Propensity-score matching in economic analyses: comparison with regression models, instrumental variables, residual inclusion, differences-in-differences, and decomposition methods.

PubMed

Crown, William H

2014-02-01

This paper examines the use of propensity score matching in economic analyses of observational data. Several excellent papers have previously reviewed practical aspects of propensity score estimation and other aspects of the propensity score literature. The purpose of this paper is to compare the conceptual foundation of propensity score models with alternative estimators of treatment effects. References are provided to empirical comparisons among methods that have appeared in the literature. These comparisons are available for a subset of the methods considered in this paper. However, in some cases, no pairwise comparisons of particular methods are yet available, and there are no examples of comparisons across all of the methods surveyed here. Irrespective of the availability of empirical comparisons, the goal of this paper is to provide some intuition about the relative merits of alternative estimators in health economic evaluations where nonlinearity, sample size, availability of pre/post data, heterogeneity, and missing variables can have important implications for choice of methodology. Also considered is the potential combination of propensity score matching with alternative methods such as differences-in-differences and decomposition methods that have not yet appeared in the empirical literature.

ESTIMATING TREATMENT EFFECTS ON HEALTHCARE COSTS UNDER EXOGENEITY: IS THERE A ‘MAGIC BULLET’?

PubMed Central

Polsky, Daniel; Manning, Willard G.

2011-01-01

Methods for estimating average treatment effects, under the assumption of no unmeasured confounders, include regression models; propensity score adjustments using stratification, weighting, or matching; and doubly robust estimators (a combination of both). Researchers continue to debate about the best estimator for outcomes such as health care cost data, as they are usually characterized by an asymmetric distribution and heterogeneous treatment effects,. Challenges in finding the right specifications for regression models are well documented in the literature. Propensity score estimators are proposed as alternatives to overcoming these challenges. Using simulations, we find that in moderate size samples (n= 5000), balancing on propensity scores that are estimated from saturated specifications can balance the covariate means across treatment arms but fails to balance higher-order moments and covariances amongst covariates. Therefore, unlike regression model, even if a formal model for outcomes is not required, propensity score estimators can be inefficient at best and biased at worst for health care cost data. Our simulation study, designed to take a ‘proof by contradiction’ approach, proves that no one estimator can be considered the best under all data generating processes for outcomes such as costs. The inverse-propensity weighted estimator is most likely to be unbiased under alternate data generating processes but is prone to bias under misspecification of the propensity score model and is inefficient compared to an unbiased regression estimator. Our results show that there are no ‘magic bullets’ when it comes to estimating treatment effects in health care costs. Care should be taken before naively applying any one estimator to estimate average treatment effects in these data. We illustrate the performance of alternative methods in a cost dataset on breast cancer treatment. PMID:22199462

Targeted estimation of nuisance parameters to obtain valid statistical inference.

PubMed

van der Laan, Mark J

2014-01-01

In order to obtain concrete results, we focus on estimation of the treatment specific mean, controlling for all measured baseline covariates, based on observing independent and identically distributed copies of a random variable consisting of baseline covariates, a subsequently assigned binary treatment, and a final outcome. The statistical model only assumes possible restrictions on the conditional distribution of treatment, given the covariates, the so-called propensity score. Estimators of the treatment specific mean involve estimation of the propensity score and/or estimation of the conditional mean of the outcome, given the treatment and covariates. In order to make these estimators asymptotically unbiased at any data distribution in the statistical model, it is essential to use data-adaptive estimators of these nuisance parameters such as ensemble learning, and specifically super-learning. Because such estimators involve optimal trade-off of bias and variance w.r.t. the infinite dimensional nuisance parameter itself, they result in a sub-optimal bias/variance trade-off for the resulting real-valued estimator of the estimand. We demonstrate that additional targeting of the estimators of these nuisance parameters guarantees that this bias for the estimand is second order and thereby allows us to prove theorems that establish asymptotic linearity of the estimator of the treatment specific mean under regularity conditions. These insights result in novel targeted minimum loss-based estimators (TMLEs) that use ensemble learning with additional targeted bias reduction to construct estimators of the nuisance parameters. In particular, we construct collaborative TMLEs (C-TMLEs) with known influence curve allowing for statistical inference, even though these C-TMLEs involve variable selection for the propensity score based on a criterion that measures how effective the resulting fit of the propensity score is in removing bias for the estimand. As a particular special case, we also demonstrate the required targeting of the propensity score for the inverse probability of treatment weighted estimator using super-learning to fit the propensity score.

Estimating the Effectiveness of Health-Risk Communications with Propensity-Score Matching: Application to Arsenic Groundwater Contamination in Four US Locations

PubMed Central

Leidner, Andrew J.

2014-01-01

This paper provides a demonstration of propensity-score matching estimation methods to evaluate the effectiveness of health-risk communication efforts. This study develops a two-stage regression model to investigate household and respondent characteristics as they contribute to aversion behavior to reduce exposure to arsenic-contaminated groundwater. The aversion activity under study is a household-level point-of-use filtration device. Since the acquisition of arsenic contamination information and the engagement in an aversion activity may be codetermined, a two-stage propensity-score model is developed. In the first stage, the propensity for households to acquire arsenic contamination information is estimated. Then, the propensity scores are used to weight observations in a probit regression on the decision to avert the arsenic-related health risk. Of four potential sources of information, utility, media, friend, or others, information received from a friend appears to be the source of information most associated with aversion behavior. Other statistically significant covariates in the household's decision to avert contamination include reported household income, the presence of children in household, and region-level indicator variables. These findings are primarily illustrative and demonstrate the usefulness of propensity-score methods to estimate health-risk communication effectiveness. They may also be suggestive of areas for future research. PMID:25349622

Advanced Issues in Propensity Scores: Longitudinal and Missing Data

ERIC Educational Resources Information Center

Kupzyk, Kevin A.; Beal, Sarah J.

2017-01-01

In order to investigate causality in situations where random assignment is not possible, propensity scores can be used in regression adjustment, stratification, inverse-probability treatment weighting, or matching. The basic concepts behind propensity scores have been extensively described. When data are longitudinal or missing, the estimation and…

Bayesian Model Averaging for Propensity Score Analysis

ERIC Educational Resources Information Center

Kaplan, David; Chen, Jianshen

2013-01-01

The purpose of this study is to explore Bayesian model averaging in the propensity score context. Previous research on Bayesian propensity score analysis does not take into account model uncertainty. In this regard, an internally consistent Bayesian framework for model building and estimation must also account for model uncertainty. The…

Propensity Score Analysis in R: A Software Review

ERIC Educational Resources Information Center

Keller, Bryan; Tipton, Elizabeth

2016-01-01

In this article, we review four software packages for implementing propensity score analysis in R: "Matching, MatchIt, PSAgraphics," and "twang." After briefly discussing essential elements for propensity score analysis, we apply each package to a data set from the Early Childhood Longitudinal Study in order to estimate the…

Prognostic score–based balance measures for propensity score methods in comparative effectiveness research

PubMed Central

Stuart, Elizabeth A.; Lee, Brian K.; Leacy, Finbarr P.

2013-01-01

Objective Examining covariate balance is the prescribed method for determining when propensity score methods are successful at reducing bias. This study assessed the performance of various balance measures, including a proposed balance measure based on the prognostic score (also known as the disease-risk score), to determine which balance measures best correlate with bias in the treatment effect estimate. Study Design and Setting The correlations of multiple common balance measures with bias in the treatment effect estimate produced by weighting by the odds, subclassification on the propensity score, and full matching on the propensity score were calculated. Simulated data were used, based on realistic data settings. Settings included both continuous and binary covariates and continuous covariates only. Results The standardized mean difference in prognostic scores, the mean standardized mean difference, and the mean t-statistic all had high correlations with bias in the effect estimate. Overall, prognostic scores displayed the highest correlations of all the balance measures considered. Prognostic score measure performance was generally not affected by model misspecification and performed well under a variety of scenarios. Conclusion Researchers should consider using prognostic score–based balance measures for assessing the performance of propensity score methods for reducing bias in non-experimental studies. PMID:23849158

Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression.

PubMed

Westreich, Daniel; Lessler, Justin; Funk, Michele Jonsson

2010-08-01

Propensity scores for the analysis of observational data are typically estimated using logistic regression. Our objective in this review was to assess machine learning alternatives to logistic regression, which may accomplish the same goals but with fewer assumptions or greater accuracy. We identified alternative methods for propensity score estimation and/or classification from the public health, biostatistics, discrete mathematics, and computer science literature, and evaluated these algorithms for applicability to the problem of propensity score estimation, potential advantages over logistic regression, and ease of use. We identified four techniques as alternatives to logistic regression: neural networks, support vector machines, decision trees (classification and regression trees [CART]), and meta-classifiers (in particular, boosting). Although the assumptions of logistic regression are well understood, those assumptions are frequently ignored. All four alternatives have advantages and disadvantages compared with logistic regression. Boosting (meta-classifiers) and, to a lesser extent, decision trees (particularly CART), appear to be most promising for use in the context of propensity score analysis, but extensive simulation studies are needed to establish their utility in practice. Copyright (c) 2010 Elsevier Inc. All rights reserved.

Two-step estimation in ratio-of-mediator-probability weighted causal mediation analysis.

PubMed

Bein, Edward; Deutsch, Jonah; Hong, Guanglei; Porter, Kristin E; Qin, Xu; Yang, Cheng

2018-04-15

This study investigates appropriate estimation of estimator variability in the context of causal mediation analysis that employs propensity score-based weighting. Such an analysis decomposes the total effect of a treatment on the outcome into an indirect effect transmitted through a focal mediator and a direct effect bypassing the mediator. Ratio-of-mediator-probability weighting estimates these causal effects by adjusting for the confounding impact of a large number of pretreatment covariates through propensity score-based weighting. In step 1, a propensity score model is estimated. In step 2, the causal effects of interest are estimated using weights derived from the prior step's regression coefficient estimates. Statistical inferences obtained from this 2-step estimation procedure are potentially problematic if the estimated standard errors of the causal effect estimates do not reflect the sampling uncertainty in the estimation of the weights. This study extends to ratio-of-mediator-probability weighting analysis a solution to the 2-step estimation problem by stacking the score functions from both steps. We derive the asymptotic variance-covariance matrix for the indirect effect and direct effect 2-step estimators, provide simulation results, and illustrate with an application study. Our simulation results indicate that the sampling uncertainty in the estimated weights should not be ignored. The standard error estimation using the stacking procedure offers a viable alternative to bootstrap standard error estimation. We discuss broad implications of this approach for causal analysis involving propensity score-based weighting. Copyright © 2018 John Wiley & Sons, Ltd.

Evaluating large-scale propensity score performance through real-world and synthetic data experiments.

PubMed

Tian, Yuxi; Schuemie, Martijn J; Suchard, Marc A

2018-06-22

Propensity score adjustment is a popular approach for confounding control in observational studies. Reliable frameworks are needed to determine relative propensity score performance in large-scale studies, and to establish optimal propensity score model selection methods. We detail a propensity score evaluation framework that includes synthetic and real-world data experiments. Our synthetic experimental design extends the 'plasmode' framework and simulates survival data under known effect sizes, and our real-world experiments use a set of negative control outcomes with presumed null effect sizes. In reproductions of two published cohort studies, we compare two propensity score estimation methods that contrast in their model selection approach: L1-regularized regression that conducts a penalized likelihood regression, and the 'high-dimensional propensity score' (hdPS) that employs a univariate covariate screen. We evaluate methods on a range of outcome-dependent and outcome-independent metrics. L1-regularization propensity score methods achieve superior model fit, covariate balance and negative control bias reduction compared with the hdPS. Simulation results are mixed and fluctuate with simulation parameters, revealing a limitation of simulation under the proportional hazards framework. Including regularization with the hdPS reduces commonly reported non-convergence issues but has little effect on propensity score performance. L1-regularization incorporates all covariates simultaneously into the propensity score model and offers propensity score performance superior to the hdPS marginal screen.

A Two-Step Bayesian Approach for Propensity Score Analysis: Simulations and Case Study.

PubMed

Kaplan, David; Chen, Jianshen

2012-07-01

A two-step Bayesian propensity score approach is introduced that incorporates prior information in the propensity score equation and outcome equation without the problems associated with simultaneous Bayesian propensity score approaches. The corresponding variance estimators are also provided. The two-step Bayesian propensity score is provided for three methods of implementation: propensity score stratification, weighting, and optimal full matching. Three simulation studies and one case study are presented to elaborate the proposed two-step Bayesian propensity score approach. Results of the simulation studies reveal that greater precision in the propensity score equation yields better recovery of the frequentist-based treatment effect. A slight advantage is shown for the Bayesian approach in small samples. Results also reveal that greater precision around the wrong treatment effect can lead to seriously distorted results. However, greater precision around the correct treatment effect parameter yields quite good results, with slight improvement seen with greater precision in the propensity score equation. A comparison of coverage rates for the conventional frequentist approach and proposed Bayesian approach is also provided. The case study reveals that credible intervals are wider than frequentist confidence intervals when priors are non-informative.

[Propensity score matching in SPSS].

PubMed

Huang, Fuqiang; DU, Chunlin; Sun, Menghui; Ning, Bing; Luo, Ying; An, Shengli

2015-11-01

To realize propensity score matching in PS Matching module of SPSS and interpret the analysis results. The R software and plug-in that could link with the corresponding versions of SPSS and propensity score matching package were installed. A PS matching module was added in the SPSS interface, and its use was demonstrated with test data. Score estimation and nearest neighbor matching was achieved with the PS matching module, and the results of qualitative and quantitative statistical description and evaluation were presented in the form of a graph matching. Propensity score matching can be accomplished conveniently using SPSS software.

The use of propensity score methods with survival or time-to-event outcomes: reporting measures of effect similar to those used in randomized experiments.

PubMed

Austin, Peter C

2014-03-30

Propensity score methods are increasingly being used to estimate causal treatment effects in observational studies. In medical and epidemiological studies, outcomes are frequently time-to-event in nature. Propensity-score methods are often applied incorrectly when estimating the effect of treatment on time-to-event outcomes. This article describes how two different propensity score methods (matching and inverse probability of treatment weighting) can be used to estimate the measures of effect that are frequently reported in randomized controlled trials: (i) marginal survival curves, which describe survival in the population if all subjects were treated or if all subjects were untreated; and (ii) marginal hazard ratios. The use of these propensity score methods allows one to replicate the measures of effect that are commonly reported in randomized controlled trials with time-to-event outcomes: both absolute and relative reductions in the probability of an event occurring can be determined. We also provide guidance on variable selection for the propensity score model, highlight methods for assessing the balance of baseline covariates between treated and untreated subjects, and describe the implementation of a sensitivity analysis to assess the effect of unmeasured confounding variables on the estimated treatment effect when outcomes are time-to-event in nature. The methods in the paper are illustrated by estimating the effect of discharge statin prescribing on the risk of death in a sample of patients hospitalized with acute myocardial infarction. In this tutorial article, we describe and illustrate all the steps necessary to conduct a comprehensive analysis of the effect of treatment on time-to-event outcomes. © 2013 The authors. Statistics in Medicine published by John Wiley & Sons, Ltd.

Assessing the performance of the generalized propensity score for estimating the effect of quantitative or continuous exposures on survival or time-to-event outcomes.

PubMed

Austin, Peter C

2018-01-01

Propensity score methods are frequently used to estimate the effects of interventions using observational data. The propensity score was originally developed for use with binary exposures. The generalized propensity score (GPS) is an extension of the propensity score for use with quantitative or continuous exposures (e.g. pack-years of cigarettes smoked, dose of medication, or years of education). We describe how the GPS can be used to estimate the effect of continuous exposures on survival or time-to-event outcomes. To do so we modified the concept of the dose-response function for use with time-to-event outcomes. We used Monte Carlo simulations to examine the performance of different methods of using the GPS to estimate the effect of quantitative exposures on survival or time-to-event outcomes. We examined covariate adjustment using the GPS and weighting using weights based on the inverse of the GPS. The use of methods based on the GPS was compared with the use of conventional G-computation and weighted G-computation. Conventional G-computation resulted in estimates of the dose-response function that displayed the lowest bias and the lowest variability. Amongst the two GPS-based methods, covariate adjustment using the GPS tended to have the better performance. We illustrate the application of these methods by estimating the effect of average neighbourhood income on the probability of survival following hospitalization for an acute myocardial infarction.

Drawing causal inferences using propensity scores: a practical guide for community psychologists.

PubMed

Lanza, Stephanie T; Moore, Julia E; Butera, Nicole M

2013-12-01

Confounding present in observational data impede community psychologists' ability to draw causal inferences. This paper describes propensity score methods as a conceptually straightforward approach to drawing causal inferences from observational data. A step-by-step demonstration of three propensity score methods-weighting, matching, and subclassification-is presented in the context of an empirical examination of the causal effect of preschool experiences (Head Start vs. parental care) on reading development in kindergarten. Although the unadjusted population estimate indicated that children with parental care had substantially higher reading scores than children who attended Head Start, all propensity score adjustments reduce the size of this overall causal effect by more than half. The causal effect was also defined and estimated among children who attended Head Start. Results provide no evidence for improved reading if those children had instead received parental care. We carefully define different causal effects and discuss their respective policy implications, summarize advantages and limitations of each propensity score method, and provide SAS and R syntax so that community psychologists may conduct causal inference in their own research.

Drawing Causal Inferences Using Propensity Scores: A Practical Guide for Community Psychologists

PubMed Central

Lanza, Stephanie T.; Moore, Julia E.; Butera, Nicole M.

2014-01-01

Confounding present in observational data impede community psychologists’ ability to draw causal inferences. This paper describes propensity score methods as a conceptually straightforward approach to drawing causal inferences from observational data. A step-by-step demonstration of three propensity score methods – weighting, matching, and subclassification – is presented in the context of an empirical examination of the causal effect of preschool experiences (Head Start vs. parental care) on reading development in kindergarten. Although the unadjusted population estimate indicated that children with parental care had substantially higher reading scores than children who attended Head Start, all propensity score adjustments reduce the size of this overall causal effect by more than half. The causal effect was also defined and estimated among children who attended Head Start. Results provide no evidence for improved reading if those children had instead received parental care. We carefully define different causal effects and discuss their respective policy implications, summarize advantages and limitations of each propensity score method, and provide SAS and R syntax so that community psychologists may conduct causal inference in their own research. PMID:24185755

An Assessment of Propensity Score Matching as a Nonexperimental Impact Estimator: Evidence from Mexico's PROGRESA Program

ERIC Educational Resources Information Center

Diaz, Juan Jose; Handa, Sudhanshu

2006-01-01

Not all policy questions can be addressed by social experiments. Nonexperimental evaluation methods provide an alternative to experimental designs but their results depend on untestable assumptions. This paper presents evidence on the reliability of propensity score matching (PSM), which estimates treatment effects under the assumption of…

Models for the propensity score that contemplate the positivity assumption and their application to missing data and causality.

PubMed

Molina, J; Sued, M; Valdora, M

2018-06-05

Generalized linear models are often assumed to fit propensity scores, which are used to compute inverse probability weighted (IPW) estimators. To derive the asymptotic properties of IPW estimators, the propensity score is supposed to be bounded away from zero. This condition is known in the literature as strict positivity (or positivity assumption), and, in practice, when it does not hold, IPW estimators are very unstable and have a large variability. Although strict positivity is often assumed, it is not upheld when some of the covariates are unbounded. In real data sets, a data-generating process that violates the positivity assumption may lead to wrong inference because of the inaccuracy in the estimations. In this work, we attempt to conciliate between the strict positivity condition and the theory of generalized linear models by incorporating an extra parameter, which results in an explicit lower bound for the propensity score. An additional parameter is added to fulfil the overlap assumption in the causal framework. Copyright © 2018 John Wiley & Sons, Ltd.

Using propensity scores to estimate the effects of insecticides on stream invertebrates from observational data

USGS Publications Warehouse

Lester L. Yuan,; Amina I. Pollard,; Carlisle, Daren M.

2009-01-01

Analyses of observational data can provide insights into relationships between environmental conditions and biological responses across a broader range of natural conditions than experimental studies, potentially complementing insights gained from experiments. However, observational data must be analyzed carefully to minimize the likelihood that confounding variables bias observed relationships. Propensity scores provide a robust approach for controlling for the effects of measured confounding variables when analyzing observational data. Here, we use propensity scores to estimate changes in mean invertebrate taxon richness in streams that have experienced insecticide concentrations that exceed aquatic life use benchmark concentrations. A simple comparison of richness in sites exposed to elevated insecticides with those that were not exposed suggests that exposed sites had on average 6.8 fewer taxa compared to unexposed sites. The presence of potential confounding variables makes it difficult to assert a causal relationship from this simple comparison. After controlling for confounding factors using propensity scores, the difference in richness between exposed and unexposed sites was reduced to 4.1 taxa, a difference that was still statistically significant. Because the propensity score analysis controlled for the effects of a wide variety of possible confounding variables, we infer that the change in richness observed in the propensity score analysis was likely caused by insecticide exposure.

Using propensity scores to estimate the effects of insecticides on stream invertebrates from observational data

USGS Publications Warehouse

Yuan, L.L.; Pollard, A.I.; Carlisle, D.M.

2009-01-01

Analyses of observational data can provide insights into relationships between environmental conditions and biological responses across a broader range of natural conditions than experimental studies, potentially complementing insights gained from experiments. However, observational data must be analyzed carefully to minimize the likelihood that confounding variables bias observed relationships. Propensity scores provide a robust approach for controlling for the effects of measured confounding variables when analyzing observational data. Here, we use propensity scores to estimate changes in mean invertebrate taxon richness in streams that have experienced insecticide concentrations that exceed aquatic life use benchmark concentrations. A simple comparison of richness in sites exposed to elevated insecticides with those that were not exposed suggests that exposed sites had on average 6.8 fewer taxa compared to unexposed sites. The presence of potential confounding variables makes it difficult to assert a causal relationship from this simple comparison. After controlling for confounding factors using propensity scores, the difference in richness between exposed and unexposed sites was reduced to 4.1 taxa, a difference that was still statistically significant. Because the propensity score analysis controlled for the effects of a wide variety of possible confounding variables, we infer that the change in richness observed in the propensity score analysis was likely caused by insecticide exposure. ?? 2009 SETAC.

Primer on statistical interpretation or methods report card on propensity-score matching in the cardiology literature from 2004 to 2006: a systematic review.

PubMed

Austin, Peter C

2008-09-01

Propensity-score matching is frequently used in the cardiology literature. Recent systematic reviews have found that this method is, in general, poorly implemented in the medical literature. The study objective was to examine the quality of the implementation of propensity-score matching in the general cardiology literature. A total of 44 articles published in the American Heart Journal, the American Journal of Cardiology, Circulation, the European Heart Journal, Heart, the International Journal of Cardiology, and the Journal of the American College of Cardiology between January 1, 2004, and December 31, 2006, were examined. Twenty of the 44 studies did not provide adequate information on how the propensity-score-matched pairs were formed. Fourteen studies did not report whether matching on the propensity score balanced baseline characteristics between treated and untreated subjects in the matched sample. Only 4 studies explicitly used statistical methods appropriate for matched studies to compare baseline characteristics between treated and untreated subjects. Only 11 (25%) of the 44 studies explicitly used statistical methods appropriate for the analysis of matched data when estimating the effect of treatment on the outcomes. Only 2 studies described the matching method used, assessed balance in baseline covariates by appropriate methods, and used appropriate statistical methods to estimate the treatment effect and its significance. Application of propensity-score matching was poor in the cardiology literature. Suggestions for improving the reporting and analysis of studies that use propensity-score matching are provided.

The Propensity Score Analytical Framework: An Overview and Institutional Research Example

ERIC Educational Resources Information Center

Herzog, Serge

2014-01-01

Estimating the effect of campus math tutoring support, this study demonstrates the use of propensity score weighted and matched-data analysis and examines the correspondence with results from parametric regression analysis.

Variable selection for confounder control, flexible modeling and Collaborative Targeted Minimum Loss-based Estimation in causal inference

PubMed Central

Schnitzer, Mireille E.; Lok, Judith J.; Gruber, Susan

2015-01-01

This paper investigates the appropriateness of the integration of flexible propensity score modeling (nonparametric or machine learning approaches) in semiparametric models for the estimation of a causal quantity, such as the mean outcome under treatment. We begin with an overview of some of the issues involved in knowledge-based and statistical variable selection in causal inference and the potential pitfalls of automated selection based on the fit of the propensity score. Using a simple example, we directly show the consequences of adjusting for pure causes of the exposure when using inverse probability of treatment weighting (IPTW). Such variables are likely to be selected when using a naive approach to model selection for the propensity score. We describe how the method of Collaborative Targeted minimum loss-based estimation (C-TMLE; van der Laan and Gruber, 2010) capitalizes on the collaborative double robustness property of semiparametric efficient estimators to select covariates for the propensity score based on the error in the conditional outcome model. Finally, we compare several approaches to automated variable selection in low-and high-dimensional settings through a simulation study. From this simulation study, we conclude that using IPTW with flexible prediction for the propensity score can result in inferior estimation, while Targeted minimum loss-based estimation and C-TMLE may benefit from flexible prediction and remain robust to the presence of variables that are highly correlated with treatment. However, in our study, standard influence function-based methods for the variance underestimated the standard errors, resulting in poor coverage under certain data-generating scenarios. PMID:26226129

Variable Selection for Confounder Control, Flexible Modeling and Collaborative Targeted Minimum Loss-Based Estimation in Causal Inference.

PubMed

Schnitzer, Mireille E; Lok, Judith J; Gruber, Susan

2016-05-01

This paper investigates the appropriateness of the integration of flexible propensity score modeling (nonparametric or machine learning approaches) in semiparametric models for the estimation of a causal quantity, such as the mean outcome under treatment. We begin with an overview of some of the issues involved in knowledge-based and statistical variable selection in causal inference and the potential pitfalls of automated selection based on the fit of the propensity score. Using a simple example, we directly show the consequences of adjusting for pure causes of the exposure when using inverse probability of treatment weighting (IPTW). Such variables are likely to be selected when using a naive approach to model selection for the propensity score. We describe how the method of Collaborative Targeted minimum loss-based estimation (C-TMLE; van der Laan and Gruber, 2010 [27]) capitalizes on the collaborative double robustness property of semiparametric efficient estimators to select covariates for the propensity score based on the error in the conditional outcome model. Finally, we compare several approaches to automated variable selection in low- and high-dimensional settings through a simulation study. From this simulation study, we conclude that using IPTW with flexible prediction for the propensity score can result in inferior estimation, while Targeted minimum loss-based estimation and C-TMLE may benefit from flexible prediction and remain robust to the presence of variables that are highly correlated with treatment. However, in our study, standard influence function-based methods for the variance underestimated the standard errors, resulting in poor coverage under certain data-generating scenarios.

Combining Propensity Score Methods and Complex Survey Data to Estimate Population Treatment Effects

ERIC Educational Resources Information Center

Stuart, Elizabeth A.; Dong, Nianbo; Lenis, David

2016-01-01

Complex surveys are often used to estimate causal effects regarding the effects of interventions or exposures of interest. Propensity scores (Rosenbaum & Rubin, 1983) have emerged as one popular and effective tool for causal inference in non-experimental studies, as they can help ensure that groups being compared are similar with respect to a…

Using Propensity Scores for Estimating Causal Effects: A Study in the Development of Moral Reasoning

ERIC Educational Resources Information Center

Grunwald, Heidi E.; Mayhew, Matthew J.

2008-01-01

The purpose of this study was to illustrate the use of propensity scores for creating comparison groups, partially controlling for pretreatment course selection bias, and estimating the treatment effects of selected courses on the development of moral reasoning in undergraduate students. Specifically, we used a sample of convenience for comparing…

Quantifying the causal effects of 20mph zones on road casualties in London via doubly robust estimation.

PubMed

Li, Haojie; Graham, Daniel J

2016-08-01

This paper estimates the causal effect of 20mph zones on road casualties in London. Potential confounders in the key relationship of interest are included within outcome regression and propensity score models, and the models are then combined to form a doubly robust estimator. A total of 234 treated zones and 2844 potential control zones are included in the data sample. The propensity score model is used to select a viable control group which has common support in the covariate distributions. We compare the doubly robust estimates with those obtained using three other methods: inverse probability weighting, regression adjustment, and propensity score matching. The results indicate that 20mph zones have had a significant causal impact on road casualty reduction in both absolute and proportional terms. Copyright © 2016 Elsevier Ltd. All rights reserved.

Adjusting for Confounding in Early Postlaunch Settings: Going Beyond Logistic Regression Models.

