expressions. Unlike most of the previous works that were evaluated using a single dataset, the performance of the HL-FER is assessed using three publicly available datasets under three different experimental settings: n-fold cross validation based on subjects for each dataset separately; n-fold cross validation rule based on datasets; and, finally, a last set of experiments to assess the effectiveness of each module of the HL-FER separately. Weighted average recognition accuracy of 98.7% across three different datasets, using three classifiers, indicates the success of employing the HL-FER for human FER. PMID:24316568

Using support vector machine to predict beta- and gamma-turns in proteins.

PubMed

Hu, Xiuzhen; Li, Qianzhong

2008-09-01

By using the composite vector with increment of diversity, position conservation scoring function, and predictive secondary structures to express the information of sequence, a support vector machine (SVM) algorithm for predicting beta- and gamma-turns in the proteins is proposed. The 426 and 320 nonhomologous protein chains described by Guruprasad and Rajkumar (Guruprasad and Rajkumar J. Biosci 2000, 25,143) are used for training and testing the predictive model of the beta- and gamma-turns, respectively. The overall prediction accuracy and the Matthews correlation coefficient in 7-fold cross-validation are 79.8% and 0.47, respectively, for the beta-turns. The overall prediction accuracy in 5-fold cross-validation is 61.0% for the gamma-turns. These results are significantly higher than the other algorithms in the prediction of beta- and gamma-turns using the same datasets. In addition, the 547 and 823 nonhomologous protein chains described by Fuchs and Alix (Fuchs and Alix Proteins: Struct Funct Bioinform 2005, 59, 828) are used for training and testing the predictive model of the beta- and gamma-turns, and better results are obtained. This algorithm may be helpful to improve the performance of protein turns' prediction. To ensure the ability of the SVM method to correctly classify beta-turn and non-beta-turn (gamma-turn and non-gamma-turn), the receiver operating characteristic threshold independent measure curves are provided. (c) 2008 Wiley Periodicals, Inc.

[Hyperspectral remote sensing image classification based on SVM optimized by clonal selection].

PubMed

Liu, Qing-Jie; Jing, Lin-Hai; Wang, Meng-Fei; Lin, Qi-Zhong

2013-03-01

Model selection for support vector machine (SVM) involving kernel and the margin parameter values selection is usually time-consuming, impacts training efficiency of SVM model and final classification accuracies of SVM hyperspectral remote sensing image classifier greatly. Firstly, based on combinatorial optimization theory and cross-validation method, artificial immune clonal selection algorithm is introduced to the optimal selection of SVM (CSSVM) kernel parameter a and margin parameter C to improve the training efficiency of SVM model. Then an experiment of classifying AVIRIS in India Pine site of USA was performed for testing the novel CSSVM, as well as a traditional SVM classifier with general Grid Searching cross-validation method (GSSVM) for comparison. And then, evaluation indexes including SVM model training time, classification overall accuracy (OA) and Kappa index of both CSSVM and GSSVM were all analyzed quantitatively. It is demonstrated that OA of CSSVM on test samples and whole image are 85.1% and 81.58, the differences from that of GSSVM are both within 0.08% respectively; And Kappa indexes reach 0.8213 and 0.7728, the differences from that of GSSVM are both within 0.001; While the ratio of model training time of CSSVM and GSSVM is between 1/6 and 1/10. Therefore, CSSVM is fast and accurate algorithm for hyperspectral image classification and is superior to GSSVM.

A New Method to Cross Calibrate and Validate TOMS, SBUV/2, and SCIAMACHY Measurements

NASA Technical Reports Server (NTRS)

Ahmad, Ziauddin; Hilsenrath, Ernest; Einaudi, Franco (Technical Monitor)

2001-01-01

A unique method to validate back scattered ultraviolet (buv) type satellite data that complements the measurements from existing ground networks is proposed. The method involves comparing the zenith sky radiance measurements from the ground to the nadir radiance measurements taken from space. Since the measurements are compared directly, the proposed method is superior to any other method that involves comparing derived products (for example, ozone), because comparison of derived products involve inversion algorithms which are susceptible to several type of errors. Forward radiative transfer (RT) calculations show that for an aerosol free atmosphere, the ground-based zenith sky radiance measurement and the satellite nadir radiance measurements can be predicted with an accuracy of better than 1 percent. The RT computations also show that for certain values of the solar zenith angles, the radiance comparisons could be better than half a percent. This accuracy is practically independent of ozone amount and aerosols in the atmosphere. Experiences with the Shuttle Solar Backscatter Ultraviolet (SSBUV) program show that the accuracy of the ground-based zenith sky radiance measuring instrument can be maintained at a level of a few tenth of a percent. This implies that the zenith sky radiance measurements can be used to validate Total Ozone Mapping Spectrometer (TOMS), Solar Backscatter Ultraviolet (SBUV/2), and The SCanning Imaging Absorption SpectroMeter for Atmospheric CHartographY (SCIAMACHY) radiance data. Also, this method will help improve the long term precision of the measurements for better trend detection and the accuracy of other BUV products such as tropospheric ozone and aerosols. Finally, in the long term, this method is a good candidate to inter-calibrate and validate long term observations of upcoming operational instruments such as Global Ozone Monitoring Experiment (GOME-2), Ozone Mapping Instrument (OMI), Ozone Dynamics Ultraviolet Spectrometer (ODUS), and Ozone Mapping and Profiler Suite (OMPS).

Diagnosis of diabetes diseases using an Artificial Immune Recognition System2 (AIRS2) with fuzzy K-nearest neighbor.

PubMed

Chikh, Mohamed Amine; Saidi, Meryem; Settouti, Nesma

2012-10-01

The use of expert systems and artificial intelligence techniques in disease diagnosis has been increasing gradually. Artificial Immune Recognition System (AIRS) is one of the methods used in medical classification problems. AIRS2 is a more efficient version of the AIRS algorithm. In this paper, we used a modified AIRS2 called MAIRS2 where we replace the K- nearest neighbors algorithm with the fuzzy K-nearest neighbors to improve the diagnostic accuracy of diabetes diseases. The diabetes disease dataset used in our work is retrieved from UCI machine learning repository. The performances of the AIRS2 and MAIRS2 are evaluated regarding classification accuracy, sensitivity and specificity values. The highest classification accuracy obtained when applying the AIRS2 and MAIRS2 using 10-fold cross-validation was, respectively 82.69% and 89.10%.

Estimating variance components and breeding values for number of oocytes and number of embryos in dairy cattle using a single-step genomic evaluation.

PubMed

Cornelissen, M A M C; Mullaart, E; Van der Linde, C; Mulder, H A

2017-06-01

Reproductive technologies such as multiple ovulation and embryo transfer (MOET) and ovum pick-up (OPU) accelerate genetic improvement in dairy breeding schemes. To enhance the efficiency of embryo production, breeding values for traits such as number of oocytes (NoO) and number of MOET embryos (NoM) can help in selection of donors with high MOET or OPU efficiency. The aim of this study was therefore to estimate variance components and (genomic) breeding values for NoO and NoM based on Dutch Holstein data. Furthermore, a 10-fold cross-validation was carried out to assess the accuracy of pedigree and genomic breeding values for NoO and NoM. For NoO, 40,734 OPU sessions between 1993 and 2015 were analyzed. These OPU sessions originated from 2,543 donors, from which 1,144 were genotyped. For NoM, 35,695 sessions between 1994 and 2015 were analyzed. These MOET sessions originated from 13,868 donors, from which 3,716 were genotyped. Analyses were done using only pedigree information and using a single-step genomic BLUP (ssGBLUP) approach combining genomic information and pedigree information. Heritabilities were very similar based on pedigree information or based on ssGBLUP [i.e., 0.32 (standard error = 0.03) for NoO and 0.21 (standard error = 0.01) for NoM with pedigree, 0.31 (standard error = 0.03) for NoO, and 0.22 (standard error = 0.01) for NoM with ssGBLUP]. For animals without their own information as mimicked in the cross-validation, the accuracy of pedigree-based breeding values was 0.46 for NoO and NoM. The accuracies of genomic breeding values from ssGBLUP were 0.54 for NoO and 0.52 for NoM. These results show that including genomic information increases the accuracies. These moderate accuracies in combination with a large genetic variance show good opportunities for selection of potential bull dams. Copyright © 2017 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Classification of motor intent in transradial amputees using sonomyography and spatio-temporal image analysis

NASA Astrophysics Data System (ADS)

Hariharan, Harishwaran; Aklaghi, Nima; Baker, Clayton A.; Rangwala, Huzefa; Kosecka, Jana; Sikdar, Siddhartha

2016-04-01

In spite of major advances in biomechanical design of upper extremity prosthetics, these devices continue to lack intuitive control. Conventional myoelectric control strategies typically utilize electromyography (EMG) signal amplitude sensed from forearm muscles. EMG has limited specificity in resolving deep muscle activity and poor signal-to-noise ratio. We have been investigating alternative control strategies that rely on real-time ultrasound imaging that can overcome many of the limitations of EMG. In this work, we present an ultrasound image sequence classification method that utilizes spatiotemporal features to describe muscle activity and classify motor intent. Ultrasound images of the forearm muscles were obtained from able-bodied subjects and a trans-radial amputee while they attempted different hand movements. A grid-based approach is used to test the feasibility of using spatio-temporal features by classifying hand motions performed by the subjects. Using the leave-one-out cross validation on image sequences acquired from able-bodied subjects, we observe that the grid-based approach is able to discern four hand motions with 95.31% accuracy. In case of the trans-radial amputee, we are able to discern three hand motions with 80% accuracy. In a second set of experiments, we study classification accuracy by extracting spatio-temporal sub-sequences the depict activity due to the motion of local anatomical interfaces. Short time and space limited cuboidal sequences are initially extracted and assigned an optical flow behavior label, based on a response function. The image space is clustered based on the location of cuboids and features calculated from the cuboids in each cluster. Using sequences of known motions, we extract feature vectors that describe said motion. A K-nearest neighbor classifier is designed for classification experiments. Using the leave-one-out cross validation on image sequences for an amputee subject, we demonstrate that the classifier is able to discern three important hand motions with an accuracy of 93.33% accuracy, 91-100% precision and 80-100% recall rate. We anticipate that ultrasound imaging based methods will address some limitations of conventional myoelectric sensing, while adding advantages inherent to ultrasound imaging.

A Flexible Spatio-Temporal Model for Air Pollution with Spatial and Spatio-Temporal Covariates.

PubMed

Lindström, Johan; Szpiro, Adam A; Sampson, Paul D; Oron, Assaf P; Richards, Mark; Larson, Tim V; Sheppard, Lianne

2014-09-01

The development of models that provide accurate spatio-temporal predictions of ambient air pollution at small spatial scales is of great importance for the assessment of potential health effects of air pollution. Here we present a spatio-temporal framework that predicts ambient air pollution by combining data from several different monitoring networks and deterministic air pollution model(s) with geographic information system (GIS) covariates. The model presented in this paper has been implemented in an R package, SpatioTemporal, available on CRAN. The model is used by the EPA funded Multi-Ethnic Study of Atherosclerosis and Air Pollution (MESA Air) to produce estimates of ambient air pollution; MESA Air uses the estimates to investigate the relationship between chronic exposure to air pollution and cardiovascular disease. In this paper we use the model to predict long-term average concentrations of NO x in the Los Angeles area during a ten year period. Predictions are based on measurements from the EPA Air Quality System, MESA Air specific monitoring, and output from a source dispersion model for traffic related air pollution (Caline3QHCR). Accuracy in predicting long-term average concentrations is evaluated using an elaborate cross-validation setup that accounts for a sparse spatio-temporal sampling pattern in the data, and adjusts for temporal effects. The predictive ability of the model is good with cross-validated R 2 of approximately 0.7 at subject sites. Replacing four geographic covariate indicators of traffic density with the Caline3QHCR dispersion model output resulted in very similar prediction accuracy from a more parsimonious and more interpretable model. Adding traffic-related geographic covariates to the model that included Caline3QHCR did not further improve the prediction accuracy.

Estimation of genomic breeding values for residual feed intake in a multibreed cattle population.

PubMed

Khansefid, M; Pryce, J E; Bolormaa, S; Miller, S P; Wang, Z; Li, C; Goddard, M E

2014-08-01

Residual feed intake (RFI) is a measure of the efficiency of animals in feed utilization. The accuracies of GEBV for RFI could be improved by increasing the size of the reference population. Combining RFI records of different breeds is a way to do that. The aims of this study were to 1) develop a method for calculating GEBV in a multibreed population and 2) improve the accuracies of GEBV by using SNP associated with RFI. An alternative method for calculating accuracies of GEBV using genomic BLUP (GBLUP) equations is also described and compared to cross-validation tests. The dataset included RFI records and 606,096 SNP genotypes for 5,614 Bos taurus animals including 842 Holstein heifers and 2,009 Australian and 2,763 Canadian beef cattle. A range of models were tested for combining genotype and phenotype information from different breeds and the best model included an overall effect of each SNP, an effect of each SNP specific to a breed, and a small residual polygenic effect defined by the pedigree. In this model, the Holsteins and some Angus cattle were combined into 1 "breed class" because they were the only cattle measured for RFI at an early age (6-9 mo of age) and were fed a similar diet. The average empirical accuracy (0.31), estimated by calculating the correlation between GEBV and actual phenotypes divided by the square root of estimated heritability in 5-fold cross-validation tests, was near to that expected using the GBLUP equations (0.34). The average empirical and expected accuracies were 0.30 and 0.31, respectively, when the GEBV were estimated for each breed separately. Therefore, the across-breed reference population increased the accuracy of GEBV slightly, although the gain was greater for breeds with smaller number of individuals in the reference population (0.08 in Murray Grey and 0.11 in Hereford for empirical accuracy). In a second approach, SNP that were significantly (P < 0.001) associated with RFI in the beef cattle genomewide association studies were used to create an auxiliary genomic relationship matrix for estimating GEBV in Holstein heifers. The empirical (and expected) accuracy of GEBV within Holsteins increased from 0.33 (0.35) to 0.39 (0.36) and improved even more to 0.43 (0.50) when using a multibreed reference population. Therefore, a multibreed reference population is a useful resource to find SNP with a greater than average association with RFI in 1 breed and use them to estimate GEBV in another breed.

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.

Rational selection of training and test sets for the development of validated QSAR models

NASA Astrophysics Data System (ADS)

Golbraikh, Alexander; Shen, Min; Xiao, Zhiyan; Xiao, Yun-De; Lee, Kuo-Hsiung; Tropsha, Alexander

2003-02-01

Quantitative Structure-Activity Relationship (QSAR) models are used increasingly to screen chemical databases and/or virtual chemical libraries for potentially bioactive molecules. These developments emphasize the importance of rigorous model validation to ensure that the models have acceptable predictive power. Using k nearest neighbors ( kNN) variable selection QSAR method for the analysis of several datasets, we have demonstrated recently that the widely accepted leave-one-out (LOO) cross-validated R2 (q2) is an inadequate characteristic to assess the predictive ability of the models [Golbraikh, A., Tropsha, A. Beware of q2! J. Mol. Graphics Mod. 20, 269-276, (2002)]. Herein, we provide additional evidence that there exists no correlation between the values of q 2 for the training set and accuracy of prediction ( R 2) for the test set and argue that this observation is a general property of any QSAR model developed with LOO cross-validation. We suggest that external validation using rationally selected training and test sets provides a means to establish a reliable QSAR model. We propose several approaches to the division of experimental datasets into training and test sets and apply them in QSAR studies of 48 functionalized amino acid anticonvulsants and a series of 157 epipodophyllotoxin derivatives with antitumor activity. We formulate a set of general criteria for the evaluation of predictive power of QSAR models.

In-Flight Validation of Mid and Thermal Infrared Remotely Sensed Data Using the Lake Tahoe and Salton Sea Automated Validation Sites

NASA Technical Reports Server (NTRS)

Hook, Simon J.

2008-01-01

The presentation includes an introduction, Lake Tahoe site layout and measurements, Salton Sea site layout and measurements, field instrument calibration and cross-calculations, data reduction methodology and error budgets, and example results for MODIS. Summary and conclusions are: 1) Lake Tahoe CA/NV automated validation site was established in 1999 to assess radiometric accuracy of satellite and airborne mid and thermal infrared data and products. Water surface temperatures range from 4-25C.2) Salton Sea CA automated validation site was established in 2008 to broaden range of available water surface temperatures and atmospheric water vapor test cases. Water surface temperatures range from 15-35C. 3) Sites provide all information necessary for validation every 2 mins (bulk temperature, skin temperature, air temperature, wind speed, wind direction, net radiation, relative humidity). 4) Sites have been used to validate mid and thermal infrared data and products from: ASTER, AATSR, ATSR2, MODIS-Terra, MODIS-Aqua, Landsat 5, Landsat 7, MTI, TES, MASTER, MAS. 5) Approximately 10 years of data available to help validate AVHRR.

A Comprehensive Validation Methodology for Sparse Experimental Data

NASA Technical Reports Server (NTRS)

Norman, Ryan B.; Blattnig, Steve R.

2010-01-01

A comprehensive program of verification and validation has been undertaken to assess the applicability of models to space radiation shielding applications and to track progress as models are developed over time. The models are placed under configuration control, and automated validation tests are used so that comparisons can readily be made as models are improved. Though direct comparisons between theoretical results and experimental data are desired for validation purposes, such comparisons are not always possible due to lack of data. In this work, two uncertainty metrics are introduced that are suitable for validating theoretical models against sparse experimental databases. The nuclear physics models, NUCFRG2 and QMSFRG, are compared to an experimental database consisting of over 3600 experimental cross sections to demonstrate the applicability of the metrics. A cumulative uncertainty metric is applied to the question of overall model accuracy, while a metric based on the median uncertainty is used to analyze the models from the perspective of model development by analyzing subsets of the model parameter space.

Magnetically confined electron beam system for high resolution electron transmission-beam experiments

NASA Astrophysics Data System (ADS)

Lozano, A. I.; Oller, J. C.; Krupa, K.; Ferreira da Silva, F.; Limão-Vieira, P.; Blanco, F.; Muñoz, A.; Colmenares, R.; García, G.

2018-06-01

A novel experimental setup has been implemented to provide accurate electron scattering cross sections from molecules at low and intermediate impact energies (1-300 eV) by measuring the attenuation of a magnetically confined linear electron beam from a molecular target. High-resolution electron energy is achieved through confinement in a magnetic gas trap where electrons are cooled by successive collisions with N2. Additionally, we developed and present a method to correct systematic errors arising from energy and angular resolution limitations. The accuracy of the entire measurement procedure is validated by comparing the N2 total scattering cross section in the considered energy range with benchmark values available in the literature.

Virtopsy - the concept of a centralized database in forensic medicine for analysis and comparison of radiological and autopsy data.

PubMed

Aghayev, Emin; Staub, Lukas; Dirnhofer, Richard; Ambrose, Tony; Jackowski, Christian; Yen, Kathrin; Bolliger, Stephan; Christe, Andreas; Roeder, Christoph; Aebi, Max; Thali, Michael J

2008-04-01

Recent developments in clinical radiology have resulted in additional developments in the field of forensic radiology. After implementation of cross-sectional radiology and optical surface documentation in forensic medicine, difficulties in the validation and analysis of the acquired data was experienced. To address this problem and for the comparison of autopsy and radiological data a centralized database with internet technology for forensic cases was created. The main goals of the database are (1) creation of a digital and standardized documentation tool for forensic-radiological and pathological findings; (2) establishing a basis for validation of forensic cross-sectional radiology as a non-invasive examination method in forensic medicine that means comparing and evaluating the radiological and autopsy data and analyzing the accuracy of such data; and (3) providing a conduit for continuing research and education in forensic medicine. Considering the infrequent availability of CT or MRI for forensic institutions and the heterogeneous nature of case material in forensic medicine an evaluation of benefits and limitations of cross-sectional imaging concerning certain forensic features by a single institution may be of limited value. A centralized database permitting international forensic and cross disciplinary collaborations may provide important support for forensic-radiological casework and research.

Measurement of stream channel habitat using sonar

USGS Publications Warehouse

Flug, Marshall; Seitz, Heather; Scott, John

1998-01-01

An efficient and low cost technique using a sonar system was evaluated for describing channel geometry and quantifying inundated area in a large river. The boat-mounted portable sonar equipment was used to record water depths and river width measurements for direct storage on a laptop computer. The field data collected from repeated traverses at a cross-section were evaluated to determine the precision of the system and field technique. Results from validation at two different sites showed average sample standard deviations (S.D.s) of 0.12 m for these complete cross-sections, with coefficient of variations of 10%. Validation using only the mid-channel river cross-section data yields an average sample S.D. of 0.05 m, with a coefficient of variation below 5%, at a stable and gauged river site using only measurements of water depths greater than 0.6 m. Accuracy of the sonar system was evaluated by comparison to traditionally surveyed transect data from a regularly gauged site. We observed an average mean squared deviation of 46.0 cm2, considering only that portion of the cross-section inundated by more than 0.6 m of water. Our procedure proved to be a reliable, accurate, safe, quick, and economic method to record river depths, discharges, bed conditions, and substratum composition necessary for stream habitat studies.

Diagnostic Accuracy of the Veteran Affairs' Traumatic Brain Injury Screen.

PubMed

Louise Bender Pape, Theresa; Smith, Bridget; Babcock-Parziale, Judith; Evans, Charlesnika T; Herrold, Amy A; Phipps Maieritsch, Kelly; High, Walter M

2018-01-31

To comprehensively estimate the diagnostic accuracy and reliability of the Department of Veterans Affairs (VA) Traumatic Brain Injury (TBI) Clinical Reminder Screen (TCRS). Cross-sectional, prospective, observational study using the Standards for Reporting of Diagnostic Accuracy criteria. Three VA Polytrauma Network Sites. Operation Iraqi Freedom, Operation Enduring Freedom veterans (N=433). TCRS, Comprehensive TBI Evaluation, Structured TBI Diagnostic Interview, Symptom Attribution and Classification Algorithm, and Clinician-Administered Posttraumatic Stress Disorder (PTSD) Scale. Forty-five percent of veterans screened positive on the TCRS for TBI. For detecting occurrence of historical TBI, the TCRS had a sensitivity of .56 to .74, a specificity of .63 to .93, a positive predictive value (PPV) of 25% to 45%, a negative predictive value (NPV) of 91% to 94%, and a diagnostic odds ratio (DOR) of 4 to 13. For accuracy of attributing active symptoms to the TBI, the TCRS had a sensitivity of .64 to .87, a specificity of .59 to .89, a PPV of 26% to 32%, an NPV of 92% to 95%, and a DOR of 6 to 9. The sensitivity was higher for veterans with PTSD (.80-.86) relative to veterans without PTSD (.57-.82). The specificity, however, was higher among veterans without PTSD (.75-.81) relative to veterans with PTSD (.36-.49). All indices of diagnostic accuracy changed when participants with questionably valid (QV) test profiles were eliminated from analyses. The utility of the TCRS to screen for mild TBI (mTBI) depends on the stringency of the diagnostic reference standard to which it is being compared, the presence/absence of PTSD, and QV test profiles. Further development, validation, and use of reproducible diagnostic algorithms for symptom attribution after possible mTBI would improve diagnostic accuracy. Published by Elsevier Inc.

Evidence for a confidence-accuracy relationship in memory for same- and cross-race faces.

PubMed

Nguyen, Thao B; Pezdek, Kathy; Wixted, John T

2017-12-01

Discrimination accuracy is usually higher for same- than for cross-race faces, a phenomenon known as the cross-race effect (CRE). According to prior research, the CRE occurs because memories for same- and cross-race faces rely on qualitatively different processes. However, according to a continuous dual-process model of recognition memory, memories that rely on qualitatively different processes do not differ in recognition accuracy when confidence is equated. Thus, although there are differences in overall same- and cross-race discrimination accuracy, confidence-specific accuracy (i.e., recognition accuracy at a particular level of confidence) may not differ. We analysed datasets from four recognition memory studies on same- and cross-race faces to test this hypothesis. Confidence ratings reliably predicted recognition accuracy when performance was above chance levels (Experiments 1, 2, and 3) but not when performance was at chance levels (Experiment 4). Furthermore, at each level of confidence, confidence-specific accuracy for same- and cross-race faces did not significantly differ when overall performance was above chance levels (Experiments 1, 2, and 3) but significantly differed when overall performance was at chance levels (Experiment 4). Thus, under certain conditions, high-confidence same-race and cross-race identifications may be equally reliable.

Predicting Presynaptic and Postsynaptic Neurotoxins by Developing Feature Selection Technique

PubMed Central

Yang, Yunchun; Zhang, Chunmei; Chen, Rong; Huang, Po

2017-01-01

Presynaptic and postsynaptic neurotoxins are proteins which act at the presynaptic and postsynaptic membrane. Correctly predicting presynaptic and postsynaptic neurotoxins will provide important clues for drug-target discovery and drug design. In this study, we developed a theoretical method to discriminate presynaptic neurotoxins from postsynaptic neurotoxins. A strict and objective benchmark dataset was constructed to train and test our proposed model. The dipeptide composition was used to formulate neurotoxin samples. The analysis of variance (ANOVA) was proposed to find out the optimal feature set which can produce the maximum accuracy. In the jackknife cross-validation test, the overall accuracy of 94.9% was achieved. We believe that the proposed model will provide important information to study neurotoxins. PMID:28303250

Assessing the accuracy of predictive models for numerical data: Not r nor r2, why not? Then what?

PubMed Central

2017-01-01

Assessing the accuracy of predictive models is critical because predictive models have been increasingly used across various disciplines and predictive accuracy determines the quality of resultant predictions. Pearson product-moment correlation coefficient (r) and the coefficient of determination (r2) are among the most widely used measures for assessing predictive models for numerical data, although they are argued to be biased, insufficient and misleading. In this study, geometrical graphs were used to illustrate what were used in the calculation of r and r2 and simulations were used to demonstrate the behaviour of r and r2 and to compare three accuracy measures under various scenarios. Relevant confusions about r and r2, has been clarified. The calculation of r and r2 is not based on the differences between the predicted and observed values. The existing error measures suffer various limitations and are unable to tell the accuracy. Variance explained by predictive models based on cross-validation (VEcv) is free of these limitations and is a reliable accuracy measure. Legates and McCabe’s efficiency (E1) is also an alternative accuracy measure. The r and r2 do not measure the accuracy and are incorrect accuracy measures. The existing error measures suffer limitations. VEcv and E1 are recommended for assessing the accuracy. The applications of these accuracy measures would encourage accuracy-improved predictive models to be developed to generate predictions for evidence-informed decision-making. PMID:28837692

Improving accuracies of genomic predictions for drought tolerance in maize by joint modeling of additive and dominance effects in multi-environment trials.

PubMed

Dias, Kaio Olímpio Das Graças; Gezan, Salvador Alejandro; Guimarães, Claudia Teixeira; Nazarian, Alireza; da Costa E Silva, Luciano; Parentoni, Sidney Netto; de Oliveira Guimarães, Paulo Evaristo; de Oliveira Anoni, Carina; Pádua, José Maria Villela; de Oliveira Pinto, Marcos; Noda, Roberto Willians; Ribeiro, Carlos Alexandre Gomes; de Magalhães, Jurandir Vieira; Garcia, Antonio Augusto Franco; de Souza, João Cândido; Guimarães, Lauro José Moreira; Pastina, Maria Marta

2018-07-01

Breeding for drought tolerance is a challenging task that requires costly, extensive, and precise phenotyping. Genomic selection (GS) can be used to maximize selection efficiency and the genetic gains in maize (Zea mays L.) breeding programs for drought tolerance. Here, we evaluated the accuracy of genomic selection (GS) using additive (A) and additive + dominance (AD) models to predict the performance of untested maize single-cross hybrids for drought tolerance in multi-environment trials. Phenotypic data of five drought tolerance traits were measured in 308 hybrids along eight trials under water-stressed (WS) and well-watered (WW) conditions over two years and two locations in Brazil. Hybrids' genotypes were inferred based on their parents' genotypes (inbred lines) using single-nucleotide polymorphism markers obtained via genotyping-by-sequencing. GS analyses were performed using genomic best linear unbiased prediction by fitting a factor analytic (FA) multiplicative mixed model. Two cross-validation (CV) schemes were tested: CV1 and CV2. The FA framework allowed for investigating the stability of additive and dominance effects across environments, as well as the additive-by-environment and the dominance-by-environment interactions, with interesting applications for parental and hybrid selection. Results showed differences in the predictive accuracy between A and AD models, using both CV1 and CV2, for the five traits in both water conditions. For grain yield (GY) under WS and using CV1, the AD model doubled the predictive accuracy in comparison to the A model. Through CV2, GS models benefit from borrowing information of correlated trials, resulting in an increase of 40% and 9% in the predictive accuracy of GY under WS for A and AD models, respectively. These results highlight the importance of multi-environment trial analyses using GS models that incorporate additive and dominance effects for genomic predictions of GY under drought in maize single-cross hybrids.

Tuning support vector machines for minimax and Neyman-Pearson classification.

PubMed

Davenport, Mark A; Baraniuk, Richard G; Scott, Clayton D

2010-10-01

This paper studies the training of support vector machine (SVM) classifiers with respect to the minimax and Neyman-Pearson criteria. In principle, these criteria can be optimized in a straightforward way using a cost-sensitive SVM. In practice, however, because these criteria require especially accurate error estimation, standard techniques for tuning SVM parameters, such as cross-validation, can lead to poor classifier performance. To address this issue, we first prove that the usual cost-sensitive SVM, here called the 2C-SVM, is equivalent to another formulation called the 2nu-SVM. We then exploit a characterization of the 2nu-SVM parameter space to develop a simple yet powerful approach to error estimation based on smoothing. In an extensive experimental study, we demonstrate that smoothing significantly improves the accuracy of cross-validation error estimates, leading to dramatic performance gains. Furthermore, we propose coordinate descent strategies that offer significant gains in computational efficiency, with little to no loss in performance.

Children’s School-Breakfast Reports and School-Lunch Reports (in 24-hour Dietary Recalls): Conventional and Reporting-Error-Sensitive Measures Show Inconsistent Accuracy Results for Retention Interval and for Breakfast Location

PubMed Central

Baxter, Suzanne Domel; Guinn, Caroline H.; Smith, Albert F.; Hitchcock, David B.; Royer, Julie A.; Puryear, Megan P.; Collins, Kathleen L.; Smith, Alyssa L.

2017-01-01

Validation-study data were analyzed to investigate retention interval (RI) and prompt effects on accuracy of fourth-grade children’s reports of school-breakfast and school-lunch (in 24-hour recalls), and accuracy of school-breakfast reports by breakfast location (classroom; cafeteria). Randomly-selected fourth-grade children at 10 schools in four districts were observed eating school-provided breakfast and lunch, and interviewed under one of eight conditions (two RIs [short (prior-24-hour recall obtained in afternoon); long (previous-day recall obtained in morning)] crossed with four prompts [forward (distant-to-recent), meal-name (breakfast, etc.), open (no instructions), reverse (recent-to-distant)]). Each condition had 60 children (half girls). Of 480 children, 355 and 409 reported meals satisfying criteria for reports of school-breakfast and school-lunch, respectively. For breakfast and lunch separately, a conventional measure—report rate—and reporting-error-sensitive measures—correspondence rate and inflation ratio—were calculated for energy per meal-reporting child. Correspondence rate and inflation ratio—but not report rate—showed better accuracy for school-breakfast and school-lunch reports with the short than long RI; this pattern was not found for some prompts for each sex. Correspondence rate and inflation ratio showed better school-breakfast report accuracy for the classroom than cafeteria location for each prompt, but report rate showed the opposite. For each RI, correspondence rate and inflation ratio showed better accuracy for lunch than breakfast, but report rate showed the opposite. When choosing RI and prompts for recalls, researchers and practitioners should select short RIs to maximize accuracy. Recommendations for prompt selections are less clear. As report rates distort validation-study accuracy conclusions, reporting-error-sensitive measures are recommended. PMID:26865356

Diabetic retinopathy risk prediction for fundus examination using sparse learning: a cross-sectional study.

PubMed

Oh, Ein; Yoo, Tae Keun; Park, Eun-Cheol

2013-09-13

Blindness due to diabetic retinopathy (DR) is the major disability in diabetic patients. Although early management has shown to prevent vision loss, diabetic patients have a low rate of routine ophthalmologic examination. Hence, we developed and validated sparse learning models with the aim of identifying the risk of DR in diabetic patients. Health records from the Korea National Health and Nutrition Examination Surveys (KNHANES) V-1 were used. The prediction models for DR were constructed using data from 327 diabetic patients, and were validated internally on 163 patients in the KNHANES V-1. External validation was performed using 562 diabetic patients in the KNHANES V-2. The learning models, including ridge, elastic net, and LASSO, were compared to the traditional indicators of DR. Considering the Bayesian information criterion, LASSO predicted DR most efficiently. In the internal and external validation, LASSO was significantly superior to the traditional indicators by calculating the area under the curve (AUC) of the receiver operating characteristic. LASSO showed an AUC of 0.81 and an accuracy of 73.6% in the internal validation, and an AUC of 0.82 and an accuracy of 75.2% in the external validation. The sparse learning model using LASSO was effective in analyzing the epidemiological underlying patterns of DR. This is the first study to develop a machine learning model to predict DR risk using health records. LASSO can be an excellent choice when both discriminative power and variable selection are important in the analysis of high-dimensional electronic health records.

Cross-Calibration of Ground and Airborne TIR and VSWIR Instruments for NASA's SnowEx 2017 Grand Mesa Campaign

NASA Astrophysics Data System (ADS)

Crawford, C. J.; Chickadel, C. C.; Hall, D. K.; Jennings, D. E.; Jhabvala, M. D.; Kim, E. J.; Jessica, L.; Lunsford, A.

2017-12-01

The NASA Terrestrial Hydrology Program sponsored a ground and airborne snow experiment (SnowEx) to the Grand Mesa area and Senator Beck Basin in western Colorado during February 2017. This communication summarizes efforts to develop traceable instrument calibration requirements for SnowEx Grand Mesa in support of thermal infrared (TIR) and visible-to-shortwave infrared (VSWIR) snow measurement science. Cross-calibration outcomes for TIR instruments (7-10 µm and 8-14 µm response functions) indicate that an at-sensor measurement accuracy of within 1.5 degrees Celsius was achieved across ground and airborne sensors using laboratory and field blackbody sources. A cross-calibration assessment of VSWIR spectrometers (0.35 to 2.5 µm response functions) using a National Institutes of Standard Technology (NIST) traceable source indicates an at-sensor measurement accuracy of within 5% for visible-near infrared spectral radiance (W/cm-2/sr-1/nm) and irradiance (W/m-2/nm), and within 20% for shortwave infrared measurements before a radiometric cross-calibration correction was applied. Additional validation is undertaken to assess the ground and airborne SnowEx Grand Mesa TIR and VSWIR instrument cross-calibration quality by benchmarking against on-orbit image acquisitions of the snow surface on February 14th and 15th, 2017 from Landsat Enhanced Thematic Mapper Plus (ETM+), Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER), and Sentinel-2A Multi-Spectral Instrument (MSI).

LRSSLMDA: Laplacian Regularized Sparse Subspace Learning for MiRNA-Disease Association prediction

PubMed Central

Huang, Li

2017-01-01

Predicting novel microRNA (miRNA)-disease associations is clinically significant due to miRNAs’ potential roles of diagnostic biomarkers and therapeutic targets for various human diseases. Previous studies have demonstrated the viability of utilizing different types of biological data to computationally infer new disease-related miRNAs. Yet researchers face the challenge of how to effectively integrate diverse datasets and make reliable predictions. In this study, we presented a computational model named Laplacian Regularized Sparse Subspace Learning for MiRNA-Disease Association prediction (LRSSLMDA), which projected miRNAs/diseases’ statistical feature profile and graph theoretical feature profile to a common subspace. It used Laplacian regularization to preserve the local structures of the training data and a L1-norm constraint to select important miRNA/disease features for prediction. The strength of dimensionality reduction enabled the model to be easily extended to much higher dimensional datasets than those exploited in this study. Experimental results showed that LRSSLMDA outperformed ten previous models: the AUC of 0.9178 in global leave-one-out cross validation (LOOCV) and the AUC of 0.8418 in local LOOCV indicated the model’s superior prediction accuracy; and the average AUC of 0.9181+/-0.0004 in 5-fold cross validation justified its accuracy and stability. In addition, three types of case studies further demonstrated its predictive power. Potential miRNAs related to Colon Neoplasms, Lymphoma, Kidney Neoplasms, Esophageal Neoplasms and Breast Neoplasms were predicted by LRSSLMDA. Respectively, 98%, 88%, 96%, 98% and 98% out of the top 50 predictions were validated by experimental evidences. Therefore, we conclude that LRSSLMDA would be a valuable computational tool for miRNA-disease association prediction. PMID:29253885

Remote estimation of colored dissolved organic matter and chlorophyll-a in Lake Huron using Sentinel-2 measurements

NASA Astrophysics Data System (ADS)

Chen, Jiang; Zhu, Weining; Tian, Yong Q.; Yu, Qian; Zheng, Yuhan; Huang, Litong

2017-07-01

Colored dissolved organic matter (CDOM) and chlorophyll-a (Chla) are important water quality parameters and play crucial roles in aquatic environment. Remote sensing of CDOM and Chla concentrations for inland lakes is often limited by low spatial resolution. The newly launched Sentinel-2 satellite is equipped with high spatial resolution (10, 20, and 60 m). Empirical band ratio models were developed to derive CDOM and Chla concentrations in Lake Huron. The leave-one-out cross-validation method was used for model calibration and validation. The best CDOM retrieval algorithm is a B3/B5 model with accuracy coefficient of determination (R2)=0.884, root-mean-squared error (RMSE)=0.731 m-1, relative root-mean-squared error (RRMSE)=28.02%, and bias=-0.1 m-1. The best Chla retrieval algorithm is a B5/B4 model with accuracy R2=0.49, RMSE=9.972 mg/m3, RRMSE=48.47%, and bias=-0.116 mg/m3. Neural network models were further implemented to improve inversion accuracy. The applications of the two best band ratio models to Sentinel-2 imagery with 10 m×10 m pixel size presented the high potential of the sensor for monitoring water quality of inland lakes.

Optical Coherence Tomography Machine Learning Classifiers for Glaucoma Detection: A Preliminary Study

PubMed Central

Burgansky-Eliash, Zvia; Wollstein, Gadi; Chu, Tianjiao; Ramsey, Joseph D.; Glymour, Clark; Noecker, Robert J.; Ishikawa, Hiroshi; Schuman, Joel S.

2007-01-01

Purpose Machine-learning classifiers are trained computerized systems with the ability to detect the relationship between multiple input parameters and a diagnosis. The present study investigated whether the use of machine-learning classifiers improves optical coherence tomography (OCT) glaucoma detection. Methods Forty-seven patients with glaucoma (47 eyes) and 42 healthy subjects (42 eyes) were included in this cross-sectional study. Of the glaucoma patients, 27 had early disease (visual field mean deviation [MD] ≥ −6 dB) and 20 had advanced glaucoma (MD < −6 dB). Machine-learning classifiers were trained to discriminate between glaucomatous and healthy eyes using parameters derived from OCT output. The classifiers were trained with all 38 parameters as well as with only 8 parameters that correlated best with the visual field MD. Five classifiers were tested: linear discriminant analysis, support vector machine, recursive partitioning and regression tree, generalized linear model, and generalized additive model. For the last two classifiers, a backward feature selection was used to find the minimal number of parameters that resulted in the best and most simple prediction. The cross-validated receiver operating characteristic (ROC) curve and accuracies were calculated. Results The largest area under the ROC curve (AROC) for glaucoma detection was achieved with the support vector machine using eight parameters (0.981). The sensitivity at 80% and 95% specificity was 97.9% and 92.5%, respectively. This classifier also performed best when judged by cross-validated accuracy (0.966). The best classification between early glaucoma and advanced glaucoma was obtained with the generalized additive model using only three parameters (AROC = 0.854). Conclusions Automated machine classifiers of OCT data might be useful for enhancing the utility of this technology for detecting glaucomatous abnormality. PMID:16249492

Improving the performance of the mass transfer-based reference evapotranspiration estimation approaches through a coupled wavelet-random forest methodology

NASA Astrophysics Data System (ADS)

Shiri, Jalal

2018-06-01

Among different reference evapotranspiration (ETo) modeling approaches, mass transfer-based methods have been less studied. These approaches utilize temperature and wind speed records. On the other hand, the empirical equations proposed in this context generally produce weak simulations, except when a local calibration is used for improving their performance. This might be a crucial drawback for those equations in case of local data scarcity for calibration procedure. So, application of heuristic methods can be considered as a substitute for improving the performance accuracy of the mass transfer-based approaches. However, given that the wind speed records have usually higher variation magnitudes than the other meteorological parameters, application of a wavelet transform for coupling with heuristic models would be necessary. In the present paper, a coupled wavelet-random forest (WRF) methodology was proposed for the first time to improve the performance accuracy of the mass transfer-based ETo estimation approaches using cross-validation data management scenarios in both local and cross-station scales. The obtained results revealed that the new coupled WRF model (with the minimum scatter index values of 0.150 and 0.192 for local and external applications, respectively) improved the performance accuracy of the single RF models as well as the empirical equations to great extent.

One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial Sensor

PubMed Central

Riaz, Qaiser; Vögele, Anna; Krüger, Björn; Weber, Andreas

2015-01-01

A number of previous works have shown that information about a subject is encoded in sparse kinematic information, such as the one revealed by so-called point light walkers. With the work at hand, we extend these results to classifications of soft biometrics from inertial sensor recordings at a single body location from a single step. We recorded accelerations and angular velocities of 26 subjects using integrated measurement units (IMUs) attached at four locations (chest, lower back, right wrist and left ankle) when performing standardized gait tasks. The collected data were segmented into individual walking steps. We trained random forest classifiers in order to estimate soft biometrics (gender, age and height). We applied two different validation methods to the process, 10-fold cross-validation and subject-wise cross-validation. For all three classification tasks, we achieve high accuracy values for all four sensor locations. From these results, we can conclude that the data of a single walking step (6D: accelerations and angular velocities) allow for a robust estimation of the gender, height and age of a person. PMID:26703601

In silico prediction of Tetrahymena pyriformis toxicity for diverse industrial chemicals with substructure pattern recognition and machine learning methods.

PubMed

Cheng, Feixiong; Shen, Jie; Yu, Yue; Li, Weihua; Liu, Guixia; Lee, Philip W; Tang, Yun

2011-03-01

There is an increasing need for the rapid safety assessment of chemicals by both industries and regulatory agencies throughout the world. In silico techniques are practical alternatives in the environmental hazard assessment. It is especially true to address the persistence, bioaccumulative and toxicity potentials of organic chemicals. Tetrahymena pyriformis toxicity is often used as a toxic endpoint. In this study, 1571 diverse unique chemicals were collected from the literature and composed of the largest diverse data set for T. pyriformis toxicity. Classification predictive models of T. pyriformis toxicity were developed by substructure pattern recognition and different machine learning methods, including support vector machine (SVM), C4.5 decision tree, k-nearest neighbors and random forest. The results of a 5-fold cross-validation showed that the SVM method performed better than other algorithms. The overall predictive accuracies of the SVM classification model with radial basis functions kernel was 92.2% for the 5-fold cross-validation and 92.6% for the external validation set, respectively. Furthermore, several representative substructure patterns for characterizing T. pyriformis toxicity were also identified via the information gain analysis methods. Copyright © 2010 Elsevier Ltd. All rights reserved.

The R package "sperrorest" : Parallelized spatial error estimation and variable importance assessment for geospatial machine learning

NASA Astrophysics Data System (ADS)

Schratz, Patrick; Herrmann, Tobias; Brenning, Alexander

2017-04-01

Computational and statistical prediction methods such as the support vector machine have gained popularity in remote-sensing applications in recent years and are often compared to more traditional approaches like maximum-likelihood classification. However, the accuracy assessment of such predictive models in a spatial context needs to account for the presence of spatial autocorrelation in geospatial data by using spatial cross-validation and bootstrap strategies instead of their now more widely used non-spatial equivalent. The R package sperrorest by A. Brenning [IEEE International Geoscience and Remote Sensing Symposium, 1, 374 (2012)] provides a generic interface for performing (spatial) cross-validation of any statistical or machine-learning technique available in R. Since spatial statistical models as well as flexible machine-learning algorithms can be computationally expensive, parallel computing strategies are required to perform cross-validation efficiently. The most recent major release of sperrorest therefore comes with two new features (aside from improved documentation): The first one is the parallelized version of sperrorest(), parsperrorest(). This function features two parallel modes to greatly speed up cross-validation runs. Both parallel modes are platform independent and provide progress information. par.mode = 1 relies on the pbapply package and calls interactively (depending on the platform) parallel::mclapply() or parallel::parApply() in the background. While forking is used on Unix-Systems, Windows systems use a cluster approach for parallel execution. par.mode = 2 uses the foreach package to perform parallelization. This method uses a different way of cluster parallelization than the parallel package does. In summary, the robustness of parsperrorest() is increased with the implementation of two independent parallel modes. A new way of partitioning the data in sperrorest is provided by partition.factor.cv(). This function gives the user the possibility to perform cross-validation at the level of some grouping structure. As an example, in remote sensing of agricultural land uses, pixels from the same field contain nearly identical information and will thus be jointly placed in either the test set or the training set. Other spatial sampling resampling strategies are already available and can be extended by the user.

Validation of Cross Sections with Criticality Experiment and Reaction Rates: the Neptunium Case

NASA Astrophysics Data System (ADS)

Leong, L. S.; Tassan-Got, L.; Audouin, L.; Berthier, B.; Le Naour, C.; Stéphan, C.; Paradela, C.; Tarrío, D.; Duran, I.

2014-04-01

The 237Np neutron-induced fission cross section has been recently measured in a large energy range (from eV to GeV) at the n_TOF facility at CERN. When compared to previous measurements the n_TOF fission cross section appears to be higher by 5-7% beyond the fission threshold. To check the relevance of the n_TOF data, we considered a criticality experiment performed at Los Alamos with a 6 kg sphere of 237Np, surrounded by uranium highly enriched in 235U so as to approach criticality with fast neutrons. The multiplication factor keff of the calculation is in better agreement with the experiment when we replace the ENDF/B-VII.0 evaluation of the 237Np fission cross section by the n_TOF data. We also explored the hypothesis of deficiencies of the inelastic cross section in 235U which has been invoked by some authors to explain the deviation of 750 pcm. The large modification needed to reduce the deviation seems to be incompatible with existing inelastic cross section measurements. Also we show that the νbar of 237Np can hardly be incriminated because of the high accuracy of the existing data. Fission rate ratios or averaged fission cross sections measured in several fast neutron fields seem to give contradictory results on the validation of the 237Np cross section but at least one of the benchmark experiments, where the active deposits have been well calibrated for the number of atoms, favors the n_TOF data set. These outcomes support the hypothesis of a higher fission cross section of 237Np.

Cultural and linguistic transferability of the multi-dimensional OxCAP-MH capability instrument for outcome measurement in mental health: the German language version.

PubMed

Simon, Judit; Łaszewska, Agata; Leutner, Eva; Spiel, Georg; Churchman, David; Mayer, Susanne

2018-06-05

Mental health conditions affect aspects of people's lives that are often not captured in common health-related outcome measures. The OxCAP-MH self-reported, quality of life questionnaire based on Sen's capability approach was developed in the UK to overcome these limitations. The aim of this study was to develop a linguistically and culturally valid German version of the questionnaire. Following forward and back translations, the wording underwent cultural and linguistic validation with input from a sample of 12 native German speaking mental health patients in Austria in 2015. Qualitative feedback from patients and carers was obtained via interviews and focus group meetings. Feedback from mental health researchers from Germany was incorporated to account for cross-country differences. No significant item modifications were necessary. However, changes due to ambiguous wordings, possibilities for differential interpretations, politically unacceptable expressions, cross-country language differences and differences in political and social systems, were needed. The study confirmed that all questions are relevant and understandable for people with mental health conditions in a German speaking setting and transferability of the questionnaire from English to German speaking countries is feasible. Professional translation is necessary for the linguistic accuracy of different language versions of patient-reported outcome measures but does not guarantee linguistic and cultural validity and cross-country transferability. Additional context-specific piloting is essential. The time and resources needed to achieve valid multi-lingual versions should not be underestimated. Further research is ongoing to confirm the psychometric properties of the German version.

Automated characterisation of ultrasound images of ovarian tumours: the diagnostic accuracy of a support vector machine and image processing with a local binary pattern operator

PubMed Central

Khazendar, S.; Sayasneh, A.; Al-Assam, H.; Du, H.; Kaijser, J.; Ferrara, L.; Timmerman, D.; Jassim, S.; Bourne, T.

2015-01-01

Introduction: Preoperative characterisation of ovarian masses into benign or malignant is of paramount importance to optimise patient management. Objectives: In this study, we developed and validated a computerised model to characterise ovarian masses as benign or malignant. Materials and methods: Transvaginal 2D B mode static ultrasound images of 187 ovarian masses with known histological diagnosis were included. Images were first pre-processed and enhanced, and Local Binary Pattern Histograms were then extracted from 2 × 2 blocks of each image. A Support Vector Machine (SVM) was trained using stratified cross validation with randomised sampling. The process was repeated 15 times and in each round 100 images were randomly selected. Results: The SVM classified the original non-treated static images as benign or malignant masses with an average accuracy of 0.62 (95% CI: 0.59-0.65). This performance significantly improved to an average accuracy of 0.77 (95% CI: 0.75-0.79) when images were pre-processed, enhanced and treated with a Local Binary Pattern operator (mean difference 0.15: 95% 0.11-0.19, p < 0.0001, two-tailed t test). Conclusion: We have shown that an SVM can classify static 2D B mode ultrasound images of ovarian masses into benign and malignant categories. The accuracy improves if texture related LBP features extracted from the images are considered. PMID:25897367

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

Computer-aided diagnosis for classifying benign versus malignant thyroid nodules based on ultrasound images: A comparison with radiologist-based assessments.

PubMed

Chang, Yongjun; Paul, Anjan Kumar; Kim, Namkug; Baek, Jung Hwan; Choi, Young Jun; Ha, Eun Ju; Lee, Kang Dae; Lee, Hyoung Shin; Shin, DaeSeock; Kim, Nakyoung

2016-01-01

To develop a semiautomated computer-aided diagnosis (cad) system for thyroid cancer using two-dimensional ultrasound images that can be used to yield a second opinion in the clinic to differentiate malignant and benign lesions. A total of 118 ultrasound images that included axial and longitudinal images from patients with biopsy-confirmed malignant (n = 30) and benign (n = 29) nodules were collected. Thyroid cad software was developed to extract quantitative features from these images based on thyroid nodule segmentation in which adaptive diffusion flow for active contours was used. Various features, including histogram, intensity differences, elliptical fit, gray-level co-occurrence matrixes, and gray-level run-length matrixes, were evaluated for each region imaged. Based on these imaging features, a support vector machine (SVM) classifier was used to differentiate benign and malignant nodules. Leave-one-out cross-validation with sequential forward feature selection was performed to evaluate the overall accuracy of this method. Additionally, analyses with contingency tables and receiver operating characteristic (ROC) curves were performed to compare the performance of cad with visual inspection by expert radiologists based on established gold standards. Most univariate features for this proposed cad system attained accuracies that ranged from 78.0% to 83.1%. When optimal SVM parameters that were established using a grid search method with features that radiologists use for visual inspection were employed, the authors could attain rates of accuracy that ranged from 72.9% to 84.7%. Using leave-one-out cross-validation results in a multivariate analysis of various features, the highest accuracy achieved using the proposed cad system was 98.3%, whereas visual inspection by radiologists reached 94.9% accuracy. To obtain the highest accuracies, "axial ratio" and "max probability" in axial images were most frequently included in the optimal feature sets for the authors' proposed cad system, while "shape" and "calcification" in longitudinal images were most frequently included in the optimal feature sets for visual inspection by radiologists. The computed areas under curves in the ROC analysis were 0.986 and 0.979 for the proposed cad system and visual inspection by radiologists, respectively; no significant difference was detected between these groups. The use of thyroid cad to differentiate malignant from benign lesions shows accuracy similar to that obtained via visual inspection by radiologists. Thyroid cad might be considered a viable way to generate a second opinion for radiologists in clinical practice.

Computer-aided diagnosis for classifying benign versus malignant thyroid nodules based on ultrasound images: A comparison with radiologist-based assessments

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

Chang, Yongjun; Paul, Anjan Kumar; Kim, Namkug, E-mail: namkugkim@gmail.com

Purpose: To develop a semiautomated computer-aided diagnosis (CAD) system for thyroid cancer using two-dimensional ultrasound images that can be used to yield a second opinion in the clinic to differentiate malignant and benign lesions. Methods: A total of 118 ultrasound images that included axial and longitudinal images from patients with biopsy-confirmed malignant (n = 30) and benign (n = 29) nodules were collected. Thyroid CAD software was developed to extract quantitative features from these images based on thyroid nodule segmentation in which adaptive diffusion flow for active contours was used. Various features, including histogram, intensity differences, elliptical fit, gray-level co-occurrencemore » matrixes, and gray-level run-length matrixes, were evaluated for each region imaged. Based on these imaging features, a support vector machine (SVM) classifier was used to differentiate benign and malignant nodules. Leave-one-out cross-validation with sequential forward feature selection was performed to evaluate the overall accuracy of this method. Additionally, analyses with contingency tables and receiver operating characteristic (ROC) curves were performed to compare the performance of CAD with visual inspection by expert radiologists based on established gold standards. Results: Most univariate features for this proposed CAD system attained accuracies that ranged from 78.0% to 83.1%. When optimal SVM parameters that were established using a grid search method with features that radiologists use for visual inspection were employed, the authors could attain rates of accuracy that ranged from 72.9% to 84.7%. Using leave-one-out cross-validation results in a multivariate analysis of various features, the highest accuracy achieved using the proposed CAD system was 98.3%, whereas visual inspection by radiologists reached 94.9% accuracy. To obtain the highest accuracies, “axial ratio” and “max probability” in axial images were most frequently included in the optimal feature sets for the authors’ proposed CAD system, while “shape” and “calcification” in longitudinal images were most frequently included in the optimal feature sets for visual inspection by radiologists. The computed areas under curves in the ROC analysis were 0.986 and 0.979 for the proposed CAD system and visual inspection by radiologists, respectively; no significant difference was detected between these groups. Conclusions: The use of thyroid CAD to differentiate malignant from benign lesions shows accuracy similar to that obtained via visual inspection by radiologists. Thyroid CAD might be considered a viable way to generate a second opinion for radiologists in clinical practice.« less

Calibration of Clinical Audio Recording and Analysis Systems for Sound Intensity Measurement.

PubMed

Maryn, Youri; Zarowski, Andrzej

2015-11-01

Sound intensity is an important acoustic feature of voice/speech signals. Yet recordings are performed with different microphone, amplifier, and computer configurations, and it is therefore crucial to calibrate sound intensity measures of clinical audio recording and analysis systems on the basis of output of a sound-level meter. This study was designed to evaluate feasibility, validity, and accuracy of calibration methods, including audiometric speech noise signals and human voice signals under typical speech conditions. Calibration consisted of 3 comparisons between data from 29 measurement microphone-and-computer systems and data from the sound-level meter: signal-specific comparison with audiometric speech noise at 5 levels, signal-specific comparison with natural voice at 3 levels, and cross-signal comparison with natural voice at 3 levels. Intensity measures from recording systems were then linearly converted into calibrated data on the basis of these comparisons, and validity and accuracy of calibrated sound intensity were investigated. Very strong correlations and quasisimilarity were found between calibrated data and sound-level meter data across calibration methods and recording systems. Calibration of clinical sound intensity measures according to this method is feasible, valid, accurate, and representative for a heterogeneous set of microphones and data acquisition systems in real-life circumstances with distinct noise contexts.

Assessment of the Thematic Accuracy of Land Cover Maps

NASA Astrophysics Data System (ADS)

Höhle, J.

2015-08-01

Several land cover maps are generated from aerial imagery and assessed by different approaches. The test site is an urban area in Europe for which six classes (`building', `hedge and bush', `grass', `road and parking lot', `tree', `wall and car port') had to be derived. Two classification methods were applied (`Decision Tree' and `Support Vector Machine') using only two attributes (height above ground and normalized difference vegetation index) which both are derived from the images. The assessment of the thematic accuracy applied a stratified design and was based on accuracy measures such as user's and producer's accuracy, and kappa coefficient. In addition, confidence intervals were computed for several accuracy measures. The achieved accuracies and confidence intervals are thoroughly analysed and recommendations are derived from the gained experiences. Reliable reference values are obtained using stereovision, false-colour image pairs, and positioning to the checkpoints with 3D coordinates. The influence of the training areas on the results is studied. Cross validation has been tested with a few reference points in order to derive approximate accuracy measures. The two classification methods perform equally for five classes. Trees are classified with a much better accuracy and a smaller confidence interval by means of the decision tree method. Buildings are classified by both methods with an accuracy of 99% (95% CI: 95%-100%) using independent 3D checkpoints. The average width of the confidence interval of six classes was 14% of the user's accuracy.

Parametric vs. non-parametric statistics of low resolution electromagnetic tomography (LORETA).

PubMed

Thatcher, R W; North, D; Biver, C

2005-01-01

This study compared the relative statistical sensitivity of non-parametric and parametric statistics of 3-dimensional current sources as estimated by the EEG inverse solution Low Resolution Electromagnetic Tomography (LORETA). One would expect approximately 5% false positives (classification of a normal as abnormal) at the P < .025 level of probability (two tailed test) and approximately 1% false positives at the P < .005 level. EEG digital samples (2 second intervals sampled 128 Hz, 1 to 2 minutes eyes closed) from 43 normal adult subjects were imported into the Key Institute's LORETA program. We then used the Key Institute's cross-spectrum and the Key Institute's LORETA output files (*.lor) as the 2,394 gray matter pixel representation of 3-dimensional currents at different frequencies. The mean and standard deviation *.lor files were computed for each of the 2,394 gray matter pixels for each of the 43 subjects. Tests of Gaussianity and different transforms were computed in order to best approximate a normal distribution for each frequency and gray matter pixel. The relative sensitivity of parametric vs. non-parametric statistics were compared using a "leave-one-out" cross validation method in which individual normal subjects were withdrawn and then statistically classified as being either normal or abnormal based on the remaining subjects. Log10 transforms approximated Gaussian distribution in the range of 95% to 99% accuracy. Parametric Z score tests at P < .05 cross-validation demonstrated an average misclassification rate of approximately 4.25%, and range over the 2,394 gray matter pixels was 27.66% to 0.11%. At P < .01 parametric Z score cross-validation false positives were 0.26% and ranged from 6.65% to 0% false positives. The non-parametric Key Institute's t-max statistic at P < .05 had an average misclassification error rate of 7.64% and ranged from 43.37% to 0.04% false positives. The nonparametric t-max at P < .01 had an average misclassification rate of 6.67% and ranged from 41.34% to 0% false positives of the 2,394 gray matter pixels for any cross-validated normal subject. In conclusion, adequate approximation to Gaussian distribution and high cross-validation can be achieved by the Key Institute's LORETA programs by using a log10 transform and parametric statistics, and parametric normative comparisons had lower false positive rates than the non-parametric tests.

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

Anthropometric predictors of body fat in a large population of 9-year-old school-aged children.

PubMed

Almeida, Sílvia M; Furtado, José M; Mascarenhas, Paulo; Ferraz, Maria E; Silva, Luís R; Ferreira, José C; Monteiro, Mariana; Vilanova, Manuel; Ferraz, Fernando P

2016-09-01

To develop and cross-validate predictive models for percentage body fat (%BF) from anthropometric measurements [including BMI z -score (zBMI) and calf circumference (CC)] excluding skinfold thickness. A descriptive study was carried out in 3,084 pre-pubertal children. Regression models and neural network were developed with %BF measured by Bioelectrical Impedance Analysis (BIA) as the dependent variables and age, sex and anthropometric measurements as independent predictors. All %BF grade predictive models presented a good global accuracy (≥91.3%) for obesity discrimination. Both overfat/obese and obese prediction models presented respectively good sensitivity (78.6% and 71.0%), specificity (98.0% and 99.2%) and reliability for positive or negative test results (≥82% and ≥96%). For boys, the order of parameters, by relative weight in the predictive model, was zBMI, height, waist-circumference-to-height-ratio (WHtR) squared variable (_Q), age, weight, CC_Q and hip circumference (HC)_Q (adjusted r 2  = 0.847 and RMSE = 2.852); for girls it was zBMI, WHtR_Q, height, age, HC_Q and CC_Q (adjusted r 2  = 0.872 and RMSE = 2.171). %BF can be graded and predicted with relative accuracy from anthropometric measurements excluding skinfold thickness. Fitness and cross-validation results showed that our multivariable regression model performed better in this population than did some previously published models.

Development and Psychometric Evaluation of the Brief Adolescent Gambling Screen (BAGS)

PubMed Central

Stinchfield, Randy; Wynne, Harold; Wiebe, Jamie; Tremblay, Joel

2017-01-01

The purpose of this study was to develop and evaluate the initial reliability, validity and classification accuracy of a new brief screen for adolescent problem gambling. The three-item Brief Adolescent Gambling Screen (BAGS) was derived from the nine-item Gambling Problem Severity Subscale (GPSS) of the Canadian Adolescent Gambling Inventory (CAGI) using a secondary analysis of existing CAGI data. The sample of 105 adolescents included 49 females and 56 males from Canada who completed the CAGI, a self-administered measure of DSM-IV diagnostic criteria for Pathological Gambling, and a clinician-administered diagnostic interview including the DSM-IV diagnostic criteria for Pathological Gambling (both of which were adapted to yield DSM-5 Gambling Disorder diagnosis). A stepwise multivariate discriminant function analysis selected three GPSS items as the best predictors of a diagnosis of Gambling Disorder. The BAGS demonstrated satisfactory estimates of reliability, validity and classification accuracy and was equivalent to the nine-item GPSS of the CAGI and the BAGS was more accurate than the SOGS-RA. The BAGS estimates of classification accuracy include hit rate = 0.95, sensitivity = 0.88, specificity = 0.98, false positive rate = 0.02, and false negative rate = 0.12. Since these classification estimates are preliminary, derived from a relatively small sample size, and based upon the same sample from which the items were selected, it will be important to cross-validate the BAGS with larger and more diverse samples. The BAGS should be evaluated for use as a screening tool in both clinical and school settings as well as epidemiological surveys. PMID:29312064

A Power Transformers Fault Diagnosis Model Based on Three DGA Ratios and PSO Optimization SVM

NASA Astrophysics Data System (ADS)

Ma, Hongzhe; Zhang, Wei; Wu, Rongrong; Yang, Chunyan

2018-03-01

In order to make up for the shortcomings of existing transformer fault diagnosis methods in dissolved gas-in-oil analysis (DGA) feature selection and parameter optimization, a transformer fault diagnosis model based on the three DGA ratios and particle swarm optimization (PSO) optimize support vector machine (SVM) is proposed. Using transforming support vector machine to the nonlinear and multi-classification SVM, establishing the particle swarm optimization to optimize the SVM multi classification model, and conducting transformer fault diagnosis combined with the cross validation principle. The fault diagnosis results show that the average accuracy of test method is better than the standard support vector machine and genetic algorithm support vector machine, and the proposed method can effectively improve the accuracy of transformer fault diagnosis is proved.

Identifying nursing interventions associated with the accuracy used nursing diagnoses for patients with liver cirrhosis 1

PubMed Central

Gimenes, Fernanda Raphael Escobar; Motta, Ana Paula Gobbo; da Silva, Patrícia Costa dos Santos; Gobbo, Ana Flora Fogaça; Atila, Elisabeth; de Carvalho, Emilia Campos

2017-01-01

ABSTRACT Objective: to identify the nursing interventions associated with the most accurate and frequently used NANDA International, Inc. (NANDA-I) nursing diagnoses for patients with liver cirrhosis. Method: this is a descriptive, quantitative, cross-sectional study. Results: a total of 12 nursing diagnoses were evaluated, seven of which showed high accuracy (IVC ≥ 0.8); 70 interventions were identified and 23 (32.86%) were common to more than one diagnosis. Conclusion: in general, nurses often perform nursing interventions suggested in the NIC for the seven highly accurate nursing diagnoses identified in this study to care patients with liver cirrhosis. Accurate and valid nursing diagnoses guide the selection of appropriate interventions that nurses can perform to enhance patient safety and thus improve patient health outcomes.

Comparative Study on the Different Testing Techniques in Tree Classification for Detecting the Learning Motivation

NASA Astrophysics Data System (ADS)

Juliane, C.; Arman, A. A.; Sastramihardja, H. S.; Supriana, I.

2017-03-01

Having motivation to learn is a successful requirement in a learning process, and needs to be maintained properly. This study aims to measure learning motivation, especially in the process of electronic learning (e-learning). Here, data mining approach was chosen as a research method. For the testing process, the accuracy comparative study on the different testing techniques was conducted, involving Cross Validation and Percentage Split. The best accuracy was generated by J48 algorithm with a percentage split technique reaching at 92.19 %. This study provided an overview on how to detect the presence of learning motivation in the context of e-learning. It is expected to be good contribution for education, and to warn the teachers for whom they have to provide motivation.

Fast scattering simulation tool for multi-energy x-ray imaging

NASA Astrophysics Data System (ADS)

Sossin, A.; Tabary, J.; Rebuffel, V.; Létang, J. M.; Freud, N.; Verger, L.

2015-12-01

A combination of Monte Carlo (MC) and deterministic approaches was employed as a means of creating a simulation tool capable of providing energy resolved x-ray primary and scatter images within a reasonable time interval. Libraries of Sindbad, a previously developed x-ray simulation software, were used in the development. The scatter simulation capabilities of the tool were validated through simulation with the aid of GATE and through experimentation by using a spectrometric CdTe detector. A simple cylindrical phantom with cavities and an aluminum insert was used. Cross-validation with GATE showed good agreement with a global spatial error of 1.5% and a maximum scatter spectrum error of around 6%. Experimental validation also supported the accuracy of the simulations obtained from the developed software with a global spatial error of 1.8% and a maximum error of around 8.5% in the scatter spectra.

On the accuracy of aerosol photoacoustic spectrometer calibrations using absorption by ozone

NASA Astrophysics Data System (ADS)

Davies, Nicholas W.; Cotterell, Michael I.; Fox, Cathryn; Szpek, Kate; Haywood, Jim M.; Langridge, Justin M.

2018-04-01

In recent years, photoacoustic spectroscopy has emerged as an invaluable tool for the accurate measurement of light absorption by atmospheric aerosol. Photoacoustic instruments require calibration, which can be achieved by measuring the photoacoustic signal generated by known quantities of gaseous ozone. Recent work has questioned the validity of this approach at short visible wavelengths (404 nm), indicating systematic calibration errors of the order of a factor of 2. We revisit this result and test the validity of the ozone calibration method using a suite of multipass photoacoustic cells operating at wavelengths 405, 514 and 658 nm. Using aerosolised nigrosin with mobility-selected diameters in the range 250-425 nm, we demonstrate excellent agreement between measured and modelled ensemble absorption cross sections at all wavelengths, thus demonstrating the validity of the ozone-based calibration method for aerosol photoacoustic spectroscopy at visible wavelengths.

Characterization of cross-section correction to charge exchange recombination spectroscopy rotation measurements using co- and counter-neutral-beam views.

PubMed

Solomon, W M; Burrell, K H; Feder, R; Nagy, A; Gohil, P; Groebner, R J

2008-10-01

Measurements of rotation using charge exchange recombination spectroscopy can be affected by the energy dependence of the charge exchange cross section. On DIII-D, the associated correction to the rotation can exceed 100 kms at high temperatures. In reactor-relevant low rotation conditions, the correction can be several times larger than the actual plasma rotation and therefore must be carefully validated. New chords have been added to the DIII-D CER diagnostic to view the counter-neutral-beam line. The addition of these views allows determination of the toroidal rotation without depending on detailed atomic physics calculations, while also allowing experimental characterization of the atomic physics. A database of rotation comparisons from the two views shows that the calculated cross-section correction can adequately describe the measurements, although there is a tendency for "overcorrection." In cases where accuracy better than about 15% is desired, relying on calculation of the cross-section correction may be insufficient.

Quick method (FT-NIR) for the determination of oil and major fatty acids content in whole achenes of milk thistle (Silybum marianum (L.) Gaertn.).

PubMed

Koláčková, Pavla; Růžičková, Gabriela; Gregor, Tomáš; Šišperová, Eliška

2015-08-30

Calibration models for the Fourier transform-near infrared (FT-NIR) instrument were developed for quick and non-destructive determination of oil and fatty acids in whole achenes of milk thistle. Samples with a range of oil and fatty acid levels were collected and their transmittance spectra were obtained by the FT-NIR instrument. Based on these spectra and data gained by the means of the reference method - Soxhlet extraction and gas chromatography (GC) - calibration models were created by means of partial least square (PLS) regression analysis. Precision and accuracy of the calibration models was verified via the cross-validation of validation samples whose spectra were not part of the calibration model and also according to the root mean square error of prediction (RMSEP), root mean square error of calibration (RMSEC), root mean square error of cross-validation (RMSECV) and the validation coefficient of determination (R(2) ). R(2) for whole seeds were 0.96, 0.96, 0.83 and 0.67 and the RMSEP values were 0.76, 1.68, 1.24, 0.54 for oil, linoleic (C18:2), oleic (C18:1) and palmitic (C16:0) acids, respectively. The calibration models are appropriate for the non-destructive determination of oil and fatty acids levels in whole seeds of milk thistle. © 2014 Society of Chemical Industry.

Automatic classification of small bowel mucosa alterations in celiac disease for confocal laser endomicroscopy

NASA Astrophysics Data System (ADS)

Boschetto, Davide; Di Claudio, Gianluca; Mirzaei, Hadis; Leong, Rupert; Grisan, Enrico

2016-03-01

Celiac disease (CD) is an immune-mediated enteropathy triggered by exposure to gluten and similar proteins, affecting genetically susceptible persons, increasing their risk of different complications. Small bowels mucosa damage due to CD involves various degrees of endoscopically relevant lesions, which are not easily recognized: their overall sensitivity and positive predictive values are poor even when zoom-endoscopy is used. Confocal Laser Endomicroscopy (CLE) allows skilled and trained experts to qualitative evaluate mucosa alteration such as a decrease in goblet cells density, presence of villous atrophy or crypt hypertrophy. We present a method for automatically classifying CLE images into three different classes: normal regions, villous atrophy and crypt hypertrophy. This classification is performed after a features selection process, in which four features are extracted from each image, through the application of homomorphic filtering and border identification through Canny and Sobel operators. Three different classifiers have been tested on a dataset of 67 different images labeled by experts in three classes (normal, VA and CH): linear approach, Naive-Bayes quadratic approach and a standard quadratic analysis, all validated with a ten-fold cross validation. Linear classification achieves 82.09% accuracy (class accuracies: 90.32% for normal villi, 82.35% for VA and 68.42% for CH, sensitivity: 0.68, specificity 1.00), Naive Bayes analysis returns 83.58% accuracy (90.32% for normal villi, 70.59% for VA and 84.21% for CH, sensitivity: 0.84 specificity: 0.92), while the quadratic analysis achieves a final accuracy of 94.03% (96.77% accuracy for normal villi, 94.12% for VA and 89.47% for CH, sensitivity: 0.89, specificity: 0.98).

[Rapid identification of potato cultivars using NIR-excited fluorescence and Raman spectroscopy].

PubMed

Dai, Fen; Bergholt, Mads Sylvest; Benjamin, Arnold Julian Vinoj; Hong, Tian-Sheng; Zhiwei, Huang

2014-03-01

Potato is one of the most important food in the world. Rapid and noninvasive identification of potato cultivars plays a important role in the better use of varieties. In this study, The identification ability of optical spectroscopy techniques, including near-infrared (NIR) Raman spectroscopy and NIR fluorescence spectroscopy, for invasive detection of potato cultivars was evaluated. A rapid NIR Raman spectroscopy system was applied to measure the composite Raman and NIR fluorescence spectroscopy of 3 different species of potatoes (98 samples in total) under 785 nm laser light excitation. Then pure Raman and NIR fluorescence spectroscopy were abstracted from the composite spectroscopy, respectively. At last, the partial least squares-discriminant analysis (PLS-DA) was utilized to analyze and classify Raman spectra of 3 different types of potatoes. All the samples were divided into two sets at random: the calibration set (74samples) and prediction set (24 samples), the model was validated using a leave-one-out, cross-validation method. The results showed that both the NIR-excited fluorescence spectra and pure Raman spectra could be used to identify three cultivars of potatoes. The fluorescence spectrum could distinguish the Favorita variety well (sensitivity: 1, specificity: 0.86 and accuracy: 0.92), but the result for Diamant (sensitivity: 0.75, specificity: 0.75 and accuracy: 0. 75) and Granola (sensitivity: 0.16, specificity: 0.89 and accuracy: 0.71) cultivars identification were a bit poorer. We demonstrated that Raman spectroscopy uncovered the main biochemical compositions contained in potato species, and provided a better classification sensitivity, specificity and accuracy (sensitivity: 1, specificity: 1 and accuracy: 1 for all 3 potato cultivars identification) among the three types of potatoes as compared to fluorescence spectroscopy.

Radiogenomics to characterize regional genetic heterogeneity in glioblastoma

PubMed Central

Hu, Leland S.; Ning, Shuluo; Eschbacher, Jennifer M.; Baxter, Leslie C.; Gaw, Nathan; Ranjbar, Sara; Plasencia, Jonathan; Dueck, Amylou C.; Peng, Sen; Smith, Kris A.; Nakaji, Peter; Karis, John P.; Quarles, C. Chad; Wu, Teresa; Loftus, Joseph C.; Jenkins, Robert B.; Sicotte, Hugues; Kollmeyer, Thomas M.; O'Neill, Brian P.; Elmquist, William; Hoxworth, Joseph M.; Frakes, David; Sarkaria, Jann; Swanson, Kristin R.; Tran, Nhan L.; Li, Jing; Mitchell, J. Ross

2017-01-01

Background Glioblastoma (GBM) exhibits profound intratumoral genetic heterogeneity. Each tumor comprises multiple genetically distinct clonal populations with different therapeutic sensitivities. This has implications for targeted therapy and genetically informed paradigms. Contrast-enhanced (CE)-MRI and conventional sampling techniques have failed to resolve this heterogeneity, particularly for nonenhancing tumor populations. This study explores the feasibility of using multiparametric MRI and texture analysis to characterize regional genetic heterogeneity throughout MRI-enhancing and nonenhancing tumor segments. Methods We collected multiple image-guided biopsies from primary GBM patients throughout regions of enhancement (ENH) and nonenhancing parenchyma (so called brain-around-tumor, [BAT]). For each biopsy, we analyzed DNA copy number variants for core GBM driver genes reported by The Cancer Genome Atlas. We co-registered biopsy locations with MRI and texture maps to correlate regional genetic status with spatially matched imaging measurements. We also built multivariate predictive decision-tree models for each GBM driver gene and validated accuracies using leave-one-out-cross-validation (LOOCV). Results We collected 48 biopsies (13 tumors) and identified significant imaging correlations (univariate analysis) for 6 driver genes: EGFR, PDGFRA, PTEN, CDKN2A, RB1, and TP53. Predictive model accuracies (on LOOCV) varied by driver gene of interest. Highest accuracies were observed for PDGFRA (77.1%), EGFR (75%), CDKN2A (87.5%), and RB1 (87.5%), while lowest accuracy was observed in TP53 (37.5%). Models for 4 driver genes (EGFR, RB1, CDKN2A, and PTEN) showed higher accuracy in BAT samples (n = 16) compared with those from ENH segments (n = 32). Conclusion MRI and texture analysis can help characterize regional genetic heterogeneity, which offers potential diagnostic value under the paradigm of individualized oncology. PMID:27502248

Watch-Dog: Detecting Self-Harming Activities From Wrist Worn Accelerometers.

PubMed

Bharti, Pratool; Panwar, Anurag; Gopalakrishna, Ganesh; Chellappan, Sriram

2018-05-01

In a 2012 survey, in the United States alone, there were more than 35 000 reported suicides with approximately 1800 of being psychiatric inpatients. Recent Centers for Disease Control and Prevention (CDC) reports indicate an upward trend in these numbers. In psychiatric facilities, staff perform intermittent or continuous observation of patients manually in order to prevent such tragedies, but studies show that they are insufficient, and also consume staff time and resources. In this paper, we present the Watch-Dog system, to address the problem of detecting self-harming activities when attempted by in-patients in clinical settings. Watch-Dog comprises of three key components-Data sensed by tiny accelerometer sensors worn on wrists of subjects; an efficient algorithm to classify whether a user is active versus dormant (i.e., performing a physical activity versus not performing any activity); and a novel decision selection algorithm based on random forests and continuity indices for fine grained activity classification. With data acquired from 11 subjects performing a series of activities (both self-harming and otherwise), Watch-Dog achieves a classification accuracy of , , and for same-user 10-fold cross-validation, cross-user 10-fold cross-validation, and cross-user leave-one-out evaluation, respectively. We believe that the problem addressed in this paper is practical, important, and timely. We also believe that our proposed system is practically deployable, and related discussions are provided in this paper.

Using airborne laser scanning profiles to validate marine geoid models

NASA Astrophysics Data System (ADS)

Julge, Kalev; Gruno, Anti; Ellmann, Artu; Liibusk, Aive; Oja, Tõnis

2014-05-01

Airborne laser scanning (ALS) is a remote sensing method which utilizes LiDAR (Light Detection And Ranging) technology. The datasets collected are important sources for large range of scientific and engineering applications. Mostly the ALS is used to measure terrain surfaces for compilation of Digital Elevation Models but it can also be used in other applications. This contribution focuses on usage of ALS system for measuring sea surface heights and validating gravimetric geoid models over marine areas. This is based on the ALS ability to register echoes of LiDAR pulse from the water surface. A case study was carried out to analyse the possibilities for validating marine geoid models by using ALS profiles. A test area at the southern shores of the Gulf of Finland was selected for regional geoid validation. ALS measurements were carried out by the Estonian Land Board in spring 2013 at different altitudes and using different scan rates. The one wavelength Leica ALS50-II laser scanner on board of a small aircraft was used to determine the sea level (with respect to the GRS80 reference ellipsoid), which follows roughly the equipotential surface of the Earth's gravity field. For the validation a high-resolution (1'x2') regional gravimetric GRAV-GEOID2011 model was used. This geoid model covers the entire area of Estonia and surrounding waters of the Baltic Sea. The fit between the geoid model and GNSS/levelling data within the Estonian dry land revealed RMS of residuals ±1… ±2 cm. Note that such fitting validation cannot proceed over marine areas. Therefore, an ALS observation-based methodology was developed to evaluate the GRAV-GEOID2011 quality over marine areas. The accuracy of acquired ALS dataset were analyzed, also an optimal width of nadir-corridor containing good quality ALS data was determined. Impact of ALS scan angle range and flight altitude to obtainable vertical accuracy were investigated as well. The quality of point cloud is analysed by cross validation between overlapped flight lines and the comparison with tide gauge stations readings. The comparisons revealed that the ALS based profiles of sea level heights agree reasonably with the regional geoid model (within accuracy of the ALS data and after applying corrections due to sea level variations). Thus ALS measurements are suitable for measuring sea surface heights and validating marine geoid models.

Assessing Predictive Properties of Genome-Wide Selection in Soybeans

PubMed Central

Xavier, Alencar; Muir, William M.; Rainey, Katy Martin

2016-01-01

Many economically important traits in plant breeding have low heritability or are difficult to measure. For these traits, genomic selection has attractive features and may boost genetic gains. Our goal was to evaluate alternative scenarios to implement genomic selection for yield components in soybean (Glycine max L. merr). We used a nested association panel with cross validation to evaluate the impacts of training population size, genotyping density, and prediction model on the accuracy of genomic prediction. Our results indicate that training population size was the factor most relevant to improvement in genome-wide prediction, with greatest improvement observed in training sets up to 2000 individuals. We discuss assumptions that influence the choice of the prediction model. Although alternative models had minor impacts on prediction accuracy, the most robust prediction model was the combination of reproducing kernel Hilbert space regression and BayesB. Higher genotyping density marginally improved accuracy. Our study finds that breeding programs seeking efficient genomic selection in soybeans would best allocate resources by investing in a representative training set. PMID:27317786

Determination of sex by armbone dimensions.

PubMed

Aye, Victor Omakoji

2010-06-15

Sex determination is a vital part of the medico-legal system but can be difficult in cases where the body is damaged. The purpose of this study was to develop a technique for sex determination from three arm-bone dimensions (wrist circumference, arm length and arm span). This knowledge can be applied in cases of mass disaster, homicide and events such as sports. Data were collected for 95 Nigerian male students and 90 Nigerian female students using physical anthropometry. Discriminant function presented the wrist dimension as the dominant contributor in this study. Combination equations for both the wrist and arm-span dimensions correctly classified sex (male/female) with an accuracy rate of 84.9%. On cross-validation, sex was also established with the same 84.9% accuracy rate. Sex determination was higher in males. Sexual dimorphism was established in this study, although the wrist circumference was more distinct than arm span; a combination of both generated sex with an accuracy prediction rate of 84.9%. (c) 2010 Elsevier Ireland Ltd. All rights reserved.

Vibration extraction based on fast NCC algorithm and high-speed camera.

PubMed

Lei, Xiujun; Jin, Yi; Guo, Jie; Zhu, Chang'an

2015-09-20

In this study, a high-speed camera system is developed to complete the vibration measurement in real time and to overcome the mass introduced by conventional contact measurements. The proposed system consists of a notebook computer and a high-speed camera which can capture the images as many as 1000 frames per second. In order to process the captured images in the computer, the normalized cross-correlation (NCC) template tracking algorithm with subpixel accuracy is introduced. Additionally, a modified local search algorithm based on the NCC is proposed to reduce the computation time and to increase efficiency significantly. The modified algorithm can rapidly accomplish one displacement extraction 10 times faster than the traditional template matching without installing any target panel onto the structures. Two experiments were carried out under laboratory and outdoor conditions to validate the accuracy and efficiency of the system performance in practice. The results demonstrated the high accuracy and efficiency of the camera system in extracting vibrating signals.

Automatic Prediction of Conversion from Mild Cognitive Impairment to Probable Alzheimer’s Disease using Structural Magnetic Resonance Imaging

PubMed Central

Nho, Kwangsik; Shen, Li; Kim, Sungeun; Risacher, Shannon L.; West, John D.; Foroud, Tatiana; Jack, Clifford R.; Weiner, Michael W.; Saykin, Andrew J.

2010-01-01

Mild Cognitive Impairment (MCI) is thought to be a precursor to the development of early Alzheimer’s disease (AD). For early diagnosis of AD, the development of a model that is able to predict the conversion of amnestic MCI to AD is challenging. Using automatic whole-brain MRI analysis techniques and pattern classification methods, we developed a model to differentiate AD from healthy controls (HC), and then applied it to the prediction of MCI conversion to AD. Classification was performed using support vector machines (SVMs) together with a SVM-based feature selection method, which selected a set of most discriminating predictors for optimizing prediction accuracy. We obtained 90.5% cross-validation accuracy for classifying AD and HC, and 72.3% accuracy for predicting MCI conversion to AD. These analyses suggest that a classifier trained to separate HC vs. AD has substantial potential for predicting MCI conversion to AD. PMID:21347037

Pathological brain detection based on wavelet entropy and Hu moment invariants.

PubMed

Zhang, Yudong; Wang, Shuihua; Sun, Ping; Phillips, Preetha

2015-01-01

With the aim of developing an accurate pathological brain detection system, we proposed a novel automatic computer-aided diagnosis (CAD) to detect pathological brains from normal brains obtained by magnetic resonance imaging (MRI) scanning. The problem still remained a challenge for technicians and clinicians, since MR imaging generated an exceptionally large information dataset. A new two-step approach was proposed in this study. We used wavelet entropy (WE) and Hu moment invariants (HMI) for feature extraction, and the generalized eigenvalue proximal support vector machine (GEPSVM) for classification. To further enhance classification accuracy, the popular radial basis function (RBF) kernel was employed. The 10 runs of k-fold stratified cross validation result showed that the proposed "WE + HMI + GEPSVM + RBF" method was superior to existing methods w.r.t. classification accuracy. It obtained the average classification accuracies of 100%, 100%, and 99.45% over Dataset-66, Dataset-160, and Dataset-255, respectively. The proposed method is effective and can be applied to realistic use.

Studies on Antiretroviral Drug Concentrations in Breast Milk: Validation of a Liquid Chromatography–Tandem Mass Spectrometric Method for the Determination of 7 Anti-Human Immunodeficiency Virus Medications

PubMed Central

Rezk, Naser L.; White, Nicole; Bridges, Arlene S.; Abdel-Megeed, Mohamed F.; Mohamed, Tarek M.; Moselhy, Said S.; Kashuba, Angela D. M.

2010-01-01

Studying the pharmacokinetics of antiretroviral drugs in breast milk has important implications for the health of both the mother and the infant, particularly in resource-poor countries. Breast milk is a highly complex biological matrix, yet it is necessary to develop and validate methods in this matrix, which simultaneously measure multiple analytes, as women may be taking any number of drug combinations to combat human immunodeficiency virus infection. Here, we report a novel extraction method coupled to high-performance liquid chromatography and tandem mass spectrometry for the accurate, precise, and specific measurement of 7 antiretroviral drugs currently prescribed to infected mothers. Using 200 µL of human breast milk, simultaneous quantification of lamivudine (3TC), stavudine (d4T), zidovudine (ZDV), nevirapine (NVP), nelfinavir (NFV), ritonavir, and lopinavir was validated over the range of 10–10,000 ng/mL. Intraday accuracy and precision for all analytes were 99.3% and 5.0 %, respectively. Interday accuracy and precision were 99.4 % and 7.8%, respectively. Cross-assay validation with UV detection was performed using clinical breast milk samples, and the results of the 2 assays were in good agreement (P = 0.0001, r = 0.97). Breast milk to plasma concentration ratios for the different antiretroviral drugs were determined as follows: 3TC = 2.96, d4T = 1.73, ZDV = 1.17, NVP = 0.82, and NFV = 0.21. PMID:18758393

Accuracies of univariate and multivariate genomic prediction models in African cassava.

PubMed

Okeke, Uche Godfrey; Akdemir, Deniz; Rabbi, Ismail; Kulakow, Peter; Jannink, Jean-Luc

2017-12-04

Genomic selection (GS) promises to accelerate genetic gain in plant breeding programs especially for crop species such as cassava that have long breeding cycles. Practically, to implement GS in cassava breeding, it is necessary to evaluate different GS models and to develop suitable models for an optimized breeding pipeline. In this paper, we compared (1) prediction accuracies from a single-trait (uT) and a multi-trait (MT) mixed model for a single-environment genetic evaluation (Scenario 1), and (2) accuracies from a compound symmetric multi-environment model (uE) parameterized as a univariate multi-kernel model to a multivariate (ME) multi-environment mixed model that accounts for genotype-by-environment interaction for multi-environment genetic evaluation (Scenario 2). For these analyses, we used 16 years of public cassava breeding data for six target cassava traits and a fivefold cross-validation scheme with 10-repeat cycles to assess model prediction accuracies. In Scenario 1, the MT models had higher prediction accuracies than the uT models for all traits and locations analyzed, which amounted to on average a 40% improved prediction accuracy. For Scenario 2, we observed that the ME model had on average (across all locations and traits) a 12% improved prediction accuracy compared to the uE model. We recommend the use of multivariate mixed models (MT and ME) for cassava genetic evaluation. These models may be useful for other plant species.

Refining Time-Activity Classification of Human Subjects Using the Global Positioning System

PubMed Central

Hu, Maogui; Li, Wei; Li, Lianfa; Houston, Douglas; Wu, Jun

2016-01-01

Background Detailed spatial location information is important in accurately estimating personal exposure to air pollution. Global Position System (GPS) has been widely used in tracking personal paths and activities. Previous researchers have developed time-activity classification models based on GPS data, most of them were developed for specific regions. An adaptive model for time-location classification can be widely applied to air pollution studies that use GPS to track individual level time-activity patterns. Methods Time-activity data were collected for seven days using GPS loggers and accelerometers from thirteen adult participants from Southern California under free living conditions. We developed an automated model based on random forests to classify major time-activity patterns (i.e. indoor, outdoor-static, outdoor-walking, and in-vehicle travel). Sensitivity analysis was conducted to examine the contribution of the accelerometer data and the supplemental spatial data (i.e. roadway and tax parcel data) to the accuracy of time-activity classification. Our model was evaluated using both leave-one-fold-out and leave-one-subject-out methods. Results Maximum speeds in averaging time intervals of 7 and 5 minutes, and distance to primary highways with limited access were found to be the three most important variables in the classification model. Leave-one-fold-out cross-validation showed an overall accuracy of 99.71%. Sensitivities varied from 84.62% (outdoor walking) to 99.90% (indoor). Specificities varied from 96.33% (indoor) to 99.98% (outdoor static). The exclusion of accelerometer and ambient light sensor variables caused a slight loss in sensitivity for outdoor walking, but little loss in overall accuracy. However, leave-one-subject-out cross-validation showed considerable loss in sensitivity for outdoor static and outdoor walking conditions. Conclusions The random forests classification model can achieve high accuracy for the four major time-activity categories. The model also performed well with just GPS, road and tax parcel data. However, caution is warranted when generalizing the model developed from a small number of subjects to other populations. PMID:26919723

Magnetic resonance spectroscopy and brain volumetry in mild cognitive impairment. A prospective study.

PubMed

Fayed, Nicolás; Modrego, Pedro J; García-Martí, Gracián; Sanz-Requena, Roberto; Marti-Bonmatí, Luis

2017-05-01

To assess the accuracy of magnetic resonance spectroscopy (1H-MRS) and brain volumetry in mild cognitive impairment (MCI) to predict conversion to probable Alzheimer's disease (AD). Forty-eight patients fulfilling the criteria of amnestic MCI who underwent a conventional magnetic resonance imaging (MRI) followed by MRS, and T1-3D on 1.5 Tesla MR unit. At baseline the patients underwent neuropsychological examination. 1H-MRS of the brain was carried out by exploring the left medial occipital lobe and ventral posterior cingulated cortex (vPCC) using the LCModel software. A high resolution T1-3D sequence was acquired to carry out the volumetric measurement. A cortical and subcortical parcellation strategy was used to obtain the volumes of each area within the brain. The patients were followed up to detect conversion to probable AD. After a 3-year follow-up, 15 (31.2%) patients converted to AD. The myo-inositol in the occipital cortex and glutamate+glutamine (Glx) in the posterior cingulate cortex predicted conversion to probable AD at 46.1% sensitivity and 90.6% specificity. The positive predictive value was 66.7%, and the negative predictive value was 80.6%, with an overall cross-validated classification accuracy of 77.8%. The volume of the third ventricle, the total white matter and entorhinal cortex predict conversion to probable AD at 46.7% sensitivity and 90.9% specificity. The positive predictive value was 70%, and the negative predictive value was 78.9%, with an overall cross-validated classification accuracy of 77.1%. Combining volumetric measures in addition to the MRS measures the prediction to probable AD has a 38.5% sensitivity and 87.5% specificity, with a positive predictive value of 55.6%, a negative predictive value of 77.8% and an overall accuracy of 73.3%. Either MRS or brain volumetric measures are markers separately of cognitive decline and may serve as a noninvasive tool to monitor cognitive changes and progression to dementia in patients with amnestic MCI, but the results do not support the routine use in the clinical settings. Copyright © 2016 Elsevier Inc. All rights reserved.

Accuracy assessment of high resolution satellite imagery orientation by leave-one-out method

NASA Astrophysics Data System (ADS)

Brovelli, Maria Antonia; Crespi, Mattia; Fratarcangeli, Francesca; Giannone, Francesca; Realini, Eugenio

Interest in high-resolution satellite imagery (HRSI) is spreading in several application fields, at both scientific and commercial levels. Fundamental and critical goals for the geometric use of this kind of imagery are their orientation and orthorectification, processes able to georeference the imagery and correct the geometric deformations they undergo during acquisition. In order to exploit the actual potentialities of orthorectified imagery in Geomatics applications, the definition of a methodology to assess the spatial accuracy achievable from oriented imagery is a crucial topic. In this paper we want to propose a new method for accuracy assessment based on the Leave-One-Out Cross-Validation (LOOCV), a model validation method already applied in different fields such as machine learning, bioinformatics and generally in any other field requiring an evaluation of the performance of a learning algorithm (e.g. in geostatistics), but never applied to HRSI orientation accuracy assessment. The proposed method exhibits interesting features which are able to overcome the most remarkable drawbacks involved by the commonly used method (Hold-Out Validation — HOV), based on the partitioning of the known ground points in two sets: the first is used in the orientation-orthorectification model (GCPs — Ground Control Points) and the second is used to validate the model itself (CPs — Check Points). In fact the HOV is generally not reliable and it is not applicable when a low number of ground points is available. To test the proposed method we implemented a new routine that performs the LOOCV in the software SISAR, developed by the Geodesy and Geomatics Team at the Sapienza University of Rome to perform the rigorous orientation of HRSI; this routine was tested on some EROS-A and QuickBird images. Moreover, these images were also oriented using the world recognized commercial software OrthoEngine v. 10 (included in the Geomatica suite by PCI), manually performing the LOOCV since only the HOV is implemented. The software comparison guaranteed about the overall correctness and good performances of the SISAR model, whereas the results showed the good features of the LOOCV method.

Benchmark of Machine Learning Methods for Classification of a SENTINEL-2 Image

NASA Astrophysics Data System (ADS)

Pirotti, F.; Sunar, F.; Piragnolo, M.

2016-06-01

Thanks to mainly ESA and USGS, a large bulk of free images of the Earth is readily available nowadays. One of the main goals of remote sensing is to label images according to a set of semantic categories, i.e. image classification. This is a very challenging issue since land cover of a specific class may present a large spatial and spectral variability and objects may appear at different scales and orientations. In this study, we report the results of benchmarking 9 machine learning algorithms tested for accuracy and speed in training and classification of land-cover classes in a Sentinel-2 dataset. The following machine learning methods (MLM) have been tested: linear discriminant analysis, k-nearest neighbour, random forests, support vector machines, multi layered perceptron, multi layered perceptron ensemble, ctree, boosting, logarithmic regression. The validation is carried out using a control dataset which consists of an independent classification in 11 land-cover classes of an area about 60 km2, obtained by manual visual interpretation of high resolution images (20 cm ground sampling distance) by experts. In this study five out of the eleven classes are used since the others have too few samples (pixels) for testing and validating subsets. The classes used are the following: (i) urban (ii) sowable areas (iii) water (iv) tree plantations (v) grasslands. Validation is carried out using three different approaches: (i) using pixels from the training dataset (train), (ii) using pixels from the training dataset and applying cross-validation with the k-fold method (kfold) and (iii) using all pixels from the control dataset. Five accuracy indices are calculated for the comparison between the values predicted with each model and control values over three sets of data: the training dataset (train), the whole control dataset (full) and with k-fold cross-validation (kfold) with ten folds. Results from validation of predictions of the whole dataset (full) show the random forests method with the highest values; kappa index ranging from 0.55 to 0.42 respectively with the most and least number pixels for training. The two neural networks (multi layered perceptron and its ensemble) and the support vector machines - with default radial basis function kernel - methods follow closely with comparable performance.

Improving diagnostic recognition of primary hyperparathyroidism with machine learning.

PubMed

Somnay, Yash R; Craven, Mark; McCoy, Kelly L; Carty, Sally E; Wang, Tracy S; Greenberg, Caprice C; Schneider, David F

2017-04-01

Parathyroidectomy offers the only cure for primary hyperparathyroidism, but today only 50% of primary hyperparathyroidism patients are referred for operation, in large part, because the condition is widely under-recognized. The diagnosis of primary hyperparathyroidism can be especially challenging with mild biochemical indices. Machine learning is a collection of methods in which computers build predictive algorithms based on labeled examples. With the aim of facilitating diagnosis, we tested the ability of machine learning to distinguish primary hyperparathyroidism from normal physiology using clinical and laboratory data. This retrospective cohort study used a labeled training set and 10-fold cross-validation to evaluate accuracy of the algorithm. Measures of accuracy included area under the receiver operating characteristic curve, precision (sensitivity), and positive and negative predictive value. Several different algorithms and ensembles of algorithms were tested using the Weka platform. Among 11,830 patients managed operatively at 3 high-volume endocrine surgery programs from March 2001 to August 2013, 6,777 underwent parathyroidectomy for confirmed primary hyperparathyroidism, and 5,053 control patients without primary hyperparathyroidism underwent thyroidectomy. Test-set accuracies for machine learning models were determined using 10-fold cross-validation. Age, sex, and serum levels of preoperative calcium, phosphate, parathyroid hormone, vitamin D, and creatinine were defined as potential predictors of primary hyperparathyroidism. Mild primary hyperparathyroidism was defined as primary hyperparathyroidism with normal preoperative calcium or parathyroid hormone levels. After testing a variety of machine learning algorithms, Bayesian network models proved most accurate, classifying correctly 95.2% of all primary hyperparathyroidism patients (area under receiver operating characteristic = 0.989). Omitting parathyroid hormone from the model did not decrease the accuracy significantly (area under receiver operating characteristic = 0.985). In mild disease cases, however, the Bayesian network model classified correctly 71.1% of patients with normal calcium and 92.1% with normal parathyroid hormone levels preoperatively. Bayesian networking and AdaBoost improved the accuracy of all parathyroid hormone patients to 97.2% cases (area under receiver operating characteristic = 0.994), and 91.9% of primary hyperparathyroidism patients with mild disease. This was significantly improved relative to Bayesian networking alone (P < .0001). Machine learning can diagnose accurately primary hyperparathyroidism without human input even in mild disease. Incorporation of this tool into electronic medical record systems may aid in recognition of this under-diagnosed disorder. Copyright © 2016 Elsevier Inc. All rights reserved.

Automated brain volumetrics in multiple sclerosis: a step closer to clinical application.

PubMed

Wang, C; Beadnall, H N; Hatton, S N; Bader, G; Tomic, D; Silva, D G; Barnett, M H

2016-07-01

Whole brain volume (WBV) estimates in patients with multiple sclerosis (MS) correlate more robustly with clinical disability than traditional, lesion-based metrics. Numerous algorithms to measure WBV have been developed over the past two decades. We compare Structural Image Evaluation using Normalisation of Atrophy-Cross-sectional (SIENAX) to NeuroQuant and MSmetrix, for assessment of cross-sectional WBV in patients with MS. MRIs from 61 patients with relapsing-remitting MS and 2 patients with clinically isolated syndrome were analysed. WBV measurements were calculated using SIENAX, NeuroQuant and MSmetrix. Statistical agreement between the methods was evaluated using linear regression and Bland-Altman plots. Precision and accuracy of WBV measurement was calculated for (1) NeuroQuant versus SIENAX and (2) MSmetrix versus SIENAX. Precision (Pearson's r) of WBV estimation for NeuroQuant and MSmetrix versus SIENAX was 0.983 and 0.992, respectively. Accuracy (Cb) was 0.871 and 0.994, respectively. NeuroQuant and MSmetrix showed a 5.5% and 1.0% volume difference compared with SIENAX, respectively, that was consistent across low and high values. In the analysed population, NeuroQuant and MSmetrix both quantified cross-sectional WBV with comparable statistical agreement to SIENAX, a well-validated cross-sectional tool that has been used extensively in MS clinical studies. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://www.bmj.com/company/products-services/rights-and-licensing/

An adaptive deep learning approach for PPG-based identification.

PubMed

Jindal, V; Birjandtalab, J; Pouyan, M Baran; Nourani, M

2016-08-01

Wearable biosensors have become increasingly popular in healthcare due to their capabilities for low cost and long term biosignal monitoring. This paper presents a novel two-stage technique to offer biometric identification using these biosensors through Deep Belief Networks and Restricted Boltzman Machines. Our identification approach improves robustness in current monitoring procedures within clinical, e-health and fitness environments using Photoplethysmography (PPG) signals through deep learning classification models. The approach is tested on TROIKA dataset using 10-fold cross validation and achieved an accuracy of 96.1%.

Vector splines on the sphere with application to the estimation of vorticity and divergence from discrete, noisy data

NASA Technical Reports Server (NTRS)

Wahba, G.

1982-01-01

Vector smoothing splines on the sphere are defined. Theoretical properties are briefly alluded to. The appropriate Hilbert space norms used in a specific meteorological application are described and justified via a duality theorem. Numerical procedures for computing the splines as well as the cross validation estimate of two smoothing parameters are given. A Monte Carlo study is described which suggests the accuracy with which upper air vorticity and divergence can be estimated using measured wind vectors from the North American radiosonde network.