PubMed

Schmidt, Amand F; Klungel, Olaf H; Groenwold, Rolf H H

2016-01-01

Postlaunch data on medical treatments can be analyzed to explore adverse events or relative effectiveness in real-life settings. These analyses are often complicated by the number of potential confounders and the possibility of model misspecification. We conducted a simulation study to compare the performance of logistic regression, propensity score, disease risk score, and stabilized inverse probability weighting methods to adjust for confounding. Model misspecification was induced in the independent derivation dataset. We evaluated performance using relative bias confidence interval coverage of the true effect, among other metrics. At low events per coefficient (1.0 and 0.5), the logistic regression estimates had a large relative bias (greater than -100%). Bias of the disease risk score estimates was at most 13.48% and 18.83%. For the propensity score model, this was 8.74% and >100%, respectively. At events per coefficient of 1.0 and 0.5, inverse probability weighting frequently failed or reduced to a crude regression, resulting in biases of -8.49% and 24.55%. Coverage of logistic regression estimates became less than the nominal level at events per coefficient ≤5. For the disease risk score, inverse probability weighting, and propensity score, coverage became less than nominal at events per coefficient ≤2.5, ≤1.0, and ≤1.0, respectively. Bias of misspecified disease risk score models was 16.55%. In settings with low events/exposed subjects per coefficient, disease risk score methods can be useful alternatives to logistic regression models, especially when propensity score models cannot be used. Despite better performance of disease risk score methods than logistic regression and propensity score models in small events per coefficient settings, bias, and coverage still deviated from nominal.

Identifying Baseline Covariates for Use in Propensity Scores: A Novel Approach Illustrated for a Nonrandomized Study of Recovery High Schools

ERIC Educational Resources Information Center

Tanner-Smith, Emily E.; Lipsey, Mark W.

2014-01-01

There are many situations where random assignment of participants to treatment and comparison conditions may be unethical or impractical. This article provides an overview of propensity score techniques that can be used for estimating treatment effects in nonrandomized quasi-experimental studies. After reviewing the logic of propensity score…

Propensity-score matching in the cardiovascular surgery literature from 2004 to 2006: a systematic review and suggestions for improvement.

PubMed

Austin, Peter C

2007-11-01

I conducted a systematic review of the use of propensity score matching in the cardiovascular surgery literature. I examined the adequacy of reporting and whether appropriate statistical methods were used. I examined 60 articles published in the Annals of Thoracic Surgery, European Journal of Cardio-thoracic Surgery, Journal of Cardiovascular Surgery, and the Journal of Thoracic and Cardiovascular Surgery between January 1, 2004, and December 31, 2006. Thirty-one of the 60 studies did not provide adequate information on how the propensity score-matched pairs were formed. Eleven (18%) of studies did not report on whether matching on the propensity score balanced baseline characteristics between treated and untreated subjects in the matched sample. No studies used appropriate methods to compare baseline characteristics between treated and untreated subjects in the propensity score-matched sample. Eight (13%) of the 60 studies explicitly used statistical methods appropriate for the analysis of matched data when estimating the effect of treatment on the outcomes. Two studies used appropriate methods for some outcomes, but not for all outcomes. Thirty-nine (65%) studies explicitly used statistical methods that were inappropriate for matched-pairs data when estimating the effect of treatment on outcomes. Eleven studies did not report the statistical tests that were used to assess the statistical significance of the treatment effect. Analysis of propensity score-matched samples tended to be poor in the cardiovascular surgery literature. Most statistical analyses ignored the matched nature of the sample. I provide suggestions for improving the reporting and analysis of studies that use propensity score matching.

A review of the application of propensity score methods yielded increasing use, advantages in specific settings, but not substantially different estimates compared with conventional multivariable methods

PubMed Central

Stürmer, Til; Joshi, Manisha; Glynn, Robert J.; Avorn, Jerry; Rothman, Kenneth J.; Schneeweiss, Sebastian

2006-01-01

Objective Propensity score analyses attempt to control for confounding in non-experimental studies by adjusting for the likelihood that a given patient is exposed. Such analyses have been proposed to address confounding by indication, but there is little empirical evidence that they achieve better control than conventional multivariate outcome modeling. Study design and methods Using PubMed and Science Citation Index, we assessed the use of propensity scores over time and critically evaluated studies published through 2003. Results Use of propensity scores increased from a total of 8 papers before 1998 to 71 in 2003. Most of the 177 published studies abstracted assessed medications (N=60) or surgical interventions (N=51), mainly in cardiology and cardiac surgery (N=90). Whether PS methods or conventional outcome models were used to control for confounding had little effect on results in those studies in which such comparison was possible. Only 9 out of 69 studies (13%) had an effect estimate that differed by more than 20% from that obtained with a conventional outcome model in all PS analyses presented. Conclusions Publication of results based on propensity score methods has increased dramatically, but there is little evidence that these methods yield substantially different estimates compared with conventional multivariable methods. PMID:16632131

Propensity Score Estimation With Boosted Regression for Evaluating Causal Effects in Observational Studies

ERIC Educational Resources Information Center

McCaffrey, Daniel F.; Ridgeway, Greg; Morral, Andrew R.

2004-01-01

Causal effect modeling with naturalistic rather than experimental data is challenging. In observational studies participants in different treatment conditions may also differ on pretreatment characteristics that influence outcomes. Propensity score methods can theoretically eliminate these confounds for all observed covariates, but accurate…

It's all about balance: propensity score matching in the context of complex survey data.

PubMed

Lenis, David; Nguyen, Trang Quynh; Dong, Nianbo; Stuart, Elizabeth A

2017-12-27

Many research studies aim to draw causal inferences using data from large, nationally representative survey samples, and many of these studies use propensity score matching to make those causal inferences as rigorous as possible given the non-experimental nature of the data. However, very few applied studies are careful about incorporating the survey design with the propensity score analysis, which may mean that the results do not generate population inferences. This may be because few methodological studies examine how to best combine these methods. Furthermore, even fewer of them investigate different non-response mechanisms. This study examines methods for handling survey weights in propensity score matching analyses of survey data under different non-response mechanisms. Our main conclusions are: (i) whether the survey weights are incorporated in the estimation of the propensity score does not impact estimation of the population treatment effect, as long as good population treated-comparison balance is achieved on confounders, (ii) survey weights must be used in the outcome analysis, and (iii) the transferring of survey weights (i.e., assigning the weights of the treated units to the comparison units matched to them) can be beneficial under certain non-response mechanisms. © The Author 2017. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

The search for causal inferences: using propensity scores post hoc to reduce estimation error with nonexperimental research.

PubMed

Tumlinson, Samuel E; Sass, Daniel A; Cano, Stephanie M

2014-03-01

While experimental designs are regarded as the gold standard for establishing causal relationships, such designs are usually impractical owing to common methodological limitations. The objective of this article is to illustrate how propensity score matching (PSM) and using propensity scores (PS) as a covariate are viable alternatives to reduce estimation error when experimental designs cannot be implemented. To mimic common pediatric research practices, data from 140 simulated participants were used to resemble an experimental and nonexperimental design that assessed the effect of treatment status on participant weight loss for diabetes. Pretreatment participant characteristics (age, gender, physical activity, etc.) were then used to generate PS for use in the various statistical approaches. Results demonstrate how PSM and using the PS as a covariate can be used to reduce estimation error and improve statistical inferences. References for issues related to the implementation of these procedures are provided to assist researchers.

The association between the availability of sugar-sweetened beverage in school vending machines and its consumption among adolescents in California: a propensity score matching approach.

PubMed

Shi, Lu

2010-01-01

There is controversy over to what degree banning sugar-sweetened beverage (SSB) sales at schools could decrease the SSB intake. This paper uses the adolescent sample of 2005 California Health Interview Survey to estimate the association between the availability of SSB from school vending machines and the amount of SSB consumption. Propensity score stratification and kernel-based propensity score matching are used to address the selection bias issue in cross-sectional data. Propensity score stratification shows that adolescents who had access to SSB through their school vending machines consumed 0.170 more drinks of SSB than those who did not (P < .05). Kernel-based propensity score matching shows the SSB consumption difference to be 0.158 on the prior day (P < .05). This paper strengthens the evidence for the association between SSB availability via school vending machines and the actual SSB consumption, while future studies are needed to explore changes in other beverages after SSB becomes less available.

Applications of Small Area Estimation to Generalization with Subclassification by Propensity Scores

ERIC Educational Resources Information Center

Chan, Wendy

2018-01-01

Policymakers have grown increasingly interested in how experimental results may generalize to a larger population. However, recently developed propensity score-based methods are limited by small sample sizes, where the experimental study is generalized to a population that is at least 20 times larger. This is particularly problematic for methods…

Propensity Score Estimation with Data Mining Techniques: Alternatives to Logistic Regression

ERIC Educational Resources Information Center

Keller, Bryan S. B.; Kim, Jee-Seon; Steiner, Peter M.

2013-01-01

Propensity score analysis (PSA) is a methodological technique which may correct for selection bias in a quasi-experiment by modeling the selection process using observed covariates. Because logistic regression is well understood by researchers in a variety of fields and easy to implement in a number of popular software packages, it has…

Multigroup Propensity Score Approach to Evaluating an Effectiveness Trial of the New Beginnings Program.

PubMed

Tein, Jenn-Yun; Mazza, Gina L; Gunn, Heather J; Kim, Hanjoe; Stuart, Elizabeth A; Sandler, Irwin N; Wolchik, Sharlene A

2018-06-01

We used a multigroup propensity score approach to evaluate a randomized effectiveness trial of the New Beginnings Program (NBP), an intervention targeting divorced or separated families. Two features of effectiveness trials, high nonattendance rates and inclusion of an active control, make program effects harder to detect. To estimate program effects based on actual intervention participation, we created a synthetic inactive control comprised of nonattenders and assessed the impact of attending the NBP or active control relative to no intervention (inactive control). We estimated propensity scores using generalized boosted models and applied inverse probability of treatment weighting for the comparisons. Relative to the inactive control, NBP strengthened parenting quality as well as reduced child exposure to interparental conflict, parent psychological distress, and child internalizing problems. Some effects were moderated by parent gender, parent ethnicity, or child age. On the other hand, the effects of active versus inactive control were minimal for parenting and in the unexpected direction for child internalizing problems. Findings from the propensity score approach complement and enhance the interpretation of findings from the intention-to-treat approach.

Globally efficient non-parametric inference of average treatment effects by empirical balancing calibration weighting

PubMed Central

Chan, Kwun Chuen Gary; Yam, Sheung Chi Phillip; Zhang, Zheng

2015-01-01

Summary The estimation of average treatment effects based on observational data is extremely important in practice and has been studied by generations of statisticians under different frameworks. Existing globally efficient estimators require non-parametric estimation of a propensity score function, an outcome regression function or both, but their performance can be poor in practical sample sizes. Without explicitly estimating either functions, we consider a wide class calibration weights constructed to attain an exact three-way balance of the moments of observed covariates among the treated, the control, and the combined group. The wide class includes exponential tilting, empirical likelihood and generalized regression as important special cases, and extends survey calibration estimators to different statistical problems and with important distinctions. Global semiparametric efficiency for the estimation of average treatment effects is established for this general class of calibration estimators. The results show that efficiency can be achieved by solely balancing the covariate distributions without resorting to direct estimation of propensity score or outcome regression function. We also propose a consistent estimator for the efficient asymptotic variance, which does not involve additional functional estimation of either the propensity score or the outcome regression functions. The proposed variance estimator outperforms existing estimators that require a direct approximation of the efficient influence function. PMID:27346982

Globally efficient non-parametric inference of average treatment effects by empirical balancing calibration weighting.

PubMed

Chan, Kwun Chuen Gary; Yam, Sheung Chi Phillip; Zhang, Zheng

2016-06-01

The estimation of average treatment effects based on observational data is extremely important in practice and has been studied by generations of statisticians under different frameworks. Existing globally efficient estimators require non-parametric estimation of a propensity score function, an outcome regression function or both, but their performance can be poor in practical sample sizes. Without explicitly estimating either functions, we consider a wide class calibration weights constructed to attain an exact three-way balance of the moments of observed covariates among the treated, the control, and the combined group. The wide class includes exponential tilting, empirical likelihood and generalized regression as important special cases, and extends survey calibration estimators to different statistical problems and with important distinctions. Global semiparametric efficiency for the estimation of average treatment effects is established for this general class of calibration estimators. The results show that efficiency can be achieved by solely balancing the covariate distributions without resorting to direct estimation of propensity score or outcome regression function. We also propose a consistent estimator for the efficient asymptotic variance, which does not involve additional functional estimation of either the propensity score or the outcome regression functions. The proposed variance estimator outperforms existing estimators that require a direct approximation of the efficient influence function.

Assessment of Patient-Specific Surgery Effect Based on Weighted Estimation and Propensity Scoring in the Re-Analysis of the Sciatica Trial

PubMed Central

Mertens, Bart J. A.; Jacobs, Wilco C. H.; Brand, Ronald; Peul, Wilco C.

2014-01-01

We consider a re-analysis of the wait-and-see (control) arm of a recent clinical trial on sciatica. While the original randomised trial was designed to evaluate the public policy effect of a conservative wait-and-see approach versus early surgery, we investigate the impact of surgery at the individual patient level in a re-analysis of the wait-and-see group data. Both marginal structural model re-weighted estimates as well as propensity score adjusted analyses are presented. Results indicate that patients with high propensity to receive surgery may have beneficial effects at 2 years from delayed disc surgery. PMID:25353633

Propensity Score-Based Methods versus MTE-Based Methods in Causal Inference: Identification, Estimation, and Application

ERIC Educational Resources Information Center

Zhou, Xiang; Xie, Yu

2016-01-01

Since the seminal introduction of the propensity score (PS) by Rosenbaum and Rubin, PS-based methods have been widely used for drawing causal inferences in the behavioral and social sciences. However, the PS approach depends on the ignorability assumption: there are no unobserved confounders once observed covariates are taken into account. For…

Acceleration in Elementary School: Using Propensity Score Matching to Estimate the Effects on Academic Achievement

ERIC Educational Resources Information Center

Kretschmann, Julia; Vock, Miriam; Lüdtke, Oliver

2014-01-01

Using German data, we examined the effects of one specific type of acceleration--grade skipping--on academic performance. Prior research on the effects of acceleration has suffered from methodological restrictions, especially due to a lack of appropriate comparison groups and a priori measurements. For this reason, propensity score matching was…

The Association between the Availability of Sugar-Sweetened Beverage in School Vending Machines and Its Consumption among Adolescents in California: A Propensity Score Matching Approach

PubMed Central

Shi, Lu

2010-01-01

There is controversy over to what degree banning sugar-sweetened beverage (SSB) sales at schools could decrease the SSB intake. This paper uses the adolescent sample of 2005 California Health Interview Survey to estimate the association between the availability of SSB from school vending machines and the amount of SSB consumption. Propensity score stratification and kernel-based propensity score matching are used to address the selection bias issue in cross-sectional data. Propensity score stratification shows that adolescents who had access to SSB through their school vending machines consumed 0.170 more drinks of SSB than those who did not (P < .05). Kernel-based propensity score matching shows the SSB consumption difference to be 0.158 on the prior day (P < .05). This paper strengthens the evidence for the association between SSB availability via school vending machines and the actual SSB consumption, while future studies are needed to explore changes in other beverages after SSB becomes less available. PMID:20976298

Using Non-experimental Data to Estimate Treatment Effects

PubMed Central

Stuart, Elizabeth A.; Marcus, Sue M.; Horvitz-Lennon, Marcela V.; Gibbons, Robert D.; Normand, Sharon-Lise T.

2009-01-01

While much psychiatric research is based on randomized controlled trials (RCTs), where patients are randomly assigned to treatments, sometimes RCTs are not feasible. This paper describes propensity score approaches, which are increasingly used for estimating treatment effects in non-experimental settings. The primary goal of propensity score methods is to create sets of treated and comparison subjects who look as similar as possible, in essence replicating a randomized experiment, at least with respect to observed patient characteristics. A study to estimate the metabolic effects of antipsychotic medication in a sample of Florida Medicaid beneficiaries with schizophrenia illustrates methods. PMID:20563313

Use of disease risk scores in pharmacoepidemiologic studies.

PubMed

Arbogast, Patrick G; Ray, Wayne A

2009-02-01

Automated databases are increasingly used in pharmacoepidemiologic studies. These databases include records of prescribed medications and encounters with medical care providers from which one can construct very detailed surrogate measures for both drug exposure and covariates that are potential confounders. Often it is possible to track day-by-day changes in these variables. However, while this information is often critical for study success, its volume can pose challenges for statistical analysis. One common approach is the use of propensity scores. An alternative approach is to construct a disease risk score. This is analogous to the propensity score in that it calculates a summary measure from the covariates. However, the disease risk score estimates the probability or rate of disease occurrence conditional on being unexposed. The association between exposure and disease is then estimated adjusting for the disease risk score in place of the individual covariates. This review describes the use of disease risk scores in pharmacoepidemiologic studies, and includes a brief discussion of their history, a more detailed description of their construction and use, a summary of simulation studies comparing their performance vis-á-vis traditional models, a comparison of their utility with that of propensity scores, and some further topics for future research.

Double propensity-score adjustment: A solution to design bias or bias due to incomplete matching.

PubMed

Austin, Peter C

2017-02-01

Propensity-score matching is frequently used to reduce the effects of confounding when using observational data to estimate the effects of treatments. Matching allows one to estimate the average effect of treatment in the treated. Rosenbaum and Rubin coined the term "bias due to incomplete matching" to describe the bias that can occur when some treated subjects are excluded from the matched sample because no appropriate control subject was available. The presence of incomplete matching raises important questions around the generalizability of estimated treatment effects to the entire population of treated subjects. We describe an analytic solution to address the bias due to incomplete matching. Our method is based on using optimal or nearest neighbor matching, rather than caliper matching (which frequently results in the exclusion of some treated subjects). Within the sample matched on the propensity score, covariate adjustment using the propensity score is then employed to impute missing potential outcomes under lack of treatment for each treated subject. Using Monte Carlo simulations, we found that the proposed method resulted in estimates of treatment effect that were essentially unbiased. This method resulted in decreased bias compared to caliper matching alone and compared to either optimal matching or nearest neighbor matching alone. Caliper matching alone resulted in design bias or bias due to incomplete matching, while optimal matching or nearest neighbor matching alone resulted in bias due to residual confounding. The proposed method also tended to result in estimates with decreased mean squared error compared to when caliper matching was used.

Double propensity-score adjustment: A solution to design bias or bias due to incomplete matching

PubMed Central

2016-01-01

Propensity-score matching is frequently used to reduce the effects of confounding when using observational data to estimate the effects of treatments. Matching allows one to estimate the average effect of treatment in the treated. Rosenbaum and Rubin coined the term “bias due to incomplete matching” to describe the bias that can occur when some treated subjects are excluded from the matched sample because no appropriate control subject was available. The presence of incomplete matching raises important questions around the generalizability of estimated treatment effects to the entire population of treated subjects. We describe an analytic solution to address the bias due to incomplete matching. Our method is based on using optimal or nearest neighbor matching, rather than caliper matching (which frequently results in the exclusion of some treated subjects). Within the sample matched on the propensity score, covariate adjustment using the propensity score is then employed to impute missing potential outcomes under lack of treatment for each treated subject. Using Monte Carlo simulations, we found that the proposed method resulted in estimates of treatment effect that were essentially unbiased. This method resulted in decreased bias compared to caliper matching alone and compared to either optimal matching or nearest neighbor matching alone. Caliper matching alone resulted in design bias or bias due to incomplete matching, while optimal matching or nearest neighbor matching alone resulted in bias due to residual confounding. The proposed method also tended to result in estimates with decreased mean squared error compared to when caliper matching was used. PMID:25038071

On the Importance of Reliable Covariate Measurement in Selection Bias Adjustments Using Propensity Scores

ERIC Educational Resources Information Center

Steiner, Peter M.; Cook, Thomas D.; Shadish, William R.

2011-01-01

The effect of unreliability of measurement on propensity score (PS) adjusted treatment effects has not been previously studied. The authors report on a study simulating different degrees of unreliability in the multiple covariates that were used to estimate the PS. The simulation uses the same data as two prior studies. Shadish, Clark, and Steiner…

Beyond Binary: Using Propensity Scores to Account for Varying Levels of Program Participation in Randomized Controlled Trials

ERIC Educational Resources Information Center

Stuart, Elizabeth A.; Warkentien, Siri; Jo, Booil

2011-01-01

The purpose of the current project is to explore the use of propensity scores to estimate the effects of interventions within randomized control trials, accounting for varying levels of implementation or fidelity. This work extends that of Jo and Stuart (2009) to settings with multiple or continuous measures of implementation. Rather than focus…

Two-Year versus One-Year Head Start Program Impact: Addressing Selection Bias by Comparing Regression Modeling with Propensity Score Analysis

ERIC Educational Resources Information Center

Leow, Christine; Wen, Xiaoli; Korfmacher, Jon

2015-01-01

This article compares regression modeling and propensity score analysis as different types of statistical techniques used in addressing selection bias when estimating the impact of two-year versus one-year Head Start on children's school readiness. The analyses were based on the national Head Start secondary dataset. After controlling for…

Taking the Missing Propensity into Account When Estimating Competence Scores: Evaluation of Item Response Theory Models for Nonignorable Omissions

ERIC Educational Resources Information Center

Köhler, Carmen; Pohl, Steffi; Carstensen, Claus H.

2015-01-01

When competence tests are administered, subjects frequently omit items. These missing responses pose a threat to correctly estimating the proficiency level. Newer model-based approaches aim to take nonignorable missing data processes into account by incorporating a latent missing propensity into the measurement model. Two assumptions are typically…

Propensity scores-potential outcomes framework to incorporate severity probabilities in the highway safety manual crash prediction algorithm.

PubMed

Sasidharan, Lekshmi; Donnell, Eric T

2014-10-01

Accurate estimation of the expected number of crashes at different severity levels for entities with and without countermeasures plays a vital role in selecting countermeasures in the framework of the safety management process. The current practice is to use the American Association of State Highway and Transportation Officials' Highway Safety Manual crash prediction algorithms, which combine safety performance functions and crash modification factors, to estimate the effects of safety countermeasures on different highway and street facility types. Many of these crash prediction algorithms are based solely on crash frequency, or assume that severity outcomes are unchanged when planning for, or implementing, safety countermeasures. Failing to account for the uncertainty associated with crash severity outcomes, and assuming crash severity distributions remain unchanged in safety performance evaluations, limits the utility of the Highway Safety Manual crash prediction algorithms in assessing the effect of safety countermeasures on crash severity. This study demonstrates the application of a propensity scores-potential outcomes framework to estimate the probability distribution for the occurrence of different crash severity levels by accounting for the uncertainties associated with them. The probability of fatal and severe injury crash occurrence at lighted and unlighted intersections is estimated in this paper using data from Minnesota. The results show that the expected probability of occurrence of fatal and severe injury crashes at a lighted intersection was 1 in 35 crashes and the estimated risk ratio indicates that the respective probabilities at an unlighted intersection was 1.14 times higher compared to lighted intersections. The results from the potential outcomes-propensity scores framework are compared to results obtained from traditional binary logit models, without application of propensity scores matching. Traditional binary logit analysis suggests that the probability of occurrence of severe injury crashes is higher at lighted intersections compared to unlighted intersections, which contradicts the findings obtained from the propensity scores-potential outcomes framework. This finding underscores the importance of having comparable treated and untreated entities in traffic safety countermeasure evaluations. Copyright © 2014 Elsevier Ltd. All rights reserved.

Prediction and analysis of protein solubility using a novel scoring card method with dipeptide composition

PubMed Central

2012-01-01

Background Existing methods for predicting protein solubility on overexpression in Escherichia coli advance performance by using ensemble classifiers such as two-stage support vector machine (SVM) based classifiers and a number of feature types such as physicochemical properties, amino acid and dipeptide composition, accompanied with feature selection. It is desirable to develop a simple and easily interpretable method for predicting protein solubility, compared to existing complex SVM-based methods. Results This study proposes a novel scoring card method (SCM) by using dipeptide composition only to estimate solubility scores of sequences for predicting protein solubility. SCM calculates the propensities of 400 individual dipeptides to be soluble using statistic discrimination between soluble and insoluble proteins of a training data set. Consequently, the propensity scores of all dipeptides are further optimized using an intelligent genetic algorithm. The solubility score of a sequence is determined by the weighted sum of all propensity scores and dipeptide composition. To evaluate SCM by performance comparisons, four data sets with different sizes and variation degrees of experimental conditions were used. The results show that the simple method SCM with interpretable propensities of dipeptides has promising performance, compared with existing SVM-based ensemble methods with a number of feature types. Furthermore, the propensities of dipeptides and solubility scores of sequences can provide insights to protein solubility. For example, the analysis of dipeptide scores shows high propensity of α-helix structure and thermophilic proteins to be soluble. Conclusions The propensities of individual dipeptides to be soluble are varied for proteins under altered experimental conditions. For accurately predicting protein solubility using SCM, it is better to customize the score card of dipeptide propensities by using a training data set under the same specified experimental conditions. The proposed method SCM with solubility scores and dipeptide propensities can be easily applied to the protein function prediction problems that dipeptide composition features play an important role. Availability The used datasets, source codes of SCM, and supplementary files are available at http://iclab.life.nctu.edu.tw/SCM/. PMID:23282103

Bayesian propensity scores for high-dimensional causal inference: A comparison of drug-eluting to bare-metal coronary stents.

PubMed

Spertus, Jacob V; Normand, Sharon-Lise T

2018-04-23

High-dimensional data provide many potential confounders that may bolster the plausibility of the ignorability assumption in causal inference problems. Propensity score methods are powerful causal inference tools, which are popular in health care research and are particularly useful for high-dimensional data. Recent interest has surrounded a Bayesian treatment of propensity scores in order to flexibly model the treatment assignment mechanism and summarize posterior quantities while incorporating variance from the treatment model. We discuss methods for Bayesian propensity score analysis of binary treatments, focusing on modern methods for high-dimensional Bayesian regression and the propagation of uncertainty. We introduce a novel and simple estimator for the average treatment effect that capitalizes on conjugacy of the beta and binomial distributions. Through simulations, we show the utility of horseshoe priors and Bayesian additive regression trees paired with our new estimator, while demonstrating the importance of including variance from the treatment regression model. An application to cardiac stent data with almost 500 confounders and 9000 patients illustrates approaches and facilitates comparison with existing alternatives. As measured by a falsifiability endpoint, we improved confounder adjustment compared with past observational research of the same problem. © 2018 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Channeling in the Use of Nonprescription Paracetamol and Ibuprofen in an Electronic Medical Records Database: Evidence and Implications.

PubMed

Weinstein, Rachel B; Ryan, Patrick; Berlin, Jesse A; Matcho, Amy; Schuemie, Martijn; Swerdel, Joel; Patel, Kayur; Fife, Daniel

2017-12-01

Over-the-counter analgesics such as paracetamol and ibuprofen are among the most widely used, and having a good understanding of their safety profile is important to public health. Prior observational studies estimating the risks associated with paracetamol use acknowledge the inherent limitations of these studies. One threat to the validity of observational studies is channeling bias, i.e. the notion that patients are systematically exposed to one drug or the other, based on current and past comorbidities, in a manner that affects estimated relative risk. The aim of this study was to examine whether evidence of channeling bias exists in observational studies that compare paracetamol with ibuprofen, and, if so, the extent to which confounding adjustment can mitigate this bias. In a cohort of 140,770 patients, we examined whether those who received any paracetamol (including concomitant users) were more likely to have prior diagnoses of gastrointestinal (GI) bleeding, myocardial infarction (MI), stroke, or renal disease than those who received ibuprofen alone. We compared propensity score distributions between drugs, and examined the degree to which channeling bias could be controlled using a combination of negative control disease outcome models and large-scale propensity score matching. Analyses were conducted using the Clinical Practice Research Datalink. The proportions of prior MI, GI bleeding, renal disease, and stroke were significantly higher in those prescribed any paracetamol versus ibuprofen alone, after adjusting for sex and age. We were not able to adequately remove selection bias using a selected set of covariates for propensity score adjustment; however, when we fit the propensity score model using a substantially larger number of covariates, evidence of residual bias was attenuated. Although using selected covariates for propensity score adjustment may not sufficiently reduce bias, large-scale propensity score matching offers a novel approach to consider to mitigate the effects of channeling bias.

Perceived fairness of pay among people with and without disabilities: a propensity score matched analysis of working Australians.

PubMed

Milner, Allison; Aitken, Zoe; Krnjacki, Lauren; Bentley, Rebecca; Blakely, Tony; LaMontagne, Anthony D; Kavanagh, Anne M

2015-09-01

Equity and fairness at work are associated with a range of organizational and health outcomes. Past research suggests that workers with disabilities experience inequity in the workplace. It is difficult to conclude whether the presence of disability is the reason for perceived unfair treatment due to the possible confounding of effect estimates by other demographic or socioeconomic factors. The data source was the Household, Income, and Labor Dynamics in Australia (HILDA) survey (2001-2012). Propensity for disability was calculated from logistic models including gender, age, education, country of birth, and father's occupational skill level as predictors. We then used nearest neighbor (on propensity score) matched analysis to match workers with disabilities to workers without disability. Results suggest that disability is independently associated with lower fairness of pay after controlling for confounding factors in the propensity score matched analysis; although results do suggest less than half a standard deviation difference, indicating small effects. Similar results were apparent in standard multivariable regression models and alternative propensity score analyses (stratification, covariate adjustment using the propensity score, and inverse probability of treatment weighting). Whilst neither multivariable regression nor propensity scores adjust for unmeasured confounding, and there remains the potential for other biases, similar results for the two methodological approaches to confounder adjustment provide some confidence of an independent association of disability with perceived unfairness of pay. Based on this, we suggest that the disparity in the perceived fairness of pay between people with and without disabilities may be explained by worse treatment of people with disabilities in the workplace.

An evaluation of exact matching and propensity score methods as applied in a comparative effectiveness study of inhaled corticosteroids in asthma.

PubMed

Burden, Anne; Roche, Nicolas; Miglio, Cristiana; Hillyer, Elizabeth V; Postma, Dirkje S; Herings, Ron Mc; Overbeek, Jetty A; Khalid, Javaria Mona; van Eickels, Daniela; Price, David B

2017-01-01

Cohort matching and regression modeling are used in observational studies to control for confounding factors when estimating treatment effects. Our objective was to evaluate exact matching and propensity score methods by applying them in a 1-year pre-post historical database study to investigate asthma-related outcomes by treatment. We drew on longitudinal medical record data in the PHARMO database for asthma patients prescribed the treatments to be compared (ciclesonide and fine-particle inhaled corticosteroid [ICS]). Propensity score methods that we evaluated were propensity score matching (PSM) using two different algorithms, the inverse probability of treatment weighting (IPTW), covariate adjustment using the propensity score, and propensity score stratification. We defined balance, using standardized differences, as differences of <10% between cohorts. Of 4064 eligible patients, 1382 (34%) were prescribed ciclesonide and 2682 (66%) fine-particle ICS. The IPTW and propensity score-based methods retained more patients (96%-100%) than exact matching (90%); exact matching selected less severe patients. Standardized differences were >10% for four variables in the exact-matched dataset and <10% for both PSM algorithms and the weighted pseudo-dataset used in the IPTW method. With all methods, ciclesonide was associated with better 1-year asthma-related outcomes, at one-third the prescribed dose, than fine-particle ICS; results varied slightly by method, but direction and statistical significance remained the same. We found that each method has its particular strengths, and we recommend at least two methods be applied for each matched cohort study to evaluate the robustness of the findings. Balance diagnostics should be applied with all methods to check the balance of confounders between treatment cohorts. If exact matching is used, the calculation of a propensity score could be useful to identify variables that require balancing, thereby informing the choice of matching criteria together with clinical considerations.

An evaluation of exact matching and propensity score methods as applied in a comparative effectiveness study of inhaled corticosteroids in asthma

PubMed Central

Burden, Anne; Roche, Nicolas; Miglio, Cristiana; Hillyer, Elizabeth V; Postma, Dirkje S; Herings, Ron MC; Overbeek, Jetty A; Khalid, Javaria Mona; van Eickels, Daniela; Price, David B

2017-01-01

Background Cohort matching and regression modeling are used in observational studies to control for confounding factors when estimating treatment effects. Our objective was to evaluate exact matching and propensity score methods by applying them in a 1-year pre–post historical database study to investigate asthma-related outcomes by treatment. Methods We drew on longitudinal medical record data in the PHARMO database for asthma patients prescribed the treatments to be compared (ciclesonide and fine-particle inhaled corticosteroid [ICS]). Propensity score methods that we evaluated were propensity score matching (PSM) using two different algorithms, the inverse probability of treatment weighting (IPTW), covariate adjustment using the propensity score, and propensity score stratification. We defined balance, using standardized differences, as differences of <10% between cohorts. Results Of 4064 eligible patients, 1382 (34%) were prescribed ciclesonide and 2682 (66%) fine-particle ICS. The IPTW and propensity score-based methods retained more patients (96%–100%) than exact matching (90%); exact matching selected less severe patients. Standardized differences were >10% for four variables in the exact-matched dataset and <10% for both PSM algorithms and the weighted pseudo-dataset used in the IPTW method. With all methods, ciclesonide was associated with better 1-year asthma-related outcomes, at one-third the prescribed dose, than fine-particle ICS; results varied slightly by method, but direction and statistical significance remained the same. Conclusion We found that each method has its particular strengths, and we recommend at least two methods be applied for each matched cohort study to evaluate the robustness of the findings. Balance diagnostics should be applied with all methods to check the balance of confounders between treatment cohorts. If exact matching is used, the calculation of a propensity score could be useful to identify variables that require balancing, thereby informing the choice of matching criteria together with clinical considerations. PMID:28356782

Using propensity scores in difference-in-differences models to estimate the effects of a policy change

PubMed Central

Stuart, Elizabeth A.; Huskamp, Haiden A.; Duckworth, Kenneth; Simmons, Jeffrey; Song, Zirui; Chernew, Michael; Barry, Colleen L.

2014-01-01

Difference-in-difference (DD) methods are a common strategy for evaluating the effects of policies or programs that are instituted at a particular point in time, such as the implementation of a new law. The DD method compares changes over time in a group unaffected by the policy intervention to the changes over time in a group affected by the policy intervention, and attributes the “difference-in-differences” to the effect of the policy. DD methods provide unbiased effect estimates if the trend over time would have been the same between the intervention and comparison groups in the absence of the intervention. However, a concern with DD models is that the program and intervention groups may differ in ways that would affect their trends over time, or their compositions may change over time. Propensity score methods are commonly used to handle this type of confounding in other non-experimental studies, but the particular considerations when using them in the context of a DD model have not been well investigated. In this paper, we describe the use of propensity scores in conjunction with DD models, in particular investigating a propensity score weighting strategy that weights the four groups (defined by time and intervention status) to be balanced on a set of characteristics. We discuss the conceptual issues associated with this approach, including the need for caution when selecting variables to include in the propensity score model, particularly given the multiple time point nature of the analysis. We illustrate the ideas and method with an application estimating the effects of a new payment and delivery system innovation (an accountable care organization model called the “Alternative Quality Contract” (AQC) implemented by Blue Cross Blue Shield of Massachusetts) on health plan enrollee out-of-pocket mental health service expenditures. We find no evidence that the AQC affected out-of-pocket mental health service expenditures of enrollees. PMID:25530705

The use of propensity scores to assess the generalizability of results from randomized trials

PubMed Central

Stuart, Elizabeth A.; Cole, Stephen R.; Bradshaw, Catherine P.; Leaf, Philip J.

2014-01-01

Randomized trials remain the most accepted design for estimating the effects of interventions, but they do not necessarily answer a question of primary interest: Will the program be effective in a target population in which it may be implemented? In other words, are the results generalizable? There has been very little statistical research on how to assess the generalizability, or “external validity,” of randomized trials. We propose the use of propensity-score-based metrics to quantify the similarity of the participants in a randomized trial and a target population. In this setting the propensity score model predicts participation in the randomized trial, given a set of covariates. The resulting propensity scores are used first to quantify the difference between the trial participants and the target population, and then to match, subclassify, or weight the control group outcomes to the population, assessing how well the propensity score-adjusted outcomes track the outcomes actually observed in the population. These metrics can serve as a first step in assessing the generalizability of results from randomized trials to target populations. This paper lays out these ideas, discusses the assumptions underlying the approach, and illustrates the metrics using data on the evaluation of a schoolwide prevention program called Positive Behavioral Interventions and Supports. PMID:24926156

Does non-central nervous system tuberculosis increase the risk of ischemic stroke? A population-based propensity score-matched follow-up study.

PubMed

Wu, Chueh-Hung; Chen, Li-Sheng; Yen, Ming-Fang; Chiu, Yueh-Hsia; Fann, Ching-Yuan; Chen, Hsiu-Hsi; Pan, Shin-Liang

2014-01-01

Previous studies on the association between tuberculosis and the risk of developing ischemic stroke have generated inconsistent results. We therefore performed a population-based, propensity score-matched longitudinal follow-up study to investigate whether contracting non-central nervous system (CNS) tuberculosis leads to an increased risk of ischemic stroke. We used a logistic regression model that includes age, sex, pre-existing comorbidities and socioeconomic status as covariates to compute the propensity score. A total of 5804 persons with at least three ambulatory visits in 2001 with the principal diagnosis of non-CNS tuberculosis were enrolled in the tuberculosis group. The non-tuberculosis group consisted of 5804, propensity score-matched subjects without tuberculosis. The three-year ischemic stroke-free survival rates for these 2 groups were estimated using the Kaplan-Meier method. The stratified Cox proportional hazards regression was used to estimate the effect of tuberculosis on the occurrence of ischemic stroke. During three-year follow-up, 176 subjects in the tuberculosis group (3.0%) and 207 in the non-tuberculosis group (3.6%) had ischemic stroke. The hazard ratio for developing ischemic stroke in the tuberculosis group was 0.92 compared to the non-tuberculosis group (95% confidence interval: 0.73-1.14, P = 0.4299). Non-CNS tuberculosis does not increase the risk of subsequent ischemic stroke.

A comparison of 12 algorithms for matching on the propensity score.

PubMed

Austin, Peter C

2014-03-15

Propensity-score matching is increasingly being used to reduce the confounding that can occur in observational studies examining the effects of treatments or interventions on outcomes. We used Monte Carlo simulations to examine the following algorithms for forming matched pairs of treated and untreated subjects: optimal matching, greedy nearest neighbor matching without replacement, and greedy nearest neighbor matching without replacement within specified caliper widths. For each of the latter two algorithms, we examined four different sub-algorithms defined by the order in which treated subjects were selected for matching to an untreated subject: lowest to highest propensity score, highest to lowest propensity score, best match first, and random order. We also examined matching with replacement. We found that (i) nearest neighbor matching induced the same balance in baseline covariates as did optimal matching; (ii) when at least some of the covariates were continuous, caliper matching tended to induce balance on baseline covariates that was at least as good as the other algorithms; (iii) caliper matching tended to result in estimates of treatment effect with less bias compared with optimal and nearest neighbor matching; (iv) optimal and nearest neighbor matching resulted in estimates of treatment effect with negligibly less variability than did caliper matching; (v) caliper matching had amongst the best performance when assessed using mean squared error; (vi) the order in which treated subjects were selected for matching had at most a modest effect on estimation; and (vii) matching with replacement did not have superior performance compared with caliper matching without replacement. © 2013 The Authors. Statistics in Medicine published by John Wiley & Sons, Ltd.

A comparison of 12 algorithms for matching on the propensity score

PubMed Central

Austin, Peter C

2014-01-01

Propensity-score matching is increasingly being used to reduce the confounding that can occur in observational studies examining the effects of treatments or interventions on outcomes. We used Monte Carlo simulations to examine the following algorithms for forming matched pairs of treated and untreated subjects: optimal matching, greedy nearest neighbor matching without replacement, and greedy nearest neighbor matching without replacement within specified caliper widths. For each of the latter two algorithms, we examined four different sub-algorithms defined by the order in which treated subjects were selected for matching to an untreated subject: lowest to highest propensity score, highest to lowest propensity score, best match first, and random order. We also examined matching with replacement. We found that (i) nearest neighbor matching induced the same balance in baseline covariates as did optimal matching; (ii) when at least some of the covariates were continuous, caliper matching tended to induce balance on baseline covariates that was at least as good as the other algorithms; (iii) caliper matching tended to result in estimates of treatment effect with less bias compared with optimal and nearest neighbor matching; (iv) optimal and nearest neighbor matching resulted in estimates of treatment effect with negligibly less variability than did caliper matching; (v) caliper matching had amongst the best performance when assessed using mean squared error; (vi) the order in which treated subjects were selected for matching had at most a modest effect on estimation; and (vii) matching with replacement did not have superior performance compared with caliper matching without replacement. © 2013 The Authors. Statistics in Medicine published by John Wiley & Sons, Ltd. PMID:24123228

Evaluating the effectiveness of flood damage mitigation measures by the application of Propensity Score Matching

NASA Astrophysics Data System (ADS)

Hudson, P.; Botzen, W. J. W.; Kreibich, H.; Bubeck, P.; Aerts, J. C. J. H.

2014-01-01

The employment of damage mitigation measures by individuals is an important component of integrated flood risk management. In order to promote efficient damage mitigation measures, accurate estimates of their damage mitigation potential are required. That is, for correctly assessing the damage mitigation measures' effectiveness from survey data, one needs to control for sources of bias. A biased estimate can occur if risk characteristics differ between individuals who have, or have not, implemented mitigation measures. This study removed this bias by applying an econometric evaluation technique called Propensity Score Matching to a survey of German households along along two major rivers major rivers that were flooded in 2002, 2005 and 2006. The application of this method detected substantial overestimates of mitigation measures' effectiveness if bias is not controlled for, ranging from nearly € 1700 to € 15 000 per measure. Bias-corrected effectiveness estimates of several mitigation measures show that these measures are still very effective since they prevent between € 6700-14 000 of flood damage. This study concludes with four main recommendations regarding how to better apply Propensity Score Matching in future studies, and makes several policy recommendations.

Evaluating the effectiveness of flood damage mitigation measures by the application of propensity score matching

NASA Astrophysics Data System (ADS)

Hudson, P.; Botzen, W. J. W.; Kreibich, H.; Bubeck, P.; Aerts, J. C. J. H.

2014-07-01

The employment of damage mitigation measures (DMMs) by individuals is an important component of integrated flood risk management. In order to promote efficient damage mitigation measures, accurate estimates of their damage mitigation potential are required. That is, for correctly assessing the damage mitigation measures' effectiveness from survey data, one needs to control for sources of bias. A biased estimate can occur if risk characteristics differ between individuals who have, or have not, implemented mitigation measures. This study removed this bias by applying an econometric evaluation technique called propensity score matching (PSM) to a survey of German households along three major rivers that were flooded in 2002, 2005, and 2006. The application of this method detected substantial overestimates of mitigation measures' effectiveness if bias is not controlled for, ranging from nearly EUR 1700 to 15 000 per measure. Bias-corrected effectiveness estimates of several mitigation measures show that these measures are still very effective since they prevent between EUR 6700 and 14 000 of flood damage per flood event. This study concludes with four main recommendations regarding how to better apply propensity score matching in future studies, and makes several policy recommendations.

Impact of an entertainment-education television drama on health knowledge and behavior in Bangladesh: an application of propensity score matching.

PubMed

Do, Mai P; Kincaid, D Lawrence

2006-01-01

Shabuj Chaya is a weekly television drama broadcast during a 13-week period in Bangladesh in 2000. It used an entertainment-education format to increase health knowledge and to promote visits to health clinic and modern contraceptive use. The purpose of this article is to demonstrate how a relatively new statistical technique, propensity score matching in conjunction with structural equation modeling, can be used to obtain an unbiased estimate of changes in health outcomes that can be attributed to exposure to the drama. The analysis is conducted with data from an after-only, cross-sectional survey of 4,492 men and women from the intended audience. The results from propensity score matching approximate what would be expected from a randomized control group design.

Myopia and cognitive dysfunction among elderly Chinese adults: a propensity score matching analysis.

PubMed

Sun, Hong-Peng; Liu, Hu; Xu, Yong; Pan, Chen-Wei

2016-03-01

The association between myopia and cognitive dysfunction among elderly adults was assessed by applying a Propensity Score Matching (PSM) approach. This is a statistical method which allows investigators to estimate causal treatment effects using observational or nonrandomised data. The study was designed as a community-based cross-sectional study based on a Chinese cohort aged 60 years or older in China. Objective refraction was measured using an autorefractor and subjective refraction was used to refine vision, using the results of the objective refraction as the starting point. Myopia was defined as a spherical equivalent value of less than -0.50 dioptre (D) in the right eye. The Abbreviated Mental Test (AMT) was used for cognitive assessment. The propensity scores for myopia were formulated using 13 potential confounders. We matched the propensity scores for subjects with and without myopia within a caliper of 0.01 of logit function of propensity scores. About 4123 elderly adults who successfully completed the AMT were included in this analysis. The odds ratio (OR) of cognitive dysfunction for myopia before matching was 1.98 (95% confidence interval [CI] 1.61, 2.44; p < 0.001). There were significant covariate imbalances between comparison groups and after propensity score matching, covariate imbalance was significantly reduced. After propensity score matching, the OR of cognitive dysfunction was marginally significant and the magnitude of association was reduced (OR: 1.31 95% CI 1.00, 1.71; p = 0.05). Traditional multivariate logistic regression modelling found an OR of 1.52 (95% CI 1.23, 2.06; p < 0.001) after adjusting for the 13 potential confounders. Myopia was associated with a higher prevalence of cognitive dysfunction among elderly Chinese aged 60 years or older in China. The PSM approach may be a useful method to address selection bias in observational studies when randomised trials cannot ethically be conducted. © 2015 The Authors Ophthalmic & Physiological Optics © 2015 The College of Optometrists.

Propensity score matching with clustered data. An application to the estimation of the impact of caesarean section on the Apgar score.

PubMed

Arpino, Bruno; Cannas, Massimo

2016-05-30

This article focuses on the implementation of propensity score matching for clustered data. Different approaches to reduce bias due to cluster-level confounders are considered and compared using Monte Carlo simulations. We investigated methods that exploit the clustered structure of the data in two ways: in the estimation of the propensity score model (through the inclusion of fixed or random effects) or in the implementation of the matching algorithm. In addition to a pure within-cluster matching, we also assessed the performance of a new approach, 'preferential' within-cluster matching. This approach first searches for control units to be matched to treated units within the same cluster. If matching is not possible within-cluster, then the algorithm searches in other clusters. All considered approaches successfully reduced the bias due to the omission of a cluster-level confounder. The preferential within-cluster matching approach, combining the advantages of within-cluster and between-cluster matching, showed a relatively good performance both in the presence of big and small clusters, and it was often the best method. An important advantage of this approach is that it reduces the number of unmatched units as compared with a pure within-cluster matching. We applied these methods to the estimation of the effect of caesarean section on the Apgar score using birth register data. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

Taking the Missing Propensity Into Account When Estimating Competence Scores

PubMed Central

Pohl, Steffi; Carstensen, Claus H.

2014-01-01

When competence tests are administered, subjects frequently omit items. These missing responses pose a threat to correctly estimating the proficiency level. Newer model-based approaches aim to take nonignorable missing data processes into account by incorporating a latent missing propensity into the measurement model. Two assumptions are typically made when using these models: (1) The missing propensity is unidimensional and (2) the missing propensity and the ability are bivariate normally distributed. These assumptions may, however, be violated in real data sets and could, thus, pose a threat to the validity of this approach. The present study focuses on modeling competencies in various domains, using data from a school sample (N = 15,396) and an adult sample (N = 7,256) from the National Educational Panel Study. Our interest was to investigate whether violations of unidimensionality and the normal distribution assumption severely affect the performance of the model-based approach in terms of differences in ability estimates. We propose a model with a competence dimension, a unidimensional missing propensity and a distributional assumption more flexible than a multivariate normal. Using this model for ability estimation results in different ability estimates compared with a model ignoring missing responses. Implications for ability estimation in large-scale assessments are discussed. PMID:29795844

Estimating the palliative effect of percutaneous endoscopic gastrostomy in an observational registry using principal stratification and generalized propensity scores

PubMed Central

Mishra-Kalyani, Pallavi S.; Johnson, Brent A.; Glass, Jonathan D.; Long, Qi

2016-01-01

Clinical disease registries offer a rich collection of valuable patient information but also pose challenges that require special care and attention in statistical analyses. The goal of this paper is to propose a statistical framework that allows for estimating the effect of surgical insertion of a percutaneous endogastrostomy (PEG) tube for patients living with amyotrophic lateral sclerosis (ALS) using data from a clinical registry. Although all ALS patients are informed about PEG, only some patients agree to the procedure which, leads to the potential for selection bias. Assessing the effect of PEG is further complicated by the aggressively fatal disease, such that time to death competes directly with both the opportunity to receive PEG and clinical outcome measurements. Our proposed methodology handles the “censoring by death” phenomenon through principal stratification and selection bias for PEG treatment through generalized propensity scores. We develop a fully Bayesian modeling approach to estimate the survivor average causal effect (SACE) of PEG on BMI, a surrogate outcome measure of nutrition and quality of life. The use of propensity score methods within the principal stratification framework demonstrates a significant and positive effect of PEG treatment, particularly when time of treatment is included in the treatment definition. PMID:27640365

Estimating the palliative effect of percutaneous endoscopic gastrostomy in an observational registry using principal stratification and generalized propensity scores

NASA Astrophysics Data System (ADS)

Mishra-Kalyani, Pallavi S.; Johnson, Brent A.; Glass, Jonathan D.; Long, Qi

2016-09-01

Clinical disease registries offer a rich collection of valuable patient information but also pose challenges that require special care and attention in statistical analyses. The goal of this paper is to propose a statistical framework that allows for estimating the effect of surgical insertion of a percutaneous endogastrostomy (PEG) tube for patients living with amyotrophic lateral sclerosis (ALS) using data from a clinical registry. Although all ALS patients are informed about PEG, only some patients agree to the procedure which, leads to the potential for selection bias. Assessing the effect of PEG is further complicated by the aggressively fatal disease, such that time to death competes directly with both the opportunity to receive PEG and clinical outcome measurements. Our proposed methodology handles the “censoring by death” phenomenon through principal stratification and selection bias for PEG treatment through generalized propensity scores. We develop a fully Bayesian modeling approach to estimate the survivor average causal effect (SACE) of PEG on BMI, a surrogate outcome measure of nutrition and quality of life. The use of propensity score methods within the principal stratification framework demonstrates a significant and positive effect of PEG treatment, particularly when time of treatment is included in the treatment definition.

Evaluating uses of data mining techniques in propensity score estimation: a simulation study.

PubMed

Setoguchi, Soko; Schneeweiss, Sebastian; Brookhart, M Alan; Glynn, Robert J; Cook, E Francis

2008-06-01

In propensity score modeling, it is a standard practice to optimize the prediction of exposure status based on the covariate information. In a simulation study, we examined in what situations analyses based on various types of exposure propensity score (EPS) models using data mining techniques such as recursive partitioning (RP) and neural networks (NN) produce unbiased and/or efficient results. We simulated data for a hypothetical cohort study (n = 2000) with a binary exposure/outcome and 10 binary/continuous covariates with seven scenarios differing by non-linear and/or non-additive associations between exposure and covariates. EPS models used logistic regression (LR) (all possible main effects), RP1 (without pruning), RP2 (with pruning), and NN. We calculated c-statistics (C), standard errors (SE), and bias of exposure-effect estimates from outcome models for the PS-matched dataset. Data mining techniques yielded higher C than LR (mean: NN, 0.86; RPI, 0.79; RP2, 0.72; and LR, 0.76). SE tended to be greater in models with higher C. Overall bias was small for each strategy, although NN estimates tended to be the least biased. C was not correlated with the magnitude of bias (correlation coefficient [COR] = -0.3, p = 0.1) but increased SE (COR = 0.7, p < 0.001). Effect estimates from EPS models by simple LR were generally robust. NN models generally provided the least numerically biased estimates. C was not associated with the magnitude of bias but was with the increased SE.

An examination of the effects of mountaintop removal coal mining on respiratory symptoms and COPD using propensity scores.

PubMed

Hendryx, Michael; Luo, Juhua

2015-01-01

Previous research on public health consequences of mountaintop removal (MTR) coal mining has been limited by the observational nature of the data. The current study used propensity scores, a method designed to overcome this limitation, to draw more confident causal inferences about mining effects on respiratory health using non-experimental data. These data come from a health survey of 682 adults residing in two rural areas of Virginia, USA characterized by the presence or absence of MTR mining. Persons with a history of occupational exposure as coal miners were excluded. Nine covariates including age, sex, current and former smoking, overweight, obesity, high school education, college education, and exposure to coal as a home-heating source were selected to estimate propensity scores. Propensity scores were tested for balance and then used as weights to create quasi-experimental exposed and unexposed groups. Results indicated that persons in the mountaintop mining group had significantly (p < 0.0001) elevated prevalence of respiratory symptoms and chronic obstructive pulmonary disease. The results suggest that impaired respiratory health results from exposure to MTR environments and not from other risks.

Propensity Scores in Pharmacoepidemiology: Beyond the Horizon.

PubMed

Jackson, John W; Schmid, Ian; Stuart, Elizabeth A

2017-12-01

Propensity score methods have become commonplace in pharmacoepidemiology over the past decade. Their adoption has confronted formidable obstacles that arise from pharmacoepidemiology's reliance on large healthcare databases of considerable heterogeneity and complexity. These include identifying clinically meaningful samples, defining treatment comparisons, and measuring covariates in ways that respect sound epidemiologic study design. Additional complexities involve correctly modeling treatment decisions in the face of variation in healthcare practice, and dealing with missing information and unmeasured confounding. In this review, we examine the application of propensity score methods in pharmacoepidemiology with particular attention to these and other issues, with an eye towards standards of practice, recent methodological advances, and opportunities for future progress. Propensity score methods have matured in ways that can advance comparative effectiveness and safety research in pharmacoepidemiology. These include natural extensions for categorical treatments, matching algorithms that can optimize sample size given design constraints, weighting estimators that asymptotically target matched and overlap samples, and the incorporation of machine learning to aid in covariate selection and model building. These recent and encouraging advances should be further evaluated through simulation and empirical studies, but nonetheless represent a bright path ahead for the observational study of treatment benefits and harms.

Self-reported hand washing behaviors and foodborne illness: a propensity score matching approach.

PubMed

Ali, Mir M; Verrill, Linda; Zhang, Yuanting

2014-03-01

Hand washing is a simple and effective but easily overlooked way to reduce cross-contamination and the transmission of foodborne pathogens. In this study, we used the propensity score matching methodology to account for potential selection bias to explore our hypothesis that always washing hands before food preparation tasks is associated with a reduction in the probability of reported foodborne illness. Propensity score matching can simulate random assignment to a condition so that pretreatment observable differences between a treatment group and a control group are homogenous on all the covariates except the treatment variable. Using the U.S. Food and Drug Administration's 2010 Food Safety Survey, we estimated the effect of self-reported hand washing behavior on the probability of self-reported foodborne illness. Our results indicate that reported washing of hands with soap always before food preparation leads to a reduction in the probability of reported foodborne illness.

Something from nothing: Estimating consumption rates using propensity scores, with application to emissions reduction policies

PubMed Central

Büchs, Milena; Schnepf, Sylke V.

2017-01-01

Consumption surveys often record zero purchases of a good because of a short observation window. Measures of distribution are then precluded and only mean consumption rates can be inferred. We show that Propensity Score Matching can be applied to recover the distribution of consumption rates. We demonstrate the method using the UK National Travel Survey, in which c.40% of motorist households purchase no fuel. Estimated consumption rates are plausible judging by households’ annual mileages, and highly skewed. We apply the same approach to estimate CO2 emissions and outcomes of a carbon cap or tax. Reliance on means apparently distorts analysis of such policies because of skewness of the underlying distributions. The regressiveness of a simple tax or cap is overstated, and redistributive features of a revenue-neutral policy are understated. PMID:29020029

Right mini-parasternotomy may be a good minimally invasive alternative to full sternotomy for cardiac valve operations-a propensity-adjusted analysis.

PubMed

Chiu, K M; Chen, R J; Lin, T Y; Chen, J S; Huang, J H; Huang, C Y; Chu, S H

2014-03-26

Limited realworld data existed for miniparasternotomy approach with good sample size in Asian cohorts and most previous studies were eclipsed by case heterogeneity. The goal of this study was to compare safety and quality outcomes of cardiac noncoronary valve operations by miniparasternotomy and full sternotomy approaches on riskadjusted basis. From our hospital database, we retrieved the cases of non-coronary valve operations from 1 January 2005 to 31 December 2012, including re-do, emergent, and combined procedures. Estimated EuroScore-II and propensity score for choosing mini-parasternotomy were adjusted for in the regression models on hospital mortality, complications (pneumonia, stroke, sepsis, etc.), and quality parameters (length of stay, ICU time, ventilator time, etc.). Non-complicated cases, defined as survival to discharge, ventilator use not over one week, and intensive care unit stay not over two weeks, were used for quality parameters. There were 283 miniparasternotomy and 177 full sternotomy cases. EuroScore-II differed significantly (medians 2.1 vs. 4.7, p<0.001). Propensity scores for choosing miniparasternotomy were higher with lower EuroScore-II (OR=0.91 per 1%, p<0.001), aortic regurgitation (OR=2.3, p=0.005), and aortic non-mitral valve disease (OR=3.9, p<0.001). Adjusted for propensity score and EuroScore-II, mini-parasternotomy group had less pneumonia (OR=0.32, p=0.043), less sepsis (OR=0.31, p=0.045), and shorter non-complicated length of stay (coefficient=7.2 (day), p<0.001) than full sternotomy group, whereas Kaplan-Meier survival, non-complicated ICU time, non-complicated ventilator time, and 30-day mortality did not differ significantly. The propensity-adjusted analysis demonstrated encouraging safety and quality outcomes for mini-parasternotomy valve operation in carefully selected patients.