Near-affine-invariant texture learning for lung tissue analysis using isotropic wavelet frames.

PubMed

Depeursinge, Adrien; Van de Ville, Dimitri; Platon, Alexandra; Geissbuhler, Antoine; Poletti, Pierre-Alexandre; Müller, Henning

2012-07-01

We propose near-affine-invariant texture descriptors derived from isotropic wavelet frames for the characterization of lung tissue patterns in high-resolution computed tomography (HRCT) imaging. Affine invariance is desirable to enable learning of nondeterministic textures without a priori localizations, orientations, or sizes. When combined with complementary gray-level histograms, the proposed method allows a global classification accuracy of 76.9% with balanced precision among five classes of lung tissue using a leave-one-patient-out cross validation, in accordance with clinical practice.

Batch Effect Confounding Leads to Strong Bias in Performance Estimates Obtained by Cross-Validation

PubMed Central

Delorenzi, Mauro

2014-01-01

Background With the large amount of biological data that is currently publicly available, many investigators combine multiple data sets to increase the sample size and potentially also the power of their analyses. However, technical differences (“batch effects”) as well as differences in sample composition between the data sets may significantly affect the ability to draw generalizable conclusions from such studies. Focus The current study focuses on the construction of classifiers, and the use of cross-validation to estimate their performance. In particular, we investigate the impact of batch effects and differences in sample composition between batches on the accuracy of the classification performance estimate obtained via cross-validation. The focus on estimation bias is a main difference compared to previous studies, which have mostly focused on the predictive performance and how it relates to the presence of batch effects. Data We work on simulated data sets. To have realistic intensity distributions, we use real gene expression data as the basis for our simulation. Random samples from this expression matrix are selected and assigned to group 1 (e.g., ‘control’) or group 2 (e.g., ‘treated’). We introduce batch effects and select some features to be differentially expressed between the two groups. We consider several scenarios for our study, most importantly different levels of confounding between groups and batch effects. Methods We focus on well-known classifiers: logistic regression, Support Vector Machines (SVM), k-nearest neighbors (kNN) and Random Forests (RF). Feature selection is performed with the Wilcoxon test or the lasso. Parameter tuning and feature selection, as well as the estimation of the prediction performance of each classifier, is performed within a nested cross-validation scheme. The estimated classification performance is then compared to what is obtained when applying the classifier to independent data. PMID:24967636

Assessing the accuracy and stability of variable selection ...

EPA Pesticide Factsheets

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 datasets 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 add/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 dataset 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 dataset. Two types of RF models are compared: a full variable set model with all 212 predictors, and a reduced variable set model selected using a backwards 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 substanti

In-lab versus at-home activity recognition in ambulatory subjects with incomplete spinal cord injury.

PubMed

Albert, Mark V; Azeze, Yohannes; Courtois, Michael; Jayaraman, Arun

2017-02-06

Although commercially available activity trackers can aid in tracking therapy and recovery of patients, most devices perform poorly for patients with irregular movement patterns. Standard machine learning techniques can be applied on recorded accelerometer signals in order to classify the activities of ambulatory subjects with incomplete spinal cord injury in a way that is specific to this population and the location of the recording-at home or in the clinic. Subjects were instructed to perform a standardized set of movements while wearing a waist-worn accelerometer in the clinic and at-home. Activities included lying, sitting, standing, walking, wheeling, and stair climbing. Multiple classifiers and validation methods were used to quantify the ability of the machine learning techniques to distinguish the activities recorded in-lab or at-home. In the lab, classifiers trained and tested using within-subject cross-validation provided an accuracy of 91.6%. When the classifier was trained on data collected in the lab but tested on at home data, the accuracy fell to 54.6% indicating distinct movement patterns between locations. However, the accuracy of the at-home classifications, when training the classifier with at-home data, improved to 85.9%. Individuals with unique movement patterns can benefit from using tailored activity recognition algorithms easily implemented using modern machine learning methods on collected movement data.

Dynamic vehicle-track interaction in switches and crossings and the influence of rail pad stiffness - field measurements and validation of a simulation model

NASA Astrophysics Data System (ADS)

Pålsson, Björn A.; Nielsen, Jens C. O.

2015-06-01

A model for simulation of dynamic interaction between a railway vehicle and a turnout (switch and crossing, S&C) is validated versus field measurements. In particular, the implementation and accuracy of viscously damped track models with different complexities are assessed. The validation data come from full-scale field measurements of dynamic track stiffness and wheel-rail contact forces in a demonstrator turnout that was installed as part of the INNOTRACK project with funding from the European Union Sixth Framework Programme. Vertical track stiffness at nominal wheel loads, in the frequency range up to 20 Hz, was measured using a rolling stiffness measurement vehicle (RSMV). Vertical and lateral wheel-rail contact forces were measured by an instrumented wheel set mounted in a freight car featuring Y25 bogies. The measurements were performed for traffic in both the through and diverging routes, and in the facing and trailing moves. The full set of test runs was repeated with different types of rail pad to investigate the influence of rail pad stiffness on track stiffness and contact forces. It is concluded that impact loads on the crossing can be reduced by using more resilient rail pads. To allow for vehicle dynamics simulations at low computational cost, the track models are discretised space-variant mass-spring-damper models that are moving with each wheel set of the vehicle model. Acceptable agreement between simulated and measured vertical contact forces at the crossing can be obtained when the standard GENSYS track model is extended with one ballast/subgrade mass under each rail. This model can be tuned to capture the large phase delay in dynamic track stiffness at low frequencies, as measured by the RSMV, while remaining sufficiently resilient at higher frequencies.

New public QSAR model for carcinogenicity

PubMed Central

2010-01-01

Background One of the main goals of the new chemical regulation REACH (Registration, Evaluation and Authorization of Chemicals) is to fulfill the gaps in data concerned with properties of chemicals affecting the human health. (Q)SAR models are accepted as a suitable source of information. The EU funded CAESAR project aimed to develop models for prediction of 5 endpoints for regulatory purposes. Carcinogenicity is one of the endpoints under consideration. Results Models for prediction of carcinogenic potency according to specific requirements of Chemical regulation were developed. The dataset of 805 non-congeneric chemicals extracted from Carcinogenic Potency Database (CPDBAS) was used. Counter Propagation Artificial Neural Network (CP ANN) algorithm was implemented. In the article two alternative models for prediction carcinogenicity are described. The first model employed eight MDL descriptors (model A) and the second one twelve Dragon descriptors (model B). CAESAR's models have been assessed according to the OECD principles for the validation of QSAR. For the model validity we used a wide series of statistical checks. Models A and B yielded accuracy of training set (644 compounds) equal to 91% and 89% correspondingly; the accuracy of the test set (161 compounds) was 73% and 69%, while the specificity was 69% and 61%, respectively. Sensitivity in both cases was equal to 75%. The accuracy of the leave 20% out cross validation for the training set of models A and B was equal to 66% and 62% respectively. To verify if the models perform correctly on new compounds the external validation was carried out. The external test set was composed of 738 compounds. We obtained accuracy of external validation equal to 61.4% and 60.0%, sensitivity 64.0% and 61.8% and specificity equal to 58.9% and 58.4% respectively for models A and B. Conclusion Carcinogenicity is a particularly important endpoint and it is expected that QSAR models will not replace the human experts opinions and conventional methods. However, we believe that combination of several methods will provide useful support to the overall evaluation of carcinogenicity. In present paper models for classification of carcinogenic compounds using MDL and Dragon descriptors were developed. Models could be used to set priorities among chemicals for further testing. The models at the CAESAR site were implemented in java and are publicly accessible. PMID:20678182

Approaches to maximising the accuracy of anthropometric data on children: review and empirical evaluation using the Australian Longitudinal Study of Indigenous Children.

PubMed

Thurber, Katherine A; Banks, Emily; Banwell, Cathy

2014-11-28

Despite the burgeoning research interest in weight status, in parallel with the increase in obesity worldwide, research describing methods to optimise the validity and accuracy of measured anthropometric data is lacking. Even when 'gold standard' methods are employed, no data are 100% accurate, yet the accuracy of anthropometric data is critical to produce robust and interpretable findings. To date, described methods for identifying data that are likely to be inaccurate seem to be ad hoc or lacking in clear justification. This paper reviews approaches to evaluating the accuracy of cross-sectional and longitudinal data on height and weight in children, focusing on recommendations from the World Health Organization (WHO). This review, together with expert consultation, informed the development of a method for processing and verifying longitudinal anthropometric measurements of children. This approach was then applied to data from the Australian Longitudinal Study of Indigenous Children. The review identified the need to assess the likely plausibility of data by (a) examining deviation from the WHO reference population by calculating age- and sex-adjusted height, weight and body mass index z-scores, and (b) examining changes in height and weight in individuals over time. The method developed identified extreme measurements and implausible intraindividual trajectories. It provides evidence-based criteria for the exclusion of data points that are most likely to be affected by measurement error. This paper presents a probabilistic approach to identifying anthropometric measurements that are likely to be implausible. This systematic, practical method is intended to be reproducible in other settings, including for validating large databases.

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.

Diagnostic validation of three test methods for detection of cyprinid herpesvirus 3 (CyHV-3).

PubMed

Clouthier, Sharon C; McClure, Carol; Schroeder, Tamara; Desai, Megan; Hawley, Laura; Khatkar, Sunita; Lindsay, Melissa; Lowe, Geoff; Richard, Jon; Anderson, Eric D

2017-03-06

Cyprinid herpesvirus 3 (CyHV-3) is the aetiological agent of koi herpesvirus disease in koi and common carp. The disease is notifiable to the World Organisation for Animal Health. Three tests-quantitative polymerase chain reaction (qPCR), conventional PCR (cPCR) and virus isolation by cell culture (VI)-were validated to assess their fitness as diagnostic tools for detection of CyHV-3. Test performance metrics of diagnostic accuracy were sensitivity (DSe) and specificity (DSp). Repeatability and reproducibility were measured to assess diagnostic precision. Estimates of test accuracy, in the absence of a gold standard reference test, were generated using latent class models. Test samples originated from wild common carp naturally exposed to CyHV-3 or domesticated koi either virus free or experimentally infected with the virus. Three laboratories in Canada participated in the precision study. Moderate to high repeatability (81 to 99%) and reproducibility (72 to 97%) were observed for the qPCR and cPCR tests. The lack of agreement observed between some of the PCR test pair results was attributed to cross-contamination of samples with CyHV-3 nucleic acid. Accuracy estimates for the PCR tests were 99% for DSe and 93% for DSp. Poor precision was observed for the VI test (4 to 95%). Accuracy estimates for VI/qPCR were 90% for DSe and 88% for DSp. Collectively, the results show that the CyHV-3 qPCR test is a suitable tool for surveillance, presumptive diagnosis and certification of individuals or populations as CyHV-3 free.

Identification of Long Bone Fractures in Radiology Reports Using Natural Language Processing to support Healthcare Quality Improvement.

PubMed

Grundmeier, Robert W; Masino, Aaron J; Casper, T Charles; Dean, Jonathan M; Bell, Jamie; Enriquez, Rene; Deakyne, Sara; Chamberlain, James M; Alpern, Elizabeth R

2016-11-09

Important information to support healthcare quality improvement is often recorded in free text documents such as radiology reports. Natural language processing (NLP) methods may help extract this information, but these methods have rarely been applied outside the research laboratories where they were developed. To implement and validate NLP tools to identify long bone fractures for pediatric emergency medicine quality improvement. Using freely available statistical software packages, we implemented NLP methods to identify long bone fractures from radiology reports. A sample of 1,000 radiology reports was used to construct three candidate classification models. A test set of 500 reports was used to validate the model performance. Blinded manual review of radiology reports by two independent physicians provided the reference standard. Each radiology report was segmented and word stem and bigram features were constructed. Common English "stop words" and rare features were excluded. We used 10-fold cross-validation to select optimal configuration parameters for each model. Accuracy, recall, precision and the F1 score were calculated. The final model was compared to the use of diagnosis codes for the identification of patients with long bone fractures. There were 329 unique word stems and 344 bigrams in the training documents. A support vector machine classifier with Gaussian kernel performed best on the test set with accuracy=0.958, recall=0.969, precision=0.940, and F1 score=0.954. Optimal parameters for this model were cost=4 and gamma=0.005. The three classification models that we tested all performed better than diagnosis codes in terms of accuracy, precision, and F1 score (diagnosis code accuracy=0.932, recall=0.960, precision=0.896, and F1 score=0.927). NLP methods using a corpus of 1,000 training documents accurately identified acute long bone fractures from radiology reports. Strategic use of straightforward NLP methods, implemented with freely available software, offers quality improvement teams new opportunities to extract information from narrative documents.

Stroke Risk Stratification and its Validation using Ultrasonic Echolucent Carotid Wall Plaque Morphology: A Machine Learning Paradigm.

PubMed

Araki, Tadashi; Jain, Pankaj K; Suri, Harman S; Londhe, Narendra D; Ikeda, Nobutaka; El-Baz, Ayman; Shrivastava, Vimal K; Saba, Luca; Nicolaides, Andrew; Shafique, Shoaib; Laird, John R; Gupta, Ajay; Suri, Jasjit S

2017-01-01

Stroke risk stratification based on grayscale morphology of the ultrasound carotid wall has recently been shown to have a promise in classification of high risk versus low risk plaque or symptomatic versus asymptomatic plaques. In previous studies, this stratification has been mainly based on analysis of the far wall of the carotid artery. Due to the multifocal nature of atherosclerotic disease, the plaque growth is not restricted to the far wall alone. This paper presents a new approach for stroke risk assessment by integrating assessment of both the near and far walls of the carotid artery using grayscale morphology of the plaque. Further, this paper presents a scientific validation system for stroke risk assessment. Both these innovations have never been presented before. The methodology consists of an automated segmentation system of the near wall and far wall regions in grayscale carotid B-mode ultrasound scans. Sixteen grayscale texture features are computed, and fed into the machine learning system. The training system utilizes the lumen diameter to create ground truth labels for the stratification of stroke risk. The cross-validation procedure is adapted in order to obtain the machine learning testing classification accuracy through the use of three sets of partition protocols: (5, 10, and Jack Knife). The mean classification accuracy over all the sets of partition protocols for the automated system in the far and near walls is 95.08% and 93.47%, respectively. The corresponding accuracies for the manual system are 94.06% and 92.02%, respectively. The precision of merit of the automated machine learning system when compared against manual risk assessment system are 98.05% and 97.53% for the far and near walls, respectively. The ROC of the risk assessment system for the far and near walls is close to 1.0 demonstrating high accuracy. Copyright © 2016 Elsevier Ltd. All rights reserved.

Differential privacy-based evaporative cooling feature selection and classification with relief-F and random forests.

PubMed

Le, Trang T; Simmons, W Kyle; Misaki, Masaya; Bodurka, Jerzy; White, Bill C; Savitz, Jonathan; McKinney, Brett A

2017-09-15

Classification of individuals into disease or clinical categories from high-dimensional biological data with low prediction error is an important challenge of statistical learning in bioinformatics. Feature selection can improve classification accuracy but must be incorporated carefully into cross-validation to avoid overfitting. Recently, feature selection methods based on differential privacy, such as differentially private random forests and reusable holdout sets, have been proposed. However, for domains such as bioinformatics, where the number of features is much larger than the number of observations p≫n , these differential privacy methods are susceptible to overfitting. We introduce private Evaporative Cooling, a stochastic privacy-preserving machine learning algorithm that uses Relief-F for feature selection and random forest for privacy preserving classification that also prevents overfitting. We relate the privacy-preserving threshold mechanism to a thermodynamic Maxwell-Boltzmann distribution, where the temperature represents the privacy threshold. We use the thermal statistical physics concept of Evaporative Cooling of atomic gases to perform backward stepwise privacy-preserving feature selection. On simulated data with main effects and statistical interactions, we compare accuracies on holdout and validation sets for three privacy-preserving methods: the reusable holdout, reusable holdout with random forest, and private Evaporative Cooling, which uses Relief-F feature selection and random forest classification. In simulations where interactions exist between attributes, private Evaporative Cooling provides higher classification accuracy without overfitting based on an independent validation set. In simulations without interactions, thresholdout with random forest and private Evaporative Cooling give comparable accuracies. We also apply these privacy methods to human brain resting-state fMRI data from a study of major depressive disorder. Code available at http://insilico.utulsa.edu/software/privateEC . brett-mckinney@utulsa.edu. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Temporal regularization of ultrasound-based liver motion estimation for image-guided radiation therapy

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

O’Shea, Tuathan P., E-mail: tuathan.oshea@icr.ac.uk; Bamber, Jeffrey C.; Harris, Emma J.

Purpose: Ultrasound-based motion estimation is an expanding subfield of image-guided radiation therapy. Although ultrasound can detect tissue motion that is a fraction of a millimeter, its accuracy is variable. For controlling linear accelerator tracking and gating, ultrasound motion estimates must remain highly accurate throughout the imaging sequence. This study presents a temporal regularization method for correlation-based template matching which aims to improve the accuracy of motion estimates. Methods: Liver ultrasound sequences (15–23 Hz imaging rate, 2.5–5.5 min length) from ten healthy volunteers under free breathing were used. Anatomical features (blood vessels) in each sequence were manually annotated for comparison withmore » normalized cross-correlation based template matching. Five sequences from a Siemens Acuson™ scanner were used for algorithm development (training set). Results from incremental tracking (IT) were compared with a temporal regularization method, which included a highly specific similarity metric and state observer, known as the α–β filter/similarity threshold (ABST). A further five sequences from an Elekta Clarity™ system were used for validation, without alteration of the tracking algorithm (validation set). Results: Overall, the ABST method produced marked improvements in vessel tracking accuracy. For the training set, the mean and 95th percentile (95%) errors (defined as the difference from manual annotations) were 1.6 and 1.4 mm, respectively (compared to 6.2 and 9.1 mm, respectively, for IT). For each sequence, the use of the state observer leads to improvement in the 95% error. For the validation set, the mean and 95% errors for the ABST method were 0.8 and 1.5 mm, respectively. Conclusions: Ultrasound-based motion estimation has potential to monitor liver translation over long time periods with high accuracy. Nonrigid motion (strain) and the quality of the ultrasound data are likely to have an impact on tracking performance. A future study will investigate spatial uniformity of motion and its effect on the motion estimation errors.« less

Quantifying Vocal Mimicry in the Greater Racket-Tailed Drongo: A Comparison of Automated Methods and Human Assessment

PubMed Central

Agnihotri, Samira; Sundeep, P. V. D. S.; Seelamantula, Chandra Sekhar; Balakrishnan, Rohini

2014-01-01

Objective identification and description of mimicked calls is a primary component of any study on avian vocal mimicry but few studies have adopted a quantitative approach. We used spectral feature representations commonly used in human speech analysis in combination with various distance metrics to distinguish between mimicked and non-mimicked calls of the greater racket-tailed drongo, Dicrurus paradiseus and cross-validated the results with human assessment of spectral similarity. We found that the automated method and human subjects performed similarly in terms of the overall number of correct matches of mimicked calls to putative model calls. However, the two methods also misclassified different subsets of calls and we achieved a maximum accuracy of ninety five per cent only when we combined the results of both the methods. This study is the first to use Mel-frequency Cepstral Coefficients and Relative Spectral Amplitude - filtered Linear Predictive Coding coefficients to quantify vocal mimicry. Our findings also suggest that in spite of several advances in automated methods of song analysis, corresponding cross-validation by humans remains essential. PMID:24603717

Cross-validation of a Shortened Battery for the Assessment of Dysexecutive Disorders in Alzheimer Disease.

PubMed

Godefroy, Olivier; Martinaud, Olivier; Verny, Marc; Mosca, Chrystèle; Lenoir, Hermine; Bretault, Eric; Devendeville, Agnès; Diouf, Momar; Pere, Jean-Jacques; Bakchine, Serge; Delabrousse-Mayoux, Jean-Philippe; Roussel, Martine

2016-01-01

The frequency of executive disorders in mild-to-moderate Alzheimer disease (AD) has been demonstrated by the application of a comprehensive battery. The present study analyzed data from 2 recent multicenter studies based on the same executive battery. The objective was to derive a shortened battery by using the GREFEX population as a training dataset and by cross-validating the results in the REFLEX population. A total of 102 AD patients of the GREFEX study (MMSE=23.2±2.9) and 72 patients of the REFLEX study (MMSE=20.8±3.5) were included. Tests were selected and receiver operating characteristic curves were generated relative to the performance of 780 controls from the GREFEX study. Stepwise logistic regression identified 3 cognitive tests (Six Elements Task, categorical fluency and Trail Making Test B error) and behavioral disorders globally referred as global hypoactivity (P=0.0001, all). This shortened battery was as accurate as the entire GREFEX battery in diagnosing dysexecutive disorders in both training group and the validation group. Bootstrap procedure confirmed the stability of AUC. A shortened battery based on 3 cognitive tests and 3 behavioral domains provides a high diagnosis accuracy of executive disorders in mild-to-moderate AD.

A Computational Model for Predicting RNase H Domain of Retrovirus.

PubMed

Wu, Sijia; Zhang, Xinman; Han, Jiuqiang

2016-01-01

RNase H (RNH) is a pivotal domain in retrovirus to cleave the DNA-RNA hybrid for continuing retroviral replication. The crucial role indicates that RNH is a promising drug target for therapeutic intervention. However, annotated RNHs in UniProtKB database have still been insufficient for a good understanding of their statistical characteristics so far. In this work, a computational RNH model was proposed to annotate new putative RNHs (np-RNHs) in the retroviruses. It basically predicts RNH domains through recognizing their start and end sites separately with SVM method. The classification accuracy rates are 100%, 99.01% and 97.52% respectively corresponding to jack-knife, 10-fold cross-validation and 5-fold cross-validation test. Subsequently, this model discovered 14,033 np-RNHs after scanning sequences without RNH annotations. All these predicted np-RNHs and annotated RNHs were employed to analyze the length, hydrophobicity and evolutionary relationship of RNH domains. They are all related to retroviral genera, which validates the classification of retroviruses to a certain degree. In the end, a software tool was designed for the application of our prediction model. The software together with datasets involved in this paper can be available for free download at https://sourceforge.net/projects/rhtool/files/?source=navbar.

Earth Science Enterprise Scientific Data Purchase Project: Verification and Validation

NASA Technical Reports Server (NTRS)

Jenner, Jeff; Policelli, Fritz; Fletcher, Rosea; Holecamp, Kara; Owen, Carolyn; Nicholson, Lamar; Dartez, Deanna

2000-01-01

This paper presents viewgraphs on the Earth Science Enterprise Scientific Data Purchase Project's verification,and validation process. The topics include: 1) What is Verification and Validation? 2) Why Verification and Validation? 3) Background; 4) ESE Data Purchas Validation Process; 5) Data Validation System and Ingest Queue; 6) Shipment Verification; 7) Tracking and Metrics; 8) Validation of Contract Specifications; 9) Earth Watch Data Validation; 10) Validation of Vertical Accuracy; and 11) Results of Vertical Accuracy Assessment.

Compressive Sensing with Cross-Validation and Stop-Sampling for Sparse Polynomial Chaos Expansions

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

Huan, Xun; Safta, Cosmin; Sargsyan, Khachik

Compressive sensing is a powerful technique for recovering sparse solutions of underdetermined linear systems, which is often encountered in uncertainty quanti cation analysis of expensive and high-dimensional physical models. We perform numerical investigations employing several com- pressive sensing solvers that target the unconstrained LASSO formulation, with a focus on linear systems that arise in the construction of polynomial chaos expansions. With core solvers of l1 ls, SpaRSA, CGIST, FPC AS, and ADMM, we develop techniques to mitigate over tting through an automated selection of regularization constant based on cross-validation, and a heuristic strategy to guide the stop-sampling decision. Practical recommendationsmore » on parameter settings for these tech- niques are provided and discussed. The overall method is applied to a series of numerical examples of increasing complexity, including large eddy simulations of supersonic turbulent jet-in-cross flow involving a 24-dimensional input. Through empirical phase-transition diagrams and convergence plots, we illustrate sparse recovery performance under structures induced by polynomial chaos, accuracy and computational tradeoffs between polynomial bases of different degrees, and practi- cability of conducting compressive sensing for a realistic, high-dimensional physical application. Across test cases studied in this paper, we find ADMM to have demonstrated empirical advantages through consistent lower errors and faster computational times.« less

Enzyme-linked immunosorbent assay (ELISA) for the detection of use of the synthetic cannabinoid agonists UR-144 and XLR-11 in human urine.

PubMed

Mohr, Amanda L A; Ofsa, Bill; Keil, Alyssa Marie; Simon, John R; McMullin, Matthew; Logan, Barry K

2014-09-01

Ongoing changes in the synthetic cannabinoid drug market create the need for relevant targeted immunoassays for rapid screening of biological samples. We describe the validation and performance characteristics of an enzyme-linked immunosorbent assay designed to detect use of one of the most prevalent synthetic cannabinoids in urine, UR-144, by targeting its pentanoic acid metabolite. Fluorinated UR-144 (XLR-11) has been demonstrated to metabolize to this common product. The assay has significant cross-reactivity with UR-144-5-OH, UR-144-4-OH and XLR-11-4-OH metabolites, but <10% cross-reactivity with the parent compounds, and no measurable cross-reactivity with other synthetic cannabinoids and their metabolites at concentrations of <1,000 ng/mL. The assay's cutoff is 5 ng/mL relative to the pentanoic acid metabolite of UR-144, which is used as the calibrator. The method was validated with 90 positive and negative control urine samples for UR-144, XLR-11 and its metabolites tested versus liquid chromatography-tandem mass spectrometry. The accuracy, sensitivity and specificity were determined to be 100% for the assay at the specified cutoff. © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

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.

Combining accuracy assessment of land-cover maps with environmental monitoring programs

Treesearch

Stephen V. Stehman; Raymond L. Czaplewski; Sarah M. Nusser; Limin Yang; Zhiliang Zhu

2000-01-01

A scientifically valid accuracy assessment of a large-area, land-cover map is expensive. Environmental monitoring programs offer a potential source of data to partially defray the cost of accuracy assessment while still maintaining the statistical validity. In this article, three general strategies for combining accuracy assessment and environmental monitoring...

Multivariate methods on the excitation emission matrix fluorescence spectroscopic data of diesel-kerosene mixtures: a comparative study.

PubMed

Divya, O; Mishra, Ashok K

2007-05-29

Quantitative determination of kerosene fraction present in diesel has been carried out based on excitation emission matrix fluorescence (EEMF) along with parallel factor analysis (PARAFAC) and N-way partial least squares regression (N-PLS). EEMF is a simple, sensitive and nondestructive method suitable for the analysis of multifluorophoric mixtures. Calibration models consisting of varying compositions of diesel and kerosene were constructed and their validation was carried out using leave-one-out cross validation method. The accuracy of the model was evaluated through the root mean square error of prediction (RMSEP) for the PARAFAC, N-PLS and unfold PLS methods. N-PLS was found to be a better method compared to PARAFAC and unfold PLS method because of its low RMSEP values.

[Validity and reliability of the Culture of Quality Health Services questionnaire in Mexico].

PubMed

Herrera-Kiengelher, L; Zepeda-Zaragoza, J; Austria-Corrales, F; Vázquez-Zarate, V M

2013-01-01

Patient Safety is a major public health problem worldwide and is responsibility of all those involved in health care. Establishing a Safety Culture has proved to be a factor that favors the integration of work teams, communication and construction of clear procedures in various organizations. Promote a culture of safety depends on several factors, such as organization, work unit and staff. Objective assessment of these factors will help to identify areas for improvement and establish strategic lines of action. [corrected] To adapt, validate and calibrate the questionnaire Culture of Quality in Health Services (CQHS) in Mexican population. A cross with a stratified representative sample of 522 health workers. The questionnaire was translated and adapted from Singer's. Content was validated by experts, internal consistency, confirmatory factorial validity and item calibration with Samejima's Graded Response Model. Convergent and divergent construct validity was confirmed from the CQHS, item calibration showed that the questionnaire is able to discriminate between patients and represent different levels of the hypothesized dimensions with greater accuracy and lower standard error. The CQHS is a valid and reliable instrument to assess patient safety culture in hospitals in Mexico. Copyright © 2013 SECA. Published by Elsevier Espana. All rights reserved.

Minimal ensemble based on subset selection using ECG to diagnose categories of CAN.

PubMed

Abawajy, Jemal; Kelarev, Andrei; Yi, Xun; Jelinek, Herbert F

2018-07-01

Early diagnosis of cardiac autonomic neuropathy (CAN) is critical for reversing or decreasing its progression and prevent complications. Diagnostic accuracy or precision is one of the core requirements of CAN detection. As the standard Ewing battery tests suffer from a number of shortcomings, research in automating and improving the early detection of CAN has recently received serious attention in identifying additional clinical variables and designing advanced ensembles of classifiers to improve the accuracy or precision of CAN diagnostics. Although large ensembles are commonly proposed for the automated diagnosis of CAN, large ensembles are characterized by slow processing speed and computational complexity. This paper applies ECG features and proposes a new ensemble-based approach for diagnosis of CAN progression. We introduce a Minimal Ensemble Based On Subset Selection (MEBOSS) for the diagnosis of all categories of CAN including early, definite and atypical CAN. MEBOSS is based on a novel multi-tier architecture applying classifier subset selection as well as the training subset selection during several steps of its operation. Our experiments determined the diagnostic accuracy or precision obtained in 5 × 2 cross-validation for various options employed in MEBOSS and other classification systems. The experiments demonstrate the operation of the MEBOSS procedure invoking the most effective classifiers available in the open source software environment SageMath. The results of our experiments show that for the large DiabHealth database of CAN related parameters MEBOSS outperformed other classification systems available in SageMath and achieved 94% to 97% precision in 5 × 2 cross-validation correctly distinguishing any two CAN categories to a maximum of five categorizations including control, early, definite, severe and atypical CAN. These results show that MEBOSS architecture is effective and can be recommended for practical implementations in systems for the diagnosis of CAN progression. Copyright © 2018 Elsevier B.V. All rights reserved.

Use of Neuroanatomical Pattern Classification to Identify Subjects in At-Risk Mental States of Psychosis and Predict Disease Transition

PubMed Central

Koutsouleris, Nikolaos; Meisenzahl, Eva M.; Davatzikos, Christos; Bottlender, Ronald; Frodl, Thomas; Scheuerecker, Johanna; Schmitt, Gisela; Zetzsche, Thomas; Decker, Petra; Reiser, Maximilian; Möller, Hans-Jürgen; Gaser, Christian

2014-01-01

Context Identification of individuals at high risk of developing psychosis has relied on prodromal symptomatology. Recently, machine learning algorithms have been successfully used for magnetic resonance imaging–based diagnostic classification of neuropsychiatric patient populations. Objective To determine whether multivariate neuroanatomical pattern classification facilitates identification of individuals in different at-risk mental states (ARMS) of psychosis and enables the prediction of disease transition at the individual level. Design Multivariate neuroanatomical pattern classification was performed on the structural magnetic resonance imaging data of individuals in early or late ARMS vs healthy controls (HCs). The predictive power of the method was then evaluated by categorizing the baseline imaging data of individuals with transition to psychosis vs those without transition vs HCs after 4 years of clinical follow-up. Classification generalizability was estimated by cross-validation and by categorizing an independent cohort of 45 new HCs. Setting Departments of Psychiatry and Psychotherapy, Ludwig-Maximilians-University, Munich, Germany. Participants The first classification analysis included 20 early and 25 late at-risk individuals and 25 matched HCs. The second analysis consisted of 15 individuals with transition, 18 without transition, and 17 matched HCs. Main Outcome Measures Specificity, sensitivity, and accuracy of classification. Results The 3-group, cross-validated classification accuracies of the first analysis were 86% (HCs vs the rest), 91% (early at-risk individuals vs the rest), and 86% (late at-risk individuals vs the rest). The accuracies in the second analysis were 90% (HCs vs the rest), 88% (individuals with transition vs the rest), and 86% (individuals without transition vs the rest). Independent HCs were correctly classified in 96% (first analysis) and 93% (second analysis) of cases. Conclusions Different ARMSs and their clinical outcomes may be reliably identified on an individual basis by assessing patterns of whole-brain neuroanatomical abnormalities. These patterns may serve as valuable biomarkers for the clinician to guide early detection in the prodromal phase of psychosis. PMID:19581561

SU-F-R-22: Malignancy Classification for Small Pulmonary Nodules with Radiomics and Logistic Regression

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

Huang, W; Tu, S

Purpose: We conducted a retrospective study of Radiomics research for classifying malignancy of small pulmonary nodules. A machine learning algorithm of logistic regression and open research platform of Radiomics, IBEX (Imaging Biomarker Explorer), were used to evaluate the classification accuracy. Methods: The training set included 100 CT image series from cancer patients with small pulmonary nodules where the average diameter is 1.10 cm. These patients registered at Chang Gung Memorial Hospital and received a CT-guided operation of lung cancer lobectomy. The specimens were classified by experienced pathologists with a B (benign) or M (malignant). CT images with slice thickness ofmore » 0.625 mm were acquired from a GE BrightSpeed 16 scanner. The study was formally approved by our institutional internal review board. Nodules were delineated and 374 feature parameters were extracted from IBEX. We first used the t-test and p-value criteria to study which feature can differentiate between group B and M. Then we implemented a logistic regression algorithm to perform nodule malignancy classification. 10-fold cross-validation and the receiver operating characteristic curve (ROC) were used to evaluate the classification accuracy. Finally hierarchical clustering analysis, Spearman rank correlation coefficient, and clustering heat map were used to further study correlation characteristics among different features. Results: 238 features were found differentiable between group B and M based on whether their statistical p-values were less than 0.05. A forward search algorithm was used to select an optimal combination of features for the best classification and 9 features were identified. Our study found the best accuracy of classifying malignancy was 0.79±0.01 with the 10-fold cross-validation. The area under the ROC curve was 0.81±0.02. Conclusion: Benign nodules may be treated as a malignant tumor in low-dose CT and patients may undergo unnecessary surgeries or treatments. Our study may help radiologists to differentiate nodule malignancy for low-dose CT.« less

BME Estimation of Residential Exposure to Ambient PM10 and Ozone at Multiple Time Scales

PubMed Central

Yu, Hwa-Lung; Chen, Jiu-Chiuan; Christakos, George; Jerrett, Michael

2009-01-01

Background Long-term human exposure to ambient pollutants can be an important contributing or etiologic factor of many chronic diseases. Spatiotemporal estimation (mapping) of long-term exposure at residential areas based on field observations recorded in the U.S. Environmental Protection Agency’s Air Quality System often suffer from missing data issues due to the scarce monitoring network across space and the inconsistent recording periods at different monitors. Objective We developed and compared two upscaling methods: UM1 (data aggregation followed by exposure estimation) and UM2 (exposure estimation followed by data aggregation) for the long-term PM10 (particulate matter with aerodynamic diameter ≤ 10 μm) and ozone exposure estimations and applied them in multiple time scales to estimate PM and ozone exposures for the residential areas of the Health Effects of Air Pollution on Lupus (HEAPL) study. Method We used Bayesian maximum entropy (BME) analysis for the two upscaling methods. We performed spatiotemporal cross-validations at multiple time scales by UM1 and UM2 to assess the estimation accuracy across space and time. Results Compared with the kriging method, the integration of soft information by the BME method can effectively increase the estimation accuracy for both pollutants. The spatiotemporal distributions of estimation errors from UM1 and UM2 were similar. The cross-validation results indicated that UM2 is generally better than UM1 in exposure estimations at multiple time scales in terms of predictive accuracy and lack of bias. For yearly PM10 estimations, both approaches have comparable performance, but the implementation of UM1 is associated with much lower computation burden. Conclusion BME-based upscaling methods UM1 and UM2 can assimilate core and site-specific knowledge bases of different formats for long-term exposure estimation. This study shows that UM1 can perform reasonably well when the aggregation process does not alter the spatiotemporal structure of the original data set; otherwise, UM2 is preferable. PMID:19440491

Deep facial analysis: A new phase I epilepsy evaluation using computer vision.

PubMed

Ahmedt-Aristizabal, David; Fookes, Clinton; Nguyen, Kien; Denman, Simon; Sridharan, Sridha; Dionisio, Sasha

2018-05-01

Semiology observation and characterization play a major role in the presurgical evaluation of epilepsy. However, the interpretation of patient movements has subjective and intrinsic challenges. In this paper, we develop approaches to attempt to automatically extract and classify semiological patterns from facial expressions. We address limitations of existing computer-based analytical approaches of epilepsy monitoring, where facial movements have largely been ignored. This is an area that has seen limited advances in the literature. Inspired by recent advances in deep learning, we propose two deep learning models, landmark-based and region-based, to quantitatively identify changes in facial semiology in patients with mesial temporal lobe epilepsy (MTLE) from spontaneous expressions during phase I monitoring. A dataset has been collected from the Mater Advanced Epilepsy Unit (Brisbane, Australia) and is used to evaluate our proposed approach. Our experiments show that a landmark-based approach achieves promising results in analyzing facial semiology, where movements can be effectively marked and tracked when there is a frontal face on visualization. However, the region-based counterpart with spatiotemporal features achieves more accurate results when confronted with extreme head positions. A multifold cross-validation of the region-based approach exhibited an average test accuracy of 95.19% and an average AUC of 0.98 of the ROC curve. Conversely, a leave-one-subject-out cross-validation scheme for the same approach reveals a reduction in accuracy for the model as it is affected by data limitations and achieves an average test accuracy of 50.85%. Overall, the proposed deep learning models have shown promise in quantifying ictal facial movements in patients with MTLE. In turn, this may serve to enhance the automated presurgical epilepsy evaluation by allowing for standardization, mitigating bias, and assessing key features. The computer-aided diagnosis may help to support clinical decision-making and prevent erroneous localization and surgery. Copyright © 2018 Elsevier Inc. 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

Fourth-grade children’s dietary reporting accuracy by meal component: Results from a validation study that manipulated retention interval and prompts

PubMed Central

Baxter, Suzanne D.; Hitchcock, David B.; Royer, Julie A.; Smith, Albert F.; Guinn, Caroline H.

2017-01-01

We examined reporting accuracy by meal component (beverage, bread, breakfast meat, combination entrée, condiment, dessert, entrée, fruit, vegetable) with validation-study data on 455 fourth-grade children (mean age = 9.92 ± 0.41 years) observed eating school meals and randomized to one of eight dietary recall conditions (two retention intervals [short, long] crossed with four prompts [forward, meal-name, open, reverse]). Accuracy category (match [observed and reported], omission [observed but unreported], intrusion [unobserved but reported]) was a polytomous nominal item response variable. We fit a multilevel cumulative logit model with item variables meal component and serving period (breakfast, lunch) and child variables retention interval, prompt and sex. Significant accuracy category predictors were meal component (p < 0.0003), retention interval (p < 0.0003), meal-component × serving-period (p < 0.0003) and meal-component × retention-interval (p = 0.001). The relationship of meal component and accuracy category was much stronger for lunch than breakfast. For lunch, beverages were matches more often, omissions much less often and intrusions more often than expected under independence; fruits and desserts were omissions more often. For the meal-component × retention-interval interaction, for the short retention interval, beverages were intrusions much more often but combination entrées and condiments were intrusions less often; for the long retention interval, beverages were matches more often and omissions less often but fruits were matches less often. Accuracy for each meal component appeared better with the short than long retention interval. For lunch and for the short retention interval, children’s reporting was most accurate for entrée and combination entrée meal components, whereas it was least accurate for vegetable and fruit meal components. Results have implications for conclusions of studies and interventions assessed with dietary recalls obtained from children. PMID:28174038

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.

Gesture recognition for smart home applications using portable radar sensors.

PubMed

Wan, Qian; Li, Yiran; Li, Changzhi; Pal, Ranadip

2014-01-01

In this article, we consider the design of a human gesture recognition system based on pattern recognition of signatures from a portable smart radar sensor. Powered by AAA batteries, the smart radar sensor operates in the 2.4 GHz industrial, scientific and medical (ISM) band. We analyzed the feature space using principle components and application-specific time and frequency domain features extracted from radar signals for two different sets of gestures. We illustrate that a nearest neighbor based classifier can achieve greater than 95% accuracy for multi class classification using 10 fold cross validation when features are extracted based on magnitude differences and Doppler shifts as compared to features extracted through orthogonal transformations. The reported results illustrate the potential of intelligent radars integrated with a pattern recognition system for high accuracy smart home and health monitoring purposes.

Linear combination methods to improve diagnostic/prognostic accuracy on future observations

PubMed Central

Kang, Le; Liu, Aiyi; Tian, Lili

2014-01-01

Multiple diagnostic tests or biomarkers can be combined to improve diagnostic accuracy. The problem of finding the optimal linear combinations of biomarkers to maximise the area under the receiver operating characteristic curve has been extensively addressed in the literature. The purpose of this article is threefold: (1) to provide an extensive review of the existing methods for biomarker combination; (2) to propose a new combination method, namely, the nonparametric stepwise approach; (3) to use leave-one-pair-out cross-validation method, instead of re-substitution method, which is overoptimistic and hence might lead to wrong conclusion, to empirically evaluate and compare the performance of different linear combination methods in yielding the largest area under receiver operating characteristic curve. A data set of Duchenne muscular dystrophy was analysed to illustrate the applications of the discussed combination methods. PMID:23592714

Projective invariant biplanar registration of a compact modular orthopaedic robot.

PubMed

Luan, Sheng; Sun, Lei; Hu, Lei; Hao, Aimin; Li, Changsheng; Tang, Peifu; Zhang, Lihai; Du, Hailong

2014-01-01

This paper presents a compact orthopedic robot designed with modular concept. The layout of the modular configuration is adaptive to various conditions such as surgical workspace and targeting path. A biplanar algorithm is adopted for the mapping from the fluoroscopic image to the robot, while the former affine based method is satisfactory only when the projection rays are basically perpendicular to the reference coordinate planes. This paper introduces the area cross-ratio as a projective invariant to improve the registration accuracy for non-orthogonal orientations, so that the robotic system could be applied to more orthopedic procedures under various C-Arm orientation conditions. The system configurations for femoral neck screw and sacroiliac screw fixation are presented. The accuracy of the robotic system and its efficacy for the two typical applications are validated by experiments.

Cross-coupled control for all-terrain rovers.

PubMed

Reina, Giulio

2013-01-08

Mobile robots are increasingly being used in challenging outdoor environments for applications that include construction, mining, agriculture, military and planetary exploration. In order to accomplish the planned task, it is critical that the motion control system ensure accuracy and robustness. The achievement of high performance on rough terrain is tightly connected with the minimization of vehicle-terrain dynamics effects such as slipping and skidding. This paper presents a cross-coupled controller for a 4-wheel-drive/4-wheel-steer robot, which optimizes the wheel motors' control algorithm to reduce synchronization errors that would otherwise result in wheel slip with conventional controllers. Experimental results, obtained with an all-terrain rover operating on agricultural terrain, are presented to validate the system. It is shown that the proposed approach is effective in reducing slippage and vehicle posture errors.

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

Does cognitive performance map to categorical diagnoses of schizophrenia, schizoaffective disorder and bipolar disorder? A discriminant functions analysis.

PubMed

Van Rheenen, Tamsyn E; Bryce, Shayden; Tan, Eric J; Neill, Erica; Gurvich, Caroline; Louise, Stephanie; Rossell, Susan L

2016-03-01

Despite known overlaps in the pattern of cognitive impairments in individuals with bipolar disorder (BD), schizophrenia (SZ) and schizoaffective disorder (SZA), few studies have examined the extent to which cognitive performance validates traditional diagnostic boundaries in these groups. Individuals with SZ (n=49), schizoaffective disorder (n=33) and BD (n=35) completed a battery of cognitive tests measuring the domains of processing speed, immediate memory, semantic memory, learning, working memory, executive function and sustained attention. A discriminant functions analysis revealed a significant function comprising semantic memory, immediate memory and processing speed that maximally separated patients with SZ from those with BD. Initial classification scores on the basis of this function showed modest diagnostic accuracy, owing in part to the misclassification of SZA patients as having SZ. When SZA patients were removed from the model, a second cross-validated classifier yielded slightly improved diagnostic accuracy and a single function solution, of which semantic memory loaded most heavily. A cluster of non-executive cognitive processes appears to have some validity in mapping onto traditional nosological boundaries. However, since semantic memory performance was the primary driver of the discrimination between BD and SZ, it is possible that performance differences between the disorders in this cognitive domain in particular, index separate underlying aetiologies. Copyright © 2015 Elsevier B.V. All rights reserved.

Estimation of total genetic effects for survival time in crossbred laying hens showing cannibalism, using pedigree or genomic information.

PubMed

Brinker, T; Raymond, B; Bijma, P; Vereijken, A; Ellen, E D

2017-02-01

Mortality of laying hens due to cannibalism is a major problem in the egg-laying industry. Survival depends on two genetic effects: the direct genetic effect of the individual itself (DGE) and the indirect genetic effects of its group mates (IGE). For hens housed in sire-family groups, DGE and IGE cannot be estimated using pedigree information, but the combined effect of DGE and IGE is estimated in the total breeding value (TBV). Genomic information provides information on actual genetic relationships between individuals and might be a tool to improve TBV accuracy. We investigated whether genomic information of the sire increased TBV accuracy compared with pedigree information, and we estimated genetic parameters for survival time. A sire model with pedigree information (BLUP) and a sire model with genomic information (ssGBLUP) were used. We used survival time records of 7290 crossbred offspring with intact beaks from four crosses. Cross-validation was used to compare the models. Using ssGBLUP did not improve TBV accuracy compared with BLUP which is probably due to the limited number of sires available per cross (~50). Genetic parameter estimates were similar for BLUP and ssGBLUP. For both BLUP and ssGBLUP, total heritable variance (T 2 ), expressed as a proportion of phenotypic variance, ranged from 0.03 ± 0.04 to 0.25 ± 0.09. Further research is needed on breeding value estimation for socially affected traits measured on individuals kept in single-family groups. © 2016 The Authors. Journal of Animal Breeding and Genetics Published by Blackwell Verlag GmbH.

Gene expression-based molecular diagnostic system for malignant gliomas is superior to histological diagnosis.

PubMed

Shirahata, Mitsuaki; Iwao-Koizumi, Kyoko; Saito, Sakae; Ueno, Noriko; Oda, Masashi; Hashimoto, Nobuo; Takahashi, Jun A; Kato, Kikuya

2007-12-15

Current morphology-based glioma classification methods do not adequately reflect the complex biology of gliomas, thus limiting their prognostic ability. In this study, we focused on anaplastic oligodendroglioma and glioblastoma, which typically follow distinct clinical courses. Our goal was to construct a clinically useful molecular diagnostic system based on gene expression profiling. The expression of 3,456 genes in 32 patients, 12 and 20 of whom had prognostically distinct anaplastic oligodendroglioma and glioblastoma, respectively, was measured by PCR array. Next to unsupervised methods, we did supervised analysis using a weighted voting algorithm to construct a diagnostic system discriminating anaplastic oligodendroglioma from glioblastoma. The diagnostic accuracy of this system was evaluated by leave-one-out cross-validation. The clinical utility was tested on a microarray-based data set of 50 malignant gliomas from a previous study. Unsupervised analysis showed divergent global gene expression patterns between the two tumor classes. A supervised binary classification model showed 100% (95% confidence interval, 89.4-100%) diagnostic accuracy by leave-one-out cross-validation using 168 diagnostic genes. Applied to a gene expression data set from a previous study, our model correlated better with outcome than histologic diagnosis, and also displayed 96.6% (28 of 29) consistency with the molecular classification scheme used for these histologically controversial gliomas in the original article. Furthermore, we observed that histologically diagnosed glioblastoma samples that shared anaplastic oligodendroglioma molecular characteristics tended to be associated with longer survival. Our molecular diagnostic system showed reproducible clinical utility and prognostic ability superior to traditional histopathologic diagnosis for malignant glioma.

Prostate tissue characterization/classification in 144 patient population using wavelet and higher order spectra features from transrectal ultrasound images.

PubMed

Pareek, Gyan; Acharya, U Rajendra; Sree, S Vinitha; Swapna, G; Yantri, Ratna; Martis, Roshan Joy; Saba, Luca; Krishnamurthi, Ganapathy; Mallarini, Giorgio; El-Baz, Ayman; Al Ekish, Shadi; Beland, Michael; Suri, Jasjit S

2013-12-01

In this work, we have proposed an on-line computer-aided diagnostic system called "UroImage" that classifies a Transrectal Ultrasound (TRUS) image into cancerous or non-cancerous with the help of non-linear Higher Order Spectra (HOS) features and Discrete Wavelet Transform (DWT) coefficients. The UroImage system consists of an on-line system where five significant features (one DWT-based feature and four HOS-based features) are extracted from the test image. These on-line features are transformed by the classifier parameters obtained using the training dataset to determine the class. We trained and tested six classifiers. The dataset used for evaluation had 144 TRUS images which were split into training and testing sets. Three-fold and ten-fold cross-validation protocols were adopted for training and estimating the accuracy of the classifiers. The ground truth used for training was obtained using the biopsy results. Among the six classifiers, using 10-fold cross-validation technique, Support Vector Machine and Fuzzy Sugeno classifiers presented the best classification accuracy of 97.9% with equally high values for sensitivity, specificity and positive predictive value. Our proposed automated system, which achieved more than 95% values for all the performance measures, can be an adjunct tool to provide an initial diagnosis for the identification of patients with prostate cancer. The technique, however, is limited by the limitations of 2D ultrasound guided biopsy, and we intend to improve our technique by using 3D TRUS images in the future.

Automatic Classification of Sub-Techniques in Classical Cross-Country Skiing Using a Machine Learning Algorithm on Micro-Sensor Data

PubMed Central

Seeberg, Trine M.; Tjønnås, Johannes; Haugnes, Pål; Sandbakk, Øyvind

2017-01-01

The automatic classification of sub-techniques in classical cross-country skiing provides unique possibilities for analyzing the biomechanical aspects of outdoor skiing. This is currently possible due to the miniaturization and flexibility of wearable inertial measurement units (IMUs) that allow researchers to bring the laboratory to the field. In this study, we aimed to optimize the accuracy of the automatic classification of classical cross-country skiing sub-techniques by using two IMUs attached to the skier’s arm and chest together with a machine learning algorithm. The novelty of our approach is the reliable detection of individual cycles using a gyroscope on the skier’s arm, while a neural network machine learning algorithm robustly classifies each cycle to a sub-technique using sensor data from an accelerometer on the chest. In this study, 24 datasets from 10 different participants were separated into the categories training-, validation- and test-data. Overall, we achieved a classification accuracy of 93.9% on the test-data. Furthermore, we illustrate how an accurate classification of sub-techniques can be combined with data from standard sports equipment including position, altitude, speed and heart rate measuring systems. Combining this information has the potential to provide novel insight into physiological and biomechanical aspects valuable to coaches, athletes and researchers. PMID:29283421

Assessing behavioural changes in ALS: cross-validation of ALS-specific measures.

PubMed

Pinto-Grau, Marta; Costello, Emmet; O'Connor, Sarah; Elamin, Marwa; Burke, Tom; Heverin, Mark; Pender, Niall; Hardiman, Orla

2017-07-01

The Beaumont Behavioural Inventory (BBI) is a behavioural proxy report for the assessment of behavioural changes in ALS. This tool has been validated against the FrSBe, a non-ALS-specific behavioural assessment, and further comparison of the BBI against a disease-specific tool was considered. This study cross-validates the BBI against the ALS-FTD-Q. Sixty ALS patients, 8% also meeting criteria for FTD, were recruited. All patients were evaluated using the BBI and the ALS-FTD-Q, completed by a carer. Correlational analysis was performed to assess construct validity. Precision, sensitivity, specificity, and overall accuracy of the BBI when compared to the ALS-FTD-Q, were obtained. The mean score of the whole sample on the BBI was 11.45 ± 13.06. ALS-FTD patients scored significantly higher than non-demented ALS patients (31.6 ± 14.64, 9.62 ± 11.38; p < 0.0001). A significant large positive correlation between the BBI and the ALS-FTD-Q was observed (r = 0.807, p < 0.0001), and no significant correlations between the BBI and other clinical/demographic characteristics indicate good convergent and discriminant validity, respectively. 72% of overall concordance was observed. Precision, sensitivity, and specificity for the classification of severely impaired patients were adequate. However, lower concordance in the classification of mild behavioural changes was observed, with higher sensitivity using the BBI, most likely secondary to BBI items which endorsed behavioural aspects not measured by the ALS-FTD-Q. Good construct validity has been further confirmed when the BBI is compared to an ALS-specific tool. Furthermore, the BBI is a more comprehensive behavioural assessment for ALS, as it measures the whole behavioural spectrum in this condition.

Time Domain Tool Validation Using ARES I-X Flight Data

NASA Technical Reports Server (NTRS)

Hough, Steven; Compton, James; Hannan, Mike; Brandon, Jay

2011-01-01

The ARES I-X vehicle was launched from NASA's Kennedy Space Center (KSC) on October 28, 2009 at approximately 11:30 EDT. ARES I-X was the first test flight for NASA s ARES I launch vehicle, and it was the first non-Shuttle launch vehicle designed and flown by NASA since Saturn. The ARES I-X had a 4-segment solid rocket booster (SRB) first stage and a dummy upper stage (US) to emulate the properties of the ARES I US. During ARES I-X pre-flight modeling and analysis, six (6) independent time domain simulation tools were developed and cross validated. Each tool represents an independent implementation of a common set of models and parameters in a different simulation framework and architecture. Post flight data and reconstructed models provide the means to validate a subset of the simulations against actual flight data and to assess the accuracy of pre-flight dispersion analysis. Post flight data consists of telemetered Operational Flight Instrumentation (OFI) data primarily focused on flight computer outputs and sensor measurements as well as Best Estimated Trajectory (BET) data that estimates vehicle state information from all available measurement sources. While pre-flight models were found to provide a reasonable prediction of the vehicle flight, reconstructed models were generated to better represent and simulate the ARES I-X flight. Post flight reconstructed models include: SRB propulsion model, thrust vector bias models, mass properties, base aerodynamics, and Meteorological Estimated Trajectory (wind and atmospheric data). The result of the effort is a set of independently developed, high fidelity, time-domain simulation tools that have been cross validated and validated against flight data. This paper presents the process and results of high fidelity aerospace modeling, simulation, analysis and tool validation in the time domain.

Accuracy of taxonomy prediction for 16S rRNA and fungal ITS sequences

PubMed Central

2018-01-01

Prediction of taxonomy for marker gene sequences such as 16S ribosomal RNA (rRNA) is a fundamental task in microbiology. Most experimentally observed sequences are diverged from reference sequences of authoritatively named organisms, creating a challenge for prediction methods. I assessed the accuracy of several algorithms using cross-validation by identity, a new benchmark strategy which explicitly models the variation in distances between query sequences and the closest entry in a reference database. When the accuracy of genus predictions was averaged over a representative range of identities with the reference database (100%, 99%, 97%, 95% and 90%), all tested methods had ≤50% accuracy on the currently-popular V4 region of 16S rRNA. Accuracy was found to fall rapidly with identity; for example, better methods were found to have V4 genus prediction accuracy of ∼100% at 100% identity but ∼50% at 97% identity. The relationship between identity and taxonomy was quantified as the probability that a rank is the lowest shared by a pair of sequences with a given pair-wise identity. With the V4 region, 95% identity was found to be a twilight zone where taxonomy is highly ambiguous because the probabilities that the lowest shared rank between pairs of sequences is genus, family, order or class are approximately equal. PMID:29682424

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.

Validation of a multiplex electrochemiluminescent immunoassay platform in human and mouse samples

PubMed Central

Bastarache, J.A.; Koyama, T.; Wickersham, N.E; Ware, L.B.

2014-01-01

Despite the widespread use of multiplex immunoassays, there are very few scientific reports that test the accuracy and reliability of a platform prior to publication of experimental data. Our laboratory has previously demonstrated the need for new assay platform validation prior to use of biologic samples from large studies in order to optimize sample handling and assay performance. In this study, our goal was to test the accuracy and reproducibility of an electrochemiluminescent multiplex immunoassay platform (Meso Scale Discovery, MSD®) and compare this platform to validated, singleplex immunoassays (R&D Systems®) using actual study subject (human plasma and mouse bronchoalveolar lavage fluid (BALF) and plasma) samples. We found that the MSD platform performed well on intra- and inter-assay comparisons, spike and recovery and cross-platform comparisons. The mean intra-assay CV% and range for MSD was 3.49 (0.0-10.4) for IL-6 and 2.04 (0.1-7.9) for IL-8. The correlation between values for identical samples measured on both MSD and R&D was R=0.97 for both analytes. The mouse MSD assay had a broader range of CV% with means ranging from 9.5-28.5 depending on the analyte. The range of mean CV% was similar for single plex ELISAs at 4.3-23.7 depending on the analyte. Regardless of species or sample type, CV% was more variable at lower protein concentrations. In conclusion, we validated a multiplex electrochemiluminscent assay system and found that it has superior test characteristics in human plasma compared to mouse BALF and plasma. Both human and MSD assays compared favorably to well-validated singleplex ELISA's PMID:24768796

Stationary Wavelet Transform and AdaBoost with SVM Based Pathological Brain Detection in MRI Scanning.

PubMed

Nayak, Deepak Ranjan; Dash, Ratnakar; Majhi, Banshidhar

2017-01-01

This paper presents an automatic classification system for segregating pathological brain from normal brains in magnetic resonance imaging scanning. The proposed system employs contrast limited adaptive histogram equalization scheme to enhance the diseased region in brain MR images. Two-dimensional stationary wavelet transform is harnessed to extract features from the preprocessed images. The feature vector is constructed using the energy and entropy values, computed from the level- 2 SWT coefficients. Then, the relevant and uncorrelated features are selected using symmetric uncertainty ranking filter. Subsequently, the selected features are given input to the proposed AdaBoost with support vector machine classifier, where SVM is used as the base classifier of AdaBoost algorithm. To validate the proposed system, three standard MR image datasets, Dataset-66, Dataset-160, and Dataset- 255 have been utilized. The 5 runs of k-fold stratified cross validation results indicate the suggested scheme offers better performance than other existing schemes in terms of accuracy and number of features. The proposed system earns ideal classification over Dataset-66 and Dataset-160; whereas, for Dataset- 255, an accuracy of 99.45% is achieved. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

The Principle of the Micro-Electronic Neural Bridge and a Prototype System Design.

PubMed

Huang, Zong-Hao; Wang, Zhi-Gong; Lu, Xiao-Ying; Li, Wen-Yuan; Zhou, Yu-Xuan; Shen, Xiao-Yan; Zhao, Xin-Tai

2016-01-01

The micro-electronic neural bridge (MENB) aims to rebuild lost motor function of paralyzed humans by routing movement-related signals from the brain, around the damage part in the spinal cord, to the external effectors. This study focused on the prototype system design of the MENB, including the principle of the MENB, the neural signal detecting circuit and the functional electrical stimulation (FES) circuit design, and the spike detecting and sorting algorithm. In this study, we developed a novel improved amplitude threshold spike detecting method based on variable forward difference threshold for both training and bridging phase. The discrete wavelet transform (DWT), a new level feature coefficient selection method based on Lilliefors test, and the k-means clustering method based on Mahalanobis distance were used for spike sorting. A real-time online spike detecting and sorting algorithm based on DWT and Euclidean distance was also implemented for the bridging phase. Tested by the data sets available at Caltech, in the training phase, the average sensitivity, specificity, and clustering accuracies are 99.43%, 97.83%, and 95.45%, respectively. Validated by the three-fold cross-validation method, the average sensitivity, specificity, and classification accuracy are 99.43%, 97.70%, and 96.46%, respectively.

Physiological reactivity to nonideographic virtual reality stimuli in veterans with and without PTSD.

PubMed

Webb, Andrea K; Vincent, Ashley L; Jin, Alvin B; Pollack, Mark H

2015-02-01

Post-traumatic stress disorder (PTSD) currently is diagnosed via clinical interview in which subjective self reports of traumatic events and associated experiences are discussed with a mental health professional. The reliability and validity of diagnoses can be improved with the use of objective physiological measures. In this study, physiological activity was recorded from 58 male veterans (PTSD Diagnosis n = 16; Trauma Exposed/No PTSD Diagnosis: n = 23; No Trauma/No PTSD Diagnosis: n = 19) with and without PTSD and combat trauma exposure in response to emotionally evocative non-idiographic virtual reality stimuli. Statistically significant differences among the Control, Trauma, and PTSD groups were present during the viewing of two virtual reality videos. Skin conductance and interbeat interval features were extracted for each of ten video events (five events of increasing severity per video). These features were submitted to three stepwise discriminant function analyses to assess classification accuracy for Control versus Trauma, Control versus PTSD, and Trauma versus PTSD pairings of participant groups. Leave-one-out cross-validation classification accuracy was between 71 and 94%. These results are promising and suggest the utility of objective physiological measures in assisting with PTSD diagnosis.

Auditory evoked potentials in patients with major depressive disorder measured by Emotiv system.

PubMed

Wang, Dongcui; Mo, Fongming; Zhang, Yangde; Yang, Chao; Liu, Jun; Chen, Zhencheng; Zhao, Jinfeng

2015-01-01

In a previous study (unpublished), Emotiv headset was validated for capturing event-related potentials (ERPs) from normal subjects. In the present follow-up study, the signal quality of Emotiv headset was tested by the accuracy rate of discriminating Major Depressive Disorder (MDD) patients from the normal subjects. ERPs of 22 MDD patients and 15 normal subjects were induced by an auditory oddball task and the amplitude of N1, N2 and P3 of ERP components were specifically analyzed. The features of ERPs were statistically investigated. It is found that Emotiv headset is capable of discriminating the abnormal N1, N2 and P3 components in MDD patients. Relief-F algorithm was applied to all features for feature selection. The selected features were then input to a linear discriminant analysis (LDA) classifier with leave-one-out cross-validation to characterize the ERP features of MDD. 127 possible combinations out of the selected 7 ERP features were classified using LDA. The best classification accuracy was achieved to be 89.66%. These results suggest that MDD patients are identifiable from normal subjects by ERPs measured by Emotiv headset.

Multiple sensor integration for seizure onset detection in human patients comparing conventional disc versus novel tripolar concentric ring electrodes.

PubMed

Makeyev, Oleksandr; Ding, Quan; Martínez-Juárez, Iris E; Gaitanis, John; Kay, Steven M; Besio, Walter G

2013-01-01

As epilepsy affects approximately one percent of the world population, electrical stimulation of the brain has recently shown potential for additive seizure control therapy. Closed-loop systems that apply electrical stimulation when seizure onset is automatically detected require high accuracy of automatic seizure detection based on electrographic brain activity. To improve this accuracy we propose to use noninvasive tripolar concentric ring electrodes that have been shown to have significantly better signal-to-noise ratio, spatial selectivity, and mutual information compared to conventional disc electrodes. The proposed detection methodology is based on integration of multiple sensors using exponentially embedded family (EEF). In this preliminary study it is validated on over 26.3 hours of data collected using both tripolar concentric ring and conventional disc electrodes concurrently each from 7 human patients with epilepsy including five seizures. For a cross-validation based group model EEF correctly detected 100% and 80% of seizures respectively with <0.76 and <1.56 false positive detections per hour respectively for the two electrode modalities. These results clearly suggest the potential of seizure onset detection based on data from tripolar concentric ring electrodes.

Support vector machine and principal component analysis for microarray data classification

NASA Astrophysics Data System (ADS)

Astuti, Widi; Adiwijaya

2018-03-01

Cancer is a leading cause of death worldwide although a significant proportion of it can be cured if it is detected early. In recent decades, technology called microarray takes an important role in the diagnosis of cancer. By using data mining technique, microarray data classification can be performed to improve the accuracy of cancer diagnosis compared to traditional techniques. The characteristic of microarray data is small sample but it has huge dimension. Since that, there is a challenge for researcher to provide solutions for microarray data classification with high performance in both accuracy and running time. This research proposed the usage of Principal Component Analysis (PCA) as a dimension reduction method along with Support Vector Method (SVM) optimized by kernel functions as a classifier for microarray data classification. The proposed scheme was applied on seven data sets using 5-fold cross validation and then evaluation and analysis conducted on term of both accuracy and running time. The result showed that the scheme can obtained 100% accuracy for Ovarian and Lung Cancer data when Linear and Cubic kernel functions are used. In term of running time, PCA greatly reduced the running time for every data sets.

Improving the prediction of going concern of Taiwanese listed companies using a hybrid of LASSO with data mining techniques.

PubMed

Goo, Yeung-Ja James; Chi, Der-Jang; Shen, Zong-De

2016-01-01

The purpose of this study is to establish rigorous and reliable going concern doubt (GCD) prediction models. This study first uses the least absolute shrinkage and selection operator (LASSO) to select variables and then applies data mining techniques to establish prediction models, such as neural network (NN), classification and regression tree (CART), and support vector machine (SVM). The samples of this study include 48 GCD listed companies and 124 NGCD (non-GCD) listed companies from 2002 to 2013 in the TEJ database. We conduct fivefold cross validation in order to identify the prediction accuracy. According to the empirical results, the prediction accuracy of the LASSO-NN model is 88.96 % (Type I error rate is 12.22 %; Type II error rate is 7.50 %), the prediction accuracy of the LASSO-CART model is 88.75 % (Type I error rate is 13.61 %; Type II error rate is 14.17 %), and the prediction accuracy of the LASSO-SVM model is 89.79 % (Type I error rate is 10.00 %; Type II error rate is 15.83 %).

Considerations Underlying the Use of Mixed Group Validation

ERIC Educational Resources Information Center

Jewsbury, Paul A.; Bowden, Stephen C.

2013-01-01

Mixed Group Validation (MGV) is an approach for estimating the diagnostic accuracy of tests. MGV is a promising alternative to the more commonly used Known Groups Validation (KGV) approach for estimating diagnostic accuracy. The advantage of MGV lies in the fact that the approach does not require a perfect external validity criterion or gold…

Micro-Doppler Based Classification of Human Aquatic Activities via Transfer Learning of Convolutional Neural Networks.

PubMed

Park, Jinhee; Javier, Rios Jesus; Moon, Taesup; Kim, Youngwook

2016-11-24

Accurate classification of human aquatic activities using radar has a variety of potential applications such as rescue operations and border patrols. Nevertheless, the classification of activities on water using radar has not been extensively studied, unlike the case on dry ground, due to its unique challenge. Namely, not only is the radar cross section of a human on water small, but the micro-Doppler signatures are much noisier due to water drops and waves. In this paper, we first investigate whether discriminative signatures could be obtained for activities on water through a simulation study. Then, we show how we can effectively achieve high classification accuracy by applying deep convolutional neural networks (DCNN) directly to the spectrogram of real measurement data. From the five-fold cross-validation on our dataset, which consists of five aquatic activities, we report that the conventional feature-based scheme only achieves an accuracy of 45.1%. In contrast, the DCNN trained using only the collected data attains 66.7%, and the transfer learned DCNN, which takes a DCNN pre-trained on a RGB image dataset and fine-tunes the parameters using the collected data, achieves a much higher 80.3%, which is a significant performance boost.

Development of a multi-sensor elevation time series pole-ward of 86°S in support of altimetry validation and ice sheet mass balance studies

NASA Astrophysics Data System (ADS)

Studinger, M.; Brunt, K. M.; Casey, K.; Medley, B.; Neumann, T.; Manizade, S.; Linkswiler, M. A.

2015-12-01

In order to produce a cross-calibrated long-term record of ice-surface elevation change for input into ice sheet models and mass balance studies it is necessary to "link the measurements made by airborne laser altimeters, satellite measurements of ICESat, ICESat-2, and CryoSat-2" [IceBridge Level 1 Science Requirements, 2012] and determine the biases and the spatial variations between radar altimeters and laser altimeters using different wavelengths. The convergence zones of all ICESat tracks (86°S) and all ICESat-2 and CryoSat-2 tracks (88°S) are in regions of relatively low accumulation, making them ideal for satellite altimetry calibration. In preparation for ICESat-2 validation, the IceBridge and ICESat-2 science teams have designed IceBridge data acquisitions around 86°S and 88°S. Several aspects need to be considered when comparing and combining elevation measurements from different radar and laser altimeters, including: a) foot print size and spatial sampling pattern; b) accuracy and precision of each data sets; c) varying signal penetration into the snow; and d) changes in geodetic reference frames over time, such as the International Terrestrial Reference Frame (ITRF). The presentation will focus on the analysis of several IceBridge flights around 86 and 88°S with the LVIS and ATM airborne laser altimeters and will evaluate the accuracy and precision of these data sets. To properly interpret the observed elevation change (dh/dt) as mass change, however, the various processes that control surface elevation fluctuations must be quantified and therefore future work will quantify the spatial variability in snow accumulation rates pole-ward of 86°S and in particular around 88°S. Our goal is to develop a cross-validated multi-sensor time series of surface elevation change pole-ward of 86°S that, in combination with measured accumulation rates, will support ICESat-2 calibration and validation and ice sheet mass balance studies.

Developmental Changes in Cross-Situational Word Learning: The Inverse Effect of Initial Accuracy

ERIC Educational Resources Information Center

Fitneva, Stanka A.; Christiansen, Morten H.

2017-01-01

Intuitively, the accuracy of initial word-referent mappings should be positively correlated with the outcome of learning. Yet recent evidence suggests an inverse effect of initial accuracy in adults, whereby greater accuracy of initial mappings is associated with poorer outcomes in a cross-situational learning task. Here, we examine the impact of…

Performance evaluation of non-targeted peak-based cross-sample analysis for comprehensive two-dimensional gas chromatography-mass spectrometry data and application to processed hazelnut profiling.

PubMed

Kiefl, Johannes; Cordero, Chiara; Nicolotti, Luca; Schieberle, Peter; Reichenbach, Stephen E; Bicchi, Carlo

2012-06-22

The continuous interest in non-targeted profiling induced the development of tools for automated cross-sample analysis. Such tools were found to be selective or not comprehensive thus delivering a biased view on the qualitative/quantitative peak distribution across 2D sample chromatograms. Therefore, the performance of non-targeted approaches needs to be critically evaluated. This study focused on the development of a validation procedure for non-targeted, peak-based, GC×GC-MS data profiling. The procedure introduced performance parameters such as specificity, precision, accuracy, and uncertainty for a profiling method known as Comprehensive Template Matching. The performance was assessed by applying a three-week validation protocol based on CITAC/EURACHEM guidelines. Optimized ¹D and ²D retention times search windows, MS match factor threshold, detection threshold, and template threshold were evolved from two training sets by a semi-automated learning process. The effectiveness of proposed settings to consistently match 2D peak patterns was established by evaluating the rate of mismatched peaks and was expressed in terms of results accuracy. The study utilized 23 different 2D peak patterns providing the chemical fingerprints of raw and roasted hazelnuts (Corylus avellana L.) from different geographical origins, of diverse varieties and different roasting degrees. The validation results show that non-targeted peak-based profiling can be reliable with error rates lower than 10% independent of the degree of analytical variance. The optimized Comprehensive Template Matching procedure was employed to study hazelnut roasting profiles and in particular to find marker compounds strongly dependent on the thermal treatment, and to establish the correlation of potential marker compounds to geographical origin and variety/cultivar and finally to reveal the characteristic release of aroma active compounds. Copyright © 2012 Elsevier B.V. All rights reserved.

Bird Radar Validation in the Field by Time-Referencing Line-Transect Surveys

PubMed Central

Dokter, Adriaan M.; Baptist, Martin J.; Ens, Bruno J.; Krijgsveld, Karen L.; van Loon, E. Emiel

2013-01-01

Track-while-scan bird radars are widely used in ornithological studies, but often the precise detection capabilities of these systems are unknown. Quantification of radar performance is essential to avoid observational biases, which requires practical methods for validating a radar’s detection capability in specific field settings. In this study a method to quantify the detection capability of a bird radar is presented, as well a demonstration of this method in a case study. By time-referencing line-transect surveys, visually identified birds were automatically linked to individual tracks using their transect crossing time. Detection probabilities were determined as the fraction of the total set of visual observations that could be linked to radar tracks. To avoid ambiguities in assigning radar tracks to visual observations, the observer’s accuracy in determining a bird’s transect crossing time was taken into account. The accuracy was determined by examining the effect of a time lag applied to the visual observations on the number of matches found with radar tracks. Effects of flight altitude, distance, surface substrate and species size on the detection probability by the radar were quantified in a marine intertidal study area. Detection probability varied strongly with all these factors, as well as species-specific flight behaviour. The effective detection range for single birds flying at low altitude for an X-band marine radar based system was estimated at ∼1.5 km. Within this range the fraction of individual flying birds that were detected by the radar was 0.50±0.06 with a detection bias towards higher flight altitudes, larger birds and high tide situations. Besides radar validation, which we consider essential when quantification of bird numbers is important, our method of linking radar tracks to ground-truthed field observations can facilitate species-specific studies using surveillance radars. The methodology may prove equally useful for optimising tracking algorithms. PMID:24066103

Prediction of redox-sensitive cysteines using sequential distance and other sequence-based features.

PubMed

Sun, Ming-An; Zhang, Qing; Wang, Yejun; Ge, Wei; Guo, Dianjing

2016-08-24

Reactive oxygen species can modify the structure and function of proteins and may also act as important signaling molecules in various cellular processes. Cysteine thiol groups of proteins are particularly susceptible to oxidation. Meanwhile, their reversible oxidation is of critical roles for redox regulation and signaling. Recently, several computational tools have been developed for predicting redox-sensitive cysteines; however, those methods either only focus on catalytic redox-sensitive cysteines in thiol oxidoreductases, or heavily depend on protein structural data, thus cannot be widely used. In this study, we analyzed various sequence-based features potentially related to cysteine redox-sensitivity, and identified three types of features for efficient computational prediction of redox-sensitive cysteines. These features are: sequential distance to the nearby cysteines, PSSM profile and predicted secondary structure of flanking residues. After further feature selection using SVM-RFE, we developed Redox-Sensitive Cysteine Predictor (RSCP), a SVM based classifier for redox-sensitive cysteine prediction using primary sequence only. Using 10-fold cross-validation on RSC758 dataset, the accuracy, sensitivity, specificity, MCC and AUC were estimated as 0.679, 0.602, 0.756, 0.362 and 0.727, respectively. When evaluated using 10-fold cross-validation with BALOSCTdb dataset which has structure information, the model achieved performance comparable to current structure-based method. Further validation using an independent dataset indicates it is robust and of relatively better accuracy for predicting redox-sensitive cysteines from non-enzyme proteins. In this study, we developed a sequence-based classifier for predicting redox-sensitive cysteines. The major advantage of this method is that it does not rely on protein structure data, which ensures more extensive application compared to other current implementations. Accurate prediction of redox-sensitive cysteines not only enhances our understanding about the redox sensitivity of cysteine, it may also complement the proteomics approach and facilitate further experimental investigation of important redox-sensitive cysteines.

Validation of Coevolving Residue Algorithms via Pipeline Sensitivity Analysis: ELSC and OMES and ZNMI, Oh My!

PubMed Central

Brown, Christopher A.; Brown, Kevin S.

2010-01-01

Correlated amino acid substitution algorithms attempt to discover groups of residues that co-fluctuate due to either structural or functional constraints. Although these algorithms could inform both ab initio protein folding calculations and evolutionary studies, their utility for these purposes has been hindered by a lack of confidence in their predictions due to hard to control sources of error. To complicate matters further, naive users are confronted with a multitude of methods to choose from, in addition to the mechanics of assembling and pruning a dataset. We first introduce a new pair scoring method, called ZNMI (Z-scored-product Normalized Mutual Information), which drastically improves the performance of mutual information for co-fluctuating residue prediction. Second and more important, we recast the process of finding coevolving residues in proteins as a data-processing pipeline inspired by the medical imaging literature. We construct an ensemble of alignment partitions that can be used in a cross-validation scheme to assess the effects of choices made during the procedure on the resulting predictions. This pipeline sensitivity study gives a measure of reproducibility (how similar are the predictions given perturbations to the pipeline?) and accuracy (are residue pairs with large couplings on average close in tertiary structure?). We choose a handful of published methods, along with ZNMI, and compare their reproducibility and accuracy on three diverse protein families. We find that (i) of the algorithms tested, while none appear to be both highly reproducible and accurate, ZNMI is one of the most accurate by far and (ii) while users should be wary of predictions drawn from a single alignment, considering an ensemble of sub-alignments can help to determine both highly accurate and reproducible couplings. Our cross-validation approach should be of interest both to developers and end users of algorithms that try to detect correlated amino acid substitutions. PMID:20531955

Bird radar validation in the field by time-referencing line-transect surveys.

PubMed

Dokter, Adriaan M; Baptist, Martin J; Ens, Bruno J; Krijgsveld, Karen L; van Loon, E Emiel

2013-01-01

Track-while-scan bird radars are widely used in ornithological studies, but often the precise detection capabilities of these systems are unknown. Quantification of radar performance is essential to avoid observational biases, which requires practical methods for validating a radar's detection capability in specific field settings. In this study a method to quantify the detection capability of a bird radar is presented, as well a demonstration of this method in a case study. By time-referencing line-transect surveys, visually identified birds were automatically linked to individual tracks using their transect crossing time. Detection probabilities were determined as the fraction of the total set of visual observations that could be linked to radar tracks. To avoid ambiguities in assigning radar tracks to visual observations, the observer's accuracy in determining a bird's transect crossing time was taken into account. The accuracy was determined by examining the effect of a time lag applied to the visual observations on the number of matches found with radar tracks. Effects of flight altitude, distance, surface substrate and species size on the detection probability by the radar were quantified in a marine intertidal study area. Detection probability varied strongly with all these factors, as well as species-specific flight behaviour. The effective detection range for single birds flying at low altitude for an X-band marine radar based system was estimated at ~1.5 km. Within this range the fraction of individual flying birds that were detected by the radar was 0.50 ± 0.06 with a detection bias towards higher flight altitudes, larger birds and high tide situations. Besides radar validation, which we consider essential when quantification of bird numbers is important, our method of linking radar tracks to ground-truthed field observations can facilitate species-specific studies using surveillance radars. The methodology may prove equally useful for optimising tracking algorithms.

Nutritional evaluation of commercial dry dog foods by near infrared reflectance spectroscopy.

PubMed

Alomar, D; Hodgkinson, S; Abarzúa, D; Fuchslocher, R; Alvarado, C; Rosales, E

2006-06-01

Near infrared reflectance spectroscopy (NIRS) was used to predict the nutritional value of dog foods sold in Chile. Fifty-nine dry foods for adult and growing dogs were collected, ground and scanned across the visible/NIR range and subsequently analysed for dry matter (DM), crude protein (CP), crude fibre (CF), total fat, linoleic acid, gross energy (GE), estimated metabolizable energy (ME) and several amino acids and minerals. Calibration equations were developed by modified partial least squares regression, and tested by cross-validation. Standard error of cross validation (SE(CV)) and coefficient of determination of cross validation (SE(CV)) were used to select best equations. Equations with good predicting accuracy were obtained for DM, CF, CP, GE and fat. Corresponding values for and SE(CV) were 0.96 and 1.7 g/kg, 0.91 and 3.1 g/kg, 0.99 and 5.0 g/kg, 0.93 and 0.26 MJ/kg, 0.89 and 12.4 g/kg. Several amino acids were also well predicted, such as arginine, leucine, isoleucine, phenylalanine-tyrosine (combined), threonine and valine, with values for and SE(CV) (g/kg) of 0.89 and 0.9, 0.94 and 1.3, 0.91 and 0.5, 0.95 and 0.9, 0.91 and 0.5, 0.93 and 0.5. Intermediate values, appropriate for ranking purposes, were obtained for ME, histidine, lysine and methionine-cysteine. Tryptophan, minerals or linoleic acid were not acceptably predicted, irrespective of the mathematical treatment applied. It is concluded that NIR can be successfully used to predict important nutritional characteristics of commercial dog foods.

Initial Validation and Results of Geoscience Laser Altimeter System Optical Properties Retrievals

NASA Technical Reports Server (NTRS)

Hlavka, Dennis L.; Hart, W. D.; Pal, S. P.; McGill, M.; Spinhirne, J. D.

2004-01-01

Verification of Geoscience Laser Altimeter System (GLAS) optical retrievals is . problematic in that passage over ground sites is both instantaneous and sparse plus space-borne passive sensors such as MODIS are too frequently out of sync with the GLAS position. In October 2003, the GLAS Validation Experiment was executed from NASA Dryden Research Center, California to greatly increase validation possibilities. The high-altitude NASA ER-2 aircraft and onboard instrumentation of Cloud Physics Lidar (CPL), MODIS Airborne Simulator (MAS), and/or MODIS/ASTER Airborne Simulator (MASTER) under-flew seven orbit tracks of GLAS for cirrus, smoke, and urban pollution optical properties inter-comparisons. These highly calibrated suite of instruments are the best data set yet to validate GLAS atmospheric parameters. In this presentation, we will focus on the inter-comparison with GLAS and CPL and draw preliminary conclusions about the accuracies of the GLAS 532nm retrievals of optical depth, extinction, backscatter cross section, and calculated extinction-to-backscatter ratio. Comparisons to an AERONET/MPL ground-based site at Monterey, California will be attempted. Examples of GLAS operational optical data products will be shown.

Combined striatal binding and cerebral influx analysis of dynamic 11C-raclopride PET improves early differentiation between multiple-system atrophy and Parkinson disease.

PubMed

Van Laere, Koen; Clerinx, Kristien; D'Hondt, Eduard; de Groot, Tjibbe; Vandenberghe, Wim

2010-04-01

Striatal dopamine D(2) receptor (D2R) PET has been proposed to differentiate between Parkinson disease (PD) and multiple-system atrophy with predominant parkinsonism (MSA-P). However, considerable overlap in striatal D(2) binding may exist between PD and MSA-P. It has been shown that imaging of neuronal activity, as determined by metabolism or perfusion, can also help distinguish PD from MSA-P. We investigated whether the differential diagnostic value of (11)C-raclopride PET could be improved by dynamic scan analysis combining D2R binding and regional tracer influx. (11)C-raclopride PET was performed in 9 MSA-P patients (mean age +/- SD, 56.2 +/- 10.2 y; disease duration, 2.9 +/- 0.8 y; median Hoehn-Yahr score, 3), 10 PD patients (mean age +/- SD, 65.7 +/- 8.1 y; disease duration, 3.3 +/- 1.5 y; median Hoehn-Yahr score, 1.5), and 10 healthy controls (mean age +/- SD, 61.6 +/- 6.5 y). Diagnosis was obtained after prolonged follow-up (MSA-P, 5.5 +/- 2.0 y; PD, 6.0 +/- 2.3 y) using validated clinical criteria. Spatially normalized parametric images of binding potential (BP) and local influx ratio (R(1) = K(1)/K'(1)) of (11)C-raclopride were obtained using a voxelwise reference tissue model with occipital cortex as reference region. Stepwise forward discriminant analysis with cross-validation, with and without the inclusion of regional R(1) values, was performed using a predefined volume-of-interest template. Using conventional BP values, we correctly classified 65.5% (all values given with cross-validation) of 29 cases only. The combination of BP and R(1) information increased discrimination accuracy to 79.3%. When healthy controls were not included and patients only were considered, BP information alone discriminated PD and MSA-P in 84.2% of cases, but the combination with R(1) data increased accuracy to 100%. Discriminant analysis using combined striatal D2R BP and cerebral influx ratio information of a single dynamic (11)C-raclopride PET scan distinguishes MSA-P and PD patients with high accuracy and is superior to conventional methods of striatal D2R binding analysis.

An artificial neural network to predict resting energy expenditure in obesity.

PubMed

Disse, Emmanuel; Ledoux, Séverine; Bétry, Cécile; Caussy, Cyrielle; Maitrepierre, Christine; Coupaye, Muriel; Laville, Martine; Simon, Chantal

2017-09-01

The resting energy expenditure (REE) determination is important in nutrition for adequate dietary prescription. The gold standard i.e. indirect calorimetry is not available in clinical settings. Thus, several predictive equations have been developed, but they lack of accuracy in subjects with extreme weight including obese populations. Artificial neural networks (ANN) are useful predictive tools in the area of artificial intelligence, used in numerous clinical fields. The aim of this study was to determine the relevance of ANN in predicting REE in obesity. A Multi-Layer Perceptron (MLP) feed-forward neural network with a back propagation algorithm was created and cross-validated in a cohort of 565 obese subjects (BMI within 30-50 kg m -2 ) with weight, height, sex and age as clinical inputs and REE measured by indirect calorimetry as output. The predictive performances of ANN were compared to those of 23 predictive REE equations in the training set and in two independent sets of 100 and 237 obese subjects for external validation. Among the 23 established prediction equations for REE evaluated, the Harris & Benedict equations recalculated by Roza were the most accurate for the obese population, followed by the USA DRI, Müller and the original Harris & Benedict equations. The final 5-fold cross-validated three-layer 4-3-1 feed-forward back propagation ANN model developed in that study improved precision and accuracy of REE prediction over linear equations (precision = 68.1%, MAPE = 8.6% and RMSPE = 210 kcal/d), independently from BMI subgroups within 30-50 kg m -2 . External validation confirmed the better predictive performances of ANN model (precision = 73% and 65%, MAPE = 7.7% and 8.6%, RMSPE = 187 kcal/d and 200 kcal/d in the 2 independent datasets) for the prediction of REE in obese subjects. We developed and validated an ANN model for the prediction of REE in obese subjects that is more precise and accurate than established REE predictive equations independent from BMI subgroups. For convenient use in clinical settings, we provide a simple ANN-REE calculator available at: https://www.crnh-rhone-alpes.fr/fr/ANN-REE-Calculator. Copyright © 2017 Elsevier Ltd and European Society for Clinical Nutrition and Metabolism. All rights reserved.

Bayesian spatiotemporal crash frequency models with mixture components for space-time interactions.

PubMed

Cheng, Wen; Gill, Gurdiljot Singh; Zhang, Yongping; Cao, Zhong

2018-03-01

The traffic safety research has developed spatiotemporal models to explore the variations in the spatial pattern of crash risk over time. Many studies observed notable benefits associated with the inclusion of spatial and temporal correlation and their interactions. However, the safety literature lacks sufficient research for the comparison of different temporal treatments and their interaction with spatial component. This study developed four spatiotemporal models with varying complexity due to the different temporal treatments such as (I) linear time trend; (II) quadratic time trend; (III) Autoregressive-1 (AR-1); and (IV) time adjacency. Moreover, the study introduced a flexible two-component mixture for the space-time interaction which allows greater flexibility compared to the traditional linear space-time interaction. The mixture component allows the accommodation of global space-time interaction as well as the departures from the overall spatial and temporal risk patterns. This study performed a comprehensive assessment of mixture models based on the diverse criteria pertaining to goodness-of-fit, cross-validation and evaluation based on in-sample data for predictive accuracy of crash estimates. The assessment of model performance in terms of goodness-of-fit clearly established the superiority of the time-adjacency specification which was evidently more complex due to the addition of information borrowed from neighboring years, but this addition of parameters allowed significant advantage at posterior deviance which subsequently benefited overall fit to crash data. The Base models were also developed to study the comparison between the proposed mixture and traditional space-time components for each temporal model. The mixture models consistently outperformed the corresponding Base models due to the advantages of much lower deviance. For cross-validation comparison of predictive accuracy, linear time trend model was adjudged the best as it recorded the highest value of log pseudo marginal likelihood (LPML). Four other evaluation criteria were considered for typical validation using the same data for model development. Under each criterion, observed crash counts were compared with three types of data containing Bayesian estimated, normal predicted, and model replicated ones. The linear model again performed the best in most scenarios except one case of using model replicated data and two cases involving prediction without including random effects. These phenomena indicated the mediocre performance of linear trend when random effects were excluded for evaluation. This might be due to the flexible mixture space-time interaction which can efficiently absorb the residual variability escaping from the predictable part of the model. The comparison of Base and mixture models in terms of prediction accuracy further bolstered the superiority of the mixture models as the mixture ones generated more precise estimated crash counts across all four models, suggesting that the advantages associated with mixture component at model fit were transferable to prediction accuracy. Finally, the residual analysis demonstrated the consistently superior performance of random effect models which validates the importance of incorporating the correlation structures to account for unobserved heterogeneity. Copyright © 2017 Elsevier Ltd. All rights reserved.

Criterion and Concurrent Validity of the activPAL™ Professional Physical Activity Monitor in Adolescent Females

PubMed Central

Dowd, Kieran P.; Harrington, Deirdre M.; Donnelly, Alan E.

2012-01-01

Background The activPAL has been identified as an accurate and reliable measure of sedentary behaviour. However, only limited information is available on the accuracy of the activPAL activity count function as a measure of physical activity, while no unit calibration of the activPAL has been completed to date. This study aimed to investigate the criterion validity of the activPAL, examine the concurrent validity of the activPAL, and perform and validate a value calibration of the activPAL in an adolescent female population. The performance of the activPAL in estimating posture was also compared with sedentary thresholds used with the ActiGraph accelerometer. Methodologies Thirty adolescent females (15 developmental; 15 cross-validation) aged 15–18 years performed 5 activities while wearing the activPAL, ActiGraph GT3X, and the Cosmed K4B2. A random coefficient statistics model examined the relationship between metabolic equivalent (MET) values and activPAL counts. Receiver operating characteristic analysis was used to determine activity thresholds and for cross-validation. The random coefficient statistics model showed a concordance correlation coefficient of 0.93 (standard error of the estimate = 1.13). An optimal moderate threshold of 2997 was determined using mixed regression, while an optimal vigorous threshold of 8229 was determined using receiver operating statistics. The activPAL count function demonstrated very high concurrent validity (r = 0.96, p<0.01) with the ActiGraph count function. Levels of agreement for sitting, standing, and stepping between direct observation and the activPAL and ActiGraph were 100%, 98.1%, 99.2% and 100%, 0%, 100%, respectively. Conclusions These findings suggest that the activPAL is a valid, objective measurement tool that can be used for both the measurement of physical activity and sedentary behaviours in an adolescent female population. PMID:23094069

Integrated Strategy Improves the Prediction Accuracy of miRNA in Large Dataset

PubMed Central

Lipps, David; Devineni, Sree

2016-01-01

MiRNAs are short non-coding RNAs of about 22 nucleotides, which play critical roles in gene expression regulation. The biogenesis of miRNAs is largely determined by the sequence and structural features of their parental RNA molecules. Based on these features, multiple computational tools have been developed to predict if RNA transcripts contain miRNAs or not. Although being very successful, these predictors started to face multiple challenges in recent years. Many predictors were optimized using datasets of hundreds of miRNA samples. The sizes of these datasets are much smaller than the number of known miRNAs. Consequently, the prediction accuracy of these predictors in large dataset becomes unknown and needs to be re-tested. In addition, many predictors were optimized for either high sensitivity or high specificity. These optimization strategies may bring in serious limitations in applications. Moreover, to meet continuously raised expectations on these computational tools, improving the prediction accuracy becomes extremely important. In this study, a meta-predictor mirMeta was developed by integrating a set of non-linear transformations with meta-strategy. More specifically, the outputs of five individual predictors were first preprocessed using non-linear transformations, and then fed into an artificial neural network to make the meta-prediction. The prediction accuracy of meta-predictor was validated using both multi-fold cross-validation and independent dataset. The final accuracy of meta-predictor in newly-designed large dataset is improved by 7% to 93%. The meta-predictor is also proved to be less dependent on datasets, as well as has refined balance between sensitivity and specificity. This study has two folds of importance: First, it shows that the combination of non-linear transformations and artificial neural networks improves the prediction accuracy of individual predictors. Second, a new miRNA predictor with significantly improved prediction accuracy is developed for the community for identifying novel miRNAs and the complete set of miRNAs. Source code is available at: https://github.com/xueLab/mirMeta PMID:28002428

Validation of the Edinburgh Postnatal Depression Scale (EPDS) on the Thai–Myanmar border

PubMed Central

Ing, Harriet; Fellmeth, Gracia; White, Jitrachote; Stein, Alan; Simpson, Julie A; McGready, Rose

2017-01-01

Postnatal depression is common and may have severe consequences for women and their children. Locally validated screening tools are required to identify at-risk women in marginalised populations. The Edinburgh Postnatal Depression Scale (EPDS) is one of the most frequently used tools globally. This cross-sectional study assessed the validity and acceptability of the EPDS in Karen and Burmese among postpartum migrant and refugee women on the Thai–Myanmar border. The EPDS was administered to participants and results compared with a diagnostic interview. Local staff provided feedback on the acceptability of the EPDS through a focus group discussion. Results from 670 women showed high accuracy and reasonable internal consistency of the EPDS. However, acceptability to local staff was low, limiting the utility of the EPDS in this setting despite its good psychometrics. Further work is required to identify a tool that is acceptable and sensitive to cultural manifestations of depression in this vulnerable population. PMID:28699396

Assessment of Some Atomization Models Used in Spray Calculations

NASA Technical Reports Server (NTRS)

Raju, M. S.; Bulzin, Dan

2011-01-01

The paper presents the results from a validation study undertaken as a part of the NASA s fundamental aeronautics initiative on high altitude emissions in order to assess the accuracy of several atomization models used in both non-superheat and superheat spray calculations. As a part of this investigation we have undertaken the validation based on four different cases to investigate the spray characteristics of (1) a flashing jet generated by the sudden release of pressurized R134A from cylindrical nozzle, (2) a liquid jet atomizing in a subsonic cross flow, (3) a Parker-Hannifin pressure swirl atomizer, and (4) a single-element Lean Direct Injector (LDI) combustor experiment. These cases were chosen because of their importance in some aerospace applications. The validation is based on some 3D and axisymmetric calculations involving both reacting and non-reacting sprays. In general, the predicted results provide reasonable agreement for both mean droplet sizes (D32) and average droplet velocities but mostly underestimate the droplets sizes in the inner radial region of a cylindrical jet.

CFD Simulation and Experimental Validation of Fluid Flow and Particle Transport in a Model of Alveolated Airways

PubMed Central

Ma, Baoshun; Ruwet, Vincent; Corieri, Patricia; Theunissen, Raf; Riethmuller, Michel; Darquenne, Chantal

2009-01-01

Accurate modeling of air flow and aerosol transport in the alveolated airways is essential for quantitative predictions of pulmonary aerosol deposition. However, experimental validation of such modeling studies has been scarce. The objective of this study is to validate CFD predictions of flow field and particle trajectory with experiments within a scaled-up model of alveolated airways. Steady flow (Re = 0.13) of silicone oil was captured by particle image velocimetry (PIV), and the trajectories of 0.5 mm and 1.2 mm spherical iron beads (representing 0.7 to 14.6 μm aerosol in vivo) were obtained by particle tracking velocimetry (PTV). At twelve selected cross sections, the velocity profiles obtained by CFD matched well with those by PIV (within 1.7% on average). The CFD predicted trajectories also matched well with PTV experiments. These results showed that air flow and aerosol transport in models of human alveolated airways can be simulated by CFD techniques with reasonable accuracy. PMID:20161301

CFD Simulation and Experimental Validation of Fluid Flow and Particle Transport in a Model of Alveolated Airways.

PubMed

Ma, Baoshun; Ruwet, Vincent; Corieri, Patricia; Theunissen, Raf; Riethmuller, Michel; Darquenne, Chantal

2009-05-01

Accurate modeling of air flow and aerosol transport in the alveolated airways is essential for quantitative predictions of pulmonary aerosol deposition. However, experimental validation of such modeling studies has been scarce. The objective of this study is to validate CFD predictions of flow field and particle trajectory with experiments within a scaled-up model of alveolated airways. Steady flow (Re = 0.13) of silicone oil was captured by particle image velocimetry (PIV), and the trajectories of 0.5 mm and 1.2 mm spherical iron beads (representing 0.7 to 14.6 mum aerosol in vivo) were obtained by particle tracking velocimetry (PTV). At twelve selected cross sections, the velocity profiles obtained by CFD matched well with those by PIV (within 1.7% on average). The CFD predicted trajectories also matched well with PTV experiments. These results showed that air flow and aerosol transport in models of human alveolated airways can be simulated by CFD techniques with reasonable accuracy.

Cross-cultural adaptation and validation to Brazil of the Obesity-related Problems Scale.

PubMed

Brasil, Andreia Mara Brolezzi; Brasil, Fábio; Maurício, Angélica Aparecida; Vilela, Regina Maria

2017-01-01

To validate a reliable version of the Obesity-related Problems Scale in Portuguese to use it in Brazil. The Obesity-related Problems Scale was translated and transculturally adapted. Later it was simultaneously self-applied with a 12-item version of the World Health Organization Disability Assessment Schedule 2.0 (WHODAS 2.0), to 50 obese patients and 50 non-obese individuals, and applied again to half of them after 14 days. The Obesity-related Problems scale was able to differentiate obese from non-obese individuals with higher accuracy than WHODAS 2.0, correlating with this scale and with body mass index. The factor analysis determined a two-dimensional structure, which was confirmed with χ2/df=1.81, SRMR=0.05, and CFI=0.97. The general a coefficient was 0.90 and the inter-item intra-class correlation, in the reapplication, ranged from 0.75 to 0.87. The scale proved to be valid and reliable for use in the Brazilian population, without the need to exclude items.

Experimentally validated modification to Cook-Torrance BRDF model for improved accuracy

NASA Astrophysics Data System (ADS)

Butler, Samuel D.; Ethridge, James A.; Nauyoks, Stephen E.; Marciniak, Michael A.

2017-09-01

The BRDF describes optical scatter off realistic surfaces. The microfacet BRDF model assumes geometric optics but is computationally simple compared to wave optics models. In this work, MERL BRDF data is fitted to the original Cook-Torrance microfacet model, and a modified Cook-Torrance model using the polarization factor in place of the mathematically problematic cross section conversion and geometric attenuation terms. The results provide experimental evidence that this modified Cook-Torrance model leads to improved fits, particularly for large incident and scattered angles. These results are expected to lead to more accurate BRDF modeling for remote sensing.

Multiclassifier fusion in human brain MR segmentation: modelling convergence.

PubMed

Heckemann, Rolf A; Hajnal, Joseph V; Aljabar, Paul; Rueckert, Daniel; Hammers, Alexander

2006-01-01

Segmentations of MR images of the human brain can be generated by propagating an existing atlas label volume to the target image. By fusing multiple propagated label volumes, the segmentation can be improved. We developed a model that predicts the improvement of labelling accuracy and precision based on the number of segmentations used as input. Using a cross-validation study on brain image data as well as numerical simulations, we verified the model. Fit parameters of this model are potential indicators of the quality of a given label propagation method or the consistency of the input segmentations used.

Part-of-speech tagging for clinical text: wall or bridge between institutions?

PubMed Central

Fan, Jung-wei; Prasad, Rashmi; Yabut, Rommel M.; Loomis, Richard M.; Zisook, Daniel S.; Mattison, John E.; Huang, Yang

2011-01-01

Part-of-speech (POS) tagging is a fundamental step required by various NLP systems. The training of a POS tagger relies on sufficient quality annotations. However, the annotation process is both knowledge-intensive and time-consuming in the clinical domain. A promising solution appears to be for institutions to share their annotation efforts, and yet there is little research on associated issues. We performed experiments to understand how POS tagging performance would be affected by using a pre-trained tagger versus raw training data across different institutions. We manually annotated a set of clinical notes at Kaiser Permanente Southern California (KPSC) and a set from the University of Pittsburg Medical Center (UPMC), and trained/tested POS taggers with intra- and inter-institution settings. The cTAKES POS tagger was also included in the comparison to represent a tagger partially trained from the notes of a third institution, Mayo Clinic at Rochester. Intra-institution 5-fold cross-validation estimated an accuracy of 0.953 and 0.945 on the KPSC and UPMC notes respectively. Trained purely on KPSC notes, the accuracy was 0.897 when tested on UPMC notes. Trained purely on UPMC notes, the accuracy was 0.904 when tested on KPSC notes. Applying the cTAKES tagger pre-trained with Mayo Clinic’s notes, the accuracy was 0.881 on KPSC notes and 0.883 on UPMC notes. After adding UPMC annotations to KPSC training data, the average accuracy on tested KPSC notes increased to 0.965. After adding KPSC annotations to UPMC training data, the average accuracy on tested UPMC notes increased to 0.953. The results indicated: first, the performance of pre-trained POS taggers dropped about 5% when applied directly across the institutions; second, mixing annotations from another institution following the same guideline increased tagging accuracy for about 1%. Our findings suggest that institutions can benefit more from sharing raw annotations but less from sharing pre-trained models for the POS tagging task. We believe the study could also provide general insights on cross-institution data sharing for other types of NLP tasks. PMID:22195091

Part-of-speech tagging for clinical text: wall or bridge between institutions?