Propensity score matching of the gymnastics for diabetes mellitus using logistic regression

NASA Astrophysics Data System (ADS)

Otok, Bambang Widjanarko; Aisyah, Amalia; Purhadi, Andari, Shofi

2017-12-01

Diabetes Mellitus (DM) is a group of metabolic diseases with characteristics shows an abnormal blood glucose level occurring due to pancreatic insulin deficiency, decreased insulin effectiveness or both. The report from the ministry of health shows that DMs prevalence data of East Java province is 2.1%, while the DMs prevalence of Indonesia is only 1,5%. Given the high cases of DM in East Java, it needs the preventive action to control factors causing the complication of DM. This study aims to determine the combination factors causing the complication of DM to reduce the bias by confounding variables using Propensity Score Matching (PSM) with the method of propensity score estimation is binary logistic regression. The data used in this study is the medical record from As-Shafa clinic consisting of 6 covariates and health complication as response variable. The result of PSM analysis showed that there are 22 of 126 DMs patients attending gymnastics paired with patients who didnt attend to diabetes gymnastics. The Average Treatment of Treated (ATT) estimation results showed that the more patients who didnt attend to gymnastics, the more likely the risk for the patients having DMs complications.

Survival analysis using inverse probability of treatment weighted methods based on the generalized propensity score.

PubMed

Sugihara, Masahiro

2010-01-01

In survival analysis, treatment effects are commonly evaluated based on survival curves and hazard ratios as causal treatment effects. In observational studies, these estimates may be biased due to confounding factors. The inverse probability of treatment weighted (IPTW) method based on the propensity score is one of the approaches utilized to adjust for confounding factors between binary treatment groups. As a generalization of this methodology, we developed an exact formula for an IPTW log-rank test based on the generalized propensity score for survival data. This makes it possible to compare the group differences of IPTW Kaplan-Meier estimators of survival curves using an IPTW log-rank test for multi-valued treatments. As causal treatment effects, the hazard ratio can be estimated using the IPTW approach. If the treatments correspond to ordered levels of a treatment, the proposed method can be easily extended to the analysis of treatment effect patterns with contrast statistics. In this paper, the proposed method is illustrated with data from the Kyushu Lipid Intervention Study (KLIS), which investigated the primary preventive effects of pravastatin on coronary heart disease (CHD). The results of the proposed method suggested that pravastatin treatment reduces the risk of CHD and that compliance to pravastatin treatment is important for the prevention of CHD. (c) 2009 John Wiley & Sons, Ltd.

Best (but oft-forgotten) practices: propensity score methods in clinical nutrition research.

PubMed

Ali, M Sanni; Groenwold, Rolf Hh; Klungel, Olaf H

2016-08-01

In observational studies, treatment assignment is a nonrandom process and treatment groups may not be comparable in their baseline characteristics, a phenomenon known as confounding. Propensity score (PS) methods can be used to achieve comparability of treated and nontreated groups in terms of their observed covariates and, as such, control for confounding in estimating treatment effects. In this article, we provide a step-by-step guidance on how to use PS methods. For illustrative purposes, we used simulated data based on an observational study of the relation between oral nutritional supplementation and hospital length of stay. We focused on the key aspects of PS analysis, including covariate selection, PS estimation, covariate balance assessment, treatment effect estimation, and reporting. PS matching, stratification, covariate adjustment, and weighting are discussed. R codes and example data are provided to show the different steps in a PS analysis. © 2016 American Society for Nutrition.

Applying Propensity Score Methods in Medical Research: Pitfalls and Prospects

PubMed Central

Luo, Zhehui; Gardiner, Joseph C.; Bradley, Cathy J.

2012-01-01

The authors review experimental and nonexperimental causal inference methods, focusing on assumptions for the validity of instrumental variables and propensity score (PS) methods. They provide guidance in four areas for the analysis and reporting of PS methods in medical research and selectively evaluate mainstream medical journal articles from 2000 to 2005 in the four areas, namely, examination of balance, overlapping support description, use of estimated PS for evaluation of treatment effect, and sensitivity analyses. In spite of the many pitfalls, when appropriately evaluated and applied, PS methods can be powerful tools in assessing average treatment effects in observational studies. Appropriate PS applications can create experimental conditions using observational data when randomized controlled trials are not feasible and, thus, lead researchers to an efficient estimator of the average treatment effect. PMID:20442340

A Review of Propensity-Score Methods and Their Use in Cardiovascular Research.

PubMed

Deb, Saswata; Austin, Peter C; Tu, Jack V; Ko, Dennis T; Mazer, C David; Kiss, Alex; Fremes, Stephen E

2016-02-01

Observational studies using propensity-score methods have been increasing in the cardiovascular literature because randomized controlled trials are not always feasible or ethical. However, propensity-score methods can be confusing, and the general audience may not fully understand the importance of this technique. The objectives of this review are to describe (1) the fundamentals of propensity score methods, (2) the techniques to assess for propensity-score model adequacy, (3) the 4 major methods for using the propensity score (matching, stratification, covariate adjustment, and inverse probability of treatment weighting [IPTW]) using examples from previously published cardiovascular studies, and (4) the strengths and weaknesses of these 4 techniques. Our review suggests that matching or IPTW using the propensity score have shown to be most effective in reducing bias of the treatment effect. Copyright © 2016 Canadian Cardiovascular Society. Published by Elsevier Inc. All rights reserved.

Using School Scholarships to Estimate the Effect of Private Education on the Academic Achievement of Low-Income Students in Chile

ERIC Educational Resources Information Center

Anand, Priyanka; Mizala, Alejandra; Repetto, Andrea

2009-01-01

This paper estimates the impact of private education on the academic achievement of low-income students in Chile. To deal with selection bias, we use propensity score matching to compare the test scores of reduced-fee paying, low-income students in fee-charging private voucher schools to those of similar students in public schools and free private…

An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies

ERIC Educational Resources Information Center

Austin, Peter C.

2011-01-01

The propensity score is the probability of treatment assignment conditional on observed baseline characteristics. The propensity score allows one to design and analyze an observational (nonrandomized) study so that it mimics some of the particular characteristics of a randomized controlled trial. In particular, the propensity score is a balancing…

Associations between Depressive State and Impaired Higher-Level Functional Capacity in the Elderly with Long-Term Care Requirements.

PubMed

Ogata, Soshiro; Hayashi, Chisato; Sugiura, Keiko; Hayakawa, Kazuo

2015-01-01

Depressive state has been reported to be significantly associated with higher-level functional capacity among community-dwelling elderly. However, few studies have investigated the associations among people with long-term care requirements. We aimed to investigate the associations between depressive state and higher-level functional capacity and obtain marginal odds ratios using propensity score analyses in people with long-term care requirements. We conducted a cross-sectional study based on participants aged ≥ 65 years (n = 545) who were community dwelling and used outpatient care services for long-term preventive care. We measured higher-level functional capacity, depressive state, and possible confounders. Then, we estimated the marginal odds ratios (i.e., the change in odds of impaired higher-level functional capacity if all versus no participants were exposed to depressive state) by logistic models using generalized linear models with the inverse probability of treatment weighting (IPTW) for propensity score and design-based standard errors. Depressive state was used as the exposure variable and higher-level functional capacity as the outcome variable. The all absolute standardized differences after the IPTW using the propensity scores were < 10% which indicated negligible differences in the mean or prevalence of the covariates between non-depressive state and depressive state. The marginal odds ratios were estimated by the logistic models with IPTW using the propensity scores. The marginal odds ratios were 2.17 (95%CI: 1.13-4.19) for men and 2.57 (95%CI: 1.26-5.26) for women. Prevention of depressive state may contribute to not only depressive state but also higher-level functional capacity.

Incremental cost of nosocomial bacteremia according to the focus of infection and antibiotic sensitivity of the causative microorganism in a university hospital.

PubMed

Riu, Marta; Chiarello, Pietro; Terradas, Roser; Sala, Maria; Garcia-Alzorriz, Enric; Castells, Xavier; Grau, Santiago; Cots, Francesc

2017-04-01

To estimate the incremental cost of nosocomial bacteremia according to the causative focus and classified by the antibiotic sensitivity of the microorganism.Patients admitted to Hospital del Mar in Barcelona from 2005 to 2012 were included. We analyzed the total hospital costs of patients with nosocomial bacteremia caused by microorganisms with a high prevalence and, often, with multidrug-resistance. A control group was defined by selecting patients without bacteremia in the same diagnosis-related group.Our hospital has a cost accounting system (full-costing) that uses activity-based criteria to estimate per-patient costs. A logistic regression was fitted to estimate the probability of developing bacteremia (propensity score) and was used for propensity-score matching adjustment. This propensity score was included in an econometric model to adjust the incremental cost of patients with bacteremia with differentiation of the causative focus and antibiotic sensitivity.The mean incremental cost was estimated at &OV0556;15,526. The lowest incremental cost corresponded to bacteremia caused by multidrug-sensitive urinary infection (&OV0556;6786) and the highest to primary or unknown sources of bacteremia caused by multidrug-resistant microorganisms (&OV0556;29,186).This is one of the first analyses to include all episodes of bacteremia produced during hospital stays in a single study. The study included accurate information about the focus and antibiotic sensitivity of the causative organism and actual hospital costs. It provides information that could be useful to improve, establish, and prioritize prevention strategies for nosocomial infections.

Estimating Effects with Rare Outcomes and High Dimensional Covariates: Knowledge is Power

PubMed Central

Ahern, Jennifer; Galea, Sandro; van der Laan, Mark

2016-01-01

Many of the secondary outcomes in observational studies and randomized trials are rare. Methods for estimating causal effects and associations with rare outcomes, however, are limited, and this represents a missed opportunity for investigation. In this article, we construct a new targeted minimum loss-based estimator (TMLE) for the effect or association of an exposure on a rare outcome. We focus on the causal risk difference and statistical models incorporating bounds on the conditional mean of the outcome, given the exposure and measured confounders. By construction, the proposed estimator constrains the predicted outcomes to respect this model knowledge. Theoretically, this bounding provides stability and power to estimate the exposure effect. In finite sample simulations, the proposed estimator performed as well, if not better, than alternative estimators, including a propensity score matching estimator, inverse probability of treatment weighted (IPTW) estimator, augmented-IPTW and the standard TMLE algorithm. The new estimator yielded consistent estimates if either the conditional mean outcome or the propensity score was consistently estimated. As a substitution estimator, TMLE guaranteed the point estimates were within the parameter range. We applied the estimator to investigate the association between permissive neighborhood drunkenness norms and alcohol use disorder. Our results highlight the potential for double robust, semiparametric efficient estimation with rare events and high dimensional covariates. PMID:28529839

Sequential Neighborhood Effects: The Effect of Long-Term Exposure to Concentrated Disadvantage on Children's Reading and Math Test Scores.

PubMed

Hicks, Andrew L; Handcock, Mark S; Sastry, Narayan; Pebley, Anne R

2018-02-01

Prior research has suggested that children living in a disadvantaged neighborhood have lower achievement test scores, but these studies typically have not estimated causal effects that account for neighborhood choice. Recent studies used propensity score methods to account for the endogeneity of neighborhood exposures, comparing disadvantaged and nondisadvantaged neighborhoods. We develop an alternative propensity function approach in which cumulative neighborhood effects are modeled as a continuous treatment variable. This approach offers several advantages. We use our approach to examine the cumulative effects of neighborhood disadvantage on reading and math test scores in Los Angeles. Our substantive results indicate that recency of exposure to disadvantaged neighborhoods may be more important than average exposure for children's test scores. We conclude that studies of child development should consider both average cumulative neighborhood exposure and the timing of this exposure.

Sequential Neighborhood Effects: The Effect of Long-Term Exposure to Concentrated Disadvantage on Children's Reading and Math Test Scores

PubMed Central

Hicks, Andrew L.; Handcock, Mark S.; Sastry, Narayan

2018-01-01

Prior research has suggested that children living in a disadvantaged neighborhood have lower achievement test scores, but these studies typically have not estimated causal effects that account for neighborhood choice. Recent studies used propensity score methods to account for the endogeneity of neighborhood exposures, comparing disadvantaged and nondisadvantaged neighborhoods. We develop an alternative propensity function approach in which cumulative neighborhood effects are modeled as a continuous treatment variable. This approach offers several advantages. We use our approach to examine the cumulative effects of neighborhood disadvantage on reading and math test scores in Los Angeles. Our substantive results indicate that recency of exposure to disadvantaged neighborhoods may be more important than average exposure for children's test scores. We conclude that studies of child development should consider both average cumulative neighborhood exposure and the timing of this exposure. PMID:29192386

Measuring the impact of Hurricane Katrina on access to a personal healthcare provider: the use of the National Survey of Children's Health for an external comparison group.

PubMed

Stehling-Ariza, Tasha; Park, Yoon Soo; Sury, Jonathan J; Abramson, David

2012-04-01

This paper examined the effect of Hurricane Katrina on children's access to personal healthcare providers and evaluated the use of propensity score methods to compare a nationally representative sample of children, as a proxy for an unexposed group, with a smaller exposed sample. 2007 data from the Gulf Coast Child and Family Health (G-CAFH) Study, a longitudinal cohort of households displaced or greatly impacted by Hurricane Katrina, were matched with 2007 National Survey of Children's Health (NSCH) data using propensity score techniques. Propensity scores were created using poverty level, household educational attainment, and race/ethnicity, with and without the addition of child age and gender. The outcome was defined as having a personal healthcare provider. Additional confounders (household structure, neighborhood safety, health and insurance status) were also examined. All covariates except gender differed significantly between the exposed (G-CAFH) and unexposed (NSCH) samples. Fewer G-CAFH children had a personal healthcare provider (65 %) compared to those from NSCH (90 %). Adjusting for all covariates, the propensity score analysis showed exposed children were 20 % less likely to have a personal healthcare provider compared to unexposed children in the US (OR = 0.80, 95 % CI 0.76, 0.84), whereas the logistic regression analysis estimated a stronger effect (OR = 0.28, 95 % CI 0.21, 0.39). Two years after Hurricane Katrina, children exposed to the storm had significantly lower odds of having a personal health care provider compared to unexposed children. Propensity score matching techniques may be useful for combining separate data samples when no clear unexposed group exists.

Comparison between treatment effects in a randomised controlled trial and an observational study using propensity scores in primary care.

PubMed

Stuart, Beth L; Grebel, Louise En; Butler, Christopher C; Hood, Kerenza; Verheij, Theo J M; Little, Paul

2017-09-01

Although randomised controlled trials (RCTs) are considered 'gold standard' evidence, they are not always feasible or appropriate, and may represent a select population. Observational studies provide a useful alternative to enhance applicability, but results can be biased due to confounding. To explore the utility of propensity scores for causal inference in an observational study. Comparison of the effect of amoxicillin on key outcomes in an international RCT and observational study of lower respiratory tract infections. Propensity scores were calculated and applied as probability weights in the analyses. The adjusted results were compared with the effects reported in the RCT. Groups were well balanced in the RCT but significantly imbalanced in the observational study, with evidence of confounding by indication: patients receiving antibiotics tended to be older and more unwell at baseline consultation. In the trial duration of symptoms (hazard ratio 1.06, 95% CI = 0.96 to 1.18) and symptom severity (-0.07, 95% CI = -0.15 to 0.007) did not differ between groups. Weighting by propensity score in the observational study resulted in very similar estimates of effect: duration of symptoms (hazard ratio 1.06, 95% CI = 0.80 to 1.40) and difference for symptom severity (-0.07, 95% CI = -0.34 to 0.20). The observational study, after conditioning on propensity score, echoed the trial results. Provided that detailed information is available on potential sources of confounding, effects of interventions can probably be assessed reasonably well in observational datasets, allowing them to be more directly compared with the results of RCTs. © British Journal of General Practice 2017.

Right miniparasternotomy may be a good minimally invasive alternative to full sternotomy for cardiac valve operations: a propensity-adjusted analysis.

PubMed

Chiu, Kuan M; Chen, Robert J; Lin, Tzu Y; Chen, Jer S; Huang, Jin H; Huang, Chun Y; Chu, Shu H

2016-02-01

Limited real-world data existed for mini-parasternotomy approach with good sample size in Asian cohorts and most previous studies were eclipsed by case heterogeneity. The goal of this study was to compare safety and quality outcomes of cardiac non-coronary valve operations by mini-parasternotomy and full sternotomy approaches on risk-adjusted basis. METHODS From our hospital database, we retrieved the cases of non-coronary valve operations from 1 January 2005 to 31 December 2012, including re-do, emergent, and combined procedures. Estimated EuroScore-II and propensity score for choosing mini-parasternotomy were adjusted for in the regression models on hospital mortality, complications (pneumonia, stroke, sepsis, etc.), and quality parameters (length of stay, ICU time, ventilator time, etc.). Non-complicated cases, defined as survival to discharge, ventilator use not over one week, and intensive care unit stay not over two weeks, were used for quality parameters. There were 283 mini-parasternotomy and 177 full sternotomy cases. EuroScore-II differed significantly (medians 2.1 vs. 4.7, P<0.001). Propensity scores for choosing mini-parasternotomy were higher with lower EuroScore-II (OR=0.91 per 1%, P<0.001), aortic regurgitation (OR=2.3, P=0.005), and aortic non-mitral valve disease (OR=3.9, P<0.001). Adjusted for propensity score and EuroScore-II, mini-parasternotomy group had less pneumonia (OR=0.32, P=0.043), less sepsis (OR=0.31, P=0.045), and shorter non-complicated length of stay (coefficient=-7.2 (day), P<0.001) than full sternotomy group, whereas Kaplan-Meier survival, non-complicated ICU time, non-complicated ventilator time, and 30-day mortality did not differ significantly. The propensity-adjusted analysis demonstrated encouraging safety and quality outcomes for mini-parasternotomy valve operation in carefully selected patients.

Metrics for covariate balance in cohort studies of causal effects.

PubMed

Franklin, Jessica M; Rassen, Jeremy A; Ackermann, Diana; Bartels, Dorothee B; Schneeweiss, Sebastian

2014-05-10

Inferring causation from non-randomized studies of exposure requires that exposure groups can be balanced with respect to prognostic factors for the outcome. Although there is broad agreement in the literature that balance should be checked, there is confusion regarding the appropriate metric. We present a simulation study that compares several balance metrics with respect to the strength of their association with bias in estimation of the effect of a binary exposure on a binary, count, or continuous outcome. The simulations utilize matching on the propensity score with successively decreasing calipers to produce datasets with varying covariate balance. We propose the post-matching C-statistic as a balance metric and found that it had consistently strong associations with estimation bias, even when the propensity score model was misspecified, as long as the propensity score was estimated with sufficient study size. This metric, along with the average standardized difference and the general weighted difference, outperformed all other metrics considered in association with bias, including the unstandardized absolute difference, Kolmogorov-Smirnov and Lévy distances, overlapping coefficient, Mahalanobis balance, and L1 metrics. Of the best-performing metrics, the C-statistic and general weighted difference also have the advantage that they automatically evaluate balance on all covariates simultaneously and can easily incorporate balance on interactions among covariates. Therefore, when combined with the usual practice of comparing individual covariate means and standard deviations across exposure groups, these metrics may provide useful summaries of the observed covariate imbalance. Copyright © 2013 John Wiley & Sons, Ltd.

An alternative empirical likelihood method in missing response problems and causal inference.

PubMed

Ren, Kaili; Drummond, Christopher A; Brewster, Pamela S; Haller, Steven T; Tian, Jiang; Cooper, Christopher J; Zhang, Biao

2016-11-30

Missing responses are common problems in medical, social, and economic studies. When responses are missing at random, a complete case data analysis may result in biases. A popular debias method is inverse probability weighting proposed by Horvitz and Thompson. To improve efficiency, Robins et al. proposed an augmented inverse probability weighting method. The augmented inverse probability weighting estimator has a double-robustness property and achieves the semiparametric efficiency lower bound when the regression model and propensity score model are both correctly specified. In this paper, we introduce an empirical likelihood-based estimator as an alternative to Qin and Zhang (2007). Our proposed estimator is also doubly robust and locally efficient. Simulation results show that the proposed estimator has better performance when the propensity score is correctly modeled. Moreover, the proposed method can be applied in the estimation of average treatment effect in observational causal inferences. Finally, we apply our method to an observational study of smoking, using data from the Cardiovascular Outcomes in Renal Atherosclerotic Lesions clinical trial. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

Propensity Score Weighting with Error-Prone Covariates

ERIC Educational Resources Information Center

McCaffrey, Daniel F.; Lockwood, J. R.; Setodji, Claude M.

2011-01-01

Inverse probability weighting (IPW) estimates are widely used in applications where data are missing due to nonresponse or censoring or in observational studies of causal effects where the counterfactuals cannot be observed. This extensive literature has shown the estimators to be consistent and asymptotically normal under very general conditions,…

Outcome of Early Initiation of Peritoneal Dialysis in Patients with End-Stage Renal Failure

PubMed Central

Oh, Kook-Hwan; Hwang, Young-Hwan; Cho, Jung-Hwa; Kim, Mira; Ju, Kyung Don; Joo, Kwon Wook; Kim, Dong Ki; Kim, Yon Su; Ahn, Curie

2012-01-01

Recent studies reported that early initiation of hemodialysis may increase mortality. However, studies that assessed the influence of early initiation of peritoneal dialysis (PD) yielded controversial results. In the present study, we evaluated the prognosis of early initiation of PD on the various outcomes of end stage renal failure patients by using propensity-score matching methods. Incident PD patients (n = 491) who started PD at SNU Hospital were enrolled. The patients were divided into 'early starters (n = 244)' and 'late starters (n = 247)' on the basis of the estimated glomerular filtration rate (eGFR) at the start of dialysis. The calculated propensity-score was used for one-to-one matching. After propensity-score-based matching (n = 136, for each group), no significant differences were observed in terms of all-cause mortality (P = 0.17), technique failure (P = 0.62), cardiovascular event (P = 0.96) and composite event (P = 0.86) between the early and late starters. Stratification analysis in the propensity-score quartiles (n = 491) exhibited no trend toward better or poorer survival in terms of all-cause mortality. In conclusion, early commencement of PD does not reduce the mortality risk and other outcomes. Although the recent guidelines suggest that initiation of dialysis at higher eGFR, physicians should not determine the time to initiate PD therapy simply rely on the eGFR alone. PMID:22323864

Statistical primer: propensity score matching and its alternatives.

PubMed

Benedetto, Umberto; Head, Stuart J; Angelini, Gianni D; Blackstone, Eugene H

2018-06-01

Propensity score (PS) methods offer certain advantages over more traditional regression methods to control for confounding by indication in observational studies. Although multivariable regression models adjust for confounders by modelling the relationship between covariates and outcome, the PS methods estimate the treatment effect by modelling the relationship between confounders and treatment assignment. Therefore, methods based on the PS are not limited by the number of events, and their use may be warranted when the number of confounders is large, or the number of outcomes is small. The PS is the probability for a subject to receive a treatment conditional on a set of baseline characteristics (confounders). The PS is commonly estimated using logistic regression, and it is used to match patients with similar distribution of confounders so that difference in outcomes gives unbiased estimate of treatment effect. This review summarizes basic concepts of the PS matching and provides guidance in implementing matching and other methods based on the PS, such as stratification, weighting and covariate adjustment.

Analysis of Longitudinal Studies With Repeated Outcome Measures: Adjusting for Time-Dependent Confounding Using Conventional Methods.

PubMed

Keogh, Ruth H; Daniel, Rhian M; VanderWeele, Tyler J; Vansteelandt, Stijn

2018-05-01

Estimation of causal effects of time-varying exposures using longitudinal data is a common problem in epidemiology. When there are time-varying confounders, which may include past outcomes, affected by prior exposure, standard regression methods can lead to bias. Methods such as inverse probability weighted estimation of marginal structural models have been developed to address this problem. However, in this paper we show how standard regression methods can be used, even in the presence of time-dependent confounding, to estimate the total effect of an exposure on a subsequent outcome by controlling appropriately for prior exposures, outcomes, and time-varying covariates. We refer to the resulting estimation approach as sequential conditional mean models (SCMMs), which can be fitted using generalized estimating equations. We outline this approach and describe how including propensity score adjustment is advantageous. We compare the causal effects being estimated using SCMMs and marginal structural models, and we compare the two approaches using simulations. SCMMs enable more precise inferences, with greater robustness against model misspecification via propensity score adjustment, and easily accommodate continuous exposures and interactions. A new test for direct effects of past exposures on a subsequent outcome is described.

A robust method using propensity score stratification for correcting verification bias for binary tests

PubMed Central

He, Hua; McDermott, Michael P.

2012-01-01

Sensitivity and specificity are common measures of the accuracy of a diagnostic test. The usual estimators of these quantities are unbiased if data on the diagnostic test result and the true disease status are obtained from all subjects in an appropriately selected sample. In some studies, verification of the true disease status is performed only for a subset of subjects, possibly depending on the result of the diagnostic test and other characteristics of the subjects. Estimators of sensitivity and specificity based on this subset of subjects are typically biased; this is known as verification bias. Methods have been proposed to correct verification bias under the assumption that the missing data on disease status are missing at random (MAR), that is, the probability of missingness depends on the true (missing) disease status only through the test result and observed covariate information. When some of the covariates are continuous, or the number of covariates is relatively large, the existing methods require parametric models for the probability of disease or the probability of verification (given the test result and covariates), and hence are subject to model misspecification. We propose a new method for correcting verification bias based on the propensity score, defined as the predicted probability of verification given the test result and observed covariates. This is estimated separately for those with positive and negative test results. The new method classifies the verified sample into several subsamples that have homogeneous propensity scores and allows correction for verification bias. Simulation studies demonstrate that the new estimators are more robust to model misspecification than existing methods, but still perform well when the models for the probability of disease and probability of verification are correctly specified. PMID:21856650

A practical guide to propensity score analysis for applied clinical research.

PubMed

Lee, Jaehoon; Little, Todd D

2017-11-01

Observational studies are often the only viable options in many clinical settings, especially when it is unethical or infeasible to randomly assign participants to different treatment régimes. In such case propensity score (PS) analysis can be applied to accounting for possible selection bias and thereby addressing questions of causal inference. Many PS methods exist, yet few guidelines are available to aid applied researchers in their conduct and evaluation of a PS analysis. In this article we give an overview of available techniques for PS estimation and application, balance diagnostic, treatment effect estimation, and sensitivity assessment, as well as recent advances. We also offer a tutorial that can be used to emulate the steps of PS analysis. Our goal is to provide information that will bring PS analysis within the reach of applied clinical researchers and practitioners. Copyright © 2017 Elsevier Ltd. All rights reserved.

The Wikipedia Gender Gap Revisited: Characterizing Survey Response Bias with Propensity Score Estimation.

PubMed

Hill, Benjamin Mako; Shaw, Aaron

2013-01-01

Opt-in surveys are the most widespread method used to study participation in online communities, but produce biased results in the absence of adjustments for non-response. A 2008 survey conducted by the Wikimedia Foundation and United Nations University at Maastricht is the source of a frequently cited statistic that less than 13% of Wikipedia contributors are female. However, the same study suggested that only 39.9% of Wikipedia readers in the US were female - a finding contradicted by a representative survey of American adults by the Pew Research Center conducted less than two months later. Combining these two datasets through an application and extension of a propensity score estimation technique used to model survey non-response bias, we construct revised estimates, contingent on explicit assumptions, for several of the Wikimedia Foundation and United Nations University at Maastricht claims about Wikipedia editors. We estimate that the proportion of female US adult editors was 27.5% higher than the original study reported (22.7%, versus 17.8%), and that the total proportion of female editors was 26.8% higher (16.1%, versus 12.7%).

The Wikipedia Gender Gap Revisited: Characterizing Survey Response Bias with Propensity Score Estimation

PubMed Central

2013-01-01

Opt-in surveys are the most widespread method used to study participation in online communities, but produce biased results in the absence of adjustments for non-response. A 2008 survey conducted by the Wikimedia Foundation and United Nations University at Maastricht is the source of a frequently cited statistic that less than 13% of Wikipedia contributors are female. However, the same study suggested that only 39.9% of Wikipedia readers in the US were female – a finding contradicted by a representative survey of American adults by the Pew Research Center conducted less than two months later. Combining these two datasets through an application and extension of a propensity score estimation technique used to model survey non-response bias, we construct revised estimates, contingent on explicit assumptions, for several of the Wikimedia Foundation and United Nations University at Maastricht claims about Wikipedia editors. We estimate that the proportion of female US adult editors was 27.5% higher than the original study reported (22.7%, versus 17.8%), and that the total proportion of female editors was 26.8% higher (16.1%, versus 12.7%). PMID:23840366

Bias reduction in repeated-measures observational studies by the use of propensity score: the case of enteral sedation for critically ill patients.