PubMed

Fan, Jung-wei; Prasad, Rashmi; Yabut, Rommel M; Loomis, Richard M; Zisook, Daniel S; Mattison, John E; Huang, Yang

2011-01-01

Part-of-speech (POS) tagging is a fundamental step required by various NLP systems. The training of a POS tagger relies on sufficient quality annotations. However, the annotation process is both knowledge-intensive and time-consuming in the clinical domain. A promising solution appears to be for institutions to share their annotation efforts, and yet there is little research on associated issues. We performed experiments to understand how POS tagging performance would be affected by using a pre-trained tagger versus raw training data across different institutions. We manually annotated a set of clinical notes at Kaiser Permanente Southern California (KPSC) and a set from the University of Pittsburg Medical Center (UPMC), and trained/tested POS taggers with intra- and inter-institution settings. The cTAKES POS tagger was also included in the comparison to represent a tagger partially trained from the notes of a third institution, Mayo Clinic at Rochester. Intra-institution 5-fold cross-validation estimated an accuracy of 0.953 and 0.945 on the KPSC and UPMC notes respectively. Trained purely on KPSC notes, the accuracy was 0.897 when tested on UPMC notes. Trained purely on UPMC notes, the accuracy was 0.904 when tested on KPSC notes. Applying the cTAKES tagger pre-trained with Mayo Clinic's notes, the accuracy was 0.881 on KPSC notes and 0.883 on UPMC notes. After adding UPMC annotations to KPSC training data, the average accuracy on tested KPSC notes increased to 0.965. After adding KPSC annotations to UPMC training data, the average accuracy on tested UPMC notes increased to 0.953. The results indicated: first, the performance of pre-trained POS taggers dropped about 5% when applied directly across the institutions; second, mixing annotations from another institution following the same guideline increased tagging accuracy for about 1%. Our findings suggest that institutions can benefit more from sharing raw annotations but less from sharing pre-trained models for the POS tagging task. We believe the study could also provide general insights on cross-institution data sharing for other types of NLP tasks.

A comparison of different chemometrics approaches for the robust classification of electronic nose data.

PubMed

Gromski, Piotr S; Correa, Elon; Vaughan, Andrew A; Wedge, David C; Turner, Michael L; Goodacre, Royston

2014-11-01

Accurate detection of certain chemical vapours is important, as these may be diagnostic for the presence of weapons, drugs of misuse or disease. In order to achieve this, chemical sensors could be deployed remotely. However, the readout from such sensors is a multivariate pattern, and this needs to be interpreted robustly using powerful supervised learning methods. Therefore, in this study, we compared the classification accuracy of four pattern recognition algorithms which include linear discriminant analysis (LDA), partial least squares-discriminant analysis (PLS-DA), random forests (RF) and support vector machines (SVM) which employed four different kernels. For this purpose, we have used electronic nose (e-nose) sensor data (Wedge et al., Sensors Actuators B Chem 143:365-372, 2009). In order to allow direct comparison between our four different algorithms, we employed two model validation procedures based on either 10-fold cross-validation or bootstrapping. The results show that LDA (91.56% accuracy) and SVM with a polynomial kernel (91.66% accuracy) were very effective at analysing these e-nose data. These two models gave superior prediction accuracy, sensitivity and specificity in comparison to the other techniques employed. With respect to the e-nose sensor data studied here, our findings recommend that SVM with a polynomial kernel should be favoured as a classification method over the other statistical models that we assessed. SVM with non-linear kernels have the advantage that they can be used for classifying non-linear as well as linear mapping from analytical data space to multi-group classifications and would thus be a suitable algorithm for the analysis of most e-nose sensor data.

A prior feature SVM – MRF based method for mouse brain segmentation

PubMed Central

Wu, Teresa; Bae, Min Hyeok; Zhang, Min; Pan, Rong; Badea, Alexandra

2012-01-01

We introduce an automated method, called prior feature Support Vector Machine- Markov Random Field (pSVMRF), to segment three-dimensional mouse brain Magnetic Resonance Microscopy (MRM) images. Our earlier work, extended MRF (eMRF) integrated Support Vector Machine (SVM) and Markov Random Field (MRF) approaches, leading to improved segmentation accuracy; however, the computation of eMRF is very expensive, which may limit its performance on segmentation and robustness. In this study pSVMRF reduces training and testing time for SVM, while boosting segmentation performance. Unlike the eMRF approach, where MR intensity information and location priors are linearly combined, pSVMRF combines this information in a nonlinear fashion, and enhances the discriminative ability of the algorithm. We validate the proposed method using MR imaging of unstained and actively stained mouse brain specimens, and compare segmentation accuracy with two existing methods: eMRF and MRF. C57BL/6 mice are used for training and testing, using cross validation. For formalin fixed C57BL/6 specimens, pSVMRF outperforms both eMRF and MRF. The segmentation accuracy for C57BL/6 brains, stained or not, was similar for larger structures like hippocampus and caudate putamen, (~87%), but increased substantially for smaller regions like susbtantia nigra (from 78.36% to 91.55%), and anterior commissure (from ~50% to ~80%). To test segmentation robustness against increased anatomical variability we add two strains, BXD29 and a transgenic mouse model of Alzheimer’s Disease. Segmentation accuracy for new strains is 80% for hippocampus, and caudate putamen, indicating that pSVMRF is a promising approach for phenotyping mouse models of human brain disorders. PMID:21988893

A prior feature SVM-MRF based method for mouse brain segmentation.

PubMed

Wu, Teresa; Bae, Min Hyeok; Zhang, Min; Pan, Rong; Badea, Alexandra

2012-02-01

We introduce an automated method, called prior feature Support Vector Machine-Markov Random Field (pSVMRF), to segment three-dimensional mouse brain Magnetic Resonance Microscopy (MRM) images. Our earlier work, extended MRF (eMRF) integrated Support Vector Machine (SVM) and Markov Random Field (MRF) approaches, leading to improved segmentation accuracy; however, the computation of eMRF is very expensive, which may limit its performance on segmentation and robustness. In this study pSVMRF reduces training and testing time for SVM, while boosting segmentation performance. Unlike the eMRF approach, where MR intensity information and location priors are linearly combined, pSVMRF combines this information in a nonlinear fashion, and enhances the discriminative ability of the algorithm. We validate the proposed method using MR imaging of unstained and actively stained mouse brain specimens, and compare segmentation accuracy with two existing methods: eMRF and MRF. C57BL/6 mice are used for training and testing, using cross validation. For formalin fixed C57BL/6 specimens, pSVMRF outperforms both eMRF and MRF. The segmentation accuracy for C57BL/6 brains, stained or not, was similar for larger structures like hippocampus and caudate putamen, (~87%), but increased substantially for smaller regions like susbtantia nigra (from 78.36% to 91.55%), and anterior commissure (from ~50% to ~80%). To test segmentation robustness against increased anatomical variability we add two strains, BXD29 and a transgenic mouse model of Alzheimer's disease. Segmentation accuracy for new strains is 80% for hippocampus, and caudate putamen, indicating that pSVMRF is a promising approach for phenotyping mouse models of human brain disorders. Copyright © 2011 Elsevier Inc. All rights reserved.

Refining Prediction in Treatment-Resistant Depression: Results of Machine Learning Analyses in the TRD III Sample.

PubMed

Kautzky, Alexander; Dold, Markus; Bartova, Lucie; Spies, Marie; Vanicek, Thomas; Souery, Daniel; Montgomery, Stuart; Mendlewicz, Julien; Zohar, Joseph; Fabbri, Chiara; Serretti, Alessandro; Lanzenberger, Rupert; Kasper, Siegfried

The study objective was to generate a prediction model for treatment-resistant depression (TRD) using machine learning featuring a large set of 47 clinical and sociodemographic predictors of treatment outcome. 552 Patients diagnosed with major depressive disorder (MDD) according to DSM-IV criteria were enrolled between 2011 and 2016. TRD was defined as failure to reach response to antidepressant treatment, characterized by a Montgomery-Asberg Depression Rating Scale (MADRS) score below 22 after at least 2 antidepressant trials of adequate length and dosage were administered. RandomForest (RF) was used for predicting treatment outcome phenotypes in a 10-fold cross-validation. The full model with 47 predictors yielded an accuracy of 75.0%. When the number of predictors was reduced to 15, accuracies between 67.6% and 71.0% were attained for different test sets. The most informative predictors of treatment outcome were baseline MADRS score for the current episode; impairment of family, social, and work life; the timespan between first and last depressive episode; severity; suicidal risk; age; body mass index; and the number of lifetime depressive episodes as well as lifetime duration of hospitalization. With the application of the machine learning algorithm RF, an efficient prediction model with an accuracy of 75.0% for forecasting treatment outcome could be generated, thus surpassing the predictive capabilities of clinical evaluation. We also supply a simplified algorithm of 15 easily collected clinical and sociodemographic predictors that can be obtained within approximately 10 minutes, which reached an accuracy of 70.6%. Thus, we are confident that our model will be validated within other samples to advance an accurate prediction model fit for clinical usage in TRD. © Copyright 2017 Physicians Postgraduate Press, Inc.

Prediction of skin sensitization potency using machine learning approaches.

PubMed

Zang, Qingda; Paris, Michael; Lehmann, David M; Bell, Shannon; Kleinstreuer, Nicole; Allen, David; Matheson, Joanna; Jacobs, Abigail; Casey, Warren; Strickland, Judy

2017-07-01

The replacement of animal use in testing for regulatory classification of skin sensitizers is a priority for US federal agencies that use data from such testing. Machine learning models that classify substances as sensitizers or non-sensitizers without using animal data have been developed and evaluated. Because some regulatory agencies require that sensitizers be further classified into potency categories, we developed statistical models to predict skin sensitization potency for murine local lymph node assay (LLNA) and human outcomes. Input variables for our models included six physicochemical properties and data from three non-animal test methods: direct peptide reactivity assay; human cell line activation test; and KeratinoSens™ assay. Models were built to predict three potency categories using four machine learning approaches and were validated using external test sets and leave-one-out cross-validation. A one-tiered strategy modeled all three categories of response together while a two-tiered strategy modeled sensitizer/non-sensitizer responses and then classified the sensitizers as strong or weak sensitizers. The two-tiered model using the support vector machine with all assay and physicochemical data inputs provided the best performance, yielding accuracy of 88% for prediction of LLNA outcomes (120 substances) and 81% for prediction of human test outcomes (87 substances). The best one-tiered model predicted LLNA outcomes with 78% accuracy and human outcomes with 75% accuracy. By comparison, the LLNA predicts human potency categories with 69% accuracy (60 of 87 substances correctly categorized). These results suggest that computational models using non-animal methods may provide valuable information for assessing skin sensitization potency. Copyright © 2017 John Wiley & Sons, Ltd. Copyright © 2017 John Wiley & Sons, Ltd.

Predicting length of children's psychiatric hospitalizations: an "ecologic" approach.

PubMed

Mossman, D; Songer, D A; Baker, D G

1991-08-01

This article describes the development and validation of a simple and modestly successful model for predicting inpatient length of stay (LOS) at a state-funded facility providing acute to long term care for children and adolescents in Ohio. Six variables--diagnostic group, legal status at time of admission, attending physician, age, sex, and county of residence--explained 30% of the variation in log10LOS in the subgroup used to create the model, and 26% of log10LOS variation in the cross-validation subgroup. The model also identified LOS outliers with moderate accuracy (ROC area = .68-0.76). The authors attribute the model's success to inclusion of variables that are correlated to idiosyncratic "ecologic" factors as well as variables related to severity of illness. Future attempts to construct LOS models may adopt similar approaches.

CarcinoPred-EL: Novel models for predicting the carcinogenicity of chemicals using molecular fingerprints and ensemble learning methods.

PubMed

Zhang, Li; Ai, Haixin; Chen, Wen; Yin, Zimo; Hu, Huan; Zhu, Junfeng; Zhao, Jian; Zhao, Qi; Liu, Hongsheng

2017-05-18

Carcinogenicity refers to a highly toxic end point of certain chemicals, and has become an important issue in the drug development process. In this study, three novel ensemble classification models, namely Ensemble SVM, Ensemble RF, and Ensemble XGBoost, were developed to predict carcinogenicity of chemicals using seven types of molecular fingerprints and three machine learning methods based on a dataset containing 1003 diverse compounds with rat carcinogenicity. Among these three models, Ensemble XGBoost is found to be the best, giving an average accuracy of 70.1 ± 2.9%, sensitivity of 67.0 ± 5.0%, and specificity of 73.1 ± 4.4% in five-fold cross-validation and an accuracy of 70.0%, sensitivity of 65.2%, and specificity of 76.5% in external validation. In comparison with some recent methods, the ensemble models outperform some machine learning-based approaches and yield equal accuracy and higher specificity but lower sensitivity than rule-based expert systems. It is also found that the ensemble models could be further improved if more data were available. As an application, the ensemble models are employed to discover potential carcinogens in the DrugBank database. The results indicate that the proposed models are helpful in predicting the carcinogenicity of chemicals. A web server called CarcinoPred-EL has been built for these models ( http://ccsipb.lnu.edu.cn/toxicity/CarcinoPred-EL/ ).

Wearable technology and ECG processing for fall risk assessment, prevention and detection.

PubMed

Melillo, Paolo; Castaldo, Rossana; Sannino, Giovanna; Orrico, Ada; de Pietro, Giuseppe; Pecchia, Leandro

2015-01-01

Falls represent one of the most common causes of injury-related morbidity and mortality in later life. Subjects with cardiovascular disorders (e.g., related to autonomic dysfunctions and postural hypotension) are at higher risk of falling. Autonomic dysfunctions increasing the risk of falling in the short and mid-term could be assessed by Heart Rate Variability (HRV) extracted by electrocardiograph (ECG). We developed three trials for assessing the usefulness of ECG monitoring using wearable devices for: risk assessment of falling in the next few weeks; prevention of imminent falls due to standing hypotension; and fall detection. Statistical and data-mining methods are adopted to develop classification and regression models, validated with the cross-validation approach. The first classifier based on HRV features enabled to identify future fallers among hypertensive patients with an accuracy of 72% (sensitivity: 51.1%, specificity: 80.2%). The regression model to predict falls due to orthostatic dropdown from HRV recorded before standing achieved an overall accuracy of 80% (sensitivity: 92%, specificity: 90%). Finally, the classifier to detect simulated falls using ECG achieved an accuracy of 77.3% (sensitivity: 81.8%, specificity: 72.7%). The evidence from these three studies showed that ECG monitoring and processing could achieve satisfactory performances compared to other system for risk assessment, fall prevention and detection. This is interesting as differently from other technologies actually employed to prevent falls, ECG is recommended for many other pathologies of later life and is more accepted by senior citizens.

Aqueous two-phase systems enable multiplexing of homogeneous immunoassays

PubMed Central

Simon, Arlyne B.; Frampton, John P.; Huang, Nien-Tsu; Kurabayashi, Katsuo; Paczesny, Sophie; Takayama, Shuichi

2014-01-01

Quantitative measurement of protein biomarkers is critical for biomarker validation and early disease detection. Current multiplex immunoassays are time consuming costly and can suffer from low accuracy. For example, multiplex ELISAs require multiple, tedious, washing and blocking steps. Moreover, they suffer from nonspecific antibody cross-reactions, leading to high background and false-positive signals. Here, we show that co-localizing antibody-bead pairs in an aqueous two-phase system (ATPS) enables multiplexing of sensitive, no-wash, homogeneous assays, while preventing nonspecific antibody cross-reactions. Our cross-reaction-free, multiplex assay can simultaneously detect picomolar concentrations of four protein biomarkers ((C-X-C motif) ligand 10 (CXCL10), CXCL9, interleukin (IL)-8 and IL-6) in cell supernatants using a single assay well. The potential clinical utility of the assay is demonstrated by detecting diagnostic biomarkers (CXCL10 and CXCL9) in plasma from 88 patients at the onset of the clinical symptoms of chronic graft-versus-host disease (GVHD). PMID:25083509

Mutual coupling effects in antenna arrays, volume 1

NASA Technical Reports Server (NTRS)

Collin, R. E.

1986-01-01

Mutual coupling between rectangular apertures in a finite antenna array, in an infinite ground plane, is analyzed using the vector potential approach. The method of moments is used to solve the equations that result from setting the tangential magnetic fields across each aperture equal. The approximation uses a set of vector potential model functions to solve for equivalent magnetic currents. A computer program was written to carry out this analysis and the resulting currents were used to determine the co- and cross-polarized far zone radiation patterns. Numerical results for various arrays using several modes in the approximation are presented. Results for one and two aperture arrays are compared against published data to check on the agreement of this model with previous work. Computer derived results are also compared against experimental results to test the accuracy of the model. These tests of the accuracy of the program showed that it yields valid data.

Initial attitude determination for the hipparcos satellite

NASA Astrophysics Data System (ADS)

Van der Ha, Jozef C.

The present paper described the strategy and algorithms used during the initial on-ground three-axes attitude determination of ESA's astrometry satellite HIPPARCOS. The estimation is performed using calculated crossing times of identified stars over the Star Mapper's vertical and inclined slit systems as well as outputs from a set of rate-integrating gyros. Valid star transits in either of the two fields of view are expected to occur in average about every 30 s whereas the gyros are sampled at about 1 Hz. The state vector to be estimated consists of the three angles, three rates and three gyro drift rate components. Simulations have shown that convergence of the estimator is established within about 10 min and that the accuracies achieved are in the order of a few arcsec for the angles and a few milliarcsec per s for the rates. These stringent accuracies are in fact required for initialisation of subsequent autonomous on-board real-time attitude determination.

seXY: a tool for sex inference from genotype arrays.

PubMed

Qian, David C; Busam, Jonathan A; Xiao, Xiangjun; O'Mara, Tracy A; Eeles, Rosalind A; Schumacher, Frederick R; Phelan, Catherine M; Amos, Christopher I

2017-02-15

Checking concordance between reported sex and genotype-inferred sex is a crucial quality control measure in genome-wide association studies (GWAS). However, limited insights exist regarding the true accuracy of software that infer sex from genotype array data. We present seXY, a logistic regression model trained on both X chromosome heterozygosity and Y chromosome missingness, that consistently demonstrated >99.5% sex inference accuracy in cross-validation for 889 males and 5,361 females enrolled in prostate cancer and ovarian cancer GWAS. Compared to PLINK, one of the most popular tools for sex inference in GWAS that assesses only X chromosome heterozygosity, seXY achieved marginally better male classification and 3% more accurate female classification. https://github.com/Christopher-Amos-Lab/seXY. Christopher.I.Amos@dartmouth.edu. Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Personalized recommendation based on preferential bidirectional mass diffusion

NASA Astrophysics Data System (ADS)

Chen, Guilin; Gao, Tianrun; Zhu, Xuzhen; Tian, Hui; Yang, Zhao

2017-03-01

Recommendation system provides a promising way to alleviate the dilemma of information overload. In physical dynamics, mass diffusion has been used to design effective recommendation algorithms on bipartite network. However, most of the previous studies focus overwhelmingly on unidirectional mass diffusion from collected objects to uncollected objects, while overlooking the opposite direction, leading to the risk of similarity estimation deviation and performance degradation. In addition, they are biased towards recommending popular objects which will not necessarily promote the accuracy but make the recommendation lack diversity and novelty that indeed contribute to the vitality of the system. To overcome the aforementioned disadvantages, we propose a preferential bidirectional mass diffusion (PBMD) algorithm by penalizing the weight of popular objects in bidirectional diffusion. Experiments are evaluated on three benchmark datasets (Movielens, Netflix and Amazon) by 10-fold cross validation, and results indicate that PBMD remarkably outperforms the mainstream methods in accuracy, diversity and novelty.

Efficient HIK SVM learning for image classification.

PubMed

Wu, Jianxin

2012-10-01

Histograms are used in almost every aspect of image processing and computer vision, from visual descriptors to image representations. Histogram intersection kernel (HIK) and support vector machine (SVM) classifiers are shown to be very effective in dealing with histograms. This paper presents contributions concerning HIK SVM for image classification. First, we propose intersection coordinate descent (ICD), a deterministic and scalable HIK SVM solver. ICD is much faster than, and has similar accuracies to, general purpose SVM solvers and other fast HIK SVM training methods. We also extend ICD to the efficient training of a broader family of kernels. Second, we show an important empirical observation that ICD is not sensitive to the C parameter in SVM, and we provide some theoretical analyses to explain this observation. ICD achieves high accuracies in many problems, using its default parameters. This is an attractive property for practitioners, because many image processing tasks are too large to choose SVM parameters using cross-validation.

Extending the accuracy of the SNAP interatomic potential form

NASA Astrophysics Data System (ADS)

Wood, Mitchell A.; Thompson, Aidan P.

2018-06-01

The Spectral Neighbor Analysis Potential (SNAP) is a classical interatomic potential that expresses the energy of each atom as a linear function of selected bispectrum components of the neighbor atoms. An extension of the SNAP form is proposed that includes quadratic terms in the bispectrum components. The extension is shown to provide a large increase in accuracy relative to the linear form, while incurring only a modest increase in computational cost. The mathematical structure of the quadratic SNAP form is similar to the embedded atom method (EAM), with the SNAP bispectrum components serving as counterparts to the two-body density functions in EAM. The effectiveness of the new form is demonstrated using an extensive set of training data for tantalum structures. Similar to artificial neural network potentials, the quadratic SNAP form requires substantially more training data in order to prevent overfitting. The quality of this new potential form is measured through a robust cross-validation analysis.

Sex Assessment from the Volume of the First Metatarsal Bone: A Comparison of Linear and Volume Measurements.

PubMed

Gibelli, Daniele; Poppa, Pasquale; Cummaudo, Marco; Mattia, Mirko; Cappella, Annalisa; Mazzarelli, Debora; Zago, Matteo; Sforza, Chiarella; Cattaneo, Cristina

2017-11-01

Sexual dimorphism is a crucial characteristic of skeleton. In the last years, volumetric and surface 3D acquisition systems have enabled anthropologists to assess surfaces and volumes, whose potential still needs to be verified. This article aimed at assessing volume and linear parameters of the first metatarsal bone through 3D acquisition by laser scanning. Sixty-eight skeletons underwent 3D scan through laser scanner: Seven linear measurements and volume from each bone were assessed. A cutoff value of 13,370 mm 3 was found, with an accuracy of 80.8%. Linear measurements outperformed volume: metatarsal length and mediolateral width of base showed higher cross-validated accuracies (respectively, 82.1% and 79.1%, raising at 83.6% when both of them were included). Further studies are needed to verify the real advantage for sex assessment provided by volume measurements. © 2017 American Academy of Forensic Sciences.

Geolocation error tracking of ZY-3 three line cameras

NASA Astrophysics Data System (ADS)

Pan, Hongbo

2017-01-01

The high-accuracy geolocation of high-resolution satellite images (HRSIs) is a key issue for mapping and integrating multi-temporal, multi-sensor images. In this manuscript, we propose a new geometric frame for analysing the geometric error of a stereo HRSI, in which the geolocation error can be divided into three parts: the epipolar direction, cross base direction, and height direction. With this frame, we proved that the height error of three line cameras (TLCs) is independent of nadir images, and that the terrain effect has a limited impact on the geolocation errors. For ZY-3 error sources, the drift error in both the pitch and roll angle and its influence on the geolocation accuracy are analysed. Epipolar and common tie-point constraints are proposed to study the bundle adjustment of HRSIs. Epipolar constraints explain that the relative orientation can reduce the number of compensation parameters in the cross base direction and have a limited impact on the height accuracy. The common tie points adjust the pitch-angle errors to be consistent with each other for TLCs. Therefore, free-net bundle adjustment of a single strip cannot significantly improve the geolocation accuracy. Furthermore, the epipolar and common tie-point constraints cause the error to propagate into the adjacent strip when multiple strips are involved in the bundle adjustment, which results in the same attitude uncertainty throughout the whole block. Two adjacent strips-Orbit 305 and Orbit 381, covering 7 and 12 standard scenes separately-and 308 ground control points (GCPs) were used for the experiments. The experiments validate the aforementioned theory. The planimetric and height root mean square errors were 2.09 and 1.28 m, respectively, when two GCPs were settled at the beginning and end of the block.

Photographic Volume Estimation of CPAS Main Parachutes

NASA Technical Reports Server (NTRS)

Ray, Eric S.

2017-01-01

Capsule Parachute Assembly System (CPAS) flight tests regularly stage a helicopter to observe inflation of 116 ft D o ringsail Main parachutes. These side views can be used to generate 3-D models of inflating canopies to estimate enclosed volume. Assuming a surface of revolution is inadequate because reefed canopies in a cluster are elongated due to mutual aerodynamic interference. A method was developed to combine the side views with upward looking HD video to account for non-circular cross sections. Approximating the cross sections as elliptical greatly improves accuracy. But since that correction requires manually tracing projected outlines, the actual irregular shapes can be used to generate high fidelity models. Compensation is also made for apparent tilt angle. Validation was accomplished by comparing perimeter and projected area with known line lengths and/or high quality photogrammetry.

Cross-Coupled Control for All-Terrain Rovers

PubMed Central

Reina, Giulio

2013-01-01

Mobile robots are increasingly being used in challenging outdoor environments for applications that include construction, mining, agriculture, military and planetary exploration. In order to accomplish the planned task, it is critical that the motion control system ensure accuracy and robustness. The achievement of high performance on rough terrain is tightly connected with the minimization of vehicle-terrain dynamics effects such as slipping and skidding. This paper presents a cross-coupled controller for a 4-wheel-drive/4-wheel-steer robot, which optimizes the wheel motors' control algorithm to reduce synchronization errors that would otherwise result in wheel slip with conventional controllers. Experimental results, obtained with an all-terrain rover operating on agricultural terrain, are presented to validate the system. It is shown that the proposed approach is effective in reducing slippage and vehicle posture errors. PMID:23299625

Multi-class biological tissue classification based on a multi-classifier: Preliminary study of an automatic output power control for ultrasonic surgical units.

PubMed

Youn, Su Hyun; Sim, Taeyong; Choi, Ahnryul; Song, Jinsung; Shin, Ki Young; Lee, Il Kwon; Heo, Hyun Mu; Lee, Daeweon; Mun, Joung Hwan

2015-06-01

Ultrasonic surgical units (USUs) have the advantage of minimizing tissue damage during surgeries that require tissue dissection by reducing problems such as coagulation and unwanted carbonization, but the disadvantage of requiring manual adjustment of power output according to the target tissue. In order to overcome this limitation, it is necessary to determine the properties of in vivo tissues automatically. We propose a multi-classifier that can accurately classify tissues based on the unique impedance of each tissue. For this purpose, a multi-classifier was built based on single classifiers with high classification rates, and the classification accuracy of the proposed model was compared with that of single classifiers for various electrode types (Type-I: 6 mm invasive; Type-II: 3 mm invasive; Type-III: surface). The sensitivity and positive predictive value (PPV) of the multi-classifier by cross checks were determined. According to the 10-fold cross validation results, the classification accuracy of the proposed model was significantly higher (p<0.05 or <0.01) than that of existing single classifiers for all electrode types. In particular, the classification accuracy of the proposed model was highest when the 3mm invasive electrode (Type-II) was used (sensitivity=97.33-100.00%; PPV=96.71-100.00%). The results of this study are an important contribution to achieving automatic optimal output power adjustment of USUs according to the properties of individual tissues. Copyright © 2015 Elsevier Ltd. All rights reserved.

Modeling time-to-event (survival) data using classification tree analysis.

PubMed

Linden, Ariel; Yarnold, Paul R

2017-12-01

Time to the occurrence of an event is often studied in health research. Survival analysis differs from other designs in that follow-up times for individuals who do not experience the event by the end of the study (called censored) are accounted for in the analysis. Cox regression is the standard method for analysing censored data, but the assumptions required of these models are easily violated. In this paper, we introduce classification tree analysis (CTA) as a flexible alternative for modelling censored data. Classification tree analysis is a "decision-tree"-like classification model that provides parsimonious, transparent (ie, easy to visually display and interpret) decision rules that maximize predictive accuracy, derives exact P values via permutation tests, and evaluates model cross-generalizability. Using empirical data, we identify all statistically valid, reproducible, longitudinally consistent, and cross-generalizable CTA survival models and then compare their predictive accuracy to estimates derived via Cox regression and an unadjusted naïve model. Model performance is assessed using integrated Brier scores and a comparison between estimated survival curves. The Cox regression model best predicts average incidence of the outcome over time, whereas CTA survival models best predict either relatively high, or low, incidence of the outcome over time. Classification tree analysis survival models offer many advantages over Cox regression, such as explicit maximization of predictive accuracy, parsimony, statistical robustness, and transparency. Therefore, researchers interested in accurate prognoses and clear decision rules should consider developing models using the CTA-survival framework. © 2017 John Wiley & Sons, Ltd.

An Efficient Correction Algorithm for Eliminating Image Misalignment Effects on Co-Phasing Measurement Accuracy for Segmented Active Optics Systems

PubMed Central

Yue, Dan; Xu, Shuyan; Nie, Haitao; Wang, Zongyang

2016-01-01

The misalignment between recorded in-focus and out-of-focus images using the Phase Diversity (PD) algorithm leads to a dramatic decline in wavefront detection accuracy and image recovery quality for segmented active optics systems. This paper demonstrates the theoretical relationship between the image misalignment and tip-tilt terms in Zernike polynomials of the wavefront phase for the first time, and an efficient two-step alignment correction algorithm is proposed to eliminate these misalignment effects. This algorithm processes a spatial 2-D cross-correlation of the misaligned images, revising the offset to 1 or 2 pixels and narrowing the search range for alignment. Then, it eliminates the need for subpixel fine alignment to achieve adaptive correction by adding additional tip-tilt terms to the Optical Transfer Function (OTF) of the out-of-focus channel. The experimental results demonstrate the feasibility and validity of the proposed correction algorithm to improve the measurement accuracy during the co-phasing of segmented mirrors. With this alignment correction, the reconstructed wavefront is more accurate, and the recovered image is of higher quality. PMID:26934045

Identifying Autism from Resting-State fMRI Using Long Short-Term Memory Networks.

PubMed

Dvornek, Nicha C; Ventola, Pamela; Pelphrey, Kevin A; Duncan, James S

2017-09-01

Functional magnetic resonance imaging (fMRI) has helped characterize the pathophysiology of autism spectrum disorders (ASD) and carries promise for producing objective biomarkers for ASD. Recent work has focused on deriving ASD biomarkers from resting-state functional connectivity measures. However, current efforts that have identified ASD with high accuracy were limited to homogeneous, small datasets, while classification results for heterogeneous, multi-site data have shown much lower accuracy. In this paper, we propose the use of recurrent neural networks with long short-term memory (LSTMs) for classification of individuals with ASD and typical controls directly from the resting-state fMRI time-series. We used the entire large, multi-site Autism Brain Imaging Data Exchange (ABIDE) I dataset for training and testing the LSTM models. Under a cross-validation framework, we achieved classification accuracy of 68.5%, which is 9% higher than previously reported methods that used fMRI data from the whole ABIDE cohort. Finally, we presented interpretation of the trained LSTM weights, which highlight potential functional networks and regions that are known to be implicated in ASD.

Identifying Autism from Resting-State fMRI Using Long Short-Term Memory Networks

PubMed Central

Dvornek, Nicha C.; Ventola, Pamela; Pelphrey, Kevin A.; Duncan, James S.

2017-01-01

Functional magnetic resonance imaging (fMRI) has helped characterize the pathophysiology of autism spectrum disorders (ASD) and carries promise for producing objective biomarkers for ASD. Recent work has focused on deriving ASD biomarkers from resting-state functional connectivity measures. However, current efforts that have identified ASD with high accuracy were limited to homogeneous, small datasets, while classification results for heterogeneous, multi-site data have shown much lower accuracy. In this paper, we propose the use of recurrent neural networks with long short-term memory (LSTMs) for classification of individuals with ASD and typical controls directly from the resting-state fMRI time-series. We used the entire large, multi-site Autism Brain Imaging Data Exchange (ABIDE) I dataset for training and testing the LSTM models. Under a cross-validation framework, we achieved classification accuracy of 68.5%, which is 9% higher than previously reported methods that used fMRI data from the whole ABIDE cohort. Finally, we presented interpretation of the trained LSTM weights, which highlight potential functional networks and regions that are known to be implicated in ASD. PMID:29104967

S-193 scatterometer backscattering cross section precision/accuracy for Skylab 2 and 3 missions

NASA Technical Reports Server (NTRS)

Krishen, K.; Pounds, D. J.

1975-01-01

Procedures for measuring the precision and accuracy with which the S-193 scatterometer measured the background cross section of ground scenes are described. Homogeneous ground sites were selected, and data from Skylab missions were analyzed. The precision was expressed as the standard deviation of the scatterometer-acquired backscattering cross section. In special cases, inference of the precision of measurement was made by considering the total range from the maximum to minimum of the backscatter measurements within a data segment, rather than the standard deviation. For Skylab 2 and 3 missions a precision better than 1.5 dB is indicated. This procedure indicates an accuracy of better than 3 dB for the Skylab 2 and 3 missions. The estimates of precision and accuracy given in this report are for backscattering cross sections from -28 to 18 dB. Outside this range the precision and accuracy decrease significantly.

Psychometric evaluation of dietary self-efficacy and outcome expectation scales in female college freshmen.

PubMed

Kedem, Leia E; Evans, Ellen M; Chapman-Novakofski, Karen

2014-11-01

Lifestyle interventions commonly measure psychosocial beliefs as precursors to positive behavior change, but often overlook questionnaire validation. This can affect measurement accuracy if the survey has been developed for a different population, as differing behavioral influences may affect instrument validity. The present study aimed to explore psychometric properties of self-efficacy and outcome expectation scales-originally developed for younger children-in a population of female college freshmen (N = 268). Exploratory principal component analysis was used to investigate underlying data patterns and assess validity of previously published subscales. Composite scores for reliable subscales (Cronbach's α ≥ .70) were calculated to help characterize self-efficacy and outcome expectation beliefs in this population. The outcome expectation factor structure clearly comprised of positive (α = .81-.90) and negative outcomes (α = .63-.67). The self-efficacy factor structure included themes of motivation and effort (α = .75-.94), but items pertaining to hunger and availability cross-loaded often. Based on cross-loading patterns and low Cronbach's alpha values, respectively, self-efficacy items regarding barriers to healthy eating and negative outcome expectation items should be refined to improve reliability. Composite scores suggested that eating healthfully was associated with positive outcomes, but self-efficacy to do so was lower. Thus, dietary interventions for college students may be more successful by including skill-building activities to enhance self-efficacy and increase the likelihood of behavior change. © The Author(s) 2014.

Triaging Patient Complaints: Monte Carlo Cross-Validation of Six Machine Learning Classifiers

PubMed Central

Cooper, William O; Catron, Thomas F; Karrass, Jan; Zhang, Zhe; Singh, Munindar P

2017-01-01

Background Unsolicited patient complaints can be a useful service recovery tool for health care organizations. Some patient complaints contain information that may necessitate further action on the part of the health care organization and/or the health care professional. Current approaches depend on the manual processing of patient complaints, which can be costly, slow, and challenging in terms of scalability. Objective The aim of this study was to evaluate automatic patient triage, which can potentially improve response time and provide much-needed scale, thereby enhancing opportunities to encourage physicians to self-regulate. Methods We implemented a comparison of several well-known machine learning classifiers to detect whether a complaint was associated with a physician or his/her medical practice. We compared these classifiers using a real-life dataset containing 14,335 patient complaints associated with 768 physicians that was extracted from patient complaints collected by the Patient Advocacy Reporting System developed at Vanderbilt University and associated institutions. We conducted a 10-splits Monte Carlo cross-validation to validate our results. Results We achieved an accuracy of 82% and F-score of 81% in correctly classifying patient complaints with sensitivity and specificity of 0.76 and 0.87, respectively. Conclusions We demonstrate that natural language processing methods based on modeling patient complaint text can be effective in identifying those patient complaints requiring physician action. PMID:28760726

Noninvasive Classification of Hepatic Fibrosis Based on Texture Parameters From Double Contrast-Enhanced Magnetic Resonance Images

PubMed Central

Bahl, Gautam; Cruite, Irene; Wolfson, Tanya; Gamst, Anthony C.; Collins, Julie M.; Chavez, Alyssa D.; Barakat, Fatma; Hassanein, Tarek; Sirlin, Claude B.

2016-01-01

Purpose To demonstrate a proof of concept that quantitative texture feature analysis of double contrast-enhanced magnetic resonance imaging (MRI) can classify fibrosis noninvasively, using histology as a reference standard. Materials and Methods A Health Insurance Portability and Accountability Act (HIPAA)-compliant Institutional Review Board (IRB)-approved retrospective study of 68 patients with diffuse liver disease was performed at a tertiary liver center. All patients underwent double contrast-enhanced MRI, with histopathology-based staging of fibrosis obtained within 12 months of imaging. The MaZda software program was used to compute 279 texture parameters for each image. A statistical regularization technique, generalized linear model (GLM)-path, was used to develop a model based on texture features for dichotomous classification of fibrosis category (F ≤2 vs. F ≥3) of the 68 patients, with histology as the reference standard. The model's performance was assessed and cross-validated. There was no additional validation performed on an independent cohort. Results Cross-validated sensitivity, specificity, and total accuracy of the texture feature model in classifying fibrosis were 91.9%, 83.9%, and 88.2%, respectively. Conclusion This study shows proof of concept that accurate, noninvasive classification of liver fibrosis is possible by applying quantitative texture analysis to double contrast-enhanced MRI. Further studies are needed in independent cohorts of subjects. PMID:22851409

New clinical validation method for automated sphygmomanometer: a proposal by Japan ISO-WG for sphygmomanometer standard.

PubMed

Shirasaki, Osamu; Asou, Yosuke; Takahashi, Yukio

2007-12-01

Owing to fast or stepwise cuff deflation, or measuring at places other than the upper arm, the clinical accuracy of most recent automated sphygmomanometers (auto-BPMs) cannot be validated by one-arm simultaneous comparison, which would be the only accurate validation method based on auscultation. Two main alternative methods are provided by current standards, that is, two-arm simultaneous comparison (method 1) and one-arm sequential comparison (method 2); however, the accuracy of these validation methods might not be sufficient to compensate for the suspicious accuracy in lateral blood pressure (BP) differences (LD) and/or BP variations (BPV) between the device and reference readings. Thus, the Japan ISO-WG for sphygmomanometer standards has been studying a new method that might improve validation accuracy (method 3). The purpose of this study is to determine the appropriateness of method 3 by comparing immunity to LD and BPV with those of the current validation methods (methods 1 and 2). The validation accuracy of the above three methods was assessed in human participants [N=120, 45+/-15.3 years (mean+/-SD)]. An oscillometric automated monitor, Omron HEM-762, was used as the tested device. When compared with the others, methods 1 and 3 showed a smaller intra-individual standard deviation of device error (SD1), suggesting their higher reproducibility of validation. The SD1 by method 2 (P=0.004) significantly correlated with the participant's BP, supporting our hypothesis that the increased SD of device error by method 2 is at least partially caused by essential BPV. Method 3 showed a significantly (P=0.0044) smaller interparticipant SD of device error (SD2), suggesting its higher interparticipant consistency of validation. Among the methods of validation of the clinical accuracy of auto-BPMs, method 3, which showed the highest reproducibility and highest interparticipant consistency, can be proposed as being the most appropriate.

Development and validation of a cerebral oximeter capable of absolute accuracy.

PubMed

MacLeod, David B; Ikeda, Keita; Vacchiano, Charles; Lobbestael, Aaron; Wahr, Joyce A; Shaw, Andrew D

2012-12-01

Cerebral oximetry may be a valuable monitor, but few validation data are available, and most report the change from baseline rather than absolute accuracy, which may be affected by individuals whose oximetric values are outside the expected range. The authors sought to develop and validate a cerebral oximeter capable of absolute accuracy. An in vivo research study. A university human physiology laboratory. Healthy human volunteers were enrolled in calibration and validation studies of 2 cerebral oximetric sensors, the Nonin 8000CA and 8004CA. The 8000CA validation study identified 5 individuals with atypical cerebral oxygenation values; their data were used to design the 8004CA sensor, which subsequently underwent calibration and validation. Volunteers were taken through a stepwise hypoxia protocol to a minimum saturation of peripheral oxygen. Arteriovenous saturation (70% jugular bulb venous saturation and 30% arterial saturation) at 6 hypoxic plateaus was used as the reference value for the cerebral oximeter. Absolute accuracy was defined using a combination of the bias and precision of the paired saturations (A(RMS)). In the validation study for the 8000CA sensor (n = 9, 106 plateaus), relative accuracy was an A(RMS) of 2.7, with an absolute accuracy of 8.1, meeting the criteria for a relative (trend) monitor, but not an absolute monitor. In the validation study for the 8004CA sensor (n = 11, 119 plateaus), the A(RMS) of the 8004CA was 4.1, meeting the prespecified success criterion of <5.0. The Nonin cerebral oximeter using the 8004CA sensor can provide absolute data on regional cerebral saturation compared with arteriovenous saturation, even in subjects previously shown to have values outside the normal population distribution curves. Copyright © 2012 Elsevier Inc. All rights reserved.

AIRS Retrieval Validation During the EAQUATE

NASA Technical Reports Server (NTRS)

Zhou, Daniel K.; Smith, William L.; Cuomo, Vincenzo; Taylor, Jonathan P.; Barnet, Christopher D.; DiGirolamo, Paolo; Pappalardo, Gelsomina; Larar, Allen M.; Liu, Xu; Newman, Stuart M.

2006-01-01

Atmospheric and surface thermodynamic parameters retrieved with advanced hyperspectral remote sensors of Earth observing satellites are critical for weather prediction and scientific research. The retrieval algorithms and retrieved parameters from satellite sounders must be validated to demonstrate the capability and accuracy of both observation and data processing systems. The European AQUA Thermodynamic Experiment (EAQUATE) was conducted mainly for validation of the Atmospheric InfraRed Sounder (AIRS) on the AQUA satellite, but also for assessment of validation systems of both ground-based and aircraft-based instruments which will be used for other satellite systems such as the Infrared Atmospheric Sounding Interferometer (IASI) on the European MetOp satellite, the Cross-track Infrared Sounder (CrIS) from the NPOESS Preparatory Project and the following NPOESS series of satellites. Detailed inter-comparisons were conducted and presented using different retrieval methodologies: measurements from airborne ultraspectral Fourier transform spectrometers, aircraft in-situ instruments, dedicated dropsondes and radiosondes, and ground based Raman Lidar, as well as from the European Center for Medium range Weather Forecasting (ECMWF) modeled thermal structures. The results of this study not only illustrate the quality of the measurements and retrieval products but also demonstrate the capability of these validation systems which are put in place to validate current and future hyperspectral sounding instruments and their scientific products.

S-NPP CrIS Full Resolution Sensor Data Record Processing and Evaluations

NASA Astrophysics Data System (ADS)

Chen, Y.; Han, Y.; Wang, L.; Tremblay, D. A.; Jin, X.; Weng, F.

2014-12-01

The Cross-track Infrared Sounder (CrIS) on Suomi National Polar-orbiting Partnership Satellite (S-NPP) is a Fourier transform spectrometer. It provides a total of 1305 channels in the normal mode for sounding the atmosphere. CrIS can also be operated in the full spectral resolution (FSR) mode, in which the MWIR and SWIR band interferograms are recorded with the same maximum path difference as the LWIR band and with spectral resolution of 0.625 cm-1 for all three bands (total 2211 channels). NOAA will operate CrIS in FSR mode in December 2014 and the Joint Polar Satellite System (JPSS). Up to date, the FSR mode has been commanded three times in-orbit (02/23/2012, 03/12/2013, and 08/27/2013). Based on CrIS Algorithm Development Library (ADL), CrIS full resolution Processing System (CRPS) has developed to generate the FSR Sensor Data Record (SDR). This code can also be run for normal mode and truncation mode SDRs with recompiling. Different calibration approaches are implemented in the code in order to study the ringing effect observed in CrIS normal mode SDR and to support to select the best calibration algorithm for J1. We develop the CrIS FSR SDR Validation System to quantify the CrIS radiometric and spectral accuracy, since they are crucial for improving its data assimilation in the numerical weather prediction, and for retrieving atmospheric trace gases. In this study, CrIS full resolution SDRs are generated from CRPS using the data collected from FSR mode of S-NPP, and the radiometric and spectral accuracy are assessed by using the Community Radiative Transfer Model (CRTM) and European Centre for Medium-Range Weather Forecasts (ECMWF) forecast fields. The biases between observation and simulations are evaluated to estimate the FOV-2-FOV variability and bias under clear sky over ocean. Double difference method and Simultaneous Nadir Overpass (SNO) method are also used to assess the CrIS radiance consistency with well-validated IASI. Two basic frequency validation methods (absolute and relative spectral validations) are used to assess the CrIS spectral accuracy. Results show that CrIS SDRs from FSR have similar radiometric and spectral accuracy as those from normal mode.

Gene Polymorphism Association with Type 2 Diabetes and Related Gene-Gene and Gene-Environment Interactions in a Uyghur Population

PubMed Central

Xiao, Shan; Zeng, Xiaoyun; Fan, Yong; Su, Yinxia; Ma, Qi; Zhu, Jun; Yao, Hua

2016-01-01

Background We investigated the association between 8 single-nucleotide polymorphisms (SNPs) at 3 genetic loci (CDKAL1, CDKN2A/2B and FTO) with type 2 diabetes (T2D) in a Uyghur population. Material/Methods A case-control study of 879 Uyghur patients with T2D and 895 non-diabetic Uyghur controls was conducted at the Hospital of Xinjiang Medical University between 2010 and 2013. Eight SNPs in CDKAL1, CDKN2A/2B and FTO were analyzed using Sequenom MassARRAY®SNP genotyping. Factors associated with T2D were assessed by logistic regression analyses. Gene-gene and gene-environment interactions were analyzed by generalized multifactor dimensionality reduction. Results Genotype distributions of rs10811661 (CDKN2A/2B), rs7195539, rs8050136, and rs9939609 (FTO) and allele frequencies of rs8050136 and rs9939609 differed significantly between diabetes and control groups (all P<0.05). While rs10811661, rs8050136, and rs9939609 were eliminated after adjusting for covariates (P>0.05), rs7195539 distribution differed significantly in co-dominant and dominant models (P<0.05). In gene-gene interaction analysis, after adjusting for covariates the two-locus rs10811661-rs7195539 interaction model had a cross-validation consistency of 10/10 and the highest balanced accuracy of 0.5483 (P=0.014). In gene-environment interaction analysis, the 3-locus interaction model TG-HDL-family history of diabetes had a cross-validation consistency of 10/10 and the highest balanced accuracy of 0.7072 (P<0.001). The 4-locus interaction model, rs7195539-TG-HDL-family history of diabetes had a cross-validation consistency of 8/10 (P<0.001). Conclusions Polymorphisms in CDKN2A/2B and FTO, but not CDKAL1, may be associated with T2D, and alleles rs8050136 and rs9939609 are likely risk alleles for T2D in this population. There were potential interactions among CDKN2A/2B (rs10811661) – FTO (rs7195539) or FTO (rs7195539)-TG-HDL-family history of diabetes in the pathogenesis of T2D in a Uyghur population. PMID:26873362

Radiogenomics to characterize regional genetic heterogeneity in glioblastoma.

PubMed

Hu, Leland S; Ning, Shuluo; Eschbacher, Jennifer M; Baxter, Leslie C; Gaw, Nathan; Ranjbar, Sara; Plasencia, Jonathan; Dueck, Amylou C; Peng, Sen; Smith, Kris A; Nakaji, Peter; Karis, John P; Quarles, C Chad; Wu, Teresa; Loftus, Joseph C; Jenkins, Robert B; Sicotte, Hugues; Kollmeyer, Thomas M; O'Neill, Brian P; Elmquist, William; Hoxworth, Joseph M; Frakes, David; Sarkaria, Jann; Swanson, Kristin R; Tran, Nhan L; Li, Jing; Mitchell, J Ross

2017-01-01

Glioblastoma (GBM) exhibits profound intratumoral genetic heterogeneity. Each tumor comprises multiple genetically distinct clonal populations with different therapeutic sensitivities. This has implications for targeted therapy and genetically informed paradigms. Contrast-enhanced (CE)-MRI and conventional sampling techniques have failed to resolve this heterogeneity, particularly for nonenhancing tumor populations. This study explores the feasibility of using multiparametric MRI and texture analysis to characterize regional genetic heterogeneity throughout MRI-enhancing and nonenhancing tumor segments. We collected multiple image-guided biopsies from primary GBM patients throughout regions of enhancement (ENH) and nonenhancing parenchyma (so called brain-around-tumor, [BAT]). For each biopsy, we analyzed DNA copy number variants for core GBM driver genes reported by The Cancer Genome Atlas. We co-registered biopsy locations with MRI and texture maps to correlate regional genetic status with spatially matched imaging measurements. We also built multivariate predictive decision-tree models for each GBM driver gene and validated accuracies using leave-one-out-cross-validation (LOOCV). We collected 48 biopsies (13 tumors) and identified significant imaging correlations (univariate analysis) for 6 driver genes: EGFR, PDGFRA, PTEN, CDKN2A, RB1, and TP53. Predictive model accuracies (on LOOCV) varied by driver gene of interest. Highest accuracies were observed for PDGFRA (77.1%), EGFR (75%), CDKN2A (87.5%), and RB1 (87.5%), while lowest accuracy was observed in TP53 (37.5%). Models for 4 driver genes (EGFR, RB1, CDKN2A, and PTEN) showed higher accuracy in BAT samples (n = 16) compared with those from ENH segments (n = 32). MRI and texture analysis can help characterize regional genetic heterogeneity, which offers potential diagnostic value under the paradigm of individualized oncology. © The Author(s) 2016. Published by Oxford University Press on behalf of the Society for Neuro-Oncology. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Ultrasound is a reproducible and valid tool for measuring scar height in children with burn scars: A cross-sectional study of the psychometric properties and utility of the ultrasound and 3D camera.

PubMed

Simons, M; Kee, E Gee; Kimble, R; Tyack, Z

2017-08-01

The aim of this study was to investigate the reproducibility and validity of measuring scar height in children using ultrasound and 3D camera. Using a cross-sectional design, children with discrete burn scars were included. Reproducibility was tested using Intraclass Correlation Coefficient (ICC) for reliability, and percentage agreement within 1mm between test and re-test, standard error of measurement (SEM), smallest detectable change (SDC) and Bland Altman limits of agreement for agreement. Concurrent validity was tested using Spearman's rho for support of pre-specified hypotheses. Forty-nine participants (55 scars) were included. For ultrasound, test-retest and inter-rater reproducibility of scar thickness was acceptable for scarred skin (ICC=0.95, SDC=0.06cm and ICC=0.82, SDC=0.14cm). The ultrasound picked up changes of <1mm. Inter-rater reproducibility of maximal scar height using the 3D camera was acceptable (ICC=0.73, SDC=0.55cm). Construct validity of the ultrasound was supported with a strong correlation between the measure of scar thickness and observer ratings of thickness using the POSAS (ρ=0.61). Construct validity of the 3D camera was also supported with a moderate correlation (ρ=0.37) with the same measure using maximal scar height. The ultrasound is capable of detecting smaller changes or differences in scar thickness than the 3D camera, in children with burn scars. However agreement as part of reproducibility was lower than expected between raters for the ultrasound. Improving the accuracy of scar relocation may go some way to address agreement. Crown Copyright © 2017. Published by Elsevier Ltd. All rights reserved.

FY 2016 Status Report on the Modeling of the M8 Calibration Series using MAMMOTH

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

Baker, Benjamin Allen; Ortensi, Javier; DeHart, Mark David

2016-09-01

This report provides a summary of the progress made towards validating the multi-physics reactor analysis application MAMMOTH using data from measurements performed at the Transient Reactor Test facility, TREAT. The work completed consists of a series of comparisons of TREAT element types (standard and control rod assemblies) in small geometries as well as slotted mini-cores to reference Monte Carlo simulations to ascertain the accuracy of cross section preparation techniques. After the successful completion of these smaller problems, a full core model of the half slotted core used in the M8 Calibration series was assembled. Full core MAMMOTH simulations were comparedmore » to Serpent reference calculations to assess the cross section preparation process for this larger configuration. As part of the validation process the M8 Calibration series included a steady state wire irradiation experiment and coupling factors for the experiment region. The shape of the power distribution obtained from the MAMMOTH simulation shows excellent agreement with the experiment. Larger differences were encountered in the calculation of the coupling factors, but there is also great uncertainty on how the experimental values were obtained. Future work will focus on resolving some of these differences.« less

Large-scale collision cross-section profiling on a travelling wave ion mobility mass spectrometer

PubMed Central

Lietz, Christopher B.; Yu, Qing; Li, Lingjun

2014-01-01

Ion mobility (IM) is a gas-phase electrophoretic method that separates ions according to charge and ion-neutral collision cross-section (CCS). Herein, we attempt to apply a travelling wave (TW) IM polyalanine calibration method to shotgun proteomics and create a large peptide CCS database. Mass spectrometry methods that utilize IM, such as HDMSE, often use high transmission voltages for sensitive analysis. However, polyalanine calibration has only been demonstrated with low voltage transmission used to prevent gas-phase activation. If polyalanine ions change conformation under higher transmission voltages used for HDMSE, the calibration may no longer be valid. Thus, we aimed to characterize the accuracy of calibration and CCS measurement under high transmission voltages on a TW IM instrument using the polyalanine calibration method and found that the additional error was not significant. We also evaluated the potential error introduced by liquid chromatography (LC)-HDMSE analysis, and found it to be insignificant as well, validating the calibration method. Finally, we demonstrated the utility of building a large-population peptide CCS database by investigating the effects of terminal lysine position, via LysC or LysN digestion, on the formation of two structural sub-families formed by triply charged ions. PMID:24845359

Near infrared spectroscopy (NIRS) for on-line determination of quality parameters in intact olives.

PubMed

Salguero-Chaparro, Lourdes; Baeten, Vincent; Fernández-Pierna, Juan A; Peña-Rodríguez, Francisco

2013-08-15

The acidity, moisture and fat content in intact olive fruits were determined on-line using a NIR diode array instrument, operating on a conveyor belt. Four sets of calibrations models were obtained by means of different combinations from samples collected during 2009-2010 and 2010-2011, using full-cross and external validation. Several preprocessing treatments such as derivatives and scatter correction were investigated by using the root mean square error of cross-validation (RMSECV) and prediction (RMSEP), as control parameters. The results obtained showed RMSECV values of 2.54-3.26 for moisture, 2.35-2.71 for fat content and 2.50-3.26 for acidity parameters, depending on the calibration model developed. Calibrations for moisture, fat content and acidity gave residual predictive deviation (RPD) values of 2.76, 2.37 and 1.60, respectively. Although, it is concluded that the on-line NIRS prediction results were acceptable for the three parameters measured in intact olive samples in movement, the models developed must be improved in order to increase their accuracy before final NIRS implementation at mills. Copyright © 2013 Elsevier Ltd. All rights reserved.

Artificial intelligence techniques: An efficient new approach to challenge the assessment of complex clinical fields such as airway clearance techniques in patients with cystic fibrosis?

PubMed

Slavici, Titus; Almajan, Bogdan

2013-04-01

To construct an artificial intelligence application to assist untrained physiotherapists in determining the appropriate physiotherapy exercises to improve the quality of life of patients with cystic fibrosis. A total of 42 children (21 boys and 21 girls), age range 6-18 years, participated in a clinical survey between 2001 and 2005. Data collected during the clinical survey were entered into a neural network in order to correlate the health state indicators of the patients and the type of physiotherapy exercise to be followed. Cross-validation of the network was carried out by comparing the health state indicators achieved after following a certain physiotherapy exercise and the health state indicators predicted by the network. The lifestyle and health state indicators of the survey participants improved. The network predicted the health state indicators of the participants with an accuracy of 93%. The results of the cross-validation test were within the error margins of the real-life indicators. Using data on the clinical state of individuals with cystic fibrosis, it is possible to determine the most effective type of physiotherapy exercise for improving overall health state indicators.

ETHNOPRED: a novel machine learning method for accurate continental and sub-continental ancestry identification and population stratification correction.

PubMed

Hajiloo, Mohsen; Sapkota, Yadav; Mackey, John R; Robson, Paula; Greiner, Russell; Damaraju, Sambasivarao

2013-02-22

Population stratification is a systematic difference in allele frequencies between subpopulations. This can lead to spurious association findings in the case-control genome wide association studies (GWASs) used to identify single nucleotide polymorphisms (SNPs) associated with disease-linked phenotypes. Methods such as self-declared ancestry, ancestry informative markers, genomic control, structured association, and principal component analysis are used to assess and correct population stratification but each has limitations. We provide an alternative technique to address population stratification. We propose a novel machine learning method, ETHNOPRED, which uses the genotype and ethnicity data from the HapMap project to learn ensembles of disjoint decision trees, capable of accurately predicting an individual's continental and sub-continental ancestry. To predict an individual's continental ancestry, ETHNOPRED produced an ensemble of 3 decision trees involving a total of 10 SNPs, with 10-fold cross validation accuracy of 100% using HapMap II dataset. We extended this model to involve 29 disjoint decision trees over 149 SNPs, and showed that this ensemble has an accuracy of ≥ 99.9%, even if some of those 149 SNP values were missing. On an independent dataset, predominantly of Caucasian origin, our continental classifier showed 96.8% accuracy and improved genomic control's λ from 1.22 to 1.11. We next used the HapMap III dataset to learn classifiers to distinguish European subpopulations (North-Western vs. Southern), East Asian subpopulations (Chinese vs. Japanese), African subpopulations (Eastern vs. Western), North American subpopulations (European vs. Chinese vs. African vs. Mexican vs. Indian), and Kenyan subpopulations (Luhya vs. Maasai). In these cases, ETHNOPRED produced ensembles of 3, 39, 21, 11, and 25 disjoint decision trees, respectively involving 31, 502, 526, 242 and 271 SNPs, with 10-fold cross validation accuracy of 86.5% ± 2.4%, 95.6% ± 3.9%, 95.6% ± 2.1%, 98.3% ± 2.0%, and 95.9% ± 1.5%. However, ETHNOPRED was unable to produce a classifier that can accurately distinguish Chinese in Beijing vs. Chinese in Denver. ETHNOPRED is a novel technique for producing classifiers that can identify an individual's continental and sub-continental heritage, based on a small number of SNPs. We show that its learned classifiers are simple, cost-efficient, accurate, transparent, flexible, fast, applicable to large scale GWASs, and robust to missing values.

Highly accurate FTIR observations from the scanning HIS aircraft instrument

NASA Astrophysics Data System (ADS)

Revercomb, Henry E.; Tobin, David C.; Knuteson, Robert O.; Best, Fred A.; Smith, William L., Sr.; van Delst, Paul F. W.; LaPorte, Daniel D.; Ellington, Scott D.; Werner, Mark W.; Dedecker, Ralph G.; Garcia, Raymond K.; Ciganovich, Nick N.; Howell, Hugh B.; Olson, Erik R.; Dutcher, Steven B.; Taylor, Joseph K.

2005-01-01

Development in the mid 80s of the High-resolution Interferometer Sounder (HIS) instrument for the high altitude NASA ER2 aircraft demonstrated the capability for advanced atmospheric temperature and water vapor sounding and set the stage for new satellite instruments that are now becoming a reality [AIRS(2002), CrIS(2006), IASI(2006), GIFTS(200?), HES(2013)]. Follow-on developments at the University of Wisconsin that employ Fourier Transform Infrared (FTIR) for Earth observations include the ground-based Atmospheric Emitted Radiance Interferometer (AERI) and the new Scanning HIS aircraft instrument. The Scanning HIS is a smaller version of the original HIS that uses cross-track scanning to enhance spatial coverage. Scanning HIS and its close cousin, the NPOESS Airborne Sounder Testbed (NAST), are being used for satellite instrument validation and for atmospheric research. A novel detector configuration on Scanning HIS allows the incorporation of a single focal plane and cooler with three or four spectral bands that view the same spot on the ground. The calibration accuracy of the S-HIS and results from recent field campaigns are presented, including validation comparisons with the NASA EOS infrared observations (AIRS and MODIS). Aircraft comparisons of this type provide a mechanism for periodically testing the absolute calibration of spacecraft instruments with instrumentation for which the calibration can be carefully maintained on the ground. This capability is especially valuable for assuring the long-term consistency and accuracy of climate observations, including those from the NASA EOS spacecrafts (Terra, Aqua and Aura) and the new complement of NPOESS operational instruments. It is expected that aircraft flights of the S-HIS and the NAST will be used to check the long-term stability of AIRS and the NPOESS operational follow-on sounder, the Cross-track Infrared Sounder (CrIS), over the life of the mission.

Automatic classification of tissue malignancy for breast carcinoma diagnosis.

PubMed

Fondón, Irene; Sarmiento, Auxiliadora; García, Ana Isabel; Silvestre, María; Eloy, Catarina; Polónia, António; Aguiar, Paulo

2018-05-01

Breast cancer is the second leading cause of cancer death among women. Its early diagnosis is extremely important to prevent avoidable deaths. However, malignancy assessment of tissue biopsies is complex and dependent on observer subjectivity. Moreover, hematoxylin and eosin (H&E)-stained histological images exhibit a highly variable appearance, even within the same malignancy level. In this paper, we propose a computer-aided diagnosis (CAD) tool for automated malignancy assessment of breast tissue samples based on the processing of histological images. We provide four malignancy levels as the output of the system: normal, benign, in situ and invasive. The method is based on the calculation of three sets of features related to nuclei, colour regions and textures considering local characteristics and global image properties. By taking advantage of well-established image processing techniques, we build a feature vector for each image that serves as an input to an SVM (Support Vector Machine) classifier with a quadratic kernel. The method has been rigorously evaluated, first with a 5-fold cross-validation within an initial set of 120 images, second with an external set of 30 different images and third with images with artefacts included. Accuracy levels range from 75.8% when the 5-fold cross-validation was performed to 75% with the external set of new images and 61.11% when the extremely difficult images were added to the classification experiment. The experimental results indicate that the proposed method is capable of distinguishing between four malignancy levels with high accuracy. Our results are close to those obtained with recent deep learning-based methods. Moreover, it performs better than other state-of-the-art methods based on feature extraction, and it can help improve the CAD of breast cancer. Copyright © 2018 Elsevier Ltd. All rights reserved.

A Bayesian antedependence model for whole genome prediction.

PubMed

Yang, Wenzhao; Tempelman, Robert J

2012-04-01

Hierarchical mixed effects models have been demonstrated to be powerful for predicting genomic merit of livestock and plants, on the basis of high-density single-nucleotide polymorphism (SNP) marker panels, and their use is being increasingly advocated for genomic predictions in human health. Two particularly popular approaches, labeled BayesA and BayesB, are based on specifying all SNP-associated effects to be independent of each other. BayesB extends BayesA by allowing a large proportion of SNP markers to be associated with null effects. We further extend these two models to specify SNP effects as being spatially correlated due to the chromosomally proximal effects of causal variants. These two models, that we respectively dub as ante-BayesA and ante-BayesB, are based on a first-order nonstationary antedependence specification between SNP effects. In a simulation study involving 20 replicate data sets, each analyzed at six different SNP marker densities with average LD levels ranging from r(2) = 0.15 to 0.31, the antedependence methods had significantly (P < 0.01) higher accuracies than their corresponding classical counterparts at higher LD levels (r(2) > 0. 24) with differences exceeding 3%. A cross-validation study was also conducted on the heterogeneous stock mice data resource (http://mus.well.ox.ac.uk/mouse/HS/) using 6-week body weights as the phenotype. The antedependence methods increased cross-validation prediction accuracies by up to 3.6% compared to their classical counterparts (P < 0.001). Finally, we applied our method to other benchmark data sets and demonstrated that the antedependence methods were more accurate than their classical counterparts for genomic predictions, even for individuals several generations beyond the training data.

Diagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted MR: a machine learning approach.

PubMed

Cai, Hongmin; Peng, Yanxia; Ou, Caiwen; Chen, Minsheng; Li, Li

2014-01-01

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is increasingly used for breast cancer diagnosis as supplementary to conventional imaging techniques. Combining of diffusion-weighted imaging (DWI) of morphology and kinetic features from DCE-MRI to improve the discrimination power of malignant from benign breast masses is rarely reported. The study comprised of 234 female patients with 85 benign and 149 malignant lesions. Four distinct groups of features, coupling with pathological tests, were estimated to comprehensively characterize the pictorial properties of each lesion, which was obtained by a semi-automated segmentation method. Classical machine learning scheme including feature subset selection and various classification schemes were employed to build prognostic model, which served as a foundation for evaluating the combined effects of the multi-sided features for predicting of the types of lesions. Various measurements including cross validation and receiver operating characteristics were used to quantify the diagnostic performances of each feature as well as their combination. Seven features were all found to be statistically different between the malignant and the benign groups and their combination has achieved the highest classification accuracy. The seven features include one pathological variable of age, one morphological variable of slope, three texture features of entropy, inverse difference and information correlation, one kinetic feature of SER and one DWI feature of apparent diffusion coefficient (ADC). Together with the selected diagnostic features, various classical classification schemes were used to test their discrimination power through cross validation scheme. The averaged measurements of sensitivity, specificity, AUC and accuracy are 0.85, 0.89, 90.9% and 0.93, respectively. Multi-sided variables which characterize the morphological, kinetic, pathological properties and DWI measurement of ADC can dramatically improve the discriminatory power of breast lesions.

Improving lung cancer prognosis assessment by incorporating synthetic minority oversampling technique and score fusion method

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

Yan, Shiju; Qian, Wei; Guan, Yubao

2016-06-15

Purpose: This study aims to investigate the potential to improve lung cancer recurrence risk prediction performance for stage I NSCLS patients by integrating oversampling, feature selection, and score fusion techniques and develop an optimal prediction model. Methods: A dataset involving 94 early stage lung cancer patients was retrospectively assembled, which includes CT images, nine clinical and biological (CB) markers, and outcome of 3-yr disease-free survival (DFS) after surgery. Among the 94 patients, 74 remained DFS and 20 had cancer recurrence. Applying a computer-aided detection scheme, tumors were segmented from the CT images and 35 quantitative image (QI) features were initiallymore » computed. Two normalized Gaussian radial basis function network (RBFN) based classifiers were built based on QI features and CB markers separately. To improve prediction performance, the authors applied a synthetic minority oversampling technique (SMOTE) and a BestFirst based feature selection method to optimize the classifiers and also tested fusion methods to combine QI and CB based prediction results. Results: Using a leave-one-case-out cross-validation (K-fold cross-validation) method, the computed areas under a receiver operating characteristic curve (AUCs) were 0.716 ± 0.071 and 0.642 ± 0.061, when using the QI and CB based classifiers, respectively. By fusion of the scores generated by the two classifiers, AUC significantly increased to 0.859 ± 0.052 (p < 0.05) with an overall prediction accuracy of 89.4%. Conclusions: This study demonstrated the feasibility of improving prediction performance by integrating SMOTE, feature selection, and score fusion techniques. Combining QI features and CB markers and performing SMOTE prior to feature selection in classifier training enabled RBFN based classifier to yield improved prediction accuracy.« less

Classifying vulnerability to sleep deprivation using baseline measures of psychomotor vigilance.

PubMed

Patanaik, Amiya; Kwoh, Chee Keong; Chua, Eric C P; Gooley, Joshua J; Chee, Michael W L

2015-05-01

To identify measures derived from baseline psychomotor vigilance task (PVT) performance that can reliably predict vulnerability to sleep deprivation. Subjects underwent total sleep deprivation and completed a 10-min PVT every 1-2 h in a controlled laboratory setting. Participants were categorized as vulnerable or resistant to sleep deprivation, based on a median split of lapses that occurred following sleep deprivation. Standard reaction time, drift diffusion model (DDM), and wavelet metrics were derived from PVT response times collected at baseline. A support vector machine model that incorporated maximum relevance and minimum redundancy feature selection and wrapper-based heuristics was used to classify subjects as vulnerable or resistant using rested data. Two academic sleep laboratories. Independent samples of 135 (69 women, age 18 to 25 y), and 45 (3 women, age 22 to 32 y) healthy adults. In both datasets, DDM measures, number of consecutive reaction times that differ by more than 250 ms, and two wavelet features were selected by the model as features predictive of vulnerability to sleep deprivation. Using the best set of features selected in each dataset, classification accuracy was 77% and 82% using fivefold stratified cross-validation, respectively. In both datasets, DDM measures, number of consecutive reaction times that differ by more than 250 ms, and two wavelet features were selected by the model as features predictive of vulnerability to sleep deprivation. Using the best set of features selected in each dataset, classification accuracy was 77% and 82% using fivefold stratified cross-validation, respectively. Despite differences in experimental conditions across studies, drift diffusion model parameters associated reliably with individual differences in performance during total sleep deprivation. These results demonstrate the utility of drift diffusion modeling of baseline performance in estimating vulnerability to psychomotor vigilance decline following sleep deprivation. © 2015 Associated Professional Sleep Societies, LLC.

Landscape scale estimation of soil carbon stock using 3D modelling.

PubMed

Veronesi, F; Corstanje, R; Mayr, T

2014-07-15

Soil C is the largest pool of carbon in the terrestrial biosphere, and yet the processes of C accumulation, transformation and loss are poorly accounted for. This, in part, is due to the fact that soil C is not uniformly distributed through the soil depth profile and most current landscape level predictions of C do not adequately account the vertical distribution of soil C. In this study, we apply a method based on simple soil specific depth functions to map the soil C stock in three-dimensions at landscape scale. We used soil C and bulk density data from the Soil Survey for England and Wales to map an area in the West Midlands region of approximately 13,948 km(2). We applied a method which describes the variation through the soil profile and interpolates this across the landscape using well established soil drivers such as relief, land cover and geology. The results indicate that this mapping method can effectively reproduce the observed variation in the soil profiles samples. The mapping results were validated using cross validation and an independent validation. The cross-validation resulted in an R(2) of 36% for soil C and 44% for BULKD. These results are generally in line with previous validated studies. In addition, an independent validation was undertaken, comparing the predictions against the National Soil Inventory (NSI) dataset. The majority of the residuals of this validation are between ± 5% of soil C. This indicates high level of accuracy in replicating topsoil values. In addition, the results were compared to a previous study estimating the carbon stock of the UK. We discuss the implications of our results within the context of soil C loss factors such as erosion and the impact on regional C process models. Copyright © 2014 Elsevier B.V. All rights reserved.

Model performance evaluation (validation and calibration) in model-based studies of therapeutic interventions for cardiovascular diseases : a review and suggested reporting framework.

PubMed

Haji Ali Afzali, Hossein; Gray, Jodi; Karnon, Jonathan

2013-04-01

Decision analytic models play an increasingly important role in the economic evaluation of health technologies. Given uncertainties around the assumptions used to develop such models, several guidelines have been published to identify and assess 'best practice' in the model development process, including general modelling approach (e.g., time horizon), model structure, input data and model performance evaluation. This paper focuses on model performance evaluation. In the absence of a sufficient level of detail around model performance evaluation, concerns regarding the accuracy of model outputs, and hence the credibility of such models, are frequently raised. Following presentation of its components, a review of the application and reporting of model performance evaluation is presented. Taking cardiovascular disease as an illustrative example, the review investigates the use of face validity, internal validity, external validity, and cross model validity. As a part of the performance evaluation process, model calibration is also discussed and its use in applied studies investigated. The review found that the application and reporting of model performance evaluation across 81 studies of treatment for cardiovascular disease was variable. Cross-model validation was reported in 55 % of the reviewed studies, though the level of detail provided varied considerably. We found that very few studies documented other types of validity, and only 6 % of the reviewed articles reported a calibration process. Considering the above findings, we propose a comprehensive model performance evaluation framework (checklist), informed by a review of best-practice guidelines. This framework provides a basis for more accurate and consistent documentation of model performance evaluation. This will improve the peer review process and the comparability of modelling studies. Recognising the fundamental role of decision analytic models in informing public funding decisions, the proposed framework should usefully inform guidelines for preparing submissions to reimbursement bodies.

Estimation of sex from the lower limb measurements of Sudanese adults.

PubMed

Ahmed, Altayeb Abdalla

2013-06-10

The sex estimation from mutilated and amputated limbs or body parts is one of the most vital steps in person identification in medical-legal autopsies. Sex estimation from lower limb anthropometric measurements has demonstrated a high degree of expected accuracy in a limited range of the global population. The aims of this study were to assess the degree of the sexual dimorphism in lower limb measurements and the accuracy of utilization of these measurements for estimation of sex in a contemporary adult Sudanese population. The tibial length, bimalleolar breadth, foot length, and foot breadth of 240 right-handed Sudanese Arab subjects (120 males and 120 females) aged between 25 and 30 years were measured following international anthropometric standards. Demarking points, sexual dimorphism indices and discriminant functions were developed from 200 subjects (100 males and 100 females) who comprised the study group. All variables were sexually dimorphic. The bimalleolar breadth and foot breadth significantly contributed to sex estimation. Leg dimensions showed a higher accuracy for sex estimation than foot dimensions. Cross-validated sex classification accuracy ranged between 78% and 89.5%. The reliability of these standards was assessed in a test sample of 20 males and 20 females, and the results showed accuracy between 75% and 90%. This study provides new forensic standards for sex estimation from lower limb measurements of Sudanese adults. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

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

A cross-sectional evaluation of meditation experience on electroencephalography data by artificial neural network and support vector machine classifiers

PubMed Central

Lee, Yu-Hao; Hsieh, Ya-Ju; Shiah, Yung-Jong; Lin, Yu-Huei; Chen, Chiao-Yun; Tyan, Yu-Chang; GengQiu, JiaCheng; Hsu, Chung-Yao; Chen, Sharon Chia-Ju

2017-01-01

Abstract To quantitate the meditation experience is a subjective and complex issue because it is confounded by many factors such as emotional state, method of meditation, and personal physical condition. In this study, we propose a strategy with a cross-sectional analysis to evaluate the meditation experience with 2 artificial intelligence techniques: artificial neural network and support vector machine. Within this analysis system, 3 features of the electroencephalography alpha spectrum and variant normalizing scaling are manipulated as the evaluating variables for the detection of accuracy. Thereafter, by modulating the sliding window (the period of the analyzed data) and shifting interval of the window (the time interval to shift the analyzed data), the effect of immediate analysis for the 2 methods is compared. This analysis system is performed on 3 meditation groups, categorizing their meditation experiences in 10-year intervals from novice to junior and to senior. After an exhausted calculation and cross-validation across all variables, the high accuracy rate >98% is achievable under the criterion of 0.5-minute sliding window and 2 seconds shifting interval for both methods. In a word, the minimum analyzable data length is 0.5 minute and the minimum recognizable temporal resolution is 2 seconds in the decision of meditative classification. Our proposed classifier of the meditation experience promotes a rapid evaluation system to distinguish meditation experience and a beneficial utilization of artificial techniques for the big-data analysis. PMID:28422856

A cross-sectional evaluation of meditation experience on electroencephalography data by artificial neural network and support vector machine classifiers.

PubMed

Lee, Yu-Hao; Hsieh, Ya-Ju; Shiah, Yung-Jong; Lin, Yu-Huei; Chen, Chiao-Yun; Tyan, Yu-Chang; GengQiu, JiaCheng; Hsu, Chung-Yao; Chen, Sharon Chia-Ju

2017-04-01

To quantitate the meditation experience is a subjective and complex issue because it is confounded by many factors such as emotional state, method of meditation, and personal physical condition. In this study, we propose a strategy with a cross-sectional analysis to evaluate the meditation experience with 2 artificial intelligence techniques: artificial neural network and support vector machine. Within this analysis system, 3 features of the electroencephalography alpha spectrum and variant normalizing scaling are manipulated as the evaluating variables for the detection of accuracy. Thereafter, by modulating the sliding window (the period of the analyzed data) and shifting interval of the window (the time interval to shift the analyzed data), the effect of immediate analysis for the 2 methods is compared. This analysis system is performed on 3 meditation groups, categorizing their meditation experiences in 10-year intervals from novice to junior and to senior. After an exhausted calculation and cross-validation across all variables, the high accuracy rate >98% is achievable under the criterion of 0.5-minute sliding window and 2 seconds shifting interval for both methods. In a word, the minimum analyzable data length is 0.5 minute and the minimum recognizable temporal resolution is 2 seconds in the decision of meditative classification. Our proposed classifier of the meditation experience promotes a rapid evaluation system to distinguish meditation experience and a beneficial utilization of artificial techniques for the big-data analysis.

Estimating energy expenditure from heart rate in older adults: a case for calibration.

PubMed

Schrack, Jennifer A; Zipunnikov, Vadim; Goldsmith, Jeff; Bandeen-Roche, Karen; Crainiceanu, Ciprian M; Ferrucci, Luigi

2014-01-01

Accurate measurement of free-living energy expenditure is vital to understanding changes in energy metabolism with aging. The efficacy of heart rate as a surrogate for energy expenditure is rooted in the assumption of a linear function between heart rate and energy expenditure, but its validity and reliability in older adults remains unclear. To assess the validity and reliability of the linear function between heart rate and energy expenditure in older adults using different levels of calibration. Heart rate and energy expenditure were assessed across five levels of exertion in 290 adults participating in the Baltimore Longitudinal Study of Aging. Correlation and random effects regression analyses assessed the linearity of the relationship between heart rate and energy expenditure and cross-validation models assessed predictive performance. Heart rate and energy expenditure were highly correlated (r=0.98) and linear regardless of age or sex. Intra-person variability was low but inter-person variability was high, with substantial heterogeneity of the random intercept (s.d. =0.372) despite similar slopes. Cross-validation models indicated individual calibration data substantially improves accuracy predictions of energy expenditure from heart rate, reducing the potential for considerable measurement bias. Although using five calibration measures provided the greatest reduction in the standard deviation of prediction errors (1.08 kcals/min), substantial improvement was also noted with two (0.75 kcals/min). These findings indicate standard regression equations may be used to make population-level inferences when estimating energy expenditure from heart rate in older adults but caution should be exercised when making inferences at the individual level without proper calibration.

A Diagnostic Model for Impending Death in Cancer Patients: Preliminary Report

PubMed Central

Hui, David; Hess, Kenneth; dos Santos, Renata; Chisholm, Gary; Bruera, Eduardo

2015-01-01

Background We recently identified several highly specific bedside physical signs associated with impending death within 3 days among patients with advanced cancer. In this study, we developed and assessed a diagnostic model for impending death based on these physical signs. Methods We systematically documented 62 physical signs every 12 hours from admission to death or discharge in 357 patients with advanced cancer admitted to acute palliative care units (APCUs) at two tertiary care cancer centers. We used recursive partitioning analysis (RPA) to develop a prediction model for impending death in 3 days using admission data. We validated the model with 5 iterations of 10-fold cross-validation, and also applied the model to APCU days 2/3/4/5/6. Results Among 322/357 (90%) patients with complete data for all signs, the 3-day mortality was 24% on admission. The final model was based on 2 variables (palliative performance scale [PPS] and drooping of nasolabial fold) and had 4 terminal leaves: PPS≤20% and drooping of nasolabial fold present, PPS≤20% and drooping of nasolabial fold absent, PPS 30–60% and PPS ≥ 70%, with 3-day mortality of 94%, 42%, 16% and 3%, respectively. The diagnostic accuracy was 81% for the original tree, 80% for cross-validation, and 79%–84% for subsequent APCU days. Conclusion(s) We developed a diagnostic model for impending death within 3 days based on 2 objective bedside physical signs. This model was applicable to both APCU admission and subsequent days. Upon further external validation, this model may help clinicians to formulate the diagnosis of impending death. PMID:26218612

Lessons in molecular recognition. 2. Assessing and improving cross-docking accuracy.

PubMed

Sutherland, Jeffrey J; Nandigam, Ravi K; Erickson, Jon A; Vieth, Michal

2007-01-01

Docking methods are used to predict the manner in which a ligand binds to a protein receptor. Many studies have assessed the success rate of programs in self-docking tests, whereby a ligand is docked into the protein structure from which it was extracted. Cross-docking, or using a protein structure from a complex containing a different ligand, provides a more realistic assessment of a docking program's ability to reproduce X-ray results. In this work, cross-docking was performed with CDocker, Fred, and Rocs using multiple X-ray structures for eight proteins (two kinases, one nuclear hormone receptor, one serine protease, two metalloproteases, and two phosphodiesterases). While average cross-docking accuracy is not encouraging, it is shown that using the protein structure from the complex that contains the bound ligand most similar to the docked ligand increases docking accuracy for all methods ("similarity selection"). Identifying the most successful protein conformer ("best selection") and similarity selection substantially reduce the difference between self-docking and average cross-docking accuracy. We identify universal predictors of docking accuracy (i.e., showing consistent behavior across most protein-method combinations), and show that models for predicting docking accuracy built using these parameters can be used to select the most appropriate docking method.

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.

Validity of one-repetition maximum predictive equations in men with spinal cord injury.

PubMed

Ribeiro Neto, F; Guanais, P; Dornelas, E; Coutinho, A C B; Costa, R R G

2017-10-01

Cross-sectional study. The study aimed (a) to test the cross-validation of current one-repetition maximum (1RM) predictive equations in men with spinal cord injury (SCI); (b) to compare the current 1RM predictive equations to a newly developed equation based on the 4- to 12-repetition maximum test (4-12RM). SARAH Rehabilitation Hospital Network, Brasilia, Brazil. Forty-five men aged 28.0 years with SCI between C6 and L2 causing complete motor impairment were enrolled in the study. Volunteers were tested, in a random order, in 1RM test or 4-12RM with 2-3 interval days. Multiple regression analysis was used to generate an equation for predicting 1RM. There were no significant differences between 1RM test and the current predictive equations. ICC values were significant and were classified as excellent for all current predictive equations. The predictive equation of Lombardi presented the best Bland-Altman results (0.5 kg and 12.8 kg for mean difference and interval range around the differences, respectively). The two created equation models for 1RM demonstrated the same and a high adjusted R 2 (0.971, P<0.01), but different SEE of measured 1RM (2.88 kg or 5.4% and 2.90 kg or 5.5%). All 1RM predictive equations are accurate to assess individuals with SCI at the bench press exercise. However, the predictive equation of Lombardi presented the best associated cross-validity results. A specific 1RM prediction equation was also elaborated for individuals with SCI. The created equation should be tested in order to verify whether it presents better accuracy than the current ones.

Multiple receptor conformation docking and dock pose clustering as tool for CoMFA and CoMSIA analysis - a case study on HIV-1 protease inhibitors.

PubMed

Sivan, Sree Kanth; Manga, Vijjulatha

2012-02-01

Multiple receptors conformation docking (MRCD) and clustering of dock poses allows seamless incorporation of receptor binding conformation of the molecules on wide range of ligands with varied structural scaffold. The accuracy of the approach was tested on a set of 120 cyclic urea molecules having HIV-1 protease inhibitory activity using 12 high resolution X-ray crystal structures and one NMR resolved conformation of HIV-1 protease extracted from protein data bank. A cross validation was performed on 25 non-cyclic urea HIV-1 protease inhibitor having varied structures. The comparative molecular field analysis (CoMFA) and comparative molecular similarity indices analysis (CoMSIA) models were generated using 60 molecules in the training set by applying leave one out cross validation method, r (loo) (2) values of 0.598 and 0.674 for CoMFA and CoMSIA respectively and non-cross validated regression coefficient r(2) values of 0.983 and 0.985 were obtained for CoMFA and CoMSIA respectively. The predictive ability of these models was determined using a test set of 60 cyclic urea molecules that gave predictive correlation (r (pred) (2) ) of 0.684 and 0.64 respectively for CoMFA and CoMSIA indicating good internal predictive ability. Based on this information 25 non-cyclic urea molecules were taken as a test set to check the external predictive ability of these models. This gave remarkable out come with r (pred) (2) of 0.61 and 0.53 for CoMFA and CoMSIA respectively. The results invariably show that this method is useful for performing 3D QSAR analysis on molecules having different structural motifs.

Identification of Long Bone Fractures in Radiology Reports Using Natural Language Processing to Support Healthcare Quality Improvement

PubMed Central

Masino, Aaron J.; Casper, T. Charles; Dean, Jonathan M.; Bell, Jamie; Enriquez, Rene; Deakyne, Sara; Chamberlain, James M.; Alpern, Elizabeth R.

2016-01-01

Summary Background Important information to support healthcare quality improvement is often recorded in free text documents such as radiology reports. Natural language processing (NLP) methods may help extract this information, but these methods have rarely been applied outside the research laboratories where they were developed. Objective To implement and validate NLP tools to identify long bone fractures for pediatric emergency medicine quality improvement. Methods Using freely available statistical software packages, we implemented NLP methods to identify long bone fractures from radiology reports. A sample of 1,000 radiology reports was used to construct three candidate classification models. A test set of 500 reports was used to validate the model performance. Blinded manual review of radiology reports by two independent physicians provided the reference standard. Each radiology report was segmented and word stem and bigram features were constructed. Common English “stop words” and rare features were excluded. We used 10-fold cross-validation to select optimal configuration parameters for each model. Accuracy, recall, precision and the F1 score were calculated. The final model was compared to the use of diagnosis codes for the identification of patients with long bone fractures. Results There were 329 unique word stems and 344 bigrams in the training documents. A support vector machine classifier with Gaussian kernel performed best on the test set with accuracy=0.958, recall=0.969, precision=0.940, and F1 score=0.954. Optimal parameters for this model were cost=4 and gamma=0.005. The three classification models that we tested all performed better than diagnosis codes in terms of accuracy, precision, and F1 score (diagnosis code accuracy=0.932, recall=0.960, precision=0.896, and F1 score=0.927). Conclusions NLP methods using a corpus of 1,000 training documents accurately identified acute long bone fractures from radiology reports. Strategic use of straightforward NLP methods, implemented with freely available software, offers quality improvement teams new opportunities to extract information from narrative documents. PMID:27826610

Bilateral Image Subtraction and Multivariate Models for the Automated Triaging of Screening Mammograms

PubMed Central

Celaya-Padilla, José; Martinez-Torteya, Antonio; Rodriguez-Rojas, Juan; Galvan-Tejada, Jorge; Treviño, Victor; Tamez-Peña, José

2015-01-01

Mammography is the most common and effective breast cancer screening test. However, the rate of positive findings is very low, making the radiologic interpretation monotonous and biased toward errors. This work presents a computer-aided diagnosis (CADx) method aimed to automatically triage mammogram sets. The method coregisters the left and right mammograms, extracts image features, and classifies the subjects into risk of having malignant calcifications (CS), malignant masses (MS), and healthy subject (HS). In this study, 449 subjects (197 CS, 207 MS, and 45 HS) from a public database were used to train and evaluate the CADx. Percentile-rank (p-rank) and z-normalizations were used. For the p-rank, the CS versus HS model achieved a cross-validation accuracy of 0.797 with an area under the receiver operating characteristic curve (AUC) of 0.882; the MS versus HS model obtained an accuracy of 0.772 and an AUC of 0.842. For the z-normalization, the CS versus HS model achieved an accuracy of 0.825 with an AUC of 0.882 and the MS versus HS model obtained an accuracy of 0.698 and an AUC of 0.807. The proposed method has the potential to rank cases with high probability of malignant findings aiding in the prioritization of radiologists work list. PMID:26240818

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.

Analysis of model development strategies: predicting ventral hernia recurrence.

PubMed

Holihan, Julie L; Li, Linda T; Askenasy, Erik P; Greenberg, Jacob A; Keith, Jerrod N; Martindale, Robert G; Roth, J Scott; Liang, Mike K

2016-11-01

There have been many attempts to identify variables associated with ventral hernia recurrence; however, it is unclear which statistical modeling approach results in models with greatest internal and external validity. We aim to assess the predictive accuracy of models developed using five common variable selection strategies to determine variables associated with hernia recurrence. Two multicenter ventral hernia databases were used. Database 1 was randomly split into "development" and "internal validation" cohorts. Database 2 was designated "external validation". The dependent variable for model development was hernia recurrence. Five variable selection strategies were used: (1) "clinical"-variables considered clinically relevant, (2) "selective stepwise"-all variables with a P value <0.20 were assessed in a step-backward model, (3) "liberal stepwise"-all variables were included and step-backward regression was performed, (4) "restrictive internal resampling," and (5) "liberal internal resampling." Variables were included with P < 0.05 for the Restrictive model and P < 0.10 for the Liberal model. A time-to-event analysis using Cox regression was performed using these strategies. The predictive accuracy of the developed models was tested on the internal and external validation cohorts using Harrell's C-statistic where C > 0.70 was considered "reasonable". The recurrence rate was 32.9% (n = 173/526; median/range follow-up, 20/1-58 mo) for the development cohort, 36.0% (n = 95/264, median/range follow-up 20/1-61 mo) for the internal validation cohort, and 12.7% (n = 155/1224, median/range follow-up 9/1-50 mo) for the external validation cohort. Internal validation demonstrated reasonable predictive accuracy (C-statistics = 0.772, 0.760, 0.767, 0.757, 0.763), while on external validation, predictive accuracy dipped precipitously (C-statistic = 0.561, 0.557, 0.562, 0.553, 0.560). Predictive accuracy was equally adequate on internal validation among models; however, on external validation, all five models failed to demonstrate utility. Future studies should report multiple variable selection techniques and demonstrate predictive accuracy on external data sets for model validation. Copyright © 2016 Elsevier Inc. All rights reserved.

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.

Accuracy of estimation of genomic breeding values in pigs using low-density genotypes and imputation.

PubMed

Badke, Yvonne M; Bates, Ronald O; Ernst, Catherine W; Fix, Justin; Steibel, Juan P

2014-04-16

Genomic selection has the potential to increase genetic progress. Genotype imputation of high-density single-nucleotide polymorphism (SNP) genotypes can improve the cost efficiency of genomic breeding value (GEBV) prediction for pig breeding. Consequently, the objectives of this work were to: (1) estimate accuracy of genomic evaluation and GEBV for three traits in a Yorkshire population and (2) quantify the loss of accuracy of genomic evaluation and GEBV when genotypes were imputed under two scenarios: a high-cost, high-accuracy scenario in which only selection candidates were imputed from a low-density platform and a low-cost, low-accuracy scenario in which all animals were imputed using a small reference panel of haplotypes. Phenotypes and genotypes obtained with the PorcineSNP60 BeadChip were available for 983 Yorkshire boars. Genotypes of selection candidates were masked and imputed using tagSNP in the GeneSeek Genomic Profiler (10K). Imputation was performed with BEAGLE using 128 or 1800 haplotypes as reference panels. GEBV were obtained through an animal-centric ridge regression model using de-regressed breeding values as response variables. Accuracy of genomic evaluation was estimated as the correlation between estimated breeding values and GEBV in a 10-fold cross validation design. Accuracy of genomic evaluation using observed genotypes was high for all traits (0.65-0.68). Using genotypes imputed from a large reference panel (accuracy: R(2) = 0.95) for genomic evaluation did not significantly decrease accuracy, whereas a scenario with genotypes imputed from a small reference panel (R(2) = 0.88) did show a significant decrease in accuracy. Genomic evaluation based on imputed genotypes in selection candidates can be implemented at a fraction of the cost of a genomic evaluation using observed genotypes and still yield virtually the same accuracy. On the other side, using a very small reference panel of haplotypes to impute training animals and candidates for selection results in lower accuracy of genomic evaluation.

A support vector machine for predicting defibrillation outcomes from waveform metrics.

PubMed

Howe, Andrew; Escalona, Omar J; Di Maio, Rebecca; Massot, Bertrand; Cromie, Nick A; Darragh, Karen M; Adgey, Jennifer; McEneaney, David J

2014-03-01

Algorithms to predict shock success based on VF waveform metrics could significantly enhance resuscitation by optimising the timing of defibrillation. To investigate robust methods of predicting defibrillation success in VF cardiac arrest patients, by using a support vector machine (SVM) optimisation approach. Frequency-domain (AMSA, dominant frequency and median frequency) and time-domain (slope and RMS amplitude) VF waveform metrics were calculated in a 4.1Y window prior to defibrillation. Conventional prediction test validity of each waveform parameter was conducted and used AUC>0.6 as the criterion for inclusion as a corroborative attribute processed by the SVM classification model. The latter used a Gaussian radial-basis-function (RBF) kernel and the error penalty factor C was fixed to 1. A two-fold cross-validation resampling technique was employed. A total of 41 patients had 115 defibrillation instances. AMSA, slope and RMS waveform metrics performed test validation with AUC>0.6 for predicting termination of VF and return-to-organised rhythm. Predictive accuracy of the optimised SVM design for termination of VF was 81.9% (± 1.24 SD); positive and negative predictivity were respectively 84.3% (± 1.98 SD) and 77.4% (± 1.24 SD); sensitivity and specificity were 87.6% (± 2.69 SD) and 71.6% (± 9.38 SD) respectively. AMSA, slope and RMS were the best VF waveform frequency-time parameters predictors of termination of VF according to test validity assessment. This a priori can be used for a simplified SVM optimised design that combines the predictive attributes of these VF waveform metrics for improved prediction accuracy and generalisation performance without requiring the definition of any threshold value on waveform metrics. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

The validity of the distress thermometer in prostate cancer populations.

PubMed

Chambers, Suzanne K; Zajdlewicz, Leah; Youlden, Danny R; Holland, Jimmie C; Dunn, Jeff

2014-02-01

The Distress Thermometer (DT) is widely recommended for screening for distress after cancer. However, the validity of the DT in men with prostate cancer and over differing time points from diagnosis has not been well examined. Receiver operating characteristics analyses were used to evaluate the diagnostic accuracy of the DT compared with three commonly used standardised scales in two prospective and one cross-sectional survey of men with prostate cancer (n = 740, 189 and 463, respectively). Comparison scales included the Impact of Event Scale - Revised (IES-R, Study 1), the Hospital Anxiety and Depression Scale (HADS, Study 2) and the Brief Symptom Inventory-18 (BSI-18, Study 3). Study 1: the DT showed good accuracy against the IES-R at all time points (area under curves (AUCs) ranging from 0.84 to 0.88) and sensitivity was high (>85%). Study 2: the DT performed well against both the anxiety and depression subscales for HADS at baseline (AUC = 0.84 and 0.82, respectively), but sensitivity decreased substantially after 12 months. Study 3: validity was high for the anxiety (AUC = 0.90, sensitivity = 90%) and depression (AUC = 0.85, sensitivity = 74%) subscales of the BSI-18 but was poorer for somatization (AUC = 0.67, sensitivity = 52%). A DT cut-off between ≥3 and ≥6 maximised sensitivity and specificity across analyses. The DT is a valid tool to detect cancer-specific distress, anxiety and depression among prostate cancer patients, particularly close to diagnosis. A cut-off of ≥4 may be optimal soon after diagnosis, and for longer-term assessments, ≥3 was supported. © 2013 The Authors. Psycho-Oncology published by John Wiley & Sons, Ltd. © 2013 The Authors. Psycho-Oncology published by John Wiley & Sons, Ltd.

Classification of autism spectrum disorder using supervised learning of brain connectivity measures extracted from synchrostates

NASA Astrophysics Data System (ADS)

Jamal, Wasifa; Das, Saptarshi; Oprescu, Ioana-Anastasia; Maharatna, Koushik; Apicella, Fabio; Sicca, Federico

2014-08-01

Objective. The paper investigates the presence of autism using the functional brain connectivity measures derived from electro-encephalogram (EEG) of children during face perception tasks. Approach. Phase synchronized patterns from 128-channel EEG signals are obtained for typical children and children with autism spectrum disorder (ASD). The phase synchronized states or synchrostates temporally switch amongst themselves as an underlying process for the completion of a particular cognitive task. We used 12 subjects in each group (ASD and typical) for analyzing their EEG while processing fearful, happy and neutral faces. The minimal and maximally occurring synchrostates for each subject are chosen for extraction of brain connectivity features, which are used for classification between these two groups of subjects. Among different supervised learning techniques, we here explored the discriminant analysis and support vector machine both with polynomial kernels for the classification task. Main results. The leave one out cross-validation of the classification algorithm gives 94.7% accuracy as the best performance with corresponding sensitivity and specificity values as 85.7% and 100% respectively. Significance. The proposed method gives high classification accuracies and outperforms other contemporary research results. The effectiveness of the proposed method for classification of autistic and typical children suggests the possibility of using it on a larger population to validate it for clinical practice.

Application of Machine Learning in Postural Control Kinematics for the Diagnosis of Alzheimer's Disease

PubMed Central

Yelshyna, Darya; Bicho, Estela

2016-01-01

The use of wearable devices to study gait and postural control is a growing field on neurodegenerative disorders such as Alzheimer's disease (AD). In this paper, we investigate if machine-learning classifiers offer the discriminative power for the diagnosis of AD based on postural control kinematics. We compared Support Vector Machines (SVMs), Multiple Layer Perceptrons (MLPs), Radial Basis Function Neural Networks (RBNs), and Deep Belief Networks (DBNs) on 72 participants (36 AD patients and 36 healthy subjects) exposed to seven increasingly difficult postural tasks. The decisional space was composed of 18 kinematic variables (adjusted for age, education, height, and weight), with or without neuropsychological evaluation (Montreal cognitive assessment (MoCA) score), top ranked in an error incremental analysis. Classification results were based on threefold cross validation of 50 independent and randomized runs sets: training (50%), test (40%), and validation (10%). Having a decisional space relying solely on postural kinematics, accuracy of AD diagnosis ranged from 71.7 to 86.1%. Adding the MoCA variable, the accuracy ranged between 91 and 96.6%. MLP classifier achieved top performance in both decisional spaces. Having comprehended the interdynamic interaction between postural stability and cognitive performance, our results endorse machine-learning models as a useful tool for computer-aided diagnosis of AD based on postural control kinematics. PMID:28074090

Application of Machine Learning in Postural Control Kinematics for the Diagnosis of Alzheimer's Disease.

PubMed

Costa, Luís; Gago, Miguel F; Yelshyna, Darya; Ferreira, Jaime; David Silva, Hélder; Rocha, Luís; Sousa, Nuno; Bicho, Estela

2016-01-01

The use of wearable devices to study gait and postural control is a growing field on neurodegenerative disorders such as Alzheimer's disease (AD). In this paper, we investigate if machine-learning classifiers offer the discriminative power for the diagnosis of AD based on postural control kinematics. We compared Support Vector Machines (SVMs), Multiple Layer Perceptrons (MLPs), Radial Basis Function Neural Networks (RBNs), and Deep Belief Networks (DBNs) on 72 participants (36 AD patients and 36 healthy subjects) exposed to seven increasingly difficult postural tasks. The decisional space was composed of 18 kinematic variables (adjusted for age, education, height, and weight), with or without neuropsychological evaluation (Montreal cognitive assessment (MoCA) score), top ranked in an error incremental analysis. Classification results were based on threefold cross validation of 50 independent and randomized runs sets: training (50%), test (40%), and validation (10%). Having a decisional space relying solely on postural kinematics, accuracy of AD diagnosis ranged from 71.7 to 86.1%. Adding the MoCA variable, the accuracy ranged between 91 and 96.6%. MLP classifier achieved top performance in both decisional spaces. Having comprehended the interdynamic interaction between postural stability and cognitive performance, our results endorse machine-learning models as a useful tool for computer-aided diagnosis of AD based on postural control kinematics.

Leveraging long read sequencing from a single individual to provide a comprehensive resource for benchmarking variant calling methods

PubMed Central

Mu, John C.; Tootoonchi Afshar, Pegah; Mohiyuddin, Marghoob; Chen, Xi; Li, Jian; Bani Asadi, Narges; Gerstein, Mark B.; Wong, Wing H.; Lam, Hugo Y. K.