PubMed

Umbrello, Michele; Mistraletti, Giovanni; Corbella, Davide; Cigada, Marco; Salini, Silvia; Morabito, Alberto; Iapichino, Gaetano

2012-12-01

Within the evidence-based medicine paradigm, randomized controlled trials represent the "gold standard" to produce reliable evidence. Indeed, planning and implementing randomized controlled trials in critical care medicine presents limitations because of intrinsic and structural problems. As a consequence, observational studies still occur frequently. In these cases, propensity score (PS) (probability of receiving a treatment conditional on observed covariates) is an increasingly used technique to adjust the results. Few studies addressed the specific issue of a PS correction of repeated-measures designs. Three techniques for correcting the analysis of nonrandomized designs (matching, stratification, regression adjustment) are presented in a tutorial form and applied to a real case study: the comparison between intravenous and enteral sedative therapy in the intensive care unit setting. After showing the results before and after the use of PS, we suggest that such a tool allows to partially overcoming the bias associated with the observational nature of the study. It permits to correct the estimates for any observed covariate, while unobserved confounders cannot be controlled for. Propensity score represents a useful additional tool to estimate the effects of treatments in nonrandomized studies. In the case study, an enteral sedation approach was equally effective to an intravenous regime, allowing for a lower level of sedation and spare of resources. Copyright © 2012 Elsevier Inc. All rights reserved.

Household Financial Management and Women's Experiences of Intimate Partner Violence in the Philippines: A Study Using Propensity Score Methods.

PubMed

Tsai, Laura Cordisco

2016-04-27

This study explores the causal impact of independent management of household finances upon women's experiences of intimate partner violence (IPV) in the Philippines. Propensity score matching is used to generate a casual estimate of the impact of women's roles as household financial managers on their experiences of IPV. Findings demonstrate that managing household finances independently significantly increased the severity of IPV women experienced from their partners compared with women who managed finances jointly with partners. Findings reinforce the importance of explicit attention to intrahousehold power dynamics and gender norms in the implementation of microfinance interventions intended to empower women. © The Author(s) 2016.

Evaluation of prognostic differences in elderly patients with pneumonia treated by between pulmonologists and non-pulmonologists: a propensity score analysis.

PubMed

Komiya, Kosaku; Oka, Hiroaki; Ohama, Minoru; Uchida, Masahiro; Miyajima, Hajime; Iwashita, Tomohiko; Okabe, Eiji; Shuto, Osamu; Matsumoto, Taisuke; Ishii, Hiroshi; Kadota, Jun-Ichi

2016-07-01

The incidence of pneumonia among elderly people is increasing in aged countries, and both pulmonologists and non-pulmonologists treat such patients. The aim of this study was to assess prognostic differences between elderly patients treated by pulmonologists and those treated by non-pulmonologists. This study was a retrospective cohort using a propensity score analysis. Patients 65 years of age or over with pneumonia were consecutively included. The propensity score was estimated based on the patient's background and severity of pneumonia. The difference in 30-day and 90-day mortality depending on the attending physician's specialty was analyzed after adjusting for other variables, including the propensity score. We assessed 68 and 182 patients treated by pulmonologists and non-pulmonologists, respectively. The pulmonologists tended to be in charge of patients with hypoxemia, chronic obstructive pulmonary disease or dementia without aspiration pneumonia or renal dysfunction (area under receiver operating characteristic curve to predict treatment by a pulmonologist according to the propensity score = 0.737, P < 0.001). In the multivariate analysis, white blood count cell (adjusted hazard ratio, 1.000, P = 0.030) and the serum albumin level (0.382, P = 0.001) were associated with 30-day mortality, and a bedridden status (3.000, P = 0.013) and the serum albumin level (0.382, P < 0.001) were associated with 90-day mortality; however, the attending physician's specialty was not associated with these prognoses. The overall prognosis of pneumonia in elderly patients may not necessarily improve, irrespective of treatment by pulmonologists, and host factors seemed to be associated with mortality. © 2014 John Wiley & Sons Ltd.

Antenatal Maternity Leave and Childbirth Using the First Baby Study: A Propensity Score Analysis.

PubMed

Goodman, Julia M; Guendelman, Sylvia; Kjerulff, Kristen H

Most employed American women work during pregnancy and continue working through the month they deliver. Yet, few studies estimate the relationship between maternity leave taken during pregnancy and maternal health. We evaluate the association of antenatal leave (ANL) uptake with obstetric outcomes, assessing the potential role of protective and adverse selection pathways on this relationship. We sample 1,740 employed women who delivered at term from the First Baby Study, a prospective cohort of nulliparous women in Pennsylvania. We use propensity scores to estimate the relationship between ANL and negative delivery outcomes (labor induction, long labor duration, unplanned cesarean delivery, and self-reported negative birth experience). We estimated propensity scores using a range of employment, health, and sociodemographic variables. One-half of the sampled women worked until the day before or day of delivery. Women who stopped working at least 2 days before delivery experienced 16% more negative delivery outcomes, on average, than women who worked until delivery, driven largely by a 25% higher predicted probability of unplanned cesarean section deliveries. These robust findings hold up to a range of sensitivity analyses and demonstrate selective mechanisms operating in ANL uptake. Our findings suggest that, even after controlling for an extensive set of observable employment, health, and sociodemographic characteristics, women who take ANL continue to differ in unobserved characteristics that lead to negative delivery outcomes. Like most U.S. states, Pennsylvania does not grant paid maternity leave. In a context of limited maternity leave availability, only relatively unhealthy women take ANL. Copyright © 2016 Jacobs Institute of Women's Health. Published by Elsevier Inc. All rights reserved.

Food insecurity, food assistance and weight status in US youth: new evidence from NHANES 2007-08.

PubMed

Kohn, M J; Bell, J F; Grow, H M G; Chan, G

2014-04-01

To investigate food assistance participation as a risk factor for overweight and obesity in youth, and food insecurity as an effect modifier. The sample included youth ages 4-17, in families ≤200% of the federal poverty line in the 2007-2008 National Health and Nutrition Examination Survey (n = 1321). Food insecurity was measured with the US Department of Agriculture survey module. Food assistance participation was assessed for Supplemental Nutrition Assistance Program, Special Supplemental Nutrition Program for Women, Infants and Children and school meals. Body size was classified by age- and sex-specific body mass index (BMI) percentile, BMI z-score and waist circumference percentile. Regression models with direct covariate adjustment and programme-specific propensity scores, stratified by food insecurity, estimated associations between food assistance participation and body size. Food assistance participation was not associated with increased body size among food-insecure youth in models with direct covariate adjustment or propensity scores. Compared with low-income, food-secure youth not participating in food assistance, BMI z-scores were higher among participants in models with direct covariate adjustment (0.27-0.38 SD and 0.41-0.47 SD, for boys and girls, respectively). Using propensity scores, results were similar for boys, but less so for girls. Food assistance programme participation is associated with increased body size in food-secure youth, but not food-insecure youth. Using both direct covariate adjustment and a propensity score approach, self-selection bias may explain some, but not all, of the associations. Providing healthy food assistance that improves diet quality without contributing to excessive intake remains an important public health goal. © 2013 The Authors. Pediatric Obesity © 2013 International Association for the Study of Obesity.

Conducting Privacy-Preserving Multivariable Propensity Score Analysis When Patient Covariate Information Is Stored in Separate Locations.

PubMed

Bohn, Justin; Eddings, Wesley; Schneeweiss, Sebastian

2017-03-15

Distributed networks of health-care data sources are increasingly being utilized to conduct pharmacoepidemiologic database studies. Such networks may contain data that are not physically pooled but instead are distributed horizontally (separate patients within each data source) or vertically (separate measures within each data source) in order to preserve patient privacy. While multivariable methods for the analysis of horizontally distributed data are frequently employed, few practical approaches have been put forth to deal with vertically distributed health-care databases. In this paper, we propose 2 propensity score-based approaches to vertically distributed data analysis and test their performance using 5 example studies. We found that these approaches produced point estimates close to what could be achieved without partitioning. We further found a performance benefit (i.e., lower mean squared error) for sequentially passing a propensity score through each data domain (called the "sequential approach") as compared with fitting separate domain-specific propensity scores (called the "parallel approach"). These results were validated in a small simulation study. This proof-of-concept study suggests a new multivariable analysis approach to vertically distributed health-care databases that is practical, preserves patient privacy, and warrants further investigation for use in clinical research applications that rely on health-care databases. © The Author 2017. Published by Oxford University Press on behalf of the Johns Hopkins Bloomberg School of Public Health. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Covariate Balance in Bayesian Propensity Score Approaches for Observational Studies

ERIC Educational Resources Information Center

Chen, Jianshen; Kaplan, David

2015-01-01

Bayesian alternatives to frequentist propensity score approaches have recently been proposed. However, few studies have investigated their covariate balancing properties. This article compares a recently developed two-step Bayesian propensity score approach to the frequentist approach with respect to covariate balance. The effects of different…

Balancing Treatment and Control Groups in Quasi-Experiments: An Introduction to Propensity Scoring

ERIC Educational Resources Information Center

Connelly, Brian S.; Sackett, Paul R.; Waters, Shonna D.

2013-01-01

Organizational and applied sciences have long struggled with improving causal inference in quasi-experiments. We introduce organizational researchers to propensity scoring, a statistical technique that has become popular in other applied sciences as a means for improving internal validity. Propensity scoring statistically models how individuals in…

Bayesian Propensity Score Analysis: Simulation and Case Study

ERIC Educational Resources Information Center

Kaplan, David; Chen, Cassie J. S.

2011-01-01

Propensity score analysis (PSA) has been used in a variety of settings, such as education, epidemiology, and sociology. Most typically, propensity score analysis has been implemented within the conventional frequentist perspective of statistics. This perspective, as is well known, does not account for uncertainty in either the parameters of the…

Risk of infectious complications associated with blood transfusion in elective spinal surgery-a propensity score matched analysis.

PubMed

Kato, So; Chikuda, Hirotaka; Ohya, Junichi; Oichi, Takeshi; Matsui, Hiroki; Fushimi, Kiyohide; Takeshita, Katsushi; Tanaka, Sakae; Yasunaga, Hideo

2016-01-01

Although the negative aspects of blood transfusion are increasingly recognized, less is known about transfusion-related risks in spinal surgery. This study was designed to determine whether perioperative allogeneic blood transfusion is associated with increased risk of infectious complications after elective spinal surgery. A retrospective cohort study with propensity score matched analysis was carried out. Data of patients with spinal canal stenosis and spondylolisthesis who underwent elective lumbar surgeries (decompression or fusion) were obtained from the Diagnosis Procedure Combination database, a nationwide administrative inpatient database in Japan. Clinical outcomes included in-hospital death and the occurrence of infectious complications (surgical site infection [SSI], respiratory tract infection, urinary tract infection, and sepsis). Patients' clinical information, including sex, age, type of hospital, preoperative comorbidities, duration of anesthesia, cell saver use, and volume of allogeneic blood transfused, were investigated. Patients transfused with >840 mL (6 units) were excluded. Propensity scores for receiving transfusion were calculated, with one-to-one matching based on estimated propensity scores to adjust for patients' baseline characteristics. The proportions of complications were compared in patients with and without transfusions. This study was funded by grants from the Ministry of Health, Labour and Welfare, Japan. Of the 84,650 patients identified, 5,289 patients (6.1%) received transfusions, with 4,436 (5.2%) receiving up to 840 mL. One-to-one propensity score matching resulted in 4,275 pairs with and without transfusion. Patients transfused were at increased risk of SSI (odds ratio [OR], 1.9; 95% confidence interval [CI], 1.4-2.5; p<.001) and urinary tract infection (OR, 2.5; 95% CI, 1.5-4.2; p<.001) than those not transfused. Allogeneic blood transfusion after elective lumbar surgery was associated with increased risks of SSI and urinary tract infection. Copyright © 2015 Elsevier Inc. All rights reserved.

Applications of propensity score methods in observational comparative effectiveness and safety research: where have we come and where should we go?

PubMed

Borah, Bijan J; Moriarty, James P; Crown, William H; Doshi, Jalpa A

2014-01-01

Propensity score (PS) methods have proliferated in recent years in observational studies in general and in observational comparative effectiveness research (CER) in particular. PS methods are an important set of tools for estimating treatment effects in observational studies, enabling adjustment for measured confounders in an easy-to-understand and transparent way. This article demonstrates how PS methods have been used to address specific CER questions from 2001 through to 2012 by identifying six impactful studies from this period. This article also discusses areas for improvement, including data infrastructure, and a unified set of guidelines in terms of PS implementation and reporting, which will boost confidence in evidence generated through observational CER using PS methods.

Temporary work and depressive symptoms: a propensity score analysis.

PubMed

Quesnel-Vallée, Amélie; DeHaney, Suzanne; Ciampi, Antonio

2010-06-01

Recent decades have seen a tremendous increase in the complexity of work arrangements, through job sharing, flexible hours, career breaks, compressed work weeks, shift work, reduced job security, and part-time, contract and temporary work. In this study, we focus on one specific group of workers that arguably most embodies non-standard employment, namely temporary workers, and estimate the effect of this type of employment on depressive symptom severity. Accounting for the possibility of mental health selection into temporary work through propensity score analysis, we isolate the direct effects of temporary work on depressive symptoms with varying lags of time since exposure. We use prospective data from the U.S. National Longitudinal Survey of Youth 1979 (NLSY79), which has followed, longitudinally, from 1979 to the present, a nationally representative cohort of American men and women between 14 and 22 years of age in 1979. Three propensity score models were estimated, to capture the effect of different time lags (immediately following exposure, and 2 and 4 years post exposure) between the period of exposure to the outcome. The only significant effects were found among those who had been exposed to temporary work in the two years preceding the outcome measurement. These workers report 1.803 additional depressive symptoms from having experienced this work status (than if they had not been exposed). Moreover, this difference is both statistically and substantively significant, as it represents a 50% increase from the average level of depressive symptoms in this population. Copyright 2010 Elsevier Ltd. All rights reserved.

Effect of hydroxychloroquine on the survival of patients with systemic lupus erythematosus: data from LUMINA, a multiethnic US cohort (LUMINA L).

PubMed

Alarcón, Graciela S; McGwin, Gerald; Bertoli, Ana M; Fessler, Barri J; Calvo-Alén, Jaime; Bastian, Holly M; Vilá, Luis M; Reveille, John D

2007-09-01

In patients with systemic lupus erythematosus (SLE), hydroxychloroquine prevents disease flares and damage accrual and facilitates the response to mycophenolate mofetil in those with renal involvement. A study was undertaken to determine whether hydroxychloroquine also exerts a protective effect on survival. Patients with SLE from the multiethnic LUMINA (LUpus in MInorities: NAture vs nurture) cohort were studied. A case-control study was performed within the context of this cohort in which deceased patients (cases) were matched for disease duration (within 6 months) with alive patients (controls) in a proportion of 3:1. Survival was the outcome of interest. Propensity scores were derived by logistic regression to adjust for confounding by indication as patients with SLE with milder disease manifestations are more likely to be prescribed hydroxychloroquine. A conditional logistic regression model was used to estimate the risk of death and hydroxychloroquine use with and without the propensity score as the adjustment variable. There were 608 patients, of whom 61 had died (cases). Hydroxychloroquine had a protective effect on survival (OR 0.128 (95% CI 0.054 to 0.301 for hydroxychloroquine alone and OR 0.319 (95% CI 0.118 to 0.864) after adding the propensity score). As expected, the propensity score itself was also protective. Hydroxychloroquine, which overall is well tolerated by patients with SLE, has a protective effect on survival which is evident even after taking into consideration the factors associated with treatment decisions. This information is of importance to all clinicians involved in the care of patients with SLE.

A Step-by-Step Guide to Propensity Score Matching in R

ERIC Educational Resources Information Center

Randolph, Justus J.; Falbe, Kristina; Manuel, Austin Kureethara; Balloun, Joseph L.

2014-01-01

Propensity score matching is a statistical technique in which a treatment case is matched with one or more control cases based on each case's propensity score. This matching can help strengthen causal arguments in quasi-experimental and observational studies by reducing selection bias. In this article we concentrate on how to conduct propensity…

Teacher-child relationships and academic achievement: a multilevel propensity score model approach.

PubMed

McCormick, Meghan P; O'Connor, Erin E; Cappella, Elise; McClowry, Sandee G

2013-10-01

A robust body of research finds positive cross-sectional and longitudinal associations between teacher-child relationships and children's academic achievement in elementary school. Estimating the causal effect of teacher-child relationships on children's academic achievement, however, is challenged by selection bias at the individual and school level. To address these issues, we used two multilevel propensity score matching approaches to estimate the effect of high-quality teacher-child relationships in kindergarten on math and reading achievement during children's transition to first grade. Multi-informant data were collected on 324 low-income, Black and Hispanic students, and 112 kindergarten and first-grade teachers. Results revealed significant effects of high-quality teacher-child relationships in kindergarten on math achievement in first grade. No significant effects of teacher-child relationships were detected for reading achievement. Implications for intervention development and public policy are discussed. Copyright © 2013 Society for the Study of School Psychology. Published by Elsevier Ltd. All rights reserved.

SCMPSP: Prediction and characterization of photosynthetic proteins based on a scoring card method.

PubMed

Vasylenko, Tamara; Liou, Yi-Fan; Chen, Hong-An; Charoenkwan, Phasit; Huang, Hui-Ling; Ho, Shinn-Ying

2015-01-01

Photosynthetic proteins (PSPs) greatly differ in their structure and function as they are involved in numerous subprocesses that take place inside an organelle called a chloroplast. Few studies predict PSPs from sequences due to their high variety of sequences and structues. This work aims to predict and characterize PSPs by establishing the datasets of PSP and non-PSP sequences and developing prediction methods. A novel bioinformatics method of predicting and characterizing PSPs based on scoring card method (SCMPSP) was used. First, a dataset consisting of 649 PSPs was established by using a Gene Ontology term GO:0015979 and 649 non-PSPs from the SwissProt database with sequence identity <= 25%.- Several prediction methods are presented based on support vector machine (SVM), decision tree J48, Bayes, BLAST, and SCM. The SVM method using dipeptide features-performed well and yielded - a test accuracy of 72.31%. The SCMPSP method uses the estimated propensity scores of 400 dipeptides - as PSPs and has a test accuracy of 71.54%, which is comparable to that of the SVM method. The derived propensity scores of 20 amino acids were further used to identify informative physicochemical properties for characterizing PSPs. The analytical results reveal the following four characteristics of PSPs: 1) PSPs favour hydrophobic side chain amino acids; 2) PSPs are composed of the amino acids prone to form helices in membrane environments; 3) PSPs have low interaction with water; and 4) PSPs prefer to be composed of the amino acids of electron-reactive side chains. The SCMPSP method not only estimates the propensity of a sequence to be PSPs, it also discovers characteristics that further improve understanding of PSPs. The SCMPSP source code and the datasets used in this study are available at http://iclab.life.nctu.edu.tw/SCMPSP/.

Comparing Student Performance on the Old vs New Versions of the NAPLEX.

PubMed

Welch, Adam C; Karpen, Samuel C

2018-04-01

Objective. To determine if the new 2016 version of the North American Pharmacy Licensure Examination (NAPLEX) affected scores when controlling for student performance on other measures using data from one institution. Methods. There were 201 records from the classes of 2014-2016. Doubly robust estimation using weighted propensity scores was used to compare NAPLEX scaled scores and pass rates while considering student performance on other measures. Of the potential controllers of student performance: Pharmacy Curricular Outcomes Assessment (PCOA), scaled composite scores from the Pharmacy College Admission Test (PCAT), and P3 Grade Point Average (GPA). Only PCOA and P3 GPA were found to be appropriate for propensity scoring. Results. The weighted NAPLEX scaled scores did not significantly drop from the old (2014-2015) to the new (2016) version of NAPLEX. The change in pass rates between the new and old versions of NAPLEX were also non-significant. Conclusion. Using data from one institution, the new version itself of the NAPLEX did not have a significant effect on NAPLEX scores or first-time pass rates when controlling for student performance on other measures. Colleges are encouraged to repeat this analysis with pooled data and larger sample sizes.

Health related quality of life among myocardial infarction survivors in the United States: a propensity score matched analysis.

PubMed

Mollon, Lea; Bhattacharjee, Sandipan

2017-12-04

Little is known regarding the health-related quality of life among myocardial infarction (MI) survivors in the United States. The purpose of this population-based study was to identify differences in health-related quality of life domains between MI survivors and propensity score matched controls. This retrospective, cross-sectional matched case-control study examined differences in health-related quality of life (HRQoL) among MI survivors of myocardial infarction compared to propensity score matched controls using data from the 2015 Behavioral Risk Factor Surveillance System (BRFSS) survey. Propensity scores were generated via logistic regression for MI survivors and controls based on gender, race/ethnicity, age, body mass index (BMI), smoking status, and comorbidities. Chi-square tests were used to compare differences between MI survivors to controls for demographic variables. A multivariate analysis of HRQoL domains estimated odds ratios. Life satisfaction, sleep quality, and activity limitations were estimated using binary logistic regression. Social support, perceived general health, perceived physical health, and perceived mental health were estimated using multinomial logistic regression. Significance was set at p < 0.05. The final sample consisted of 16,729 MI survivors matched to 50,187 controls (n = 66,916). Survivors were approximately 2.7 times more likely to report fair/poor general health compared to control (AOR = 2.72, 95% CI: 2.43-3.05) and 1.5 times more likely to report limitations to daily activities (AOR = 1.46, 95% CI: 1.34-1.59). Survivors were more likely to report poor physical health >15 days in the month (AOR = 1.63, 95% CI: 1.46-1.83) and poor mental health >15 days in the month (AOR = 1.25, 95% CI: 1.07-1.46) compared to matched controls. There was no difference in survivors compared to controls in level of emotional support (rarely/never: AOR = 0.75, 95% CI: 0.48-1.18; sometimes: AOR = 0.73, 95% CI: 0.41-1.28), hours of recommended sleep (AOR = 1.14, 95% CI: 0.94-1.38), or life satisfaction (AOR = 1.62, 95% CI: 0.99-2.63). MI survivors experienced lower HRQoL on domains of general health, physical health, daily activity, and mental health compared to the general population.

On the Bias-Amplifying Effect of Near Instruments in Observational Studies

ERIC Educational Resources Information Center

Steiner, Peter M.; Kim, Yongnam

2014-01-01

In contrast to randomized experiments, the estimation of unbiased treatment effects from observational data requires an analysis that conditions on all confounding covariates. Conditioning on covariates can be done via standard parametric regression techniques or nonparametric matching like propensity score (PS) matching. The regression or…

Estimating Causal Effects in Mediation Analysis Using Propensity Scores

ERIC Educational Resources Information Center

Coffman, Donna L.

2011-01-01

Mediation is usually assessed by a regression-based or structural equation modeling (SEM) approach that we refer to as the classical approach. This approach relies on the assumption that there are no confounders that influence both the mediator, "M", and the outcome, "Y". This assumption holds if individuals are randomly…

Within-Cluster and Across-Cluster Matching with Observational Multilevel Data

ERIC Educational Resources Information Center

Kim, Jee-Seon; Steiner, Peter M.; Hall, Courtney; Thoemmes, Felix

2013-01-01

When randomized experiments cannot be conducted in practice, propensity score (PS) techniques for matching treated and control units are frequently used for estimating causal treatment effects from observational data. Despite the popularity of PS techniques, they are not yet well studied for matching multilevel data where selection into treatment…

Evaluation of a disease management program for COPD using propensity matched control group

PubMed Central

George, Pradeep Paul; Heng, Bee Hoon; Lim, Tow Keang; Abisheganaden, John; Ng, Alan Wei Keong; Lim, Fong Seng

2016-01-01

Background Disease management programs (DMPs) have proliferated recently as a means of improving the quality and efficiency of care for patients with chronic illness. These programs include education about disease, optimization of evidence-based medications, information and support from case managers, and institution of self-management principles. Chronic obstructive pulmonary disease (COPD) is a major cause of morbidity and mortality in Singapore and worldwide. DMP aims to reduce mortality, hospitalizations, and average length of stay in such patients. This study assesses the outcomes of the DMP, comparing the propensity score matched DMP patients with controls. Methods DMP patients were compared with the controls, who were COPD patients fulfilling the DMP’s inclusion criteria but not included in the program. Control patients were identified from Operations Data Store (ODS) database. The outcomes of interest were average length of stay, number of days admitted to hospital per 100 person days, readmission, and mortality rates per person year. The risk of death and readmission was estimated using Cox, and competing risk regression respectively. Propensity score was estimated to identify the predictors of DMP enrolment. DMP patients and controls were matched on their propensity score. Results There were 170 matched DMP patients and control patients having 287 and 207 hospitalizations respectively. Program patient had lower mortality than the controls (0.12 vs. 0.27 per person year); cumulative 1-year survival was 91% among program patient and 76% among the control patients. Readmission, and hospital days per 100 person-days was higher for the program patients (0.36 vs. 0.17 per person year), and (2.19 vs. 1.88 per person year) respectively. Conclusions Participation in “DMP” was associated with lower all-cause mortality when compared to the controls. This survival gain in the program patients was paradoxically associated with an increase in readmission rate and total hospital days. PMID:27499955

Evaluation of a disease management program for COPD using propensity matched control group.

PubMed

George, Pradeep Paul; Heng, Bee Hoon; Lim, Tow Keang; Abisheganaden, John; Ng, Alan Wei Keong; Verma, Akash; Lim, Fong Seng

2016-07-01

Disease management programs (DMPs) have proliferated recently as a means of improving the quality and efficiency of care for patients with chronic illness. These programs include education about disease, optimization of evidence-based medications, information and support from case managers, and institution of self-management principles. Chronic obstructive pulmonary disease (COPD) is a major cause of morbidity and mortality in Singapore and worldwide. DMP aims to reduce mortality, hospitalizations, and average length of stay in such patients. This study assesses the outcomes of the DMP, comparing the propensity score matched DMP patients with controls. DMP patients were compared with the controls, who were COPD patients fulfilling the DMP's inclusion criteria but not included in the program. Control patients were identified from Operations Data Store (ODS) database. The outcomes of interest were average length of stay, number of days admitted to hospital per 100 person days, readmission, and mortality rates per person year. The risk of death and readmission was estimated using Cox, and competing risk regression respectively. Propensity score was estimated to identify the predictors of DMP enrolment. DMP patients and controls were matched on their propensity score. There were 170 matched DMP patients and control patients having 287 and 207 hospitalizations respectively. Program patient had lower mortality than the controls (0.12 vs. 0.27 per person year); cumulative 1-year survival was 91% among program patient and 76% among the control patients. Readmission, and hospital days per 100 person-days was higher for the program patients (0.36 vs. 0.17 per person year), and (2.19 vs. 1.88 per person year) respectively. Participation in "DMP" was associated with lower all-cause mortality when compared to the controls. This survival gain in the program patients was paradoxically associated with an increase in readmission rate and total hospital days.

SSRIs and risk of suicide attempts in young people - A Danish observational register-based historical cohort study, using propensity score.

PubMed

Christiansen, Erik; Agerbo, Esben; Bilenberg, Niels; Stenager, Elsebeth

2016-01-01

SSRIs are widely used in the treatment of mental illness for both children and adults. Studies have found a slightly increased risk of suicidal thoughts and suicide attempts in young people using SSRIs but SSRIs' impact on risk for suicides in youth is not well-established. Is there indication that SSRIs might raise risk for suicide attempts in young people? We used an observational register-based historical cohort design, a large cohort of all Danish individuals born in 1983-1989 (n = 392,458) and a propensity score approach to analyse the impact from SSRIs on risk for suicide attempts. Every suicide attempt and redeemed prescription of SSRIs was analysed by Cox regression. We found a significant overlap between redeeming a prescription on SSRIs and subsequent suicide attempt. The risk for suicide attempt was highest in the first 3 months after redeeming the first prescription. The hazard ratio for suicide attempts after redeeming a prescription was estimated to 5.23, 95% CI 4.82-5.68. We conclude that the risk of suicide attempt is higher for young people in the first months after redeeming their first prescription for SSRIs, compared to non-users. For SSRI users with lower propensity score (fewer risk factors for SSRIs) the risk of suicide attempt is estimated to be highest. Although the design may miss some explicit reason for prescription of SSRIs and SSRIs might be a marker for those in high risk rather than a causal risk factor, we would recommend systematic risk assessment in the period after redeeming the first prescription.

A propensity score approach to correction for bias due to population stratification using genetic and non-genetic factors.

PubMed

Zhao, Huaqing; Rebbeck, Timothy R; Mitra, Nandita

2009-12-01

Confounding due to population stratification (PS) arises when differences in both allele and disease frequencies exist in a population of mixed racial/ethnic subpopulations. Genomic control, structured association, principal components analysis (PCA), and multidimensional scaling (MDS) approaches have been proposed to address this bias using genetic markers. However, confounding due to PS can also be due to non-genetic factors. Propensity scores are widely used to address confounding in observational studies but have not been adapted to deal with PS in genetic association studies. We propose a genomic propensity score (GPS) approach to correct for bias due to PS that considers both genetic and non-genetic factors. We compare the GPS method with PCA and MDS using simulation studies. Our results show that GPS can adequately adjust and consistently correct for bias due to PS. Under no/mild, moderate, and severe PS, GPS yielded estimated with bias close to 0 (mean=-0.0044, standard error=0.0087). Under moderate or severe PS, the GPS method consistently outperforms the PCA method in terms of bias, coverage probability (CP), and type I error. Under moderate PS, the GPS method consistently outperforms the MDS method in terms of CP. PCA maintains relatively high power compared to both MDS and GPS methods under the simulated situations. GPS and MDS are comparable in terms of statistical properties such as bias, type I error, and power. The GPS method provides a novel and robust tool for obtaining less-biased estimates of genetic associations that can consider both genetic and non-genetic factors. 2009 Wiley-Liss, Inc.

TEMPORARY WORK AND DEPRESSIVE SYMPTOMS: A PROPENSITY SCORE ANALYSIS

PubMed Central

Quesnel-Vallée, Amélie; DeHaney, Suzanne; Ciampi, Antonio

2013-01-01

Recent decades have seen a tremendous increase in the complexity of work arrangements, through job sharing, flexible hours, career breaks, compressed work weeks, shift work, reduced job security, and part-time, contract and temporary work. In this study, we focus on one specific group of workers that arguably most embodies nonstandard employment, namely temporary workers, and examine the consequences of this type of employment on depressive symptoms. This study aims to estimate the effect of being a temporary worker on depressive symptom severity. Accounting for the possibility of mental health selection into temporary work through propensity score analysis, we isolate the direct effects of temporary work on depressive symptoms with varying lags of time since exposure. We use prospective data from the U.S. National Longitudinal Survey of Youth 1979 (NLSY79), which has followed, longitudinally, from 1979 to the present, a nationally representative cohort of American men and women between 14 and 22 years of age in 1979. Three propensity score models were estimated, to capture the effect of different time lags (immediately following exposure, and 2 and 4 years post exposure) between the period of exposure to the outcome. The only significant effects were found among those who had been exposed to temporary work in the two years preceding the outcome measurement. These workers report 1.803 (95% CI 0.552; 3.055) additional depressive symptoms from having experienced this work status (than if they had not been exposed). Moreover, this difference is both statistically and substantively significant, as it represents a 50% increase from the average level of depressive symptoms in this population. PMID:20371142

Assessing the short term impact of air pollution on mortality: a matching approach.

PubMed

Baccini, Michela; Mattei, Alessandra; Mealli, Fabrizia; Bertazzi, Pier Alberto; Carugno, Michele

2017-02-10

The opportunity to assess short term impact of air pollution relies on the causal interpretation of the exposure-response association. However, up to now few studies explicitly faced this issue within a causal inference framework. In this paper, we reformulated the problem of assessing the short term impact of air pollution on health using the potential outcome approach to causal inference. We considered the impact of high daily levels of particulate matter ≤10 μm in diameter (PM 10 ) on mortality within two days from the exposure in the metropolitan area of Milan (Italy), during the period 2003-2006. Our research focus was the causal impact of a hypothetical intervention setting daily air pollution levels under a pre-fixed threshold. We applied a matching procedure based on propensity score to estimate the total number of attributable deaths (AD) during the study period. After defining the number of attributable deaths in terms of difference between potential outcomes, we used the estimated propensity score to match each high exposure day, namely each day with a level of exposure higher than 40 μg/m 3 , with a day with similar background characteristics but a level of exposure lower than 40 μg/m 3 . Then, we estimated the impact by comparing mortality between matched days. During the study period daily exposures larger than 40 μg/m 3 were responsible for 1079 deaths (90% CI: 116; 2042). The impact was more evident among the elderly than in the younger age classes. Exposures ≥ 40 μg/m 3 were responsible, among the elderly, for 1102 deaths (90% CI: 388, 1816), of which 797 from cardiovascular causes and 243 from respiratory causes. Clear evidence of an impact on respiratory mortality was found also in the age class 65-74, with 87 AD (90% CI: 11, 163). The propensity score matching turned out to be an appealing method to assess historical impacts in this field, which guarantees that the estimated total number of AD can be derived directly as sum of either age-specific or cause-specific AD, unlike the standard model-based procedure. For this reason, it is a promising approach to perform surveillance focusing on very specific causes of death or diseases, or on susceptible subpopulations. Finally, the propensity score matching is free from issues concerning the exposure-confounders-mortality modeling and does not involve extrapolation. On the one hand this enhances the internal validity of our results; on the other, it makes the approach scarcely appropriate for estimating future impacts.

Supplemental Analytic Sample Equivalence Tables for Student Characteristics and Achievement in 22 KIPP Middle Schools: A Report from the National Evaluation of KIPP Middle Schools

ERIC Educational Resources Information Center

Tuttle, Christina Clark; Teh, Bing-ru; Nichols-Barrer, Ira; Gill, Brian P.; Gleason, Philip

2010-01-01

In this set of four supplemental tables, the authors compare the baseline test scores of the treatment and matched control group samples observed in each year after KIPP entry (outcome years 1 to 4). As discussed in Chapter III, the authors used an iterative propensity score estimation procedure to calculate each student's probability of entering…

Analysis of causality from observational studies and its application in clinical research in Intensive Care Medicine.

PubMed

Coscia Requena, C; Muriel, A; Peñuelas, O

2018-02-28

Random allocation of treatment or intervention is the key feature of clinical trials and divides patients into treatment groups that are approximately balanced for baseline, and therefore comparable covariates except for the variable treatment of the study. However, in observational studies, where treatment allocation is not random, patients in the treatment and control groups often differ in covariates that are related to intervention variables. These imbalances in covariates can lead to biased estimates of the treatment effect. However, randomized clinical trials are sometimes not feasible for ethical, logistical, economic or other reasons. To resolve these situations, interest in the field of clinical research has grown in designing studies that are most similar to randomized experiments using observational (i.e. non-random) data. Observational studies using propensity score analysis methods have been increasing in the scientific papers of Intensive Care. Propensity score analyses attempt to control for confounding in non-experimental studies by adjusting for the likelihood that a given patient is exposed. However, studies with propensity indexes may be confusing, and intensivists are not familiar with this methodology and may not fully understand the importance of this technique. The objectives of this review are: to describe the fundamentals of propensity index methods; to present the techniques to adequately evaluate propensity index models; to discuss the advantages and disadvantages of these techniques. Copyright © 2018 Elsevier España, S.L.U. y SEMICYUC. All rights reserved.

Doubly robust matching estimators for high dimensional confounding adjustment.

PubMed

Antonelli, Joseph; Cefalu, Matthew; Palmer, Nathan; Agniel, Denis

2018-05-11

Valid estimation of treatment effects from observational data requires proper control of confounding. If the number of covariates is large relative to the number of observations, then controlling for all available covariates is infeasible. In cases where a sparsity condition holds, variable selection or penalization can reduce the dimension of the covariate space in a manner that allows for valid estimation of treatment effects. In this article, we propose matching on both the estimated propensity score and the estimated prognostic scores when the number of covariates is large relative to the number of observations. We derive asymptotic results for the matching estimator and show that it is doubly robust in the sense that only one of the two score models need be correct to obtain a consistent estimator. We show via simulation its effectiveness in controlling for confounding and highlight its potential to address nonlinear confounding. Finally, we apply the proposed procedure to analyze the effect of gender on prescription opioid use using insurance claims data. © 2018, The International Biometric Society.

JIM-13-0560 R1: Propensity scores for confounder adjustment when assessing the effects of medical interventions using non-experimental study designs

PubMed Central

Stürmer, Til; Wyss, Richard; Glynn, Robert J.; Brookhart, M. Alan

2014-01-01

Treatment effects, especially when comparing two or more therapeutic alternatives as in comparative effectiveness research, are likely to be heterogeneous across age, gender, co-morbidities, and co-medications. Propensity scores (PSs), an alternative to multivariable outcome models to control for measured confounding, have specific advantages in the presence of heterogeneous treatment effects. Implementing PSs using matching or weighting allows us to estimate different overall treatment effects in differently defined populations. Heterogeneous treatment effects can also be due to unmeasured confounding concentrated in those treated contrary to prediction. Sensitivity analyses based on PSs can help to assess such unmeasured confounding. PSs should be considered a primary or secondary analytic strategy in non-experimental medical research, including pharmacoepidemiology and non-experimental comparative effectiveness research. PMID:24520806

Impact of a comprehensive population health management program on health care costs.

PubMed

Grossmeier, Jessica; Seaverson, Erin L D; Mangen, David J; Wright, Steven; Dalal, Karl; Phalen, Chris; Gold, Daniel B

2013-06-01

Assess the influence of participation in a population health management (PHM) program on health care costs. A quasi-experimental study relied on logistic and ordinary least squares regression models to compare the costs of program participants with those of nonparticipants, while controlling for differences in health care costs and utilization, demographics, and health status. Propensity score models were developed and analyses were weighted by inverse propensity scores to control for selection bias. Study models yielded an estimated savings of $60.65 per wellness participant per month and $214.66 per disease management participant per month. Program savings were combined to yield an integrated return-on-investment of $3 in savings for every dollar invested. A PHM program yielded a positive return on investment after 2 years of wellness program and 1 year of integrated disease management program launch.

Robot-assisted laparoscopic versus open partial nephrectomy in patients with chronic kidney disease: A propensity score-matched comparative analysis of surgical outcomes.

PubMed

Takagi, Toshio; Kondo, Tsunenori; Tachibana, Hidekazu; Iizuka, Junpei; Omae, Kenji; Kobayashi, Hirohito; Yoshida, Kazuhiko; Tanabe, Kazunari

2017-07-01

To compare surgical outcomes between robot-assisted laparoscopic partial nephrectomy and open partial nephrectomy in patients with chronic kidney disease. Of 550 patients who underwent partial nephrectomy between 2012 and 2015, 163 patients with T1-2 renal tumors who had an estimated glomerular filtration rate between 30 and 60 mL/min/1.73 m 2 , and underwent robot-assisted laparoscopic partial nephrectomy or open partial nephrectomy were retrospectively analyzed. To minimize selection bias between the two surgical methods, patient variables were adjusted by 1:1 propensity score matching. The present study included 75 patients undergoing robot-assisted laparoscopic partial nephrectomy and 88 undergoing open partial nephrectomy. After propensity score matching, 40 patients were included in each operative group. The mean preoperative estimated glomerular filtration rate was 49 mL/min/1.73 m 2 . The mean ischemia time was 21 min in robot-assisted laparoscopic partial nephrectomy (warm ischemia) and 35 min in open partial nephrectomy (cold ischemia). Preservation of the estimated glomerular filtration rate 3-6 months postoperatively was not significantly different between robot-assisted laparoscopic partial nephrectomy and open partial nephrectomy (92% vs 91%, P = 0.9348). Estimated blood loss was significantly lower in the robot-assisted laparoscopic partial nephrectomy group than in the open partial nephrectomy group (104 vs 185 mL, P = 0.0025). The postoperative length of hospital stay was shorter in the robot-assisted laparoscopic partial nephrectomy group than in the open partial nephrectomy group (P < 0.0001). The prevalence of Clavien-Dindo grade 3 complications and a negative surgical margin status were not significantly different between the two groups. In our experience, robot-assisted laparoscopic partial nephrectomy and open partial nephrectomy provide similar outcomes in terms of functional preservation and perioperative complications among patients with chronic kidney disease. However, a lower estimated blood loss and shorter postoperative length of hospital stay can be obtained with robot-assisted laparoscopic partial nephrectomy. © 2017 The Japanese Urological Association.

Sequential cohort design applying propensity score matching to analyze the comparative effectiveness of atorvastatin and simvastatin in preventing cardiovascular events.

PubMed

Helin-Salmivaara, Arja; Lavikainen, Piia; Aarnio, Emma; Huupponen, Risto; Korhonen, Maarit Jaana

2014-01-01

Sequential cohort design (SCD) applying matching for propensity scores (PS) in accrual periods has been proposed to mitigate bias caused by channeling when calendar time is a proxy for strong confounders. We studied the channeling of patients according to atorvastatin and simvastatin initiation in Finland, starting from the market introduction of atorvastatin in 1998, and explored the SCD PS approach to analyzing the comparative effectiveness of atorvastatin versus simvastatin in the prevention of cardiovascular events (CVE). Initiators of atorvastatin or simvastatin use in the 45-75-year age range in 1998-2006 were characterized by their propensity of receiving atorvastatin over simvastatin, as estimated for 17 six-month periods. Atorvastatin (10 mg) and simvastatin (20 mg) initiators were matched 1∶1 on the PS, as estimated for the whole cohort and within each period. Cox regression models were fitted conventionally, and also for the PS matched cohort and the periodically PS matched cohort, to estimate the hazard ratios (HR) for CVEs. Atorvastatin (10 mg) was associated with a 11%-12% lower incidence of CVE in comparison with simvastatin (20 mg). The HR estimates were the same for a conventional Cox model (0.88, 95% confidence interval 0.85-0.91), for the analysis in which the PS was used to match across all periods and the Cox model was adjusted for strong confounders (0.89, 0.85-0.92), and for the analysis in which PS matching was applied within sequential periods (0.88, 0.84-0.92). The HR from a traditional PS matched analysis was 0.80 (0.77-0.83). The SCD PS approach produced effect estimates similar to those obtained in matching for PS within the whole cohort and adjusting the outcome model for strong confounders, but at the cost of efficiency. A traditional PS matched analysis without further adjustment in the outcome model produced estimates further away from unity.

Sequential FOLFIRI.3 + Gemcitabine Improves Health-Related Quality of Life Deterioration-Free Survival of Patients with Metastatic Pancreatic Adenocarcinoma: A Randomized Phase II Trial

PubMed Central

Anota, Amélie; Mouillet, Guillaume; Trouilloud, Isabelle; Dupont-Gossart, Anne-Claire; Artru, Pascal; Lecomte, Thierry; Zaanan, Aziz; Gauthier, Mélanie; Fein, Francine; Dubreuil, Olivier; Paget-Bailly, Sophie; Taieb, Julien; Bonnetain, Franck

2015-01-01

Background A randomized multicenter phase II trial was conducted to assess the sequential treatment strategy using FOLFIRI.3 and gemcitabine alternately (Arm 2) compared to gemcitabine alone (Arm 1) in patients with metastatic non pre-treated pancreatic adenocarcinoma. The primary endpoint was the progression-free survival (PFS) rate at 6 months. It concludes that the sequential treatment strategy appears to be feasible and effective with a PFS rate of 43.5% in Arm 2 at 6 months (26.1% in Arm 1). This paper reports the results of the longitudinal analysis of the health-related quality of life (HRQoL) as a secondary endpoint of this study. Methods HRQoL was evaluated using the EORTC QLQ-C30 at baseline and every two months until the end of the study or death. HRQoL deterioration-free survival (QFS) was defined as the time from randomization to a first significant deterioration as compared to the baseline score with no further significant improvement, or death. A propensity score was estimated comparing characteristics of partial and complete responders. Analyses were repeated with inverse probability weighting method using the propensity score. Multivariate Cox regression analyses were performed to identify independent factors influencing QFS. Results 98 patients were included between 2007 and 2011. Adjusting on the propensity score, patients of Arm 2 presented a longer QFS of Global Health Status (Hazard Ratio: 0.52 [0.31-0.85]), emotional functioning (0.35 [0.21–0.59]) and pain (0.50 [0.31 – 0.81]) than those of Arm 1. Conclusion Patients of Arm 2 presented a better HRQoL with a longer QFS than those of Arm 1. Moreover, the propensity score method allows to take into account the missing data depending on patients’ characteristics. Trial registration information Eudract N° 2006-005703-34. (Name of the Trial: FIRGEM). PMID:26010884

Variance estimation when using inverse probability of treatment weighting (IPTW) with survival analysis.

PubMed

Austin, Peter C

2016-12-30

Propensity score methods are used to reduce the effects of observed confounding when using observational data to estimate the effects of treatments or exposures. A popular method of using the propensity score is inverse probability of treatment weighting (IPTW). When using this method, a weight is calculated for each subject that is equal to the inverse of the probability of receiving the treatment that was actually received. These weights are then incorporated into the analyses to minimize the effects of observed confounding. Previous research has found that these methods result in unbiased estimation when estimating the effect of treatment on survival outcomes. However, conventional methods of variance estimation were shown to result in biased estimates of standard error. In this study, we conducted an extensive set of Monte Carlo simulations to examine different methods of variance estimation when using a weighted Cox proportional hazards model to estimate the effect of treatment. We considered three variance estimation methods: (i) a naïve model-based variance estimator; (ii) a robust sandwich-type variance estimator; and (iii) a bootstrap variance estimator. We considered estimation of both the average treatment effect and the average treatment effect in the treated. We found that the use of a bootstrap estimator resulted in approximately correct estimates of standard errors and confidence intervals with the correct coverage rates. The other estimators resulted in biased estimates of standard errors and confidence intervals with incorrect coverage rates. Our simulations were informed by a case study examining the effect of statin prescribing on mortality. © 2016 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd. © 2016 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd.

Maternal Employment and Child Development: A Fresh Look Using Newer Methods

ERIC Educational Resources Information Center

Hill, Jennifer L.; Waldfogel, Jane; Brooks-Gunn, Jeanne; Han, Wen-Jui

2005-01-01

The employment rate for mothers with young children has increased dramatically over the past 25 years. Estimating the effects of maternal employment on children's development is challenged by selection bias and the missing data endemic to most policy research. To address these issues, this study uses propensity score matching and multiple…

Unbiased Causal Inference from an Observational Study: Results of a Within-Study Comparison

ERIC Educational Resources Information Center

Pohl, Steffi; Steiner, Peter M.; Eisermann, Jens; Soellner, Renate; Cook, Thomas D.

2009-01-01

Adjustment methods such as propensity scores and analysis of covariance are often used for estimating treatment effects in nonexperimental data. Shadish, Clark, and Steiner used a within-study comparison to test how well these adjustments work in practice. They randomly assigned participating students to a randomized or nonrandomized experiment.…

Effects of cognitive behavioral therapy in patients with depressive disorder and comorbid insomnia: A propensity score-matched outcome study.

PubMed

Hsu, Hui-Min; Chou, Kuei-Ru; Lin, Kuan-Chia; Chen, Kuan-Yu; Su, Shu-Fang; Chung, Min-Huey

2015-10-01

We evaluated the effects of cognitive behavioral therapy for insomnia (CBT-I) in inpatients with a diagnosis of depression and comorbid insomnia. This study used a prospective, parallel-group design. The experimental group received CBT-I for no more than 90 min once weekly for 6 weeks and the control group only have health education manuals for insomnia. The following questionnaires were administered at baseline: the Hamilton Rating Scale for Depression (HAM-D), Dysfunctional Beliefs and Attitudes about Sleep (DBAS), Presleep Arousal Scale (PSAS), Sleep Hygiene Practice (SHP), and Pittsburgh Sleep Quality Index. The questionnaires were readministered after the completion of the 6-wk CBT-I intervention and 1 month following the completion of CBT-I, to determine the effects of the CBT-I intervention over time. The analysis of Generalized Estimation Equations was identified the difference between the experimental group and the control group by controlling for the variables in BZD dose and propensity score of gender, age, and the scores for the DBAS-16, PSAS, SHPS, and HAM-D. Consequently, the significant difference in the PSQI scores was observed at the 1-month follow-up assessment however, no significant intergroup difference in the PSQI scores was found at the completion of the CBT-I intervention between two groups. As a conclusion, we found that overall sleep quality significantly improved in patients who received CBT-I after we controlled for the BZD dose and propensity score, which suggests that CBT-I may represent a useful clinical strategy for improving sleep quality in patients with depression and comorbid insomnia. Copyright © 2015 Elsevier Ltd. All rights reserved.

Attributable Cost of Clostridium difficile Infection in Pediatric Patients.

PubMed

Mehrotra, Preeti; Jang, Jisun; Gidengil, Courtney; Sandora, Thomas J

2017-12-01

OBJECTIVES The attributable cost of Clostridium difficile infection (CDI) in children is unknown. We sought to determine a national estimate of attributable cost and length of stay (LOS) of CDI occurring during hospitalization in children. DESIGN AND METHODS We analyzed discharge records of patients between 2 and 18 years of age from the Agency for Healthcare Research and Quality (AHRQ) Kids' Inpatient Database. We created a logistic regression model to predict CDI during hospitalization based on demographic and clinical characteristics. Predicted probabilities from the logistic regression model were then used as propensity scores to match 1:2 CDI to non-CDI cases. Charges were converted to costs and compared between patients with CDI and propensity-score-matched controls. In a sensitivity analysis, we adjusted for LOS as a confounder by including it in both the propensity score and a generalized linear model predicting cost. RESULTS We identified 8,527 pediatric hospitalizations (0.53%) with a diagnosis of CDI and 1,597,513 discharges without CDI. In our matched cohorts, the attributable cost of CDI occurring during a hospitalization ranged from $1,917 to $8,317, depending on whether model was adjusted for LOS. When not adjusting for LOS, CDI-associated hospitalizations cost 1.6 times more than non-CDI associated hospitalizations. Attributable LOS of CDI was approximately 4 days. CONCLUSIONS Clostridium difficile infection in hospitalized children is associated with an economic burden similar to adult estimates. This finding supports a continued focus on preventing CDI in children as a priority. Pediatric CDI cost analyses should account for LOS as an important confounder of cost. Infect Control Hosp Epidemiol 2017;38:1472-1477.

Costs of Clostridium difficile infection in pediatric operations: A propensity score-matching analysis.

PubMed

Kulaylat, Afif N; Rocourt, Dorothy V; Podany, Abigail B; Engbrecht, Brett W; Twilley, Marianne; Santos, Mary C; Cilley, Robert E; Hollenbeak, Christopher S; Dillon, Peter W

2017-05-01

The purpose of this analysis was to assess the burden of Clostridium difficile infection in the hospitalized pediatric surgical population and to characterize its influence on the costs of care. There were 313,664 patients age 1-18 years who underwent a general thoracic or abdominal procedure in the Kids' Inpatient Database during 2003, 2006, 2009, and 2012. Logistic regression was used to model factors associated with the development of C difficile infection. A propensity score-matching analysis was performed to evaluate the influence of C difficile infection on mortality, duration of stay, and costs in similar patient cohorts. Population weights were used to estimate the national excess burden of C difficile infection on these outcomes. The overall prevalence of C difficile infection in the sampled cohort was 0.30%, with an increasing trend of C difficile infection over time in non-children's hospitals (P < .001). C difficile infection was associated with younger age, nonelective procedures, increasing comorbidities, and urban teaching hospital status (P < .001). An estimated 1,438 children developed C difficile infection after operation. After propensity score matching, the mean excess duration of stay and costs attributable to C difficile infection were 5.8 days and $12,801 (P < .001), accounting for 8,295 days spent in the hospital and $18.4 million (2012 USD) in spending annually. C difficile infection is a relatively uncommon but costly complication after pediatric operative procedures. Given the increasing trend of C difficile infection among hospitalized surgical patients, there is substantial opportunity for reduction of inpatient burden and associated costs in this potentially preventable nosocomial infection. Copyright © 2016 Elsevier Inc. All rights reserved.

Attributable costs of central line-associated bloodstream infections in a pediatric hematology/oncology population.

PubMed

Wilson, Matthew Z; Rafferty, Colleen; Deeter, Deana; Comito, Melanie A; Hollenbeak, Christopher S

2014-11-01

Although several studies have estimated the attributable cost and length of stay (LOS) of central line-associated bloodstream infections (CLABSIs) in the pediatric intensive care unit setting, little is known about the attributable costs and LOS of CLABSIs in the vulnerable pediatric hematology/oncology population. We studied a total of 1562 inpatient admissions for 291 pediatric hematology/oncology patients at a single tertiary care children's hospital in the mid-Atlantic region between January 2008 and May 2011. Costs were normalized to year 2011 dollars. Propensity score matching was used to estimate the effect of CLABSIs on total cost and LOS while controlling for other covariates. Sixty CLABSIs occurred during the 1562 admissions. Compared with the patients without a CLABSI, those who developed a CLABSI tended to be older (9.0 years vs 7.5 years; P = .026) and to have a tunneled catheter (46.7% vs 27.0%) and a peripherally inserted central catheter (20.0% vs 11.2%) as opposed to other types of catheters (P < .0001). Propensity score matching yielded matched groups without significant differences in patient characteristics. In the propensity score analysis, the attributable LOS of a CLABSI was 21.2 days (P < .0001), and the attributable cost of a CLABSI was $69,332 (P < .0001). Among pediatric hematology/oncology patients, CLABSI was associated with an additional LOS of 21 days and increased costs of nearly $70,000. These findings may inform decisions regarding the value of investing in efforts to prevent CLABSIs in this vulnerable population. Copyright © 2014 Association for Professionals in Infection Control and Epidemiology, Inc. Published by Elsevier Inc. All rights reserved.

Venous thromboembolism after induced abortion: a population-based, propensity-score-matched cohort study in Canada.

PubMed

Liu, Ning; Vigod, Simone N; Farrugia, M Michèle; Urquia, Marcelo L; Ray, Joel G

2018-06-08

A woman's risk of venous thromboembolism during pregnancy is estimated to be two-to-six times higher than her risk when she is not pregnant. Such risk estimates are largely based on pregnancies that result in delivery of a newborn baby; no estimates exist for the risk of venous thromboembolism after induced abortion, another common pregnancy outcome. To fill this knowledge gap, we aimed to assess the risk of venous thromboembolism in women whose first pregnancy ended with induced abortion. We did this propensity score-matched cohort study using data from the universal health-care system of Ontario, Canada. We included primigravid women who had an induced abortion between Jan 1, 2003, and Dec 31, 2015, and used a propensity score to match them to primigravid women who had a livebirth (1:1) or nulligravid women who were not pregnant on the procedure date of their matched counterpart and who did not conceive within 1 year afterwards (5:1). We excluded from our analysis women younger than 15 years or older than 49 years and individuals who had missing or invalid information about their sex, area of residence, residential income, or world region of origin. The primary outcome was risk of any venous thromboembolism within 42 days of the index date (defined as the date of an induced abortion, delivery date for livebirth, or for non-pregnant women the induced abortion date of their matched counterpart). We compared the rate of venous thromboembolism in primigravid women who had an induced abortion with the rate of venous thromboembolism in propensity-score-matched non-pregnant women and propensity-score-matched primigravid women whose pregnancy ended with a livebirth. We generated hazard ratios (HRs) of 42-day risk of venous thromboembolism after induced abortion using Cox proportional hazard models. We identified 194 086 eligible women whose first pregnancy ended with induced abortion, of whom 176 001 (90·7%) could be matched with women whose first pregnancy ended in delivery of a newborn. These 176 001 women were also matched to 880 005 non-pregnant women. The rate of venous thromboembolism within 42 days of an induced abortion was 30·1 (95% CI 22·0-38·2) per 100 000 women compared with 13·5 (11·1-16·0) per 100 000 women in the non-pregnant group (HR 2·23, 95% CI 1·61-3·08). The HR was 0·16 (95% CI 0·12-0·22) when compared with the women in the livebirth cohort, whose venous thromboembolism rate within 42 days postpartum was 184·7 (95% CI 164·6-204·7) per 100 000 women. The 42-day risk of venous thromboembolism after an induced abortion is double that of a matched non-pregnant woman, and is significantly lower than after a livebirth. This novel information can inform estimates of peri-procedural risk of venous thromboembolism after induced abortion. Clinicians could consider a lower threshold for ordering a diagnostic test to rule out venous thromboembolism after induced abortion than they would in a non-pregnant woman. Institute for Clinical Evaluative Sciences. Copyright © 2018 Elsevier Ltd. All rights reserved.

Analysis of Observational Studies in the Presence of Treatment Selection Bias: Effects of Invasive Cardiac Management on AMI Survival Using Propensity Score and Instrumental Variable Methods

PubMed Central

Stukel, Thérèse A.; Fisher, Elliott S; Wennberg, David E.; Alter, David A.; Gottlieb, Daniel J.; Vermeulen, Marian J.