2015-01-01

A high-confidence, comprehensive human variant set is critical in assessing accuracy of sequencing algorithms, which are crucial in precision medicine based on high-throughput sequencing. Although recent works have attempted to provide such a resource, they still do not encompass all major types of variants including structural variants (SVs). Thus, we leveraged the massive high-quality Sanger sequences from the HuRef genome to construct by far the most comprehensive gold set of a single individual, which was cross validated with deep Illumina sequencing, population datasets, and well-established algorithms. It was a necessary effort to completely reanalyze the HuRef genome as its previously published variants were mostly reported five years ago, suffering from compatibility, organization, and accuracy issues that prevent their direct use in benchmarking. Our extensive analysis and validation resulted in a gold set with high specificity and sensitivity. In contrast to the current gold sets of the NA12878 or HS1011 genomes, our gold set is the first that includes small variants, deletion SVs and insertion SVs up to a hundred thousand base-pairs. We demonstrate the utility of our HuRef gold set to benchmark several published SV detection tools. PMID:26412485

Combined QSAR and molecule docking studies on predicting P-glycoprotein inhibitors

NASA Astrophysics Data System (ADS)

Tan, Wen; Mei, Hu; Chao, Li; Liu, Tengfei; Pan, Xianchao; Shu, Mao; Yang, Li

2013-12-01

P-glycoprotein (P-gp) is an ATP-binding cassette multidrug transporter. The over expression of P-gp leads to the development of multidrug resistance (MDR), which is a major obstacle to effective treatment of cancer. Thus, designing effective P-gp inhibitors has an extremely important role in the overcoming MDR. In this paper, both ligand-based quantitative structure-activity relationship (QSAR) and receptor-based molecular docking are used to predict P-gp inhibitors. The results show that each method achieves good prediction performance. According to the results of tenfold cross-validation, an optimal linear SVM model with only three descriptors is established on 857 training samples, of which the overall accuracy (Acc), sensitivity, specificity, and Matthews correlation coefficient are 0.840, 0.873, 0.813, and 0.683, respectively. The SVM model is further validated by 418 test samples with the overall Acc of 0.868. Based on a homology model of human P-gp established, Surflex-dock is also performed to give binding free energy-based evaluations with the overall accuracies of 0.823 for the test set. Furthermore, a consensus evaluation is also performed by using these two methods. Both QSAR and molecular docking studies indicate that molecular volume, hydrophobicity and aromaticity are three dominant factors influencing the inhibitory activities.

Concentration determination of methyl magnesium chloride and other Grignard reagents by potentiometric titration with in-line characterization of reaction species by FTIR spectroscopy.

PubMed

Chen, Yadan; Wang, Tao; Helmy, Roy; Zhou, George X; LoBrutto, Rosario

2002-07-01

A potentiometric titration method for methyl magnesium chloride and other Grignard reagents based on the reaction with 2-butanol in THF has been developed and validated. The method employs a commercially available platinum electrode, using an electrolyte compatible with non-aqueous solvents. Well-defined titration curves were obtained, along with excellent method precision. The endpoint was precisely determined based on the first derivative of the titration curve. Different solvents such as THF, diethyl ether and methylene chloride provided similar results with regard to sharpness of the endpoint and method precision. The method was applied to a wide array of Grignard reagents including methyl magnesium bromide, ethyl magnesium chloride, propyl magnesium chloride, vinyl magnesium chloride, phenyl magnesium chloride, and benzyl magnesium chloride with similar precision and accuracy. Application of in-line FTIR was demonstrated for in situ monitoring of the titration reaction, allowing characterization of the reaction species. An authentic spectrum of the MeMgCl-THF complex was obtained using spectral subtraction and the vibrational absorbance bands were identified. FTIR also provided an alternative for detecting the titration endpoint, and the titration results so obtained, provided a cross-validation of the accuracy of the potentiometric titration.

Improved detection of congestive heart failure via probabilistic symbolic pattern recognition and heart rate variability metrics.

PubMed

Mahajan, Ruhi; Viangteeravat, Teeradache; Akbilgic, Oguz

2017-12-01

A timely diagnosis of congestive heart failure (CHF) is crucial to evade a life-threatening event. This paper presents a novel probabilistic symbol pattern recognition (PSPR) approach to detect CHF in subjects from their cardiac interbeat (R-R) intervals. PSPR discretizes each continuous R-R interval time series by mapping them onto an eight-symbol alphabet and then models the pattern transition behavior in the symbolic representation of the series. The PSPR-based analysis of the discretized series from 107 subjects (69 normal and 38 CHF subjects) yielded discernible features to distinguish normal subjects and subjects with CHF. In addition to PSPR features, we also extracted features using the time-domain heart rate variability measures such as average and standard deviation of R-R intervals. An ensemble of bagged decision trees was used to classify two groups resulting in a five-fold cross-validation accuracy, specificity, and sensitivity of 98.1%, 100%, and 94.7%, respectively. However, a 20% holdout validation yielded an accuracy, specificity, and sensitivity of 99.5%, 100%, and 98.57%, respectively. Results from this study suggest that features obtained with the combination of PSPR and long-term heart rate variability measures can be used in developing automated CHF diagnosis tools. Copyright © 2017 Elsevier B.V. All rights reserved.

Physiological reactivity to nonideographic virtual reality stimuli in veterans with and without PTSD

PubMed Central

Webb, Andrea K; Vincent, Ashley L; Jin, Alvin B; Pollack, Mark H

2015-01-01

Background Post-traumatic stress disorder (PTSD) currently is diagnosed via clinical interview in which subjective self reports of traumatic events and associated experiences are discussed with a mental health professional. The reliability and validity of diagnoses can be improved with the use of objective physiological measures. Methods In this study, physiological activity was recorded from 58 male veterans (PTSD Diagnosis n = 16; Trauma Exposed/No PTSD Diagnosis: n = 23; No Trauma/No PTSD Diagnosis: n = 19) with and without PTSD and combat trauma exposure in response to emotionally evocative non-idiographic virtual reality stimuli. Results Statistically significant differences among the Control, Trauma, and PTSD groups were present during the viewing of two virtual reality videos. Skin conductance and interbeat interval features were extracted for each of ten video events (five events of increasing severity per video). These features were submitted to three stepwise discriminant function analyses to assess classification accuracy for Control versus Trauma, Control versus PTSD, and Trauma versus PTSD pairings of participant groups. Leave-one-out cross-validation classification accuracy was between 71 and 94%. Conclusions These results are promising and suggest the utility of objective physiological measures in assisting with PTSD diagnosis. PMID:25642387

A Systematic Approach to Predicting Spring Force for Sagittal Craniosynostosis Surgery.

PubMed

Zhang, Guangming; Tan, Hua; Qian, Xiaohua; Zhang, Jian; Li, King; David, Lisa R; Zhou, Xiaobo

2016-05-01

Spring-assisted surgery (SAS) can effectively treat scaphocephaly by reshaping crania with the appropriate spring force. However, it is difficult to accurately estimate spring force without considering biomechanical properties of tissues. This study presents and validates a reliable system to accurately predict the spring force for sagittal craniosynostosis surgery. The authors randomly chose 23 patients who underwent SAS and had been followed for at least 2 years. An elastic model was designed to characterize the biomechanical behavior of calvarial bone tissue for each individual. After simulating the contact force on accurate position of the skull strip with the springs, the finite element method was applied to calculating the stress of each tissue node based on the elastic model. A support vector regression approach was then used to model the relationships between biomechanical properties generated from spring force, bone thickness, and the change of cephalic index after surgery. Therefore, for a new patient, the optimal spring force can be predicted based on the learned model with virtual spring simulation and dynamic programming approach prior to SAS. Leave-one-out cross-validation was implemented to assess the accuracy of our prediction. As a result, the mean prediction accuracy of this model was 93.35%, demonstrating the great potential of this model as a useful adjunct for preoperative planning tool.

LBflow: An extensible lattice Boltzmann framework for the simulation of geophysical flows. Part II: usage and validation

NASA Astrophysics Data System (ADS)

Llewellin, E. W.

2010-02-01

LBflow is a flexible, extensible implementation of the lattice Boltzmann method, developed with geophysical applications in mind. The theoretical basis for LBflow, and its implementation, are presented in the companion paper, 'Part I'. This article covers the practical usage of LBflow and presents guidelines for obtaining optimal results from available computing power. The relationships among simulation resolution, accuracy, runtime and memory requirements are investigated in detail. Particular attention is paid to the origin, quantification and minimization of errors. LBflow is validated against analytical, numerical and experimental results for a range of three-dimensional flow geometries. The fluid conductance of prismatic pipes with various cross sections is calculated with LBflow and found to be in excellent agreement with published results. Simulated flow along sinusoidally constricted pipes gives good agreement with experimental data for a wide range of Reynolds number. The permeability of packs of spheres is determined and shown to be in excellent agreement with analytical results. The accuracy of internal flow patterns within the investigated geometries is also in excellent quantitative agreement with published data. The development of vortices within a sinusoidally constricted pipe with increasing Reynolds number is shown, demonstrating the insight that LBflow can offer as a 'virtual laboratory' for fluid flow.

Cross-validation pitfalls when selecting and assessing regression and classification models.

PubMed

Krstajic, Damjan; Buturovic, Ljubomir J; Leahy, David E; Thomas, Simon

2014-03-29

We address the problem of selecting and assessing classification and regression models using cross-validation. Current state-of-the-art methods can yield models with high variance, rendering them unsuitable for a number of practical applications including QSAR. In this paper we describe and evaluate best practices which improve reliability and increase confidence in selected models. A key operational component of the proposed methods is cloud computing which enables routine use of previously infeasible approaches. We describe in detail an algorithm for repeated grid-search V-fold cross-validation for parameter tuning in classification and regression, and we define a repeated nested cross-validation algorithm for model assessment. As regards variable selection and parameter tuning we define two algorithms (repeated grid-search cross-validation and double cross-validation), and provide arguments for using the repeated grid-search in the general case. We show results of our algorithms on seven QSAR datasets. The variation of the prediction performance, which is the result of choosing different splits of the dataset in V-fold cross-validation, needs to be taken into account when selecting and assessing classification and regression models. We demonstrate the importance of repeating cross-validation when selecting an optimal model, as well as the importance of repeating nested cross-validation when assessing a prediction error.

Estimating the domain of applicability for machine learning QSAR models: a study on aqueous solubility of drug discovery molecules.

PubMed

Schroeter, Timon Sebastian; Schwaighofer, Anton; Mika, Sebastian; Ter Laak, Antonius; Suelzle, Detlev; Ganzer, Ursula; Heinrich, Nikolaus; Müller, Klaus-Robert

2007-12-01

We investigate the use of different Machine Learning methods to construct models for aqueous solubility. Models are based on about 4000 compounds, including an in-house set of 632 drug discovery molecules of Bayer Schering Pharma. For each method, we also consider an appropriate method to obtain error bars, in order to estimate the domain of applicability (DOA) for each model. Here, we investigate error bars from a Bayesian model (Gaussian Process (GP)), an ensemble based approach (Random Forest), and approaches based on the Mahalanobis distance to training data (for Support Vector Machine and Ridge Regression models). We evaluate all approaches in terms of their prediction accuracy (in cross-validation, and on an external validation set of 536 molecules) and in how far the individual error bars can faithfully represent the actual prediction error.

Estimating the domain of applicability for machine learning QSAR models: a study on aqueous solubility of drug discovery molecules.

PubMed

Schroeter, Timon Sebastian; Schwaighofer, Anton; Mika, Sebastian; Ter Laak, Antonius; Suelzle, Detlev; Ganzer, Ursula; Heinrich, Nikolaus; Müller, Klaus-Robert

2007-09-01

We investigate the use of different Machine Learning methods to construct models for aqueous solubility. Models are based on about 4000 compounds, including an in-house set of 632 drug discovery molecules of Bayer Schering Pharma. For each method, we also consider an appropriate method to obtain error bars, in order to estimate the domain of applicability (DOA) for each model. Here, we investigate error bars from a Bayesian model (Gaussian Process (GP)), an ensemble based approach (Random Forest), and approaches based on the Mahalanobis distance to training data (for Support Vector Machine and Ridge Regression models). We evaluate all approaches in terms of their prediction accuracy (in cross-validation, and on an external validation set of 536 molecules) and in how far the individual error bars can faithfully represent the actual prediction error.

Elastic modulus measurements at variable temperature: Validation of atomic force microscopy techniques

NASA Astrophysics Data System (ADS)

Natali, Marco; Reggente, Melania; Passeri, Daniele; Rossi, Marco

2016-06-01

The development of polymer-based nanocomposites to be used in critical thermal environments requires the characterization of their mechanical properties, which are related to their chemical composition, size, morphology and operating temperature. Atomic force microscopy (AFM) has been proven to be a useful tool to develop techniques for the mechanical characterization of these materials, thanks to its nanometer lateral resolution and to the capability of exerting ultra-low loads, down to the piconewton range. In this work, we demonstrate two techniques, one quasi-static, i.e., AFM-based indentation (I-AFM), and one dynamic, i.e., contact resonance AFM (CR-AFM), for the mechanical characterization of compliant materials at variable temperature. A cross-validation of I-AFM and CR-AFM has been performed by comparing the results obtained on two reference materials, i.e., low-density polyethylene (LDPE) and polycarbonate (PC), which demonstrated the accuracy of the techniques.

Estimating the domain of applicability for machine learning QSAR models: a study on aqueous solubility of drug discovery molecules

NASA Astrophysics Data System (ADS)

Schroeter, Timon Sebastian; Schwaighofer, Anton; Mika, Sebastian; Ter Laak, Antonius; Suelzle, Detlev; Ganzer, Ursula; Heinrich, Nikolaus; Müller, Klaus-Robert

2007-12-01

We investigate the use of different Machine Learning methods to construct models for aqueous solubility. Models are based on about 4000 compounds, including an in-house set of 632 drug discovery molecules of Bayer Schering Pharma. For each method, we also consider an appropriate method to obtain error bars, in order to estimate the domain of applicability (DOA) for each model. Here, we investigate error bars from a Bayesian model (Gaussian Process (GP)), an ensemble based approach (Random Forest), and approaches based on the Mahalanobis distance to training data (for Support Vector Machine and Ridge Regression models). We evaluate all approaches in terms of their prediction accuracy (in cross-validation, and on an external validation set of 536 molecules) and in how far the individual error bars can faithfully represent the actual prediction error.

Estimating the domain of applicability for machine learning QSAR models: a study on aqueous solubility of drug discovery molecules

NASA Astrophysics Data System (ADS)

Schroeter, Timon Sebastian; Schwaighofer, Anton; Mika, Sebastian; Ter Laak, Antonius; Suelzle, Detlev; Ganzer, Ursula; Heinrich, Nikolaus; Müller, Klaus-Robert

2007-09-01

We investigate the use of different Machine Learning methods to construct models for aqueous solubility. Models are based on about 4000 compounds, including an in-house set of 632 drug discovery molecules of Bayer Schering Pharma. For each method, we also consider an appropriate method to obtain error bars, in order to estimate the domain of applicability (DOA) for each model. Here, we investigate error bars from a Bayesian model (Gaussian Process (GP)), an ensemble based approach (Random Forest), and approaches based on the Mahalanobis distance to training data (for Support Vector Machine and Ridge Regression models). We evaluate all approaches in terms of their prediction accuracy (in cross-validation, and on an external validation set of 536 molecules) and in how far the individual error bars can faithfully represent the actual prediction error.

Modeling brook trout presence and absence from landscape variables using four different analytical methods

USGS Publications Warehouse

Steen, Paul J.; Passino-Reader, Dora R.; Wiley, Michael J.

2006-01-01

As a part of the Great Lakes Regional Aquatic Gap Analysis Project, we evaluated methodologies for modeling associations between fish species and habitat characteristics at a landscape scale. To do this, we created brook trout Salvelinus fontinalis presence and absence models based on four different techniques: multiple linear regression, logistic regression, neural networks, and classification trees. The models were tested in two ways: by application to an independent validation database and cross-validation using the training data, and by visual comparison of statewide distribution maps with historically recorded occurrences from the Michigan Fish Atlas. Although differences in the accuracy of our models were slight, the logistic regression model predicted with the least error, followed by multiple regression, then classification trees, then the neural networks. These models will provide natural resource managers a way to identify habitats requiring protection for the conservation of fish species.

Accuracy of Genomic Prediction in a Commercial Perennial Ryegrass Breeding Program.

PubMed

Fè, Dario; Ashraf, Bilal H; Pedersen, Morten G; Janss, Luc; Byrne, Stephen; Roulund, Niels; Lenk, Ingo; Didion, Thomas; Asp, Torben; Jensen, Christian S; Jensen, Just

2016-11-01

The implementation of genomic selection (GS) in plant breeding, so far, has been mainly evaluated in crops farmed as homogeneous varieties, and the results have been generally positive. Fewer results are available for species, such as forage grasses, that are grown as heterogenous families (developed from multiparent crosses) in which the control of the genetic variation is far more complex. Here we test the potential for implementing GS in the breeding of perennial ryegrass ( L.) using empirical data from a commercial forage breeding program. Biparental F and multiparental synthetic (SYN) families of diploid perennial ryegrass were genotyped using genotyping-by-sequencing, and phenotypes for five different traits were analyzed. Genotypes were expressed as family allele frequencies, and phenotypes were recorded as family means. Different models for genomic prediction were compared by using practically relevant cross-validation strategies. All traits showed a highly significant level of genetic variance, which could be traced using the genotyping assay. While there was significant genotype × environment (G × E) interaction for some traits, accuracies were high among F families and between biparental F and multiparental SYN families. We have demonstrated that the implementation of GS in grass breeding is now possible and presents an opportunity to make significant gains for various traits. Copyright © 2016 Crop Science Society of America.

Attentional reorienting triggers spatial asymmetries in a search task with cross-modal spatial cueing

PubMed Central

Paladini, Rebecca E.; Diana, Lorenzo; Zito, Giuseppe A.; Nyffeler, Thomas; Wyss, Patric; Mosimann, Urs P.; Müri, René M.; Nef, Tobias

2018-01-01

Cross-modal spatial cueing can affect performance in a visual search task. For example, search performance improves if a visual target and an auditory cue originate from the same spatial location, and it deteriorates if they originate from different locations. Moreover, it has recently been postulated that multisensory settings, i.e., experimental settings, in which critical stimuli are concurrently presented in different sensory modalities (e.g., visual and auditory), may trigger asymmetries in visuospatial attention. Thereby, a facilitation has been observed for visual stimuli presented in the right compared to the left visual space. However, it remains unclear whether auditory cueing of attention differentially affects search performance in the left and the right hemifields in audio-visual search tasks. The present study investigated whether spatial asymmetries would occur in a search task with cross-modal spatial cueing. Participants completed a visual search task that contained no auditory cues (i.e., unimodal visual condition), spatially congruent, spatially incongruent, and spatially non-informative auditory cues. To further assess participants’ accuracy in localising the auditory cues, a unimodal auditory spatial localisation task was also administered. The results demonstrated no left/right asymmetries in the unimodal visual search condition. Both an additional incongruent, as well as a spatially non-informative, auditory cue resulted in lateral asymmetries. Thereby, search times were increased for targets presented in the left compared to the right hemifield. No such spatial asymmetry was observed in the congruent condition. However, participants’ performance in the congruent condition was modulated by their tone localisation accuracy. The findings of the present study demonstrate that spatial asymmetries in multisensory processing depend on the validity of the cross-modal cues, and occur under specific attentional conditions, i.e., when visual attention has to be reoriented towards the left hemifield. PMID:29293637

Blind system identification of two-thermocouple sensor based on cross-relation method.

PubMed

Li, Yanfeng; Zhang, Zhijie; Hao, Xiaojian

2018-03-01

In dynamic temperature measurement, the dynamic characteristics of the sensor affect the accuracy of the measurement results. Thermocouples are widely used for temperature measurement in harsh conditions due to their low cost, robustness, and reliability, but because of the presence of the thermal inertia, there is a dynamic error in the dynamic temperature measurement. In order to eliminate the dynamic error, two-thermocouple sensor was used to measure dynamic gas temperature in constant velocity flow environments in this paper. Blind system identification of two-thermocouple sensor based on a cross-relation method was carried out. Particle swarm optimization algorithm was used to estimate time constants of two thermocouples and compared with the grid based search method. The method was validated on the experimental equipment built by using high temperature furnace, and the input dynamic temperature was reconstructed by using the output data of the thermocouple with small time constant.

Blind system identification of two-thermocouple sensor based on cross-relation method

NASA Astrophysics Data System (ADS)

Li, Yanfeng; Zhang, Zhijie; Hao, Xiaojian

2018-03-01

In dynamic temperature measurement, the dynamic characteristics of the sensor affect the accuracy of the measurement results. Thermocouples are widely used for temperature measurement in harsh conditions due to their low cost, robustness, and reliability, but because of the presence of the thermal inertia, there is a dynamic error in the dynamic temperature measurement. In order to eliminate the dynamic error, two-thermocouple sensor was used to measure dynamic gas temperature in constant velocity flow environments in this paper. Blind system identification of two-thermocouple sensor based on a cross-relation method was carried out. Particle swarm optimization algorithm was used to estimate time constants of two thermocouples and compared with the grid based search method. The method was validated on the experimental equipment built by using high temperature furnace, and the input dynamic temperature was reconstructed by using the output data of the thermocouple with small time constant.

The HITRAN2016 molecular spectroscopic database

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

Gordon, I. E.; Rothman, L. S.; Hill, C.

This paper describes the contents of the 2016 edition of the HITRAN molecular spectroscopic compilation. The new edition replaces the previous HITRAN edition of 2012 and its updates during the intervening years. The HITRAN molecular absorption compilation is comprised of five major components: the traditional line-by-line spectroscopic parameters required for high-resolution radiative-transfer codes, infrared absorption cross-sections for molecules not yet amenable to representation in a line-by-line form, collision-induced absorption data, aerosol indices of refraction, and general tables such as partition sums that apply globally to the data. The new HITRAN is greatly extended in terms of accuracy, spectral coverage, additionalmore » absorption phenomena, added line-shape formalisms, and validity. Moreover, molecules, isotopologues, and perturbing gases have been added that address the issues of atmospheres beyond the Earth. Of considerable note, experimental IR cross-sections for almost 200 additional significant molecules have been added to the database.« less

Performance Prediction and Validation: Data, Frameworks, and Considerations

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

Tinnesand, Heidi

2017-05-19

Improving the predictability and reliability of wind power generation and operations will reduce costs and potentially establish a framework to attract new capital into the distributed wind sector, a key cost reduction requirement highlighted in results from the distributed wind future market assessment conducted with dWind. Quantifying and refining the accuracy of project performance estimates will also directly address several of the key challenges identified by industry stakeholders in 2015 as part of the distributed wind resource assessment workshop and be cross-cutting for several other facets of the distributed wind portfolio. This presentation covers the efforts undertaken in 2016 tomore » address these topics.« less

Medical application of artificial immune recognition system (AIRS): diagnosis of atherosclerosis from carotid artery Doppler signals.

PubMed

Latifoğlu, Fatma; Kodaz, Halife; Kara, Sadik; Güneş, Salih

2007-08-01

This study was conducted to distinguish between atherosclerosis and healthy subjects. Hence, we have employed the maximum envelope of the carotid artery Doppler sonograms derived from Fast Fourier Transformation-Welch method and Artificial Immune Recognition System (AIRS). The fuzzy appearance of the carotid artery Doppler signals makes physicians suspicious about the existence of diseases and sometimes causes false diagnosis. Our technique gets around this problem using AIRS to decide and assist the physician to make the final judgment in confidence. AIRS has reached 99.29% classification accuracy using 10-fold cross validation. Results show that the proposed method classified Doppler signals successfully.

Accounting for dominance to improve genomic evaluations of dairy cows for fertility and milk production traits.

PubMed

Aliloo, Hassan; Pryce, Jennie E; González-Recio, Oscar; Cocks, Benjamin G; Hayes, Ben J

2016-02-01

Dominance effects may contribute to genetic variation of complex traits in dairy cattle, especially for traits closely related to fitness such as fertility. However, traditional genetic evaluations generally ignore dominance effects and consider additive genetic effects only. Availability of dense single nucleotide polymorphisms (SNPs) panels provides the opportunity to investigate the role of dominance in quantitative variation of complex traits at both the SNP and animal levels. Including dominance effects in the genomic evaluation of animals could also help to increase the accuracy of prediction of future phenotypes. In this study, we estimated additive and dominance variance components for fertility and milk production traits of genotyped Holstein and Jersey cows in Australia. The predictive abilities of a model that accounts for additive effects only (additive), and a model that accounts for both additive and dominance effects (additive + dominance) were compared in a fivefold cross-validation. Estimates of the proportion of dominance variation relative to phenotypic variation that is captured by SNPs, for production traits, were up to 3.8 and 7.1 % in Holstein and Jersey cows, respectively, whereas, for fertility, they were equal to 1.2 % in Holstein and very close to zero in Jersey cows. We found that including dominance in the model was not consistently advantageous. Based on maximum likelihood ratio tests, the additive + dominance model fitted the data better than the additive model, for milk, fat and protein yields in both breeds. However, regarding the prediction of phenotypes assessed with fivefold cross-validation, including dominance effects in the model improved accuracy only for fat yield in Holstein cows. Regression coefficients of phenotypes on genetic values and mean squared errors of predictions showed that the predictive ability of the additive + dominance model was superior to that of the additive model for some of the traits. In both breeds, dominance effects were significant (P < 0.01) for all milk production traits but not for fertility. Accuracy of prediction of phenotypes was slightly increased by including dominance effects in the genomic evaluation model. Thus, it can help to better identify highly performing individuals and be useful for culling decisions.

STRUM: structure-based prediction of protein stability changes upon single-point mutation.

PubMed

Quan, Lijun; Lv, Qiang; Zhang, Yang

2016-10-01

Mutations in human genome are mainly through single nucleotide polymorphism, some of which can affect stability and function of proteins, causing human diseases. Several methods have been proposed to predict the effect of mutations on protein stability; but most require features from experimental structure. Given the fast progress in protein structure prediction, this work explores the possibility to improve the mutation-induced stability change prediction using low-resolution structure modeling. We developed a new method (STRUM) for predicting stability change caused by single-point mutations. Starting from wild-type sequences, 3D models are constructed by the iterative threading assembly refinement (I-TASSER) simulations, where physics- and knowledge-based energy functions are derived on the I-TASSER models and used to train STRUM models through gradient boosting regression. STRUM was assessed by 5-fold cross validation on 3421 experimentally determined mutations from 150 proteins. The Pearson correlation coefficient (PCC) between predicted and measured changes of Gibbs free-energy gap, ΔΔG, upon mutation reaches 0.79 with a root-mean-square error 1.2 kcal/mol in the mutation-based cross-validations. The PCC reduces if separating training and test mutations from non-homologous proteins, which reflects inherent correlations in the current mutation sample. Nevertheless, the results significantly outperform other state-of-the-art methods, including those built on experimental protein structures. Detailed analyses show that the most sensitive features in STRUM are the physics-based energy terms on I-TASSER models and the conservation scores from multiple-threading template alignments. However, the ΔΔG prediction accuracy has only a marginal dependence on the accuracy of protein structure models as long as the global fold is correct. These data demonstrate the feasibility to use low-resolution structure modeling for high-accuracy stability change prediction upon point mutations. http://zhanglab.ccmb.med.umich.edu/STRUM/ CONTACT: qiang@suda.edu.cn and zhng@umich.edu Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

STRUM: structure-based prediction of protein stability changes upon single-point mutation

PubMed Central

Quan, Lijun; Lv, Qiang; Zhang, Yang

2016-01-01

Motivation: Mutations in human genome are mainly through single nucleotide polymorphism, some of which can affect stability and function of proteins, causing human diseases. Several methods have been proposed to predict the effect of mutations on protein stability; but most require features from experimental structure. Given the fast progress in protein structure prediction, this work explores the possibility to improve the mutation-induced stability change prediction using low-resolution structure modeling. Results: We developed a new method (STRUM) for predicting stability change caused by single-point mutations. Starting from wild-type sequences, 3D models are constructed by the iterative threading assembly refinement (I-TASSER) simulations, where physics- and knowledge-based energy functions are derived on the I-TASSER models and used to train STRUM models through gradient boosting regression. STRUM was assessed by 5-fold cross validation on 3421 experimentally determined mutations from 150 proteins. The Pearson correlation coefficient (PCC) between predicted and measured changes of Gibbs free-energy gap, ΔΔG, upon mutation reaches 0.79 with a root-mean-square error 1.2 kcal/mol in the mutation-based cross-validations. The PCC reduces if separating training and test mutations from non-homologous proteins, which reflects inherent correlations in the current mutation sample. Nevertheless, the results significantly outperform other state-of-the-art methods, including those built on experimental protein structures. Detailed analyses show that the most sensitive features in STRUM are the physics-based energy terms on I-TASSER models and the conservation scores from multiple-threading template alignments. However, the ΔΔG prediction accuracy has only a marginal dependence on the accuracy of protein structure models as long as the global fold is correct. These data demonstrate the feasibility to use low-resolution structure modeling for high-accuracy stability change prediction upon point mutations. Availability and Implementation: http://zhanglab.ccmb.med.umich.edu/STRUM/ Contact: qiang@suda.edu.cn and zhng@umich.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27318206

An alternative covariance estimator to investigate genetic heterogeneity in populations.

PubMed

Heslot, Nicolas; Jannink, Jean-Luc

2015-11-26

For genomic prediction and genome-wide association studies (GWAS) using mixed models, covariance between individuals is estimated using molecular markers. Based on the properties of mixed models, using available molecular data for prediction is optimal if this covariance is known. Under this assumption, adding individuals to the analysis should never be detrimental. However, some empirical studies showed that increasing training population size decreased prediction accuracy. Recently, results from theoretical models indicated that even if marker density is high and the genetic architecture of traits is controlled by many loci with small additive effects, the covariance between individuals, which depends on relationships at causal loci, is not always well estimated by the whole-genome kinship. We propose an alternative covariance estimator named K-kernel, to account for potential genetic heterogeneity between populations that is characterized by a lack of genetic correlation, and to limit the information flow between a priori unknown populations in a trait-specific manner. This is similar to a multi-trait model and parameters are estimated by REML and, in extreme cases, it can allow for an independent genetic architecture between populations. As such, K-kernel is useful to study the problem of the design of training populations. K-kernel was compared to other covariance estimators or kernels to examine its fit to the data, cross-validated accuracy and suitability for GWAS on several datasets. It provides a significantly better fit to the data than the genomic best linear unbiased prediction model and, in some cases it performs better than other kernels such as the Gaussian kernel, as shown by an empirical null distribution. In GWAS simulations, alternative kernels control type I errors as well as or better than the classical whole-genome kinship and increase statistical power. No or small gains were observed in cross-validated prediction accuracy. This alternative covariance estimator can be used to gain insight into trait-specific genetic heterogeneity by identifying relevant sub-populations that lack genetic correlation between them. Genetic correlation can be 0 between identified sub-populations by performing automatic selection of relevant sets of individuals to be included in the training population. It may also increase statistical power in GWAS.

Modeling Pathologic Response of Esophageal Cancer to Chemoradiation Therapy Using Spatial-Temporal {sup 18}F-FDG PET Features, Clinical Parameters, and Demographics

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

Zhang, Hao; Tan, Shan; Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan

2014-01-01

Purpose: To construct predictive models using comprehensive tumor features for the evaluation of tumor response to neoadjuvant chemoradiation therapy (CRT) in patients with esophageal cancer. Methods and Materials: This study included 20 patients who underwent trimodality therapy (CRT + surgery) and underwent {sup 18}F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) both before and after CRT. Four groups of tumor features were examined: (1) conventional PET/CT response measures (eg, standardized uptake value [SUV]{sub max}, tumor diameter); (2) clinical parameters (eg, TNM stage, histology) and demographics; (3) spatial-temporal PET features, which characterize tumor SUV intensity distribution, spatial patterns, geometry, and associated changesmore » resulting from CRT; and (4) all features combined. An optimal feature set was identified with recursive feature selection and cross-validations. Support vector machine (SVM) and logistic regression (LR) models were constructed for prediction of pathologic tumor response to CRT, cross-validations being used to avoid model overfitting. Prediction accuracy was assessed by area under the receiver operating characteristic curve (AUC), and precision was evaluated by confidence intervals (CIs) of AUC. Results: When applied to the 4 groups of tumor features, the LR model achieved AUCs (95% CI) of 0.57 (0.10), 0.73 (0.07), 0.90 (0.06), and 0.90 (0.06). The SVM model achieved AUCs (95% CI) of 0.56 (0.07), 0.60 (0.06), 0.94 (0.02), and 1.00 (no misclassifications). With the use of spatial-temporal PET features combined with conventional PET/CT measures and clinical parameters, the SVM model achieved very high accuracy (AUC 1.00) and precision (no misclassifications)—results that were significantly better than when conventional PET/CT measures or clinical parameters and demographics alone were used. For groups with many tumor features (groups 3 and 4), the SVM model achieved significantly higher accuracy than did the LR model. Conclusions: The SVM model that used all features including spatial-temporal PET features accurately and precisely predicted pathologic tumor response to CRT in esophageal cancer.« less

ANAlyte: A modular image analysis tool for ANA testing with indirect immunofluorescence.

PubMed

Di Cataldo, Santa; Tonti, Simone; Bottino, Andrea; Ficarra, Elisa

2016-05-01

The automated analysis of indirect immunofluorescence images for Anti-Nuclear Autoantibody (ANA) testing is a fairly recent field that is receiving ever-growing interest from the research community. ANA testing leverages on the categorization of intensity level and fluorescent pattern of IIF images of HEp-2 cells to perform a differential diagnosis of important autoimmune diseases. Nevertheless, it suffers from tremendous lack of repeatability due to subjectivity in the visual interpretation of the images. The automatization of the analysis is seen as the only valid solution to this problem. Several works in literature address individual steps of the work-flow, nonetheless integrating such steps and assessing their effectiveness as a whole is still an open challenge. We present a modular tool, ANAlyte, able to characterize a IIF image in terms of fluorescent intensity level and fluorescent pattern without any user-interactions. For this purpose, ANAlyte integrates the following: (i) Intensity Classifier module, that categorizes the intensity level of the input slide based on multi-scale contrast assessment; (ii) Cell Segmenter module, that splits the input slide into individual HEp-2 cells; (iii) Pattern Classifier module, that determines the fluorescent pattern of the slide based on the pattern of the individual cells. To demonstrate the accuracy and robustness of our tool, we experimentally validated ANAlyte on two different public benchmarks of IIF HEp-2 images with rigorous leave-one-out cross-validation strategy. We obtained overall accuracy of fluorescent intensity and pattern classification respectively around 85% and above 90%. We assessed all results by comparisons with some of the most representative state of the art works. Unlike most of the other works in the recent literature, ANAlyte aims at the automatization of all the major steps of ANA image analysis. Results on public benchmarks demonstrate that the tool can characterize HEp-2 slides in terms of intensity and fluorescent pattern with accuracy better or comparable with the state of the art techniques, even when such techniques are run on manually segmented cells. Hence, ANAlyte can be proposed as a valid solution to the problem of ANA testing automatization. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Reliability, Validity, and Classification Accuracy of the DSM-5 Diagnostic Criteria for Gambling Disorder and Comparison to DSM-IV.

PubMed

Stinchfield, Randy; McCready, John; Turner, Nigel E; Jimenez-Murcia, Susana; Petry, Nancy M; Grant, Jon; Welte, John; Chapman, Heather; Winters, Ken C

2016-09-01

The DSM-5 was published in 2013 and it included two substantive revisions for gambling disorder (GD). These changes are the reduction in the threshold from five to four criteria and elimination of the illegal activities criterion. The purpose of this study was to twofold. First, to assess the reliability, validity and classification accuracy of the DSM-5 diagnostic criteria for GD. Second, to compare the DSM-5-DSM-IV on reliability, validity, and classification accuracy, including an examination of the effect of the elimination of the illegal acts criterion on diagnostic accuracy. To compare DSM-5 and DSM-IV, eight datasets from three different countries (Canada, USA, and Spain; total N = 3247) were used. All datasets were based on similar research methods. Participants were recruited from outpatient gambling treatment services to represent the group with a GD and from the community to represent the group without a GD. All participants were administered a standardized measure of diagnostic criteria. The DSM-5 yielded satisfactory reliability, validity and classification accuracy. In comparing the DSM-5 to the DSM-IV, most comparisons of reliability, validity and classification accuracy showed more similarities than differences. There was evidence of modest improvements in classification accuracy for DSM-5 over DSM-IV, particularly in reduction of false negative errors. This reduction in false negative errors was largely a function of lowering the cut score from five to four and this revision is an improvement over DSM-IV. From a statistical standpoint, eliminating the illegal acts criterion did not make a significant impact on diagnostic accuracy. From a clinical standpoint, illegal acts can still be addressed in the context of the DSM-5 criterion of lying to others.

FY2012 summary of tasks completed on PROTEUS-thermal work.

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

Lee, C.H.; Smith, M.A.

2012-06-06

PROTEUS is a suite of the neutronics codes, both old and new, that can be used within the SHARP codes being developed under the NEAMS program. Discussion here is focused on updates and verification and validation activities of the SHARP neutronics code, DeCART, for application to thermal reactor analysis. As part of the development of SHARP tools, the different versions of the DeCART code created for PWR, BWR, and VHTR analysis were integrated. Verification and validation tests for the integrated version were started, and the generation of cross section libraries based on the subgroup method was revisited for the targetedmore » reactor types. The DeCART code has been reorganized in preparation for an efficient integration of the different versions for PWR, BWR, and VHTR analysis. In DeCART, the old-fashioned common blocks and header files have been replaced by advanced memory structures. However, the changing of variable names was minimized in order to limit problems with the code integration. Since the remaining stability problems of DeCART were mostly caused by the CMFD methodology and modules, significant work was performed to determine whether they could be replaced by more stable methods and routines. The cross section library is a key element to obtain accurate solutions. Thus, the procedure for generating cross section libraries was revisited to provide libraries tailored for the targeted reactor types. To improve accuracy in the cross section library, an attempt was made to replace the CENTRM code by the MCNP Monte Carlo code as a tool obtaining reference resonance integrals. The use of the Monte Carlo code allows us to minimize problems or approximations that CENTRM introduces since the accuracy of the subgroup data is limited by that of the reference solutions. The use of MCNP requires an additional set of libraries without resonance cross sections so that reference calculations can be performed for a unit cell in which only one isotope of interest includes resonance cross sections, among the isotopes in the composition. The OECD MHTGR-350 benchmark core was simulated using DeCART as initial focus of the verification/validation efforts. Among the benchmark problems, Exercise 1 of Phase 1 is a steady-state benchmark case for the neutronics calculation for which block-wise cross sections were provided in 26 energy groups. This type of problem was designed for a homogenized geometry solver like DIF3D rather than the high-fidelity code DeCART. Instead of the homogenized block cross sections given in the benchmark, the VHTR-specific 238-group ENDF/B-VII.0 library of DeCART was directly used for preliminary calculations. Initial results showed that the multiplication factors of a fuel pin and a fuel block with or without a control rod hole were off by 6, -362, and -183 pcm Dk from comparable MCNP solutions, respectively. The 2-D and 3-D one-third core calculations were also conducted for the all-rods-out (ARO) and all-rods-in (ARI) configurations, producing reasonable results. Figure 1 illustrates the intermediate (1.5 eV - 17 keV) and thermal (below 1.5 eV) group flux distributions. As seen from VHTR cores with annular fuels, the intermediate group fluxes are relatively high in the fuel region, but the thermal group fluxes are higher in the inner and outer graphite reflector regions than in the fuel region. To support the current project, a new three-year I-NERI collaboration involving ANL and KAERI was started in November 2011, focused on performing in-depth verification and validation of high-fidelity multi-physics simulation codes for LWR and VHTR. The work scope includes generating improved cross section libraries for the targeted reactor types, developing benchmark models for verification and validation of the neutronics code with or without thermo-fluid feedback, and performing detailed comparisons of predicted reactor parameters against both Monte Carlo solutions and experimental measurements. The following list summarizes the work conducted so far for PROTEUS-Thermal Tasks: Unification of different versions of DeCART was initiated, and at the same time code modernization was conducted to make code unification efficient; (2) Regeneration of cross section libraries was attempted for the targeted reactor types, and the procedure for generating cross section libraries was updated by replacing CENTRM with MCNP for reference resonance integrals; (3) The MHTGR-350 benchmark core was simulated using DeCART with VHTR-specific 238-group ENDF/B-VII.0 library, and MCNP calculations were performed for comparison; and (4) Benchmark problems for PWR and BWR analysis were prepared for the DeCART verification/validation effort. In the coming months, the work listed above will be completed. Cross section libraries will be generated with optimized group structures for specific reactor types.« less

Thin slices of child personality: Perceptual, situational, and behavioral contributions.

PubMed

Tackett, Jennifer L; Herzhoff, Kathrin; Kushner, Shauna C; Rule, Nicholas

2016-01-01

The present study examined whether thin-slice ratings of child personality serve as a resource-efficient and theoretically valid measurement of child personality traits. We extended theoretical work on the observability, perceptual accuracy, and situational consistency of childhood personality traits by examining intersource and interjudge agreement, cross-situational consistency, and convergent, divergent, and predictive validity of thin-slice ratings. Forty-five unacquainted independent coders rated 326 children's (ages 8-12) personality in 1 of 15 thin-slice behavioral scenarios (i.e., 3 raters per slice, for over 14,000 independent thin-slice ratings). Mothers, fathers, and children rated children's personality, psychopathology, and competence. We found robust evidence for correlations between thin-slice and mother/father ratings of child personality, within- and across-task consistency of thin-slice ratings, and convergent and divergent validity with psychopathology and competence. Surprisingly, thin-slice ratings were more consistent across situations in this child sample than previously found for adults. Taken together, these results suggest that thin slices are a valid and reliable measure to assess child personality, offering a useful method of measurement beyond questionnaires, helping to address novel questions of personality perception and consistency in childhood. (c) 2016 APA, all rights reserved).

Energy-Based Metrics for Arthroscopic Skills Assessment.

PubMed

Poursartip, Behnaz; LeBel, Marie-Eve; McCracken, Laura C; Escoto, Abelardo; Patel, Rajni V; Naish, Michael D; Trejos, Ana Luisa

2017-08-05

Minimally invasive skills assessment methods are essential in developing efficient surgical simulators and implementing consistent skills evaluation. Although numerous methods have been investigated in the literature, there is still a need to further improve the accuracy of surgical skills assessment. Energy expenditure can be an indication of motor skills proficiency. The goals of this study are to develop objective metrics based on energy expenditure, normalize these metrics, and investigate classifying trainees using these metrics. To this end, different forms of energy consisting of mechanical energy and work were considered and their values were divided by the related value of an ideal performance to develop normalized metrics. These metrics were used as inputs for various machine learning algorithms including support vector machines (SVM) and neural networks (NNs) for classification. The accuracy of the combination of the normalized energy-based metrics with these classifiers was evaluated through a leave-one-subject-out cross-validation. The proposed method was validated using 26 subjects at two experience levels (novices and experts) in three arthroscopic tasks. The results showed that there are statistically significant differences between novices and experts for almost all of the normalized energy-based metrics. The accuracy of classification using SVM and NN methods was between 70% and 95% for the various tasks. The results show that the normalized energy-based metrics and their combination with SVM and NN classifiers are capable of providing accurate classification of trainees. The assessment method proposed in this study can enhance surgical training by providing appropriate feedback to trainees about their level of expertise and can be used in the evaluation of proficiency.

A method of evolving novel feature extraction algorithms for detecting buried objects in FLIR imagery using genetic programming

NASA Astrophysics Data System (ADS)

Paino, A.; Keller, J.; Popescu, M.; Stone, K.

2014-06-01

In this paper we present an approach that uses Genetic Programming (GP) to evolve novel feature extraction algorithms for greyscale images. Our motivation is to create an automated method of building new feature extraction algorithms for images that are competitive with commonly used human-engineered features, such as Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG). The evolved feature extraction algorithms are functions defined over the image space, and each produces a real-valued feature vector of variable length. Each evolved feature extractor breaks up the given image into a set of cells centered on every pixel, performs evolved operations on each cell, and then combines the results of those operations for every cell using an evolved operator. Using this method, the algorithm is flexible enough to reproduce both LBP and HOG features. The dataset we use to train and test our approach consists of a large number of pre-segmented image "chips" taken from a Forward Looking Infrared Imagery (FLIR) camera mounted on the hood of a moving vehicle. The goal is to classify each image chip as either containing or not containing a buried object. To this end, we define the fitness of a candidate solution as the cross-fold validation accuracy of the features generated by said candidate solution when used in conjunction with a Support Vector Machine (SVM) classifier. In order to validate our approach, we compare the classification accuracy of an SVM trained using our evolved features with the accuracy of an SVM trained using mainstream feature extraction algorithms, including LBP and HOG.

Diagnosis of pulmonary hypertension from magnetic resonance imaging-based computational models and decision tree analysis.

PubMed

Lungu, Angela; Swift, Andrew J; Capener, David; Kiely, David; Hose, Rod; Wild, Jim M

2016-06-01

Accurately identifying patients with pulmonary hypertension (PH) using noninvasive methods is challenging, and right heart catheterization (RHC) is the gold standard. Magnetic resonance imaging (MRI) has been proposed as an alternative to echocardiography and RHC in the assessment of cardiac function and pulmonary hemodynamics in patients with suspected PH. The aim of this study was to assess whether machine learning using computational modeling techniques and image-based metrics of PH can improve the diagnostic accuracy of MRI in PH. Seventy-two patients with suspected PH attending a referral center underwent RHC and MRI within 48 hours. Fifty-seven patients were diagnosed with PH, and 15 had no PH. A number of functional and structural cardiac and cardiovascular markers derived from 2 mathematical models and also solely from MRI of the main pulmonary artery and heart were integrated into a classification algorithm to investigate the diagnostic utility of the combination of the individual markers. A physiological marker based on the quantification of wave reflection in the pulmonary artery was shown to perform best individually, but optimal diagnostic performance was found by the combination of several image-based markers. Classifier results, validated using leave-one-out cross validation, demonstrated that combining computation-derived metrics reflecting hemodynamic changes in the pulmonary vasculature with measurement of right ventricular morphology and function, in a decision support algorithm, provides a method to noninvasively diagnose PH with high accuracy (92%). The high diagnostic accuracy of these MRI-based model parameters may reduce the need for RHC in patients with suspected PH.

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.

Low-back electromyography (EMG) data-driven load classification for dynamic lifting tasks.

PubMed

Totah, Deema; Ojeda, Lauro; Johnson, Daniel D; Gates, Deanna; Mower Provost, Emily; Barton, Kira

2018-01-01

Numerous devices have been designed to support the back during lifting tasks. To improve the utility of such devices, this research explores the use of preparatory muscle activity to classify muscle loading and initiate appropriate device activation. The goal of this study was to determine the earliest time window that enabled accurate load classification during a dynamic lifting task. Nine subjects performed thirty symmetrical lifts, split evenly across three weight conditions (no-weight, 10-lbs and 24-lbs), while low-back muscle activity data was collected. Seven descriptive statistics features were extracted from 100 ms windows of data. A multinomial logistic regression (MLR) classifier was trained and tested, employing leave-one subject out cross-validation, to classify lifted load values. Dimensionality reduction was achieved through feature cross-correlation analysis and greedy feedforward selection. The time of full load support by the subject was defined as load-onset. Regions of highest average classification accuracy started at 200 ms before until 200 ms after load-onset with average accuracies ranging from 80% (±10%) to 81% (±7%). The average recall for each class ranged from 69-92%. These inter-subject classification results indicate that preparatory muscle activity can be leveraged to identify the intent to lift a weight up to 100 ms prior to load-onset. The high accuracies shown indicate the potential to utilize intent classification for assistive device applications. Active assistive devices, e.g. exoskeletons, could prevent back injury by off-loading low-back muscles. Early intent classification allows more time for actuators to respond and integrate seamlessly with the user.

Evaluating the statistical performance of less applied algorithms in classification of worldview-3 imagery data in an urbanized landscape

NASA Astrophysics Data System (ADS)

Ranaie, Mehrdad; Soffianian, Alireza; Pourmanafi, Saeid; Mirghaffari, Noorollah; Tarkesh, Mostafa

2018-03-01

In recent decade, analyzing the remotely sensed imagery is considered as one of the most common and widely used procedures in the environmental studies. In this case, supervised image classification techniques play a central role. Hence, taking a high resolution Worldview-3 over a mixed urbanized landscape in Iran, three less applied image classification methods including Bagged CART, Stochastic gradient boosting model and Neural network with feature extraction were tested and compared with two prevalent methods: random forest and support vector machine with linear kernel. To do so, each method was run ten time and three validation techniques was used to estimate the accuracy statistics consist of cross validation, independent validation and validation with total of train data. Moreover, using ANOVA and Tukey test, statistical difference significance between the classification methods was significantly surveyed. In general, the results showed that random forest with marginal difference compared to Bagged CART and stochastic gradient boosting model is the best performing method whilst based on independent validation there was no significant difference between the performances of classification methods. It should be finally noted that neural network with feature extraction and linear support vector machine had better processing speed than other.

Emotional textile image classification based on cross-domain convolutional sparse autoencoders with feature selection

NASA Astrophysics Data System (ADS)

Li, Zuhe; Fan, Yangyu; Liu, Weihua; Yu, Zeqi; Wang, Fengqin

2017-01-01

We aim to apply sparse autoencoder-based unsupervised feature learning to emotional semantic analysis for textile images. To tackle the problem of limited training data, we present a cross-domain feature learning scheme for emotional textile image classification using convolutional autoencoders. We further propose a correlation-analysis-based feature selection method for the weights learned by sparse autoencoders to reduce the number of features extracted from large size images. First, we randomly collect image patches on an unlabeled image dataset in the source domain and learn local features with a sparse autoencoder. We then conduct feature selection according to the correlation between different weight vectors corresponding to the autoencoder's hidden units. We finally adopt a convolutional neural network including a pooling layer to obtain global feature activations of textile images in the target domain and send these global feature vectors into logistic regression models for emotional image classification. The cross-domain unsupervised feature learning method achieves 65% to 78% average accuracy in the cross-validation experiments corresponding to eight emotional categories and performs better than conventional methods. Feature selection can reduce the computational cost of global feature extraction by about 50% while improving classification performance.

Remote Sensing of Vegetation Species Diversity: The Utility of Integrated Airborne Hyperspectral and Lidar Data

NASA Astrophysics Data System (ADS)

Krause, Keith Stuart

The change, reduction, or extinction of species is a major issue currently facing the Earth. Efforts are underway to measure, monitor, and protect habitats that contain high species diversity. Remote sensing technology shows extreme value for monitoring species diversity by mapping ecosystems and using those land cover maps or other derived data as proxies to species number and distribution. The National Ecological Observatory Network (NEON) Airborne Observation Platform (AOP) consists of remote sensing instruments such as an imaging spectrometer, a full-waveform lidar, and a high-resolution color camera. AOP collected data over the Ordway-Swisher Biological Station (OSBS) in May 2014. A majority of the OSBS site is covered by the Sandhill ecosystem, which contains a very high diversity of vegetation species and is a native habitat for several threatened fauna species. The research presented here investigates ways to analyze the AOP data to map ecosystems at the OSBS site. The research attempts to leverage the high spatial resolution data and study the variability of the data within a ground plot scale along with integrating data from the different sensors. Mathematical features are derived from the data and brought into a decision tree classification algorithm (rpart), in order to create an ecosystem map for the site. The hyperspectral and lidar features serve as proxies for chemical, functional, and structural differences in the vegetation types for each of the ecosystems. K-folds cross validation shows a training accuracy of 91%, a validation accuracy of 78%, and a 66% accuracy using independent ground validation. The results presented here represent an important contribution to utilizing integrated hyperspectral and lidar remote sensing data for ecosystem mapping, by relating the spatial variability of the data within a ground plot scale to a collection of vegetation types that make up a given ecosystem.

Integration of Attributes from Non-Linear Characterization of Cardiovascular Time-Series for Prediction of Defibrillation Outcomes

PubMed Central

Shandilya, Sharad; Kurz, Michael C.; Ward, Kevin R.; Najarian, Kayvan

2016-01-01

Objective The timing of defibrillation is mostly at arbitrary intervals during cardio-pulmonary resuscitation (CPR), rather than during intervals when the out-of-hospital cardiac arrest (OOH-CA) patient is physiologically primed for successful countershock. Interruptions to CPR may negatively impact defibrillation success. Multiple defibrillations can be associated with decreased post-resuscitation myocardial function. We hypothesize that a more complete picture of the cardiovascular system can be gained through non-linear dynamics and integration of multiple physiologic measures from biomedical signals. Materials and Methods Retrospective analysis of 153 anonymized OOH-CA patients who received at least one defibrillation for ventricular fibrillation (VF) was undertaken. A machine learning model, termed Multiple Domain Integrative (MDI) model, was developed to predict defibrillation success. We explore the rationale for non-linear dynamics and statistically validate heuristics involved in feature extraction for model development. Performance of MDI is then compared to the amplitude spectrum area (AMSA) technique. Results 358 defibrillations were evaluated (218 unsuccessful and 140 successful). Non-linear properties (Lyapunov exponent > 0) of the ECG signals indicate a chaotic nature and validate the use of novel non-linear dynamic methods for feature extraction. Classification using MDI yielded ROC-AUC of 83.2% and accuracy of 78.8%, for the model built with ECG data only. Utilizing 10-fold cross-validation, at 80% specificity level, MDI (74% sensitivity) outperformed AMSA (53.6% sensitivity). At 90% specificity level, MDI had 68.4% sensitivity while AMSA had 43.3% sensitivity. Integrating available end-tidal carbon dioxide features into MDI, for the available 48 defibrillations, boosted ROC-AUC to 93.8% and accuracy to 83.3% at 80% sensitivity. Conclusion At clinically relevant sensitivity thresholds, the MDI provides improved performance as compared to AMSA, yielding fewer unsuccessful defibrillations. Addition of partial end-tidal carbon dioxide (PetCO2) signal improves accuracy and sensitivity of the MDI prediction model. PMID:26741805

Understanding and predicting binding between human leukocyte antigens (HLAs) and peptides by network analysis.

PubMed

Luo, Heng; Ye, Hao; Ng, Hui; Shi, Leming; Tong, Weida; Mattes, William; Mendrick, Donna; Hong, Huixiao

2015-01-01

As the major histocompatibility complex (MHC), human leukocyte antigens (HLAs) are one of the most polymorphic genes in humans. Patients carrying certain HLA alleles may develop adverse drug reactions (ADRs) after taking specific drugs. Peptides play an important role in HLA related ADRs as they are the necessary co-binders of HLAs with drugs. Many experimental data have been generated for understanding HLA-peptide binding. However, efficiently utilizing the data for understanding and accurately predicting HLA-peptide binding is challenging. Therefore, we developed a network analysis based method to understand and predict HLA-peptide binding. Qualitative Class I HLA-peptide binding data were harvested and prepared from four major databases. An HLA-peptide binding network was constructed from this dataset and modules were identified by the fast greedy modularity optimization algorithm. To examine the significance of signals in the yielded models, the modularity was compared with the modularity values generated from 1,000 random networks. The peptides and HLAs in the modules were characterized by similarity analysis. The neighbor-edges based and unbiased leverage algorithm (Nebula) was developed for predicting HLA-peptide binding. Leave-one-out (LOO) validations and two-fold cross-validations were conducted to evaluate the performance of Nebula using the constructed HLA-peptide binding network. Nine modules were identified from analyzing the HLA-peptide binding network with a highest modularity compared to all the random networks. Peptide length and functional side chains of amino acids at certain positions of the peptides were different among the modules. HLA sequences were module dependent to some extent. Nebula archived an overall prediction accuracy of 0.816 in the LOO validations and average accuracy of 0.795 in the two-fold cross-validations and outperformed the method reported in the literature. Network analysis is a useful approach for analyzing large and sparse datasets such as the HLA-peptide binding dataset. The modules identified from the network analysis clustered peptides and HLAs with similar sequences and properties of amino acids. Nebula performed well in the predictions of HLA-peptide binding. We demonstrated that network analysis coupled with Nebula is an efficient approach to understand and predict HLA-peptide binding interactions and thus, could further our understanding of ADRs.

Understanding and predicting binding between human leukocyte antigens (HLAs) and peptides by network analysis

PubMed Central

2015-01-01

Background As the major histocompatibility complex (MHC), human leukocyte antigens (HLAs) are one of the most polymorphic genes in humans. Patients carrying certain HLA alleles may develop adverse drug reactions (ADRs) after taking specific drugs. Peptides play an important role in HLA related ADRs as they are the necessary co-binders of HLAs with drugs. Many experimental data have been generated for understanding HLA-peptide binding. However, efficiently utilizing the data for understanding and accurately predicting HLA-peptide binding is challenging. Therefore, we developed a network analysis based method to understand and predict HLA-peptide binding. Methods Qualitative Class I HLA-peptide binding data were harvested and prepared from four major databases. An HLA-peptide binding network was constructed from this dataset and modules were identified by the fast greedy modularity optimization algorithm. To examine the significance of signals in the yielded models, the modularity was compared with the modularity values generated from 1,000 random networks. The peptides and HLAs in the modules were characterized by similarity analysis. The neighbor-edges based and unbiased leverage algorithm (Nebula) was developed for predicting HLA-peptide binding. Leave-one-out (LOO) validations and two-fold cross-validations were conducted to evaluate the performance of Nebula using the constructed HLA-peptide binding network. Results Nine modules were identified from analyzing the HLA-peptide binding network with a highest modularity compared to all the random networks. Peptide length and functional side chains of amino acids at certain positions of the peptides were different among the modules. HLA sequences were module dependent to some extent. Nebula archived an overall prediction accuracy of 0.816 in the LOO validations and average accuracy of 0.795 in the two-fold cross-validations and outperformed the method reported in the literature. Conclusions Network analysis is a useful approach for analyzing large and sparse datasets such as the HLA-peptide binding dataset. The modules identified from the network analysis clustered peptides and HLAs with similar sequences and properties of amino acids. Nebula performed well in the predictions of HLA-peptide binding. We demonstrated that network analysis coupled with Nebula is an efficient approach to understand and predict HLA-peptide binding interactions and thus, could further our understanding of ADRs. PMID:26424483

Validity of two simple measures for estimating life-course socio-economic position in cross-sectional postal survey data in an older population: results from the North Staffordshire Osteoarthritis Project (NorStOP)

PubMed Central

2012-01-01

Background Since few cohorts encompass the whole life-course, many studies that measure socio-economic position (SEP) across the life-course rely on participant recall of SEP measures from cross-sectional postal or interview surveys. It is also particularly important that SEP measures should be appropriate for the age of the population studied, as the level of missing data has been shown to increase in older people. The aim of this study was to investigate the accuracy of recall of two SEP measures in older adults, age left school and longest job, by examining their validity in a general population postal survey in North Staffordshire, UK. Methods Sets of questions on education and longest job were included in a questionnaire at different stages of the study. All patients aged 50+ registered with three general practices were sent a baseline Health Questionnaire. 6 years later, 3410 responders were mailed a follow-up Health Questionnaire; a sub-sample of these participants took part in independent qualitative interviews. Validity was assessed by: percentage completion; internal percentage agreement within each set of questions; percentage agreement of qualitative and quantitative data for age left school and longest job; comparing recall of age left school with historical change in legal school leaving age; comparing frequency of pottery job titles with those in 1981 Census data for Stoke-on-Trent. Results The adjusted response to different stages of the study was 71–85%. Completion of questions was 83–98%. Internal agreement was 84–97% (education) and 95–100% (longest job). Comparison of survey and interview data showed 86% agreement (± 1 year) for age left school and 91% agreement for longest job. The change in age left school data concurred with the historical shift in legal school leaving age. 11% of job titles were pottery in NorStOP data and 15% in Stoke-on-Trent Census data. Conclusions The results from this study provide evidence for the accuracy of recall of two simple measures of SEP (age left school and longest job) in a postal survey of older adults. Consistency with evidence from external datasets indicated the potential validity of these measures for studying life-course SEP in population surveys. PMID:22738317

Evaluating the efficiency of spectral resolution of univariate methods manipulating ratio spectra and comparing to multivariate methods: An application to ternary mixture in common cold preparation

NASA Astrophysics Data System (ADS)

Moustafa, Azza Aziz; Salem, Hesham; Hegazy, Maha; Ali, Omnia

2015-02-01

Simple, accurate, and selective methods have been developed and validated for simultaneous determination of a ternary mixture of Chlorpheniramine maleate (CPM), Pseudoephedrine HCl (PSE) and Ibuprofen (IBF), in tablet dosage form. Four univariate methods manipulating ratio spectra were applied, method A is the double divisor-ratio difference spectrophotometric method (DD-RD). Method B is double divisor-derivative ratio spectrophotometric method (DD-RD). Method C is derivative ratio spectrum-zero crossing method (DRZC), while method D is mean centering of ratio spectra (MCR). Two multivariate methods were also developed and validated, methods E and F are Principal Component Regression (PCR) and Partial Least Squares (PLSs). The proposed methods have the advantage of simultaneous determination of the mentioned drugs without prior separation steps. They were successfully applied to laboratory-prepared mixtures and to commercial pharmaceutical preparation without any interference from additives. The proposed methods were validated according to the ICH guidelines. The obtained results were statistically compared with the official methods where no significant difference was observed regarding both accuracy and precision.

Cross-cultural adaptation and validation to Brazil of the Obesity-related Problems Scale

PubMed Central

Brasil, Andreia Mara Brolezzi; Brasil, Fábio; Maurício, Angélica Aparecida; Vilela, Regina Maria

2017-01-01

ABSTRACT Objective To validate a reliable version of the Obesity-related Problems Scale in Portuguese to use it in Brazil. Methods The Obesity-related Problems Scale was translated and transculturally adapted. Later it was simultaneously self-applied with a 12-item version of the World Health Organization Disability Assessment Schedule 2.0 (WHODAS 2.0), to 50 obese patients and 50 non-obese individuals, and applied again to half of them after 14 days. Results The Obesity-related Problems scale was able to differentiate obese from non-obese individuals with higher accuracy than WHODAS 2.0, correlating with this scale and with body mass index. The factor analysis determined a two-dimensional structure, which was confirmed with χ2/df=1.81, SRMR=0.05, and CFI=0.97. The general a coefficient was 0.90 and the inter-item intra-class correlation, in the reapplication, ranged from 0.75 to 0.87. Conclusion The scale proved to be valid and reliable for use in the Brazilian population, without the need to exclude items. PMID:29091155

Resampling procedures to identify important SNPs using a consensus approach.

PubMed

Pardy, Christopher; Motyer, Allan; Wilson, Susan

2011-11-29

Our goal is to identify common single-nucleotide polymorphisms (SNPs) (minor allele frequency > 1%) that add predictive accuracy above that gained by knowledge of easily measured clinical variables. We take an algorithmic approach to predict each phenotypic variable using a combination of phenotypic and genotypic predictors. We perform our procedure on the first simulated replicate and then validate against the others. Our procedure performs well when predicting Q1 but is less successful for the other outcomes. We use resampling procedures where possible to guard against false positives and to improve generalizability. The approach is based on finding a consensus regarding important SNPs by applying random forests and the least absolute shrinkage and selection operator (LASSO) on multiple subsamples. Random forests are used first to discard unimportant predictors, narrowing our focus to roughly 100 important SNPs. A cross-validation LASSO is then used to further select variables. We combine these procedures to guarantee that cross-validation can be used to choose a shrinkage parameter for the LASSO. If the clinical variables were unavailable, this prefiltering step would be essential. We perform the SNP-based analyses simultaneously rather than one at a time to estimate SNP effects in the presence of other causal variants. We analyzed the first simulated replicate of Genetic Analysis Workshop 17 without knowledge of the true model. Post-conference knowledge of the simulation parameters allowed us to investigate the limitations of our approach. We found that many of the false positives we identified were substantially correlated with genuine causal SNPs.

Validity of VO(2 max) in predicting blood volume: implications for the effect of fitness on aging

NASA Technical Reports Server (NTRS)

Convertino, V. A.; Ludwig, D. A.

2000-01-01

A multiple regression model was constructed to investigate the premise that blood volume (BV) could be predicted using several anthropometric variables, age, and maximal oxygen uptake (VO(2 max)). To test this hypothesis, age, calculated body surface area (height/weight composite), percent body fat (hydrostatic weight), and VO(2 max) were regressed on to BV using data obtained from 66 normal healthy men. Results from the evaluation of the full model indicated that the most parsimonious result was obtained when age and VO(2 max) were regressed on BV expressed per kilogram body weight. The full model accounted for 52% of the total variance in BV per kilogram body weight. Both age and VO(2 max) were related to BV in the positive direction. Percent body fat contributed <1% to the explained variance in BV when expressed in absolute BV (ml) or as BV per kilogram body weight. When the model was cross validated on 41 new subjects and BV per kilogram body weight was reexpressed as raw BV, the results indicated that the statistical model would be stable under cross validation (e.g., predictive applications) with an accuracy of +/- 1,200 ml at 95% confidence. Our results support the hypothesis that BV is an increasing function of aerobic fitness and to a lesser extent the age of the subject. The results may have implication as to a mechanism by which aerobic fitness and activity may be protective against reduced BV associated with aging.

Novel naïve Bayes classification models for predicting the chemical Ames mutagenicity.

PubMed

Zhang, Hui; Kang, Yan-Li; Zhu, Yuan-Yuan; Zhao, Kai-Xia; Liang, Jun-Yu; Ding, Lan; Zhang, Teng-Guo; Zhang, Ji

2017-06-01

Prediction of drug candidates for mutagenicity is a regulatory requirement since mutagenic compounds could pose a toxic risk to humans. The aim of this investigation was to develop a novel prediction model of mutagenicity by using a naïve Bayes classifier. The established model was validated by the internal 5-fold cross validation and external test sets. For comparison, the recursive partitioning classifier prediction model was also established and other various reported prediction models of mutagenicity were collected. Among these methods, the prediction performance of naïve Bayes classifier established here displayed very well and stable, which yielded average overall prediction accuracies for the internal 5-fold cross validation of the training set and external test set I set were 89.1±0.4% and 77.3±1.5%, respectively. The concordance of the external test set II with 446 marketed drugs was 90.9±0.3%. In addition, four simple molecular descriptors (e.g., Apol, No. of H donors, Num-Rings and Wiener) related to mutagenicity and five representative substructures of mutagens (e.g., aromatic nitro, hydroxyl amine, nitroso, aromatic amine and N-methyl-N-methylenemethanaminum) produced by ECFP_14 fingerprints were identified. We hope the established naïve Bayes prediction model can be applied to risk assessment processes; and the obtained important information of mutagenic chemicals can guide the design of chemical libraries for hit and lead optimization. Copyright © 2017 Elsevier B.V. All rights reserved.

Methods to validate the accuracy of an indirect calorimeter in the in-vitro setting.

PubMed

Oshima, Taku; Ragusa, Marco; Graf, Séverine; Dupertuis, Yves Marc; Heidegger, Claudia-Paula; Pichard, Claude

2017-12-01

The international ICALIC initiative aims at developing a new indirect calorimeter according to the needs of the clinicians and researchers in the field of clinical nutrition and metabolism. The project initially focuses on validating the calorimeter for use in mechanically ventilated acutely ill adult patient. However, standard methods to validate the accuracy of calorimeters have not yet been established. This paper describes the procedures for the in-vitro tests to validate the accuracy of the new indirect calorimeter, and defines the ranges for the parameters to be evaluated in each test to optimize the validation for clinical and research calorimetry measurements. Two in-vitro tests have been defined to validate the accuracy of the gas analyzers and the overall function of the new calorimeter. 1) Gas composition analysis allows validating the accuracy of O 2 and CO 2 analyzers. Reference gas of known O 2 (or CO 2 ) concentration is diluted by pure nitrogen gas to achieve predefined O 2 (or CO 2 ) concentration, to be measured by the indirect calorimeter. O 2 and CO 2 concentrations to be tested were determined according to their expected ranges of concentrations during calorimetry measurements. 2) Gas exchange simulator analysis validates O 2 consumption (VO 2 ) and CO 2 production (VCO 2 ) measurements. CO 2 gas injection into artificial breath gas provided by the mechanical ventilator simulates VCO 2 . Resulting dilution of O 2 concentration in the expiratory air is analyzed by the calorimeter as VO 2 . CO 2 gas of identical concentration to the fraction of inspired O 2 (FiO 2 ) is used to simulate identical VO 2 and VCO 2 . Indirect calorimetry results from publications were analyzed to determine the VO 2 and VCO 2 values to be tested for the validation. O 2 concentration in respiratory air is highest at inspiration, and can decrease to 15% during expiration. CO 2 concentration can be as high as 5% in expired air. To validate analyzers for measurements of FiO 2 up to 70%, ranges of O 2 and CO 2 concentrations to be tested were defined as 15-70% and 0.5-5.0%, respectively. The mean VO 2 in 426 adult mechanically ventilated patients was 270 ml/min, with 2 standard deviation (SD) ranges of 150-391 ml/min. Thus, VO 2 and VCO 2 to be simulated for the validation were defined as 150, 250, and 400 ml/min. The procedures for the in-vitro tests of the new indirect calorimeter and the ranges for the parameters to be evaluated in each test have been defined to optimize the validation of accuracy for clinical and research indirect calorimetry measurements. The combined methods will be used to validate the accuracy of the new indirect calorimeter developed by the ICALIC initiative, and should become the standard method to validate the accuracy of any future indirect calorimeters. Copyright © 2017 European Society for Clinical Nutrition and Metabolism. Published by Elsevier Ltd. All rights reserved.

Empirical gradient threshold technique for automated segmentation across image modalities and cell lines.

PubMed

Chalfoun, J; Majurski, M; Peskin, A; Breen, C; Bajcsy, P; Brady, M

2015-10-01

New microscopy technologies are enabling image acquisition of terabyte-sized data sets consisting of hundreds of thousands of images. In order to retrieve and analyze the biological information in these large data sets, segmentation is needed to detect the regions containing cells or cell colonies. Our work with hundreds of large images (each 21,000×21,000 pixels) requires a segmentation method that: (1) yields high segmentation accuracy, (2) is applicable to multiple cell lines with various densities of cells and cell colonies, and several imaging modalities, (3) can process large data sets in a timely manner, (4) has a low memory footprint and (5) has a small number of user-set parameters that do not require adjustment during the segmentation of large image sets. None of the currently available segmentation methods meet all these requirements. Segmentation based on image gradient thresholding is fast and has a low memory footprint. However, existing techniques that automate the selection of the gradient image threshold do not work across image modalities, multiple cell lines, and a wide range of foreground/background densities (requirement 2) and all failed the requirement for robust parameters that do not require re-adjustment with time (requirement 5). We present a novel and empirically derived image gradient threshold selection method for separating foreground and background pixels in an image that meets all the requirements listed above. We quantify the difference between our approach and existing ones in terms of accuracy, execution speed, memory usage and number of adjustable parameters on a reference data set. This reference data set consists of 501 validation images with manually determined segmentations and image sizes ranging from 0.36 Megapixels to 850 Megapixels. It includes four different cell lines and two image modalities: phase contrast and fluorescent. Our new technique, called Empirical Gradient Threshold (EGT), is derived from this reference data set with a 10-fold cross-validation method. EGT segments cells or colonies with resulting Dice accuracy index measurements above 0.92 for all cross-validation data sets. EGT results has also been visually verified on a much larger data set that includes bright field and Differential Interference Contrast (DIC) images, 16 cell lines and 61 time-sequence data sets, for a total of 17,479 images. This method is implemented as an open-source plugin to ImageJ as well as a standalone executable that can be downloaded from the following link: https://isg.nist.gov/. © 2015 The Authors Journal of Microscopy © 2015 Royal Microscopical Society.

Predicting risk of substantial weight gain in German adults-a multi-center cohort approach.

PubMed

Bachlechner, Ursula; Boeing, Heiner; Haftenberger, Marjolein; Schienkiewitz, Anja; Scheidt-Nave, Christa; Vogt, Susanne; Thorand, Barbara; Peters, Annette; Schipf, Sabine; Ittermann, Till; Völzke, Henry; Nöthlings, Ute; Neamat-Allah, Jasmine; Greiser, Karin-Halina; Kaaks, Rudolf; Steffen, Annika

2017-08-01

A risk-targeted prevention strategy may efficiently utilize limited resources available for prevention of overweight and obesity. Likewise, more efficient intervention trials could be designed if selection of subjects was based on risk. The aim of the study was to develop a risk score predicting substantial weight gain among German adults. We developed the risk score using information on 15 socio-demographic, dietary and lifestyle factors from 32 204 participants of five population-based German cohort studies. Substantial weight gain was defined as gaining ≥10% of weight between baseline and follow-up (>6 years apart). The cases were censored according to the theoretical point in time when the threshold of 10% baseline-based weight gain was crossed assuming linearity of weight gain. Beta coefficients derived from proportional hazards regression were used as weights to compute the risk score as a linear combination of the predictors. Cross-validation was used to evaluate the score's discriminatory accuracy. The cross-validated c index (95% CI) was 0.71 (0.67-0.75). A cutoff value of ≥475 score points yielded a sensitivity of 71% and a specificity of 63%. The corresponding positive and negative predictive values were 10.4% and 97.6%, respectively. The proposed risk score may support healthcare providers in decision making and referral and facilitate an efficient selection of subjects into intervention trials. © The Author 2016. Published by Oxford University Press on behalf of the European Public Health Association.

Predicting risk of substantial weight gain in German adults—a multi-center cohort approach

PubMed Central

Bachlechner, Ursula; Boeing, Heiner; Haftenberger, Marjolein; Schienkiewitz, Anja; Scheidt-Nave, Christa; Vogt, Susanne; Thorand, Barbara; Peters, Annette; Schipf, Sabine; Ittermann, Till; Völzke, Henry; Nöthlings, Ute; Neamat-Allah, Jasmine; Greiser, Karin-Halina; Kaaks, Rudolf

2017-01-01

Abstract Background A risk-targeted prevention strategy may efficiently utilize limited resources available for prevention of overweight and obesity. Likewise, more efficient intervention trials could be designed if selection of subjects was based on risk. The aim of the study was to develop a risk score predicting substantial weight gain among German adults. Methods We developed the risk score using information on 15 socio-demographic, dietary and lifestyle factors from 32 204 participants of five population-based German cohort studies. Substantial weight gain was defined as gaining ≥10% of weight between baseline and follow-up (>6 years apart). The cases were censored according to the theoretical point in time when the threshold of 10% baseline-based weight gain was crossed assuming linearity of weight gain. Beta coefficients derived from proportional hazards regression were used as weights to compute the risk score as a linear combination of the predictors. Cross-validation was used to evaluate the score’s discriminatory accuracy. Results The cross-validated c index (95% CI) was 0.71 (0.67–0.75). A cutoff value of ≥475 score points yielded a sensitivity of 71% and a specificity of 63%. The corresponding positive and negative predictive values were 10.4% and 97.6%, respectively. Conclusions The proposed risk score may support healthcare providers in decision making and referral and facilitate an efficient selection of subjects into intervention trials. PMID:28013243

Developing a weighted measure of speech sound accuracy.

PubMed

Preston, Jonathan L; Ramsdell, Heather L; Oller, D Kimbrough; Edwards, Mary Louise; Tobin, Stephen J

2011-02-01

To develop a system for numerically quantifying a speaker's phonetic accuracy through transcription-based measures. With a focus on normal and disordered speech in children, the authors describe a system for differentially weighting speech sound errors on the basis of various levels of phonetic accuracy using a Weighted Speech Sound Accuracy (WSSA) score. The authors then evaluate the reliability and validity of this measure. Phonetic transcriptions were analyzed from several samples of child speech, including preschoolers and young adolescents with and without speech sound disorders and typically developing toddlers. The new measure of phonetic accuracy was validated against existing measures, was used to discriminate typical and disordered speech production, and was evaluated to examine sensitivity to changes in phonetic accuracy over time. Reliability between transcribers and consistency of scores among different word sets and testing points are compared. Initial psychometric data indicate that WSSA scores correlate with other measures of phonetic accuracy as well as listeners' judgments of the severity of a child's speech disorder. The measure separates children with and without speech sound disorders and captures growth in phonetic accuracy in toddlers' speech over time. The measure correlates highly across transcribers, word lists, and testing points. Results provide preliminary support for the WSSA as a valid and reliable measure of phonetic accuracy in children's speech.

Random forests for classification in ecology

USGS Publications Warehouse

Cutler, D.R.; Edwards, T.C.; Beard, K.H.; Cutler, A.; Hess, K.T.; Gibson, J.; Lawler, J.J.

2007-01-01

Classification procedures are some of the most widely used statistical methods in ecology. Random forests (RF) is a new and powerful statistical classifier that is well established in other disciplines but is relatively unknown in ecology. Advantages of RF compared to other statistical classifiers include (1) very high classification accuracy; (2) a novel method of determining variable importance; (3) ability to model complex interactions among predictor variables; (4) flexibility to perform several types of statistical data analysis, including regression, classification, survival analysis, and unsupervised learning; and (5) an algorithm for imputing missing values. We compared the accuracies of RF and four other commonly used statistical classifiers using data on invasive plant species presence in Lava Beds National Monument, California, USA, rare lichen species presence in the Pacific Northwest, USA, and nest sites for cavity nesting birds in the Uinta Mountains, Utah, USA. We observed high classification accuracy in all applications as measured by cross-validation and, in the case of the lichen data, by independent test data, when comparing RF to other common classification methods. We also observed that the variables that RF identified as most important for classifying invasive plant species coincided with expectations based on the literature. ?? 2007 by the Ecological Society of America.

Face recognition: database acquisition, hybrid algorithms, and human studies

NASA Astrophysics Data System (ADS)

Gutta, Srinivas; Huang, Jeffrey R.; Singh, Dig; Wechsler, Harry

1997-02-01

One of the most important technologies absent in traditional and emerging frontiers of computing is the management of visual information. Faces are accessible `windows' into the mechanisms that govern our emotional and social lives. The corresponding face recognition tasks considered herein include: (1) Surveillance, (2) CBIR, and (3) CBIR subject to correct ID (`match') displaying specific facial landmarks such as wearing glasses. We developed robust matching (`classification') and retrieval schemes based on hybrid classifiers and showed their feasibility using the FERET database. The hybrid classifier architecture consist of an ensemble of connectionist networks--radial basis functions-- and decision trees. The specific characteristics of our hybrid architecture include (a) query by consensus as provided by ensembles of networks for coping with the inherent variability of the image formation and data acquisition process, and (b) flexible and adaptive thresholds as opposed to ad hoc and hard thresholds. Experimental results, proving the feasibility of our approach, yield (i) 96% accuracy, using cross validation (CV), for surveillance on a data base consisting of 904 images (ii) 97% accuracy for CBIR tasks, on a database of 1084 images, and (iii) 93% accuracy, using CV, for CBIR subject to correct ID match tasks on a data base of 200 images.

Burn-injured tissue detection for debridement surgery through the combination of non-invasive optical imaging techniques.

PubMed

Heredia-Juesas, Juan; Thatcher, Jeffrey E; Lu, Yang; Squiers, John J; King, Darlene; Fan, Wensheng; DiMaio, J Michael; Martinez-Lorenzo, Jose A

2018-04-01

The process of burn debridement is a challenging technique requiring significant skills to identify the regions that need excision and their appropriate excision depths. In order to assist surgeons, a machine learning tool is being developed to provide a quantitative assessment of burn-injured tissue. This paper presents three non-invasive optical imaging techniques capable of distinguishing four kinds of tissue-healthy skin, viable wound bed, shallow burn, and deep burn-during serial burn debridement in a porcine model. All combinations of these three techniques have been studied through a k-fold cross-validation method. In terms of global performance, the combination of all three techniques significantly improves the classification accuracy with respect to just one technique, from 0.42 up to more than 0.76. Furthermore, a non-linear spatial filtering based on the mode of a small neighborhood has been applied as a post-processing technique, in order to improve the performance of the classification. Using this technique, the global accuracy reaches a value close to 0.78 and, for some particular tissues and combination of techniques, the accuracy improves by 13%.

Validation of the Cross-Cultural Alcoholism Screening Test (CCAST).

PubMed

Gorenc, K D; Peredo, S; Pacurucu, S; Llanos, R; Vincente, B; López, R; Abreu, L F; Paez, E

1999-01-01

When screening instruments that are used in the assessment and diagnosis of alcoholism of individuals from different ethnicities, some cultural variables based on norms and societal acceptance of drinking behavior can play an important role in determining the outcome. The accepted diagnostic criteria of current market testing are based on Western standards. In this study, the Munich Alcoholism Test (31 items) was the base instrument applied to subjects from several Hispanic-American countries (Bolivia, Chile, Ecuador, Mexico, and Peru). After the sample was submitted to several statistical procedures, these 31 items were reduced to a culture-free, 31-item test named the Cross-Cultural Alcohol Screening Test (CCAST). The results of this Hispanic-American sample (n = 2,107) empirically demonstrated that CCAST measures alcoholism with an adequate degree of accuracy when compared to other available cross-cultural tests. CCAST is useful in the diagnosis of alcoholism in Spanish-speaking immigrants living in countries where English is spoken. CCAST can be used in general hospitals, psychiatric wards, emergency services and police stations. The test can be useful for other professionals, such as psychological consultants, researchers, and those conducting expertise appraisal.

A Comparison Study of Classifier Algorithms for Cross-Person Physical Activity Recognition

PubMed Central

Saez, Yago; Baldominos, Alejandro; Isasi, Pedro

2016-01-01

Physical activity is widely known to be one of the key elements of a healthy life. The many benefits of physical activity described in the medical literature include weight loss and reductions in the risk factors for chronic diseases. With the recent advances in wearable devices, such as smartwatches or physical activity wristbands, motion tracking sensors are becoming pervasive, which has led to an impressive growth in the amount of physical activity data available and an increasing interest in recognizing which specific activity a user is performing. Moreover, big data and machine learning are now cross-fertilizing each other in an approach called “deep learning”, which consists of massive artificial neural networks able to detect complicated patterns from enormous amounts of input data to learn classification models. This work compares various state-of-the-art classification techniques for automatic cross-person activity recognition under different scenarios that vary widely in how much information is available for analysis. We have incorporated deep learning by using Google’s TensorFlow framework. The data used in this study were acquired from PAMAP2 (Physical Activity Monitoring in the Ageing Population), a publicly available dataset containing physical activity data. To perform cross-person prediction, we used the leave-one-subject-out (LOSO) cross-validation technique. When working with large training sets, the best classifiers obtain very high average accuracies (e.g., 96% using extra randomized trees). However, when the data volume is drastically reduced (where available data are only 0.001% of the continuous data), deep neural networks performed the best, achieving 60% in overall prediction accuracy. We found that even when working with only approximately 22.67% of the full dataset, we can statistically obtain the same results as when working with the full dataset. This finding enables the design of more energy-efficient devices and facilitates cold starts and big data processing of physical activity records. PMID:28042838

A Comparison Study of Classifier Algorithms for Cross-Person Physical Activity Recognition.

PubMed

Saez, Yago; Baldominos, Alejandro; Isasi, Pedro

2016-12-30

Physical activity is widely known to be one of the key elements of a healthy life. The many benefits of physical activity described in the medical literature include weight loss and reductions in the risk factors for chronic diseases. With the recent advances in wearable devices, such as smartwatches or physical activity wristbands, motion tracking sensors are becoming pervasive, which has led to an impressive growth in the amount of physical activity data available and an increasing interest in recognizing which specific activity a user is performing. Moreover, big data and machine learning are now cross-fertilizing each other in an approach called "deep learning", which consists of massive artificial neural networks able to detect complicated patterns from enormous amounts of input data to learn classification models. This work compares various state-of-the-art classification techniques for automatic cross-person activity recognition under different scenarios that vary widely in how much information is available for analysis. We have incorporated deep learning by using Google's TensorFlow framework. The data used in this study were acquired from PAMAP2 (Physical Activity Monitoring in the Ageing Population), a publicly available dataset containing physical activity data. To perform cross-person prediction, we used the leave-one-subject-out (LOSO) cross-validation technique. When working with large training sets, the best classifiers obtain very high average accuracies (e.g., 96% using extra randomized trees). However, when the data volume is drastically reduced (where available data are only 0.001% of the continuous data), deep neural networks performed the best, achieving 60% in overall prediction accuracy. We found that even when working with only approximately 22.67% of the full dataset, we can statistically obtain the same results as when working with the full dataset. This finding enables the design of more energy-efficient devices and facilitates cold starts and big data processing of physical activity records.

Photon caliper to achieve submillimeter positioning accuracy

NASA Astrophysics Data System (ADS)

Gallagher, Kyle J.; Wong, Jennifer; Zhang, Junan

2017-09-01

The purpose of this study was to demonstrate the feasibility of using a commercial two-dimensional (2D) detector array with an inherent detector spacing of 5 mm to achieve submillimeter accuracy in localizing the radiation isocenter. This was accomplished by delivering the Vernier ‘dose’ caliper to a 2D detector array where the nominal scale was the 2D detector array and the non-nominal Vernier scale was the radiation dose strips produced by the high-definition (HD) multileaf collimators (MLCs) of the linear accelerator. Because the HD MLC sequence was similar to the picket fence test, we called this procedure the Vernier picket fence (VPF) test. We confirmed the accuracy of the VPF test by offsetting the HD MLC bank by known increments and comparing the known offset with the VPF test result. The VPF test was able to determine the known offset within 0.02 mm. We also cross-validated the accuracy of the VPF test in an evaluation of couch hysteresis. This was done by using both the VPF test and the ExacTrac optical tracking system to evaluate the couch position. We showed that the VPF test was in agreement with the ExacTrac optical tracking system within a root-mean-square value of 0.07 mm for both the lateral and longitudinal directions. In conclusion, we demonstrated the VPF test can determine the offset between a 2D detector array and the radiation isocenter with submillimeter accuracy. Until now, no method to locate the radiation isocenter using a 2D detector array has been able to achieve such accuracy.

Cross-Language Transfer of Word Reading Accuracy and Word Reading Fluency in Spanish-English and Chinese-English Bilinguals: Script-Universal and Script-Specific Processes

ERIC Educational Resources Information Center

Pasquarella, Adrian; Chen, Xi; Gottardo, Alexandra; Geva, Esther

2015-01-01

This study examined cross-language transfer of word reading accuracy and word reading fluency in Spanish-English and Chinese-English bilinguals. Participants included 51 Spanish-English and 64 Chinese-English bilinguals. Both groups of children completed parallel measures of phonological awareness, rapid automatized naming, word reading accuracy,…

Noninvasive Diagnosis of Nonalcoholic Fatty Liver Disease and Quantification of Liver Fat Using a New Quantitative Ultrasound Technique.

PubMed

Lin, Steven C; Heba, Elhamy; Wolfson, Tanya; Ang, Brandon; Gamst, Anthony; Han, Aiguo; Erdman, John W; O'Brien, William D; Andre, Michael P; Sirlin, Claude B; Loomba, Rohit

2015-07-01

Liver biopsy analysis is the standard method used to diagnose nonalcoholic fatty liver disease (NAFLD). Advanced magnetic resonance imaging is a noninvasive procedure that can accurately diagnose and quantify steatosis, but is expensive. Conventional ultrasound is more accessible but identifies steatosis with low levels of sensitivity, specificity, and quantitative accuracy, and results vary among technicians. A new quantitative ultrasound (QUS) technique can identify steatosis in animal models. We assessed the accuracy of QUS in the diagnosis and quantification of hepatic steatosis, comparing findings with those from magnetic resonance imaging proton density fat fraction (MRI-PDFF) analysis as a reference. We performed a prospective, cross-sectional analysis of a cohort of adults (N = 204) with NAFLD (MRI-PDFF, ≥5%) and without NAFLD (controls). Subjects underwent MRI-PDFF and QUS analyses of the liver on the same day at the University of California, San Diego, from February 2012 through March 2014. QUS parameters and backscatter coefficient (BSC) values were calculated. Patients were assigned randomly to training (n = 102; mean age, 51 ± 17 y; mean body mass index, 31 ± 7 kg/m(2)) and validation (n = 102; mean age, 49 ± 17 y; body mass index, 30 ± 6 kg/m(2)) groups; 69% of patients in each group had NAFLD. BSC (range, 0.00005-0.25 1/cm-sr) correlated with MRI-PDFF (Spearman ρ = 0.80; P < .0001). In the training group, the BSC analysis identified patients with NAFLD with an area under the curve value of 0.98 (95% confidence interval, 0.95-1.00; P < .0001). The optimal BSC cut-off value identified patients with NAFLD in the training and validation groups with 93% and 87% sensitivity, 97% and 91% specificity, 86% and 76% negative predictive values, and 99% and 95% positive predictive values, respectively. QUS measurements of BSC can accurately diagnose and quantify hepatic steatosis, based on a cross-sectional analysis that used MRI-PDFF as the reference. With further validation, QUS could be an inexpensive, widely available method to screen the general or at-risk population for NAFLD. Copyright © 2015 AGA Institute. Published by Elsevier Inc. All rights reserved.

Determining quality of caviar from Caspian Sea based on Raman spectroscopy and using artificial neural networks.

PubMed

Mohamadi Monavar, H; Afseth, N K; Lozano, J; Alimardani, R; Omid, M; Wold, J P

2013-07-15

The purpose of this study was to evaluate the feasibility of Raman spectroscopy for predicting purity of caviars. The 93 wild caviar samples of three different types, namely; Beluga, Asetra and Sevruga were analysed by Raman spectroscopy in the range 1995 cm(-1) to 545 cm(-1). Also, 60 samples from combinations of every two types were examined. The chemical origin of the samples was identified by reference measurements on pure samples. Linear chemometric methods like Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were used for data visualisation and classification which permitted clear distinction between different caviars. Non-linear methods like Artificial Neural Networks (ANN) were used to classify caviar samples. Two different networks were tested in the classification: Probabilistic Neural Network with Radial-Basis Function (PNN) and Multilayer Feed Forward Networks with Back Propagation (BP-NN). In both cases, scores of principal components (PCs) were chosen as input nodes for the input layer in PC-ANN models in order to reduce the redundancy of data and time of training. Leave One Out (LOO) cross validation was applied in order to check the performance of the networks. Results of PCA indicated that, features like type and purity can be used to discriminate different caviar samples. These findings were also supported by LDA with efficiency between 83.77% and 100%. These results were confirmed with the results obtained by developed PC-ANN models, able to classify pure caviar samples with 93.55% and 71.00% accuracy in BP network and PNN, respectively. In comparison, LDA, PNN and BP-NN models for predicting caviar types have 90.3%, 73.1% and 91.4% accuracy. Partial least squares regression (PLSR) models were built under cross validation and tested with different independent data sets, yielding determination coefficients (R(2)) of 0.86, 0.83, 0.92 and 0.91 with root mean square error (RMSE) of validation of 0.32, 0.11, 0.03 and 0.09 for fatty acids of 16.0, 20.5, 22.6 and fat, respectively. Crown Copyright © 2013. Published by Elsevier B.V. All rights reserved.

SMAP RADAR Calibration and Validation

NASA Astrophysics Data System (ADS)

West, R. D.; Jaruwatanadilok, S.; Chaubel, M. J.; Spencer, M.; Chan, S. F.; Chen, C. W.; Fore, A.

2015-12-01

The Soil Moisture Active Passive (SMAP) mission launched on Jan 31, 2015. The mission employs L-band radar and radiometer measurements to estimate soil moisture with 4% volumetric accuracy at a resolution of 10 km, and freeze-thaw state at a resolution of 1-3 km. Immediately following launch, there was a three month instrument checkout period, followed by six months of level 1 (L1) calibration and validation. In this presentation, we will discuss the calibration and validation activities and results for the L1 radar data. Early SMAP radar data were used to check commanded timing parameters, and to work out issues in the low- and high-resolution radar processors. From April 3-13 the radar collected receive only mode data to conduct a survey of RFI sources. Analysis of the RFI environment led to a preferred operating frequency. The RFI survey data were also used to validate noise subtraction and scaling operations in the radar processors. Normal radar operations resumed on April 13. All radar data were examined closely for image quality and calibration issues which led to improvements in the radar data products for the beta release at the end of July. Radar data were used to determine and correct for small biases in the reported spacecraft attitude. Geo-location was validated against coastline positions and the known positions of corner reflectors. Residual errors at the time of the beta release are about 350 m. Intra-swath biases in the high-resolution backscatter images are reduced to less than 0.3 dB for all polarizations. Radiometric cross-calibration with Aquarius was performed using areas of the Amazon rain forest. Cross-calibration was also examined using ocean data from the low-resolution processor and comparing with the Aquarius wind model function. Using all a-priori calibration constants provided good results with co-polarized measurements matching to better than 1 dB, and cross-polarized measurements matching to about 1 dB in the beta release. During the second half of the L1 cal/val period, the RFI removal algorithm will be tuned for optimal performance, and the Faraday rotation corrections used in radar processing will be further developed and validated. This work is supported by the SMAP project at the Jet Propulsion Laboratory, California Institute of Technology.

Alzheimer's Disease Diagnosis in Individual Subjects using Structural MR Images: Validation Studies

PubMed Central

Vemuri, Prashanthi; Gunter, Jeffrey L.; Senjem, Matthew L.; Whitwell, Jennifer L.; Kantarci, Kejal; Knopman, David S.; Boeve, Bradley F.; Petersen, Ronald C.; Jack, Clifford R.

2008-01-01

OBJECTIVE To develop and validate a tool for Alzheimer's disease (AD) diagnosis in individual subjects using support vector machine (SVM) based classification of structural MR (sMR) images. BACKGROUND Libraries of sMR scans of clinically well characterized subjects can be harnessed for the purpose of diagnosing new incoming subjects. METHODS 190 patients with probable AD were age- and gender-matched with 190 cognitively normal (CN) subjects. Three different classification models were implemented: Model I uses tissue densities obtained from sMR scans to give STructural Abnormality iNDex (STAND)-score; and Models II and III use tissue densities as well as covariates (demographics and Apolipoprotein E genotype) to give adjusted-STAND (aSTAND)-score. Data from 140 AD and 140 CN were used for training. The SVM parameter optimization and training was done by four-fold cross validation. The remaining independent sample of 50 AD and 50 CN were used to obtain a minimally biased estimate of the generalization error of the algorithm. RESULTS The CV accuracy of Model II and Model III aSTAND-scores was 88.5% and 89.3% respectively and the developed models generalized well on the independent test datasets. Anatomic patterns best differentiating the groups were consistent with the known distribution of neurofibrillary AD pathology. CONCLUSIONS This paper presents preliminary evidence that application of SVM-based classification of an individual sMR scan relative to a library of scans can provide useful information in individual subjects for diagnosis of AD. Including demographic and genetic information in the classification algorithm slightly improves diagnostic accuracy. PMID:18054253

Assessment of aortic valve calcium load by multidetector computed tomography. Anatomical validation, impact of scanner settings and incremental diagnostic value.

PubMed

Boulif, Jamila; Gerber, Bernhard; Slimani, Alisson; Lazam, Siham; de Meester, Christophe; Piérard, Sophie; Pasquet, Agnès; Pouleur, Anne-Catherine; Vancraeynest, David; El Khoury, Gébrine; de Kerchove, Laurent; Noirhomme, Philippe; Vanoverschelde, Jean-Louis

To validate aortic valve calcium (AVC) load measurements by multidetector row computed tomography (MDCT), to evaluate the impact of tube potential and slice thickness on AVC scores, to examine the accuracy of AVC load in distinguishing severe from nonsevere aortic stenosis (AS) and to investigate its effectiveness as an alternative diagnosis method when echocardiography remains inconclusive. We prospectively studied 266 consecutive patients with moderate to severe AS who underwent MDCT to measure AVC load and a comprehensive echocardiographic examination to assess AS severity. AVC load was validated against valve weight in 57 patients undergoing aortic valve replacement. The dependence of AVC scores on tube potential and slice thickness was also tested, as well as the relationship between AVC load and echocardiographic criteria of AS severity. MDCT Agatston score correlated well with valve weight (r = 0.82, p < 0.001) and hemodynamic indices of AS severity (all p < 0.001). Ex-vivo Agatston scores decreased significantly with increasing tube potential and slice thickness (repeated measures ANOVA p < 0.001). Multivariate analysis identified mean gradient, the indexed effective orifice area, male gender and left ventricular outflow tract cross-sectional area as independent correlates of the in-vivo AVC load. MDCT-derived AVC load correlated well with valve weight and hemodynamic indices of AS severity. It also depends on tube potential and slice thickness, thus suggesting that these parameters should be standardized to optimize reproducibility and accuracy. Copyright © 2017 Society of Cardiovascular Computed Tomography. Published by Elsevier Inc. All rights reserved.

TMS combined with EEG in genetic generalized epilepsy: A phase II diagnostic accuracy study.

PubMed

Kimiskidis, Vasilios K; Tsimpiris, Alkiviadis; Ryvlin, Philippe; Kalviainen, Reetta; Koutroumanidis, Michalis; Valentin, Antonio; Laskaris, Nikolaos; Kugiumtzis, Dimitris

2017-02-01

(A) To develop a TMS-EEG stimulation and data analysis protocol in genetic generalized epilepsy (GGE). (B) To investigate the diagnostic accuracy of TMS-EEG in GGE. Pilot experiments resulted in the development and optimization of a paired-pulse TMS-EEG protocol at rest, during hyperventilation (HV), and post-HV combined with multi-level data analysis. This protocol was applied in 11 controls (C) and 25 GGE patients (P), further dichotomized into responders to antiepileptic drugs (R, n=13) and non-responders (n-R, n=12).Features (n=57) extracted from TMS-EEG responses after multi-level analysis were given to a feature selection scheme and a Bayesian classifier, and the accuracy of assigning participants into the classes P-C and R-nR was computed. On the basis of the optimal feature subset, the cross-validated accuracy of TMS-EEG for the classification P-C was 0.86 at rest, 0.81 during HV and 0.92 at post-HV, whereas for R-nR the corresponding figures are 0.80, 0.78 and 0.65, respectively. Applying a fusion approach on all conditions resulted in an accuracy of 0.84 for the classification P-C and 0.76 for the classification R-nR. TMS-EEG can be used for diagnostic purposes and for assessing the response to antiepileptic drugs. TMS-EEG holds significant diagnostic potential in GGE. Copyright © 2016 International Federation of Clinical Neurophysiology. Published by Elsevier B.V. All rights reserved.

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.

A flow-simulation model of the tidal Potomac River

USGS Publications Warehouse

Schaffranek, Raymond W.

1987-01-01

A one-dimensional model capable of simulating flow in a network of interconnected channels has been applied to the tidal Potomac River including its major tributaries and embayments between Washington, D.C., and Indian Head, Md. The model can be used to compute water-surface elevations and flow discharges at any of 66 predetermined locations or at any alternative river cross sections definable within the network of channels. In addition, the model can be used to provide tidal-interchange flow volumes and to evaluate tidal excursions and the flushing properties of the riverine system. Comparisons of model-computed results with measured watersurface elevations and discharges demonstrate the validity and accuracy of the model. Tidal-cycle flow volumes computed by the calibrated model have been verified to be within an accuracy of ? 10 percent. Quantitative characteristics of the hydrodynamics of the tidal river are identified and discussed. The comprehensive flow data provided by the model can be used to better understand the geochemical, biological, and other processes affecting the river's water quality.

Boosting specificity of MEG artifact removal by weighted support vector machine.

PubMed

Duan, Fang; Phothisonothai, Montri; Kikuchi, Mitsuru; Yoshimura, Yuko; Minabe, Yoshio; Watanabe, Kastumi; Aihara, Kazuyuki

2013-01-01

An automatic artifact removal method of magnetoencephalogram (MEG) was presented in this paper. The method proposed is based on independent components analysis (ICA) and support vector machine (SVM). However, different from the previous studies, in this paper we consider two factors which would influence the performance. First, the imbalance factor of independent components (ICs) of MEG is handled by weighted SVM. Second, instead of simply setting a fixed weight to each class, a re-weighting scheme is used for the preservation of useful MEG ICs. Experimental results on manually marked MEG dataset showed that the method proposed could correctly distinguish the artifacts from the MEG ICs. Meanwhile, 99.72% ± 0.67 of MEG ICs were preserved. The classification accuracy was 97.91% ± 1.39. In addition, it was found that this method was not sensitive to individual differences. The cross validation (leave-one-subject-out) results showed an averaged accuracy of 97.41% ± 2.14.

Application of support vector machine for the separation of mineralised zones in the Takht-e-Gonbad porphyry deposit, SE Iran

NASA Astrophysics Data System (ADS)

Mahvash Mohammadi, Neda; Hezarkhani, Ardeshir

2018-07-01

Classification of mineralised zones is an important factor for the analysis of economic deposits. In this paper, the support vector machine (SVM), a supervised learning algorithm, based on subsurface data is proposed for classification of mineralised zones in the Takht-e-Gonbad porphyry Cu-deposit (SE Iran). The effects of the input features are evaluated via calculating the accuracy rates on the SVM performance. Ultimately, the SVM model, is developed based on input features namely lithology, alteration, mineralisation, the level and, radial basis function (RBF) as a kernel function. Moreover, the optimal amount of parameters λ and C, using n-fold cross-validation method, are calculated at level 0.001 and 0.01 respectively. The accuracy of this model is 0.931 for classification of mineralised zones in the Takht-e-Gonbad porphyry deposit. The results of the study confirm the efficiency of SVM method for classification the mineralised zones.