2007-01-01

Context Comparisons of outcomes between patients treated and untreated in observational studies may be biased due to differences in patient prognosis between groups, often because of unobserved treatment selection biases. Objective To compare 4 analytic methods for removing the effects of selection bias in observational studies: multivariable model risk adjustment, propensity score risk adjustment, propensity-based matching, and instrumental variable analysis. Design, Setting, and Patients A national cohort of 122 124 patients who were elderly (aged 65–84 years), receiving Medicare, and hospitalized with acute myocardial infarction (AMI) in 1994–1995, and who were eligible for cardiac catheterization. Baseline chart reviews were taken from the Cooperative Cardiovascular Project and linked to Medicare health administrative data to provide a rich set of prognostic variables. Patients were followed up for 7 years through December 31, 2001, to assess the association between long-term survival and cardiac catheterization within 30 days of hospital admission. Main Outcome Measure Risk-adjusted relative mortality rate using each of the analytic methods. Results Patients who received cardiac catheterization (n=73 238) were younger and had lower AMI severity than those who did not. After adjustment for prognostic factors by using standard statistical risk-adjustment methods, cardiac catheterization was associated with a 50% relative decrease in mortality (for multivariable model risk adjustment: adjusted relative risk [RR], 0.51; 95% confidence interval [CI], 0.50–0.52; for propensity score risk adjustment: adjusted RR, 0.54; 95% CI, 0.53–0.55; and for propensity-based matching: adjusted RR, 0.54; 95% CI, 0.52–0.56). Using regional catheterization rate as an instrument, instrumental variable analysis showed a 16% relative decrease in mortality (adjusted RR, 0.84; 95% CI, 0.79–0.90). The survival benefits of routine invasive care from randomized clinical trials are between 8% and 21 %. Conclusions Estimates of the observational association of cardiac catheterization with long-term AMI mortality are highly sensitive to analytic method. All standard risk-adjustment methods have the same limitations regarding removal of unmeasured treatment selection biases. Compared with standard modeling, instrumental variable analysis may produce less biased estimates of treatment effects, but is more suited to answering policy questions than specific clinical questions. PMID:17227979

The effect of bovine somatotropin on the cost of producing milk: Estimates using propensity scores.

PubMed

Tauer, Loren W

2016-04-01

Annual farm-level data from New York dairy farms from the years 1994 through 2013 were used to estimate the cost effect from bovine somatotropin (bST) using propensity score matching. Cost of production was computed using the whole-farm method, which subtracts sales of crops and animals from total costs under the assumption that the cost of producing those products is equal to their sales values. For a farm to be included in this data set, milk receipts on that farm must have comprised 85% or more of total receipts, indicating that these farms are primarily milk producers. Farm use of bST, where 25% or more of the herd was treated, ranged annually from 25 to 47% of the farms. The average cost effect from the use of bST was estimated to be a reduction of $2.67 per 100 kg of milk produced in 2013 dollars, although annual cost reduction estimates ranged from statistical zero to $3.42 in nominal dollars. Nearest neighbor matching techniques generated a similar estimate of $2.78 in 2013 dollars. These cost reductions estimated from the use of bST represented a cost savings of 5.5% per kilogram of milk produced. Herd-level production increase per cow from the use of bST over 20 yr averaged 1,160 kg. Copyright © 2016 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Do family dinners reduce the risk for early adolescent substance use? A propensity score analysis.

PubMed

Hoffmann, John P; Warnick, Elizabeth

2013-01-01

The risks of early adolescent substance use on health and well-being are well documented. In recent years, several experts have claimed that a simple preventive measure for these behaviors is for families to share evening meals. In this study, we use data from the 1997 National Longitudinal Study of Youth (n = 5,419) to estimate propensity score models designed to match on a set of covariates and predict early adolescent substance use frequency and initiation. The results indicate that family dinners are not generally associated with alcohol or cigarette use or with drug use initiation. However, a continuous measure of family dinners is modestly associated with marijuana frequency, thus suggesting a potential causal impact. These results show that family dinners may help prevent one form of substance use in the short term but do not generally affect substance use initiation or alcohol and cigarette use.

Costs and outcomes associated with alternative discharge strategies following joint replacement surgery: analysis of an observational study using a propensity score.

PubMed

Coyte, P C; Young, W; Croxford, R

2000-11-01

We estimated the impact of alternative discharge strategies, following joint replacement (JR) surgery, on acute care readmission rates and the total cost of a continuum of care. Following surgery, patients were discharged to one of four destinations. Propensity scores were used to adjust costs and outcomes for potential bias in the assignment of discharge destinations. We demonstrated that the use of rehabilitation hospitals may lower readmission rates, but at a prohibitive incremental cost of each saved readmission, that patients discharged with home care had longer acute care stays than other patients, that the provision of home care services increased health system costs, and that acute care readmission rates were greatest among patients discharged with home care. Our study should be seen as one important stepping stone towards a full economic evaluation of the continuum of care for patients.

The impact of confounder selection in propensity scores when applied to prospective cohort studies in pregnancy.

PubMed

Xu, Ronghui; Hou, Jue; Chambers, Christina D

2018-06-01

Our work was motivated by small cohort studies on the risk of birth defects in infants born to pregnant women exposed to medications. We controlled for confounding using propensity scores (PS). The extremely rare events setting renders the matching or stratification infeasible. In addition, the PS itself may be formed via different approaches to select confounders from a relatively long list of potential confounders. We carried out simulation experiments to compare different combinations of approaches: IPW or regression adjustment, with 1) including all potential confounders without selection, 2) selection based on univariate association between the candidate variable and the outcome, 3) selection based on change in effects (CIE). The simulation showed that IPW without selection leads to extremely large variances in the estimated odds ratio, which help to explain the empirical data analysis results that we had observed. Copyright © 2018 Elsevier Inc. All rights reserved.

Propensity scoring and the relationship between sexual media and adolescent sexual behavior: comment on Steinberg and Monahan (2011).

PubMed

Collins, Rebecca L; Martino, Steven C; Elliott, Marc N

2011-03-01

Longitudinal research has demonstrated a link between exposure to sexual content in media and subsequent changes in adolescent sexual behavior, including initiation of intercourse and various noncoital sexual activities. Based on a reanalysis of one of the data sets involved, Steinberg and Monahan (2011) have challenged these findings. However, propensity score approaches-especially the version of this method used by Steinberg and Monahan, which lacks covariates-do not necessarily result in more accurate estimates of treatment effects than does the regression with covariates approach employed by prior research. There are also a number of problems with the specific set of analyses presented by Steinberg and Monahan and the conclusion they draw from them. In contrast to Steinberg and Monahan's claim, there is substantial evidence of an association between sexual media exposure and adolescent sexual initiation. PsycINFO Database Record (c) 2011 APA, all rights reserved.

Kinship and nonrelative foster care: the effect of placement type on child well-being.

PubMed

Font, Sarah A

2014-01-01

This study uses a national sample of 1,215 children, ages 6-17, who spent some time in formal kinship or nonrelative foster care to identify the effect of placement type on academic achievement, behavior, and health. Several identification strategies are used to reduce selection bias, including ordinary least squares, change score models, propensity score weighting, and instrumental variables regression. The results consistently estimate a negative effect of kin placements on reading scores, but kin placements appear to have no effect on child health, and findings on children's math and cognitive skills test scores and behavioral problems are mixed. Estimated declines in both academic achievement and behavioral problems are concentrated among children who are lower functioning at baseline. © 2014 The Author. Child Development © 2014 Society for Research in Child Development, Inc.

Association between long work hours and depressive state: a pilot study of propensity score matched Japanese white-collar workers.

PubMed

Uchida, Mitsuo; Morita, Hiroshi

2018-06-01

Although long work hours have been associated with various physical health problems, studies of their association with mental health have yielded inconsistent results, due to differences in study settings, study outcome and/or unmeasured background factors. In this study, we used a propensity score method to evaluate the association between work hours and depressive state. A total of 467 Japanese white-collar workers were surveyed and divided into long and regular work hour groups according to overtime work records. Propensity score matching was performed based on 32 individual background and workplace factors, yielding 74 pairs of propensity-matched subjects. CES-D score, an indicator of depressive state, did not differ significantly among the two groups (p=0.203). However, work motivation, work control, social support and emotional stability correlated with CES-D score. These findings suggest that work control and social support factors are more associated with depressive state than control of work hours. These results also suggest that it is possible to use propensity score matching to evaluate the association between work hours and mental health in occupational study settings. Further studies, in larger populations, are required to determine the association between work hours and mental health parameters.

The effect of intrapartum antibiotics on early-onset neonatal sepsis in Dhaka, Bangladesh: a propensity score matched analysis

PubMed Central

2014-01-01

Background We estimate the effect of antibiotics given in the intrapartum period on early-onset neonatal sepsis in Dhaka, Bangladesh using propensity score techniques. Methods We followed 600 mother-newborn pairs as part of a cohort study at a maternity center in Dhaka. Some pregnant women received one dose of intravenous antibiotics during labor based on clinician discretion. Newborns were followed over the first seven days of life for early-onset neonatal sepsis defined by a modified version of the World Health Organization Young Infants Integrated Management of Childhood Illnesses criteria. Using propensity scores we matched women who received antibiotics with similar women who did not. A final logistic regression model predicting sepsis was run in the matched sample controlling for additional potential confounders. Results Of the 600 mother-newborn pairs, 48 mothers (8.0%) received antibiotics during the intrapartum period. Seventy-seven newborns (12.8%) were classified with early-onset neonatal sepsis. Antibiotics appeared to be protective (odds ratio 0.381, 95% confidence interval 0.115–1.258), however this was not statistically significant. The results were similar after adjusting for prematurity, wealth status, and maternal colonization status (odds ratio 0.361, 95% confidence interval 0.106–1.225). Conclusions Antibiotics administered during the intrapartum period may reduce the risk of early-onset neonatal sepsis in high neonatal mortality settings like Dhaka. PMID:24742087

Influencing Transfer and Baccalaureate Attainment for Community College Students through State Grant Aid: Quasi-Experimental Evidence from Texas

ERIC Educational Resources Information Center

Bordoloi Pazich, Loni

2014-01-01

This study uses statewide longitudinal data from Texas to estimate the impact of a state grant program intended to encourage low-income community college students to transfer to four-year institutions and complete the baccalaureate. Quasi-experimental methods employed include propensity score matching and regression discontinuity. Results indicate…

Estimating the Impact of the PROMISE Scholarship Using Propensity Score Weighted Frontier Fuzzy Regression Discontinuity Design

ERIC Educational Resources Information Center

Shobo, Yetty; Wong, Jen D.; Bell, Angie

2014-01-01

Regression discontinuity (RD), an "as good as randomized," research design is increasingly prominent in education research in recent years; the design gets eligible quasi-experimental designs as close as possible to experimental designs by using a stated threshold on a continuous baseline variable to assign individuals to a…

Required, Practical, or Unnecessary? An Examination and Demonstration of Propensity Score Matching Using Longitudinal Secondary Data

ERIC Educational Resources Information Center

Padgett, Ryan D.; Salisbury, Mark H.; An, Brian P.; Pascarella, Ernest T.

2010-01-01

The sophisticated analytical techniques available to institutional researchers give them an array of procedures to estimate a causal effect using observational data. But as many quantitative researchers have discovered, access to a wider selection of statistical tools does not necessarily ensure construction of a better analytical model. Moreover,…

The Effects of Runaway-Homeless Episodes on High School Dropout

ERIC Educational Resources Information Center

Aratani, Yumiko; Cooper, Janice L.

2015-01-01

This article uses data from the National Longitudinal Survey of Youth 1997 to examine the relationship between running away from home between the ages of 12 and 14 and dropping from high school among youth. Propensity score matching was conducted in estimating the effect of running away on high school dropout while controlling for confounding…

Estimating Impacts on Program-Related Subgroups Using Propensity Score Matching: Evidence from the Early College High School Study

ERIC Educational Resources Information Center

Unlu, Fatih; Yamaguchi, Ryoko; Bernstein, Larry; Edmunds, Julie

2010-01-01

This paper addresses methodological issues arising from an experimental study of North Carolina's Early College High School Initiative, a four-year longitudinal experimental study funded by Institute for Education Sciences. North Carolina implemented the Early College High School (ECHS) Initiative in response to low high school graduation rates.…

Estimating Treatment Effects via Multilevel Matching within Homogenous Groups of Clusters

ERIC Educational Resources Information Center

Steiner, Peter M.; Kim, Jee-Seon

2015-01-01

Despite the popularity of propensity score (PS) techniques they are not yet well studied for matching multilevel data where selection into treatment takes place among level-one units within clusters. This paper suggests a PS matching strategy that tries to avoid the disadvantages of within- and across-cluster matching. The idea is to first…

The Effect of Postsecondary Coenrollment on College Success: Initial Evidence and Implications for Policy and Future Research

ERIC Educational Resources Information Center

Wang, Xueli; McCready, Bo

2013-01-01

Drawing upon the latest data from the Beginning Postsecondary Students Longitudinal Study (BPS:04/09) and the Postsecondary Education Transcript Data (PETS:09), this study employed propensity score matching and postmatching logistic regression to estimate the extent to which postsecondary coenrollment affects persistence and attainment of students…

Improving Generalizations from Experiments Using Propensity Score Subclassification: Assumptions, Properties, and Contexts

ERIC Educational Resources Information Center

Tipton, Elizabeth

2013-01-01

As a result of the use of random assignment to treatment, randomized experiments typically have high internal validity. However, units are very rarely randomly selected from a well-defined population of interest into an experiment; this results in low external validity. Under nonrandom sampling, this means that the estimate of the sample average…

Handling nonresponse in surveys: analytic corrections compared with converting nonresponders.

PubMed

Jenkins, Paul; Earle-Richardson, Giulia; Burdick, Patrick; May, John

2008-02-01

A large health survey was combined with a simulation study to contrast the reduction in bias achieved by double sampling versus two weighting methods based on propensity scores. The survey used a census of one New York county and double sampling in six others. Propensity scores were modeled as a logistic function of demographic variables and were used in conjunction with a random uniform variate to simulate response in the census. These data were used to estimate the prevalence of chronic disease in a population whose parameters were defined as values from the census. Significant (p < 0.0001) predictors in the logistic function included multiple (vs. single) occupancy (odds ratio (OR) = 1.3), bank card ownership (OR = 2.1), gender (OR = 1.5), home ownership (OR = 1.3), head of household's age (OR = 1.4), and income >$18,000 (OR = 0.8). The model likelihood ratio chi-square was significant (p < 0.0001), with the area under the receiver operating characteristic curve = 0.59. Double-sampling estimates were marginally closer to population values than those from either weighting method. However, the variance was also greater (p < 0.01). The reduction in bias for point estimation from double sampling may be more than offset by the increased variance associated with this method.

Estimating the heterogeneous relationship between peer drinking and youth alcohol consumption in Chile using propensity score stratification.

PubMed

Han, Yoonsun; Grogan-Kaylor, Andrew; Delva, Jorge; Xie, Yu

2014-11-17

When estimating the association between peer and youth alcohol consumption, it is critical to account for possible differential levels of response to peer socialization processes across youth, in addition to variability in individual, family, and social factors. Failure to account for intrinsic differences in youth's response to peers may pose a threat of selection bias. To address this issue, we used a propensity score stratification method to examine whether the size of the association between peer and youth drinking is contingent upon differential predicted probabilities of associating with alcohol-consuming friends. Analyzing a Chilean youth sample (N = 914) of substance use, we found that youths are susceptible to the detrimental role of peer drinkers, but the harmful relationship with one's own drinking behavior may be exacerbated among youth who already have a high probability of socializing with peers who drink. In other words, computing a single weighted-average estimate for peer drinking would have underestimated the detrimental role of peers, particularly among at-risk youths, and overestimated the role of drinking peers among youths who are less susceptible to peer socialization processes. Heterogeneous patterns in the association between peer and youth drinking may shed light on social policies that target at-risk youths.

The Utility of Therapeutic Hypothermia for Post-Cardiac Arrest Syndrome Patients With an Initial Nonshockable Rhythm.

PubMed

Perman, Sarah M; Grossestreuer, Anne V; Wiebe, Douglas J; Carr, Brendan G; Abella, Benjamin S; Gaieski, David F

2015-12-01

Therapeutic hypothermia (TH) attenuates reperfusion injury in comatose survivors of cardiac arrest. The utility of TH in patients with nonshockable initial rhythms has not been widely accepted. We sought to determine whether TH improved neurological outcome and survival in postarrest patients with nonshockable rhythms. We identified 519 patients after in- and out-of-hospital cardiac arrest with nonshockable initial rhythms from the Penn Alliance for Therapeutic Hypothermia (PATH) registry between 2000 and 2013. Propensity score matching was used. Patient and arrest characteristics used to estimate the propensity to receive TH were age, sex, location of arrest, witnessed arrest, and duration of arrest. To determine the association between TH and outcomes, we created 2 multivariable logistic models controlling for confounders. Of 201 propensity score-matched pairs, mean age was 63 ± 17 years, 51% were male, and 60% had an initial rhythm of pulseless electric activity. Survival to hospital discharge was greater in patients who received TH (17.6% versus 28.9%; P < 0.01), as was a discharge Cerebral Performance Category of 1 to 2 (13.7% versus 21.4%; P = 0.04). In adjusted analyses, patients who received TH were more likely to survive (odds ratio, 2.8; 95% confidence interval, 1.6-4.7) and to have better neurological outcome (odds ratio, 3.5; 95% confidence interval, 1.8-6.6) than those that did not receive TH. Using propensity score matching, we found that patients with nonshockable initial rhythms treated with TH had better survival and neurological outcome at hospital discharge than those who did not receive TH. Our findings further support the use of TH in patients with initial nonshockable arrest rhythms. © 2015 American Heart Association, Inc.

Curricular Policy as a Collective Effects Problem: A Distributional Approach

PubMed Central

Penner, Andrew M.; Domina, Thurston; Penner, Emily K.; Conley, AnneMarie

2015-01-01

Current educational policies in the United States attempt to boost student achievement and promote equality by intensifying the curriculum and exposing students to more advanced coursework. This paper investigates the relationship between one such effort -- California's push to enroll all 8th grade students in Algebra -- and the distribution of student achievement. We suggest that this effort is an instance of a “collective effects” problem, where the population-level effects of a policy are different from its effects at the individual level. In such contexts, we argue that it is important to consider broader population effects as well as the difference between “treated” and “untreated” individuals. To do so, we present differences in inverse propensity score weighted distributions to investigate how this curricular policy changed the distribution of student achievement more broadly. We find that California's attempt to intensify the curriculum did not raise test scores at the bottom of the distribution, but did lower scores at the top of the distribution. These results highlight the efficacy of inverse propensity score weighting approaches for estimating collective effects, and provide a cautionary tale for curricular intensification efforts and other policies with collective effects. PMID:26004485

Adjusting for Health Status in Non-Linear Models of Health Care Disparities

PubMed Central

Cook, Benjamin L.; McGuire, Thomas G.; Meara, Ellen; Zaslavsky, Alan M.

2009-01-01

This article compared conceptual and empirical strengths of alternative methods for estimating racial disparities using non-linear models of health care access. Three methods were presented (propensity score, rank and replace, and a combined method) that adjust for health status while allowing SES variables to mediate the relationship between race and access to care. Applying these methods to a nationally representative sample of blacks and non-Hispanic whites surveyed in the 2003 and 2004 Medical Expenditure Panel Surveys (MEPS), we assessed the concordance of each of these methods with the Institute of Medicine (IOM) definition of racial disparities, and empirically compared the methods' predicted disparity estimates, the variance of the estimates, and the sensitivity of the estimates to limitations of available data. The rank and replace and combined methods (but not the propensity score method) are concordant with the IOM definition of racial disparities in that each creates a comparison group with the appropriate marginal distributions of health status and SES variables. Predicted disparities and prediction variances were similar for the rank and replace and combined methods, but the rank and replace method was sensitive to limitations on SES information. For all methods, limiting health status information significantly reduced estimates of disparities compared to a more comprehensive dataset. We conclude that the two IOM-concordant methods were similar enough that either could be considered in disparity predictions. In datasets with limited SES information, the combined method is the better choice. PMID:20352070

The Safety of Ovarian Preservation in Stage I Endometrial Endometrioid Adenocarcinoma Based on Propensity Score Matching.

PubMed

Hou, Ting; Sun, Yidi; Li, Junyi; Liu, Chenglin; Wang, Zhen; Li, Yixue; Lu, Yuan

2017-01-01

Most patients with early stage endometrial endometrioid adenocarcinoma (EEAC) are treated with hysterectomy and bilateral oophorectomy. But this surgical menopause leads to long-term sequelae for premenopausal women, especially for young women of childbearing age. This population-based study was to evaluate the safety of ovarian preservation in young women with stage I EEAC. Patients of age 50 or younger with stage I EEAC were explored from the Surveillance, Epidemiology and End Results program database during 2004 to 2013. Propensity score matching was used to randomize the data set and reduce the selection biases of doctors. Univariate analysis and multivariate cox proportional hazards model were utilized to estimate the safety of ovarian preservation. A total of 7183 patients were identified, and ovarian preservation was performed in 863 (12 %) patients. Compared with women treated with oophorectomy, patients with ovarian preservation significantly tend to be younger at diagnosis (P-value < 0.001) and more likely diagnosed as stage IA EEAC, to have better differentiated tumor tissues and smaller tumors, as well as less likely to undergo radiation and lymphadenectomy. 863 patients treated with oophorectomy were selected by propensity score matching. After propensity score matching, the differences of all characteristics between ovarian preservation and oophorectomy were not significant and potential confounders in the two groups decreased. In univariate analysis of matched population, ovarian preservation had no effect on overall (P-value=0.928) and cancer-specific (P-value=0.390) mortality. In propensityadjusted multivariate analysis, ovarian preservation was not significantly associated with overall (HR=0.69, 95%CI=0.41-1.68, P-value=0.611) and cancer-specific (HR=1.65, 95%CI=0.54-5.06, Pvalue= 0.379) survival. Ovarian preservation is safe for young women with stage I EEAC, which is not significantly associated with overall and cancer-specific mortality. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Long-Term Consequences of Early Sexual Initiation on Young Adult Health: A Causal Inference Approach

ERIC Educational Resources Information Center

Kugler, Kari C.; Vasilenko, Sara A.; Butera, Nicole M.; Coffman, Donna L.

2017-01-01

Although early sexual initiation has been linked to negative outcomes, it is unknown whether these effects are causal. In this study, we use propensity score methods to estimate the causal effect of early sexual initiation on young adult sexual risk behaviors and health outcomes using data from the National Longitudinal Study of Adolescent to…

Grants in Italian University: A Look at the Heterogeneity of Their Impact on Students' Performances

ERIC Educational Resources Information Center

Agasisti, Tommaso; Murtinu, Samuele

2016-01-01

In this paper, we estimate the effect of receiving financial aid for a cohort of students who enrolled at Politecnico di Milano (Italy) in the year 2007/2008, through a propensity score matching approach. Using administrative data about these students for four years, the impact of the financial aid on several dimensions of academic performance was…

Fighting fire with fire: estimating the efficacy of wildfire mitigation programs using propensity scores

Treesearch

David T. Butry

2009-01-01

This paper examines the effect wildfire mitigation has on broad-scale wildfire behavior. Each year, hundreds of million of dollars are spent on fire suppression and fuels management applications, yet little is known, quantitatively, of the returns to these programs in terms of their impact on wildfire extent and intensity. This is especially true when considering that...

Revisiting the Impact of Part-Time Work on Adolescent Adjustment: Distinguishing between Selection and Socialization Using Propensity Score Matching

ERIC Educational Resources Information Center

Monahan, Kathryn C.; Lee, Joanna M.; Steinberg, Laurence

2011-01-01

The impact of part-time employment on adolescent functioning remains unclear because most studies fail to adequately control for differential selection into the workplace. The present study reanalyzes data from L. Steinberg, S. Fegley, and S. M. Dornbusch (1993) using multiple imputation, which minimizes bias in effect size estimation, and 2 types…

Fall-Related Hospitalization and Facility Costs among Residents of Institutions Providing Long-Term Care

ERIC Educational Resources Information Center

Carroll, Norman V.; Delafuente, Jeffrey C.; Cox, Fred M.; Narayanan, Siva

2008-01-01

Purpose: The purpose of this study was to estimate hospital and long-term-care costs resulting from falls in long-term-care facilities (LTCFs). Design and Methods: The study used a retrospective, pre/post with comparison group design. We used matching, based on propensity scores, to control for baseline differences between fallers and non-fallers.…

The Impact of Library Resource Utilization on Undergraduate Students' Academic Performance: A Propensity Score Matching Design

ERIC Educational Resources Information Center

Kot, Felly Chiteng; Jones, Jennifer L.

2015-01-01

This study uses three cohorts of first-time, full-time undergraduate students (N = 8,652) at a large, metropolitan, public research university to examine the impact of student use of three library resources (workstations, study rooms, and research clinics) on academic performance. To deal with self-selection bias and estimate this impact more…

To Math or Not to Math: The Algebra-Calculus Pipeline and Postsecondary Mathematics Remediation

ERIC Educational Resources Information Center

Showalter, Daniel A.

2017-01-01

This article reports on a study designed to estimate the effect of high school coursetaking in the algebra-calculus pipeline on the likelihood of placing out of postsecondary remedial mathematics. A nonparametric variant of propensity score analysis was used on a nationally representative data set to remove selection bias and test for an effect…

Using Propensity Score Matching Methods to Improve Generalization from Randomized Experiments

ERIC Educational Resources Information Center

Tipton, Elizabeth

2011-01-01

The main result of an experiment is typically an estimate of the average treatment effect (ATE) and its standard error. In most experiments, the number of covariates that may be moderators is large. One way this issue is typically skirted is by interpreting the ATE as the average effect for "some" population. Cornfield and Tukey (1956)…

A Cross-National Analysis of the Relations of School Choice and Effectiveness Differences between Private-Dependent and Public Schools

ERIC Educational Resources Information Center

Dronkers, Jaap; Avram, Silvia

2010-01-01

We apply propensity score matching to the estimation of differential school effectiveness between the publicly funded private sector and the public sector in a sample of 26 countries. This technique allows us to distinguish between school choice and school effectiveness processes and thus to account for selectivity issues involved in the…

Oncologic outcomes of single-incision versus conventional laparoscopic anterior resection for sigmoid colon cancer: a propensity-score matching analysis.

PubMed

Kim, Chang Woo; Cho, Min Soo; Baek, Se Jin; Hur, Hyuk; Min, Byung Soh; Kang, Jeonghyun; Baik, Seung Hyuk; Lee, Kang Young; Kim, Nam Kyu

2015-03-01

The aim of this study was to investigate oncologic outcomes, as well as perioperative and pathologic outcomes, of single-incision laparoscopic anterior resection (SILAR) compared with conventional laparoscopic anterior resection (CLAR) for sigmoid colon cancer using propensity-score matching analysis. From July 2009 through April 2012, a total of 407 patients underwent laparoscopic anterior resection for sigmoid colon cancer. Data on short- and long-term outcomes were collected prospectively and reviewed. Propensity-score matching was applied at a ratio of 1:2 comparing the SILAR (n = 60) and CLAR (n = 120) groups. There was no difference in operation time, estimated blood loss, time to soft diet, and length of hospital stay; however, the SILAR group showed less pain on postoperative day 2 (mean 2.6 vs. 3.6; p = 0.000) and shorter length of incision (3.3 vs. 7.7 cm; p = 0.000) compared with the CLAR group. Morbidity, mortality, and pathologic outcomes were similar in both groups. The 3-year overall survival rates were 94.5 versus 97.1% (p = 0.223), and disease-free survival rates were 89.5 versus 87.4% (p = 0.751) in the SILAR and CLAR groups, respectively. The long-term oncologic outcomes, as well as short-term outcomes, of SILAR are comparable with those of CLAR. Although SILAR might have some technical difficulties, it appears to be a safe and feasible option, with better cosmetic results.

Effects of the body mass index (BMI) on the surgical outcomes of laparoscopic fundoplication for gastro-esophageal reflux disease: a propensity score-matched analysis.

PubMed

Hoshino, Masato; Omura, Nobuo; Yano, Fumiaki; Tsuboi, Kazuto; Yamamoto, Se Ryung; Akimoto, Shunsuke; Masuda, Takahiro; Kashiwagi, Hideyuki; Yanaga, Katsuhiko

2018-02-01

In the present study, we examined how the body mass index (BMI) affected the outcomes of laparoscopic fundoplication for GERD in patients, whose backgrounds were matched in a propensity score-matched analysis. We divided the patients into two groups (BMI <25 kg/m 2 and BMI ≥25 kg/m 2 ). The following background information was matched for the propensity score-matched analysis: sex, age, degree of esophageal hiatal hernia, acid exposure time, and degree of reflux esophagitis. In total, 105 subjects were extracted in each group. The surgical outcomes and postoperative outcomes of patients with BMI <25 kg/m 2 (Group A) and those with BMI ≥25 kg/m 2 (Group B) were compared and examined. There were no differences in the surgical procedure, intraoperative complications, or estimated blood loss (p = 0.876, p = 0.516, p = 0.438, respectively); however, the operative time was significantly prolonged in Group B (p = 0.003). The rate of postoperative recurrence in Group A was 17% (15/87 patients), while that in Group B was 11% (12/91 patients), and did not differ to a statistically significant extent (p = 0.533). Although the operative time for GERD in obese patients was prolonged in comparison with non-obese patients, there was no difference in the rate of postoperative recurrence.

Estimating Causal Effects With Propensity Score Models: An Evaluation of the Touch Condom Media Campaign in Pakistan.

PubMed

Beaudoin, Christopher E; Chen, Hongliang; Agha, Sohail

2016-01-01

Rapid population growth in Pakistan poses major risks, including those pertinent to public health. In the context of family planning in Pakistan, the current study evaluates the Touch condom media campaign and its effects on condom-related awareness, attitudes, behavioral intention, and behavior. This evaluation relies on 3 waves of panel survey data from men married to women ages 15-49 living in urban and rural areas in Pakistan (N = 1,012): Wave 1 was March 15 to April 7, 2009; Wave 2 was August 10 to August 24, 2009; and Wave 3 was May 1 to June 13, 2010. Analysis of variance provided evidence of improvements in 10 of 11 condom-related outcomes from Wave 1 to Wave 2 and Wave 3. In addition, there was no evidence of outcome decay 1 year after the conclusion of campaign advertising dissemination. To help compensate for violating the assumption of random assignment, propensity score modeling offered evidence of the beneficial effects of confirmed Touch ad recall on each of the 11 outcomes in at least 1 of 3 time-lagged scenarios. By using these different time-lagged scenarios (i.e., from Wave 1 to Wave 2, from Wave 1 to Wave 3, and from Wave 2 to Wave 3), propensity score modeling permitted insights into how the campaign had time-variant effects on the different types of condom-related outcomes, including carryover effects of the media campaign.

On the use and misuse of scalar scores of confounders in design and analysis of observational studies.

PubMed

Pfeiffer, R M; Riedl, R

2015-08-15

We assess the asymptotic bias of estimates of exposure effects conditional on covariates when summary scores of confounders, instead of the confounders themselves, are used to analyze observational data. First, we study regression models for cohort data that are adjusted for summary scores. Second, we derive the asymptotic bias for case-control studies when cases and controls are matched on a summary score, and then analyzed either using conditional logistic regression or by unconditional logistic regression adjusted for the summary score. Two scores, the propensity score (PS) and the disease risk score (DRS) are studied in detail. For cohort analysis, when regression models are adjusted for the PS, the estimated conditional treatment effect is unbiased only for linear models, or at the null for non-linear models. Adjustment of cohort data for DRS yields unbiased estimates only for linear regression; all other estimates of exposure effects are biased. Matching cases and controls on DRS and analyzing them using conditional logistic regression yields unbiased estimates of exposure effect, whereas adjusting for the DRS in unconditional logistic regression yields biased estimates, even under the null hypothesis of no association. Matching cases and controls on the PS yield unbiased estimates only under the null for both conditional and unconditional logistic regression, adjusted for the PS. We study the bias for various confounding scenarios and compare our asymptotic results with those from simulations with limited sample sizes. To create realistic correlations among multiple confounders, we also based simulations on a real dataset. Copyright © 2015 John Wiley & Sons, Ltd.

Regulatory considerations in the design of comparative observational studies using propensity scores.

PubMed

Yue, Lilly Q

2012-01-01

In the evaluation of medical products, including drugs, biological products, and medical devices, comparative observational studies could play an important role when properly conducted randomized, well-controlled clinical trials are infeasible due to ethical or practical reasons. However, various biases could be introduced at every stage and into every aspect of the observational study, and consequently the interpretation of the resulting statistical inference would be of concern. While there do exist statistical techniques for addressing some of the challenging issues, often based on propensity score methodology, these statistical tools probably have not been as widely employed in prospectively designing observational studies as they should be. There are also times when they are implemented in an unscientific manner, such as performing propensity score model selection for a dataset involving outcome data in the same dataset, so that the integrity of observational study design and the interpretability of outcome analysis results could be compromised. In this paper, regulatory considerations on prospective study design using propensity scores are shared and illustrated with hypothetical examples.

Can We Train Machine Learning Methods to Outperform the High-dimensional Propensity Score Algorithm?

PubMed

Karim, Mohammad Ehsanul; Pang, Menglan; Platt, Robert W

2018-03-01

The use of retrospective health care claims datasets is frequently criticized for the lack of complete information on potential confounders. Utilizing patient's health status-related information from claims datasets as surrogates or proxies for mismeasured and unobserved confounders, the high-dimensional propensity score algorithm enables us to reduce bias. Using a previously published cohort study of postmyocardial infarction statin use (1998-2012), we compare the performance of the algorithm with a number of popular machine learning approaches for confounder selection in high-dimensional covariate spaces: random forest, least absolute shrinkage and selection operator, and elastic net. Our results suggest that, when the data analysis is done with epidemiologic principles in mind, machine learning methods perform as well as the high-dimensional propensity score algorithm. Using a plasmode framework that mimicked the empirical data, we also showed that a hybrid of machine learning and high-dimensional propensity score algorithms generally perform slightly better than both in terms of mean squared error, when a bias-based analysis is used.

A propensity scoring approach to characterizing the effects of maternal smoking during pregnancy on offspring's initial responses to cigarettes and alcohol

PubMed Central

Bidwell, L. Cinnamon; Palmer, Rohan H.C.; Brick, Leslie; Madden, Pamela A.F.; Heath, Andrew C.; Knopik, Valerie S.

2016-01-01

When examining the effects of prenatal exposure to maternal smoking during pregnancy (MSDP) on later offspring substance use, it is critical to consider familial environments confounded with MSDP. The purpose of this study was to examine the effect of MSDP on offspring's initial reactions to cigarettes and alcohol, which are indicators of future substance-use related problems. We tested these effects using two propensity score approaches (1) by controlling for confounding using the MSDP propensity score and 2) examining effects of MSDP across the MSDP risk distribution by grouping individuals into quantiles based on their MSDP propensity score. This study used data from 829 unrelated mothers with a reported lifetime history of smoking to determine the propensity for smoking only during their first trimester (MSDP-E) or throughout their entire pregnancy (MSDP-T). Propensity score analyses focused on the offspring (N=1616 female twins) of a large subset of these mothers. We examined the effects of levels of MSDP-E/T on offspring initial reactions to their first experiences with alcohol and cigarettes, across the distribution of liability for MSDP-E/T. MSDP-E/T emerged as significant predictors of offspring reactions to alcohol and cigarettes, but the effects were confounded by the familial liability for MSDP. Further, the unique MSDP effects that emerged were not uniform across the MSDP familial risk distribution. Our findings underscore the importance of properly accounting for correlated familial risk factors when examining the effects of MSDP on substance related outcomes. PMID:27098899

Obsessive-compulsive disorder and its relationship with disgust vulnerability and conscientiousness.

PubMed

Inchausti, Felix; Delgado, Ana R; Prieto, Gerardo

2015-01-01

The aim of this study was to analyze the relationship between Obsessive-Compulsive Disorder (OCD) symptoms, disgust vulnerability, and the Five Factor Model (FFM) of personality. The sample consisted of 100 adult patients with OCD as a primary diagnosis and 246 with other anxiety disorders (OADs), who responded to OCD, disgust vulnerability, anxiety, depression and personality questionnaires. To perform parametric statistical calculations, all questionnaire scores were transformed from raw ordinal-scale scores to Rasch measures, with interval properties. OCD patients scored significantly higher than OAD patients on DPSS-R Disgust Sensitivity and DPSS-R Disgust Propensity, with a large effect size observed on Disgust Propensity. Furthermore, strong correlations were observed between DPSS-R Propensity to Disgust model scores and DOCS Contamination model scores. Finally, NEO FFI Conscientiousness trait was significantly higher in OCD patients.

The Benefits of College Athletic Success: An Application of the Propensity Score Design with Instrumental Variables. NBER Working Paper No. 18196

ERIC Educational Resources Information Center

Anderson, Michael L.

2012-01-01

Spending on big-time college athletics is often justified on the grounds that athletic success attracts students and raises donations. Testing this claim has proven difficult because success is not randomly assigned. We exploit data on bookmaker spreads to estimate the probability of winning each game for college football teams. We then condition…

Using Propensity Score Methods to Approximate Factorial Experimental Designs to Analyze the Relationship between Two Variables and an Outcome

ERIC Educational Resources Information Center

Dong, Nianbo

2015-01-01

Researchers have become increasingly interested in programs' main and interaction effects of two variables (A and B, e.g., two treatment variables or one treatment variable and one moderator) on outcomes. A challenge for estimating main and interaction effects is to eliminate selection bias across A-by-B groups. I introduce Rubin's causal model to…

Poverty and Gender Perspective in Productive Projects for Rural Women in Mexico: Impact Evaluation of a Pilot Project

ERIC Educational Resources Information Center

Urquieta-Salomon, Jose E.; Tepichin-Valle, Ana Maria; Tellez-Rojo, Martha Maria

2009-01-01

The objective of this study is to evaluate the impact of a pilot study that promoted productive and capacity-building activities among deprived rural women of Mexico. The evaluation design is observational; 1,278 women are interviewed, and the comparison group is estimated by propensity score matching. The results show a positive impact on the…

Addendum: han, y.; grogan-kaylor, a.; delva, j.; xie, y. Estimating the heterogeneous relationship between peer drinking and youth alcohol consumption in chile using propensity score stratification. Int. J. Environ. Res. Public health 2014, 11, 11879-11897.

PubMed

Han, Yoonsun; Grogan-Kaylor, Andrew; Delva, Jorge; Xie, Yu

2015-01-30

The authors wish to update the Acknowledgments in their paper published in International Journal of Environmental Research and Public Health [1], doi:10.3390/ijerph111111879, website: http://www.mdpi.com/1660-4601/11/11/11879.[...].

Impact of prestroke selective serotonin reuptake inhibitor treatment on stroke severity and mortality.

PubMed

Mortensen, Janne Kaergaard; Larsson, Heidi; Johnsen, Søren Paaske; Andersen, Grethe

2014-07-01

Selective serotonin reuptake inhibitors (SSRIs) have been associated with an increased risk of bleeding but also a possible neuroprotective effect in stroke. We aimed to examine the implications of prestroke SSRI use in hemorrhagic and ischemic stroke. We conducted a registry-based propensity score-matched follow-up study among first-ever patients with hemorrhage and ischemic stroke in Denmark (2003-2012). Multiple conditional logistic regression was used to compute adjusted odds ratios of severe stroke and death within 30 days. Among 1252 hemorrhagic strokes (626 prestroke SSRI users and 626 propensity score-matched nonusers), prestroke SSRI use was associated with an increased risk of the strokes being severe (adjusted propensity score-matched odds ratios, 1.41; confidence interval, 1.08-1.84) and an increased risk of death within 30 days (adjusted propensity score-matched odds ratios, 1.60; confidence interval, 1.17-2.18). Among 8956 patients with ischemic stroke (4478 prestroke SSRI users and 4478 propensity score-matched nonusers), prestroke SSRI use was not associated with the risk of severe stroke or death within 30 days. Prestroke SSRI use is associated with increased stroke severity and mortality in patients with hemorrhagic stroke. Although prestroke depression in itself may increase stroke severity and mortality, this was not found in SSRI users with ischemic stroke. © 2014 American Heart Association, Inc.

Can Propensity Score Analysis Approximate Randomized Experiments Using Pretest and Demographic Information in Pre-K Intervention Research?

PubMed

Dong, Nianbo; Lipsey, Mark W

2017-01-01

It is unclear whether propensity score analysis (PSA) based on pretest and demographic covariates will meet the ignorability assumption for replicating the results of randomized experiments. This study applies within-study comparisons to assess whether pre-Kindergarten (pre-K) treatment effects on achievement outcomes estimated using PSA based on a pretest and demographic covariates can approximate those found in a randomized experiment. Data-Four studies with samples of pre-K children each provided data on two math achievement outcome measures with baseline pretests and child demographic variables that included race, gender, age, language spoken at home, and mother's highest education. Research Design and Data Analysis-A randomized study of a pre-K math curriculum provided benchmark estimates of effects on achievement measures. Comparison samples from other pre-K studies were then substituted for the original randomized control and the effects were reestimated using PSA. The correspondence was evaluated using multiple criteria. The effect estimates using PSA were in the same direction as the benchmark estimates, had similar but not identical statistical significance, and did not differ from the benchmarks at statistically significant levels. However, the magnitude of the effect sizes differed and displayed both absolute and relative bias larger than required to show statistical equivalence with formal tests, but those results were not definitive because of the limited statistical power. We conclude that treatment effect estimates based on a single pretest and demographic covariates in PSA correspond to those from a randomized experiment on the most general criteria for equivalence.

Robot-assisted laparoscopic partial nephrectomy versus laparoscopic partial nephrectomy: A propensity score-matched comparative analysis of surgical outcomes and preserved renal parenchymal volume.

PubMed

Tachibana, Hidekazu; Takagi, Toshio; Kondo, Tsunenori; Ishida, Hideki; Tanabe, Kazunari

2018-04-01

To compare surgical outcomes, including renal function and the preserved renal parenchymal volume, between robot-assisted laparoscopic partial nephrectomy and laparoscopic partial nephrectomy using propensity score-matched analyses. In total, 253 patients, with a normal contralateral kidney, who underwent laparoscopic partial nephrectomy (n = 131) or robot-assisted laparoscopic partial nephrectomy (n = 122) with renal arterial clamping between 2010 and 2015, were included. Patients' background and tumor factors were adjusted by propensity score matching. Surgical outcomes, including postoperative renal function, complications, warm ischemia time and preserved renal parenchymal volume, evaluated by volumetric analysis, were compared between the surgical procedures. After matching, 64 patients were assigned to each group. The mean age was 56-57 years, and the mean tumor size was 22 mm. Approximately 50% of patients had low complexity tumors (RENAL nephrometry score 4-7). The incidence rate of acute kidney failure was significantly lower in the robot-assisted laparoscopic partial nephrectomy (11%) than laparoscopic partial nephrectomy (23%) group (P = 0.049), and warm ischemia time shorter in the robot-assisted laparoscopic partial nephrectomy (17 min) than laparoscopic partial nephrectomy (25 min) group (P < 0.0001). The preservation rate of renal function, measured by the estimated glomerular filtration rate, at 6 months post-surgery was 96% for robot-assisted laparoscopic partial nephrectomy and 90% for laparoscopic partial nephrectomy (P < 0.0001). The preserved renal parenchymal volume was higher for robot-assisted laparoscopic partial nephrectomy (89%) than laparoscopic partial nephrectomy (77%; P < 0.0001). The rate of perioperative complications, surgical margin status and length of hospital stay were equivalent for both techniques. Robot-assisted laparoscopic partial nephrectomy allows to achieve better preservation of renal function and parenchymal volume than laparoscopic partial nephrectomy. © 2018 The Japanese Urological Association.

Propensity Score Matching within Prognostic Strata

ERIC Educational Resources Information Center

Kelcey, Ben

2013-01-01

A central issue in nonexperimental studies is identifying comparable individuals to remove selection bias. One common way to address this selection bias is through propensity score (PS) matching. PS methods use a model of the treatment assignment to reduce the dimensionality of the covariate space and identify comparable individuals. parallel to…

Using Propensity Scores to Reduce Selection Bias in Mathematics Education Research

ERIC Educational Resources Information Center

Graham, Suzanne E.

2010-01-01

Selection bias is a problem for mathematics education researchers interested in using observational rather than experimental data to make causal inferences about the effects of different instructional methods in mathematics on student outcomes. Propensity score methods represent 1 approach to dealing with such selection bias. This article…

Multilevel Propensity Score Matching within and across Schools

ERIC Educational Resources Information Center

Kelcey, Benjamin

2011-01-01

A central issue in nonexperimental studies is the identification of comparable individuals (e.g. students) to remove selection bias. One such increasingly common method to identify comparable individuals and address selection bias is the propensity score (PS). PS methods rely on a model of the treatment assignment to identify comparable…

Propensity Score Analysis: An Alternative Statistical Approach for HRD Researchers

ERIC Educational Resources Information Center

Keiffer, Greggory L.; Lane, Forrest C.

2016-01-01

Purpose: This paper aims to introduce matching in propensity score analysis (PSA) as an alternative statistical approach for researchers looking to make causal inferences using intact groups. Design/methodology/approach: An illustrative example demonstrated the varying results of analysis of variance, analysis of covariance and PSA on a heuristic…

Cost Attributable to Nosocomial Bacteremia. Analysis According to Microorganism and Antimicrobial Sensitivity in a University Hospital in Barcelona.

PubMed

Riu, Marta; Chiarello, Pietro; Terradas, Roser; Sala, Maria; Garcia-Alzorriz, Enric; Castells, Xavier; Grau, Santiago; Cots, Francesc

2016-01-01

To calculate the incremental cost of nosocomial bacteremia caused by the most common organisms, classified by their antimicrobial susceptibility. We selected patients who developed nosocomial bacteremia caused by Staphylococcus aureus, Escherichia coli, Klebsiella pneumoniae, or Pseudomonas aeruginosa. These microorganisms were analyzed because of their high prevalence and they frequently present multidrug resistance. A control group consisted of patients classified within the same all-patient refined-diagnosis related group without bacteremia. Our hospital has an established cost accounting system (full-costing) that uses activity-based criteria to analyze cost distribution. A logistic regression model was fitted to estimate the probability of developing bacteremia for each admission (propensity score) and was used for propensity score matching adjustment. Subsequently, the propensity score was included in an econometric model to adjust the incremental cost of patients who developed bacteremia, as well as differences in this cost, depending on whether the microorganism was multidrug-resistant or multidrug-sensitive. A total of 571 admissions with bacteremia matched the inclusion criteria and 82,022 were included in the control group. The mean cost was € 25,891 for admissions with bacteremia and € 6,750 for those without bacteremia. The mean incremental cost was estimated at € 15,151 (CI, € 11,570 to € 18,733). Multidrug-resistant P. aeruginosa bacteremia had the highest mean incremental cost, € 44,709 (CI, € 34,559 to € 54,859). Antimicrobial-susceptible E. coli nosocomial bacteremia had the lowest mean incremental cost, € 10,481 (CI, € 8,752 to € 12,210). Despite their lower cost, episodes of antimicrobial-susceptible E. coli nosocomial bacteremia had a major impact due to their high frequency. Adjustment of hospital cost according to the organism causing bacteremia and antibiotic sensitivity could improve prevention strategies and allow their prioritization according to their overall impact and costs. Infection reduction is a strategy to reduce resistance.

Cost Attributable to Nosocomial Bacteremia. Analysis According to Microorganism and Antimicrobial Sensitivity in a University Hospital in Barcelona

PubMed Central

Riu, Marta; Chiarello, Pietro; Terradas, Roser; Sala, Maria; Garcia-Alzorriz, Enric; Castells, Xavier; Grau, Santiago; Cots, Francesc

2016-01-01

Aim To calculate the incremental cost of nosocomial bacteremia caused by the most common organisms, classified by their antimicrobial susceptibility. Methods We selected patients who developed nosocomial bacteremia caused by Staphylococcus aureus, Escherichia coli, Klebsiella pneumoniae, or Pseudomonas aeruginosa. These microorganisms were analyzed because of their high prevalence and they frequently present multidrug resistance. A control group consisted of patients classified within the same all-patient refined-diagnosis related group without bacteremia. Our hospital has an established cost accounting system (full-costing) that uses activity-based criteria to analyze cost distribution. A logistic regression model was fitted to estimate the probability of developing bacteremia for each admission (propensity score) and was used for propensity score matching adjustment. Subsequently, the propensity score was included in an econometric model to adjust the incremental cost of patients who developed bacteremia, as well as differences in this cost, depending on whether the microorganism was multidrug-resistant or multidrug-sensitive. Results A total of 571 admissions with bacteremia matched the inclusion criteria and 82,022 were included in the control group. The mean cost was € 25,891 for admissions with bacteremia and € 6,750 for those without bacteremia. The mean incremental cost was estimated at € 15,151 (CI, € 11,570 to € 18,733). Multidrug-resistant P. aeruginosa bacteremia had the highest mean incremental cost, € 44,709 (CI, € 34,559 to € 54,859). Antimicrobial-susceptible E. coli nosocomial bacteremia had the lowest mean incremental cost, € 10,481 (CI, € 8,752 to € 12,210). Despite their lower cost, episodes of antimicrobial-susceptible E. coli nosocomial bacteremia had a major impact due to their high frequency. Conclusions Adjustment of hospital cost according to the organism causing bacteremia and antibiotic sensitivity could improve prevention strategies and allow their prioritization according to their overall impact and costs. Infection reduction is a strategy to reduce resistance. PMID:27055117

Effects of aggregation of drug and diagnostic codes on the performance of the high-dimensional propensity score algorithm: an empirical example.

PubMed

Le, Hoa V; Poole, Charles; Brookhart, M Alan; Schoenbach, Victor J; Beach, Kathleen J; Layton, J Bradley; Stürmer, Til

2013-11-19

The High-Dimensional Propensity Score (hd-PS) algorithm can select and adjust for baseline confounders of treatment-outcome associations in pharmacoepidemiologic studies that use healthcare claims data. How hd-PS performance is affected by aggregating medications or medical diagnoses has not been assessed. We evaluated the effects of aggregating medications or diagnoses on hd-PS performance in an empirical example using resampled cohorts with small sample size, rare outcome incidence, or low exposure prevalence. In a cohort study comparing the risk of upper gastrointestinal complications in celecoxib or traditional NSAIDs (diclofenac, ibuprofen) initiators with rheumatoid arthritis and osteoarthritis, we (1) aggregated medications and International Classification of Diseases-9 (ICD-9) diagnoses into hierarchies of the Anatomical Therapeutic Chemical classification (ATC) and the Clinical Classification Software (CCS), respectively, and (2) sampled the full cohort using techniques validated by simulations to create 9,600 samples to compare 16 aggregation scenarios across 50% and 20% samples with varying outcome incidence and exposure prevalence. We applied hd-PS to estimate relative risks (RR) using 5 dimensions, predefined confounders, ≤ 500 hd-PS covariates, and propensity score deciles. For each scenario, we calculated: (1) the geometric mean RR; (2) the difference between the scenario mean ln(RR) and the ln(RR) from published randomized controlled trials (RCT); and (3) the proportional difference in the degree of estimated confounding between that scenario and the base scenario (no aggregation). Compared with the base scenario, aggregations of medications into ATC level 4 alone or in combination with aggregation of diagnoses into CCS level 1 improved the hd-PS confounding adjustment in most scenarios, reducing residual confounding compared with the RCT findings by up to 19%. Aggregation of codes using hierarchical coding systems may improve the performance of the hd-PS to control for confounders. The balance of advantages and disadvantages of aggregation is likely to vary across research settings.

Propensity score based comparison of long term outcomes with 3D conformal radiotherapy (3DCRT) versus Intensity Modulated Radiation Therapy (IMRT) in the treatment of esophageal cancer

PubMed Central

Lin, Steven H.; Wang, Lu; Myles, Bevan; Thall, Peter F.; Hofstetter, Wayne L.; Swisher, Stephen G.; Ajani, Jaffer A.; Cox, James D.; Komaki, Ritsuko; Liao, Zhongxing

2014-01-01

Purpose Although 3DCRT is the worldwide standard for the treatment of esophageal cancers, IMRT improves dose conformality and reduces radiation exposure to normal tissues. We hypothesized that the dosimetric advantages of IMRT should translate to substantive benefits in clinical outcomes compared to 3DCRT. Methods and Materials Analysis was performed on 676 nonrandomized patients (3DCRT=413, IMRT=263) with stage Ib-IVa (AJCC 2002) esophageal cancers treated with chemoradiation at a single institution from 1998–2008. An inverse probability of treatment weighting (IPW) and inclusion of propensity score (treatment probability) as a covariate were used to compare overall survival (OS) time, time to local failure, and time to distant metastasis, while accounting for effects of other clinically relevant covariates. Propensity scores were estimated using logistic regression. Results A fitted multivariate inverse probability weighted (IPW)-adjusted Cox model showed that OS time was significantly associated with several well-known prognostic factors, along with radiation modality (IMRT vs 3DCRT, HR=0.72, p<0.001). Compared to IMRT, 3DCRT patients had a significantly greater risk of dying (72.6% vs 52.9%, IPW log rank test: p<0.0001) and for local-regional recurrence (LRR) (p=0.0038). There was no difference in cancer-specific mortality (Gray’s test, p=0.86), or distant metastasis (p=0.99) between the two groups. An increased cumulative incidence of cardiac deaths was seen in the 3DCRT group (p=0.049), but most deaths were undocumented (5 year estimate: 11.7% in 3DCRT vs 5.4% in IMRT, Gray’s test, p=0.0029). Conclusions Overall survival, locoregional control, and non-cancer related deaths were significantly better for IMRT compared to 3DCRT. Although these results need confirmation, IMRT should be considered for the treatment of esophageal cancer. PMID:22867894

A comparison of risperidone and haloperidol for the risk of ischemic stroke in the elderly: a propensity score-matched cohort analysis.

PubMed

Shin, Ju-Young; Choi, Nam-Kyong; Lee, Joongyub; Park, Mi-Ju; Lee, Shin Haeng; Park, Byung-Joo

2015-08-01

With an increase in antipsychotic use in the elderly, the safety profile of antipsychotics has been emphasized. Strong concerns have been raised about whether the risk of ischemic stroke differs between risperidone and haloperidol. This study compared the risk of ischemic stroke between elderly patients taking risperidone and haloperidol. We conducted a retrospective cohort study using the Korea Health Insurance Review and Assessment Service database, applying a propensity-matched analysis. The cohort consisted of elderly patients who were newly prescribed haloperidol or risperidone between January 1, 2006 and December 31, 2009. Patients with prior cerebrovascular diseases (ICD-10, I60-I69), transient ischemic attack (ICD-10, G45), or cerebral tumors (ICD-10, C31) during 365 days prior to the initiation date were excluded. The study subjects were selected by propensity score matching. The outcome was defined as the first hospitalization for ischemic stroke (ICD-10, I63). Cox regression models were used to estimate the hazard ratio (HR) and 95% confidence intervals (95% CI) for ischemic stroke with haloperidol compared with risperidone use. A total of 14,103 patients were included in the propensity-matched cohort for each drug. Overall, the incidence rate was higher for haloperidol users compared to the risperidone users (6.43 per 1000 person-years vs. 2.88 per 1000 person-years). A substantially increased risk was observed in haloperidol users (adjusted HR = 2.02, 95% CI, 1.12-3.62). The evidence showed that haloperidol should be prescribed in the elderly with caution. © The Author(s) 2015.

Use of Multiple Imputation Method to Improve Estimation of Missing Baseline Serum Creatinine in Acute Kidney Injury Research

PubMed Central

Peterson, Josh F.; Eden, Svetlana K.; Moons, Karel G.; Ikizler, T. Alp; Matheny, Michael E.

2013-01-01

Summary Background and objectives Baseline creatinine (BCr) is frequently missing in AKI studies. Common surrogate estimates can misclassify AKI and adversely affect the study of related outcomes. This study examined whether multiple imputation improved accuracy of estimating missing BCr beyond current recommendations to apply assumed estimated GFR (eGFR) of 75 ml/min per 1.73 m2 (eGFR 75). Design, setting, participants, & measurements From 41,114 unique adult admissions (13,003 with and 28,111 without BCr data) at Vanderbilt University Hospital between 2006 and 2008, a propensity score model was developed to predict likelihood of missing BCr. Propensity scoring identified 6502 patients with highest likelihood of missing BCr among 13,003 patients with known BCr to simulate a “missing” data scenario while preserving actual reference BCr. Within this cohort (n=6502), the ability of various multiple-imputation approaches to estimate BCr and classify AKI were compared with that of eGFR 75. Results All multiple-imputation methods except the basic one more closely approximated actual BCr than did eGFR 75. Total AKI misclassification was lower with multiple imputation (full multiple imputation + serum creatinine) (9.0%) than with eGFR 75 (12.3%; P<0.001). Improvements in misclassification were greater in patients with impaired kidney function (full multiple imputation + serum creatinine) (15.3%) versus eGFR 75 (40.5%; P<0.001). Multiple imputation improved specificity and positive predictive value for detecting AKI at the expense of modestly decreasing sensitivity relative to eGFR 75. Conclusions Multiple imputation can improve accuracy in estimating missing BCr and reduce misclassification of AKI beyond currently proposed methods. PMID:23037980

TAP score: torsion angle propensity normalization applied to local protein structure evaluation

PubMed Central

Tosatto, Silvio CE; Battistutta, Roberto

2007-01-01

Background Experimentally determined protein structures may contain errors and require validation. Conformational criteria based on the Ramachandran plot are mainly used to distinguish between distorted and adequately refined models. While the readily available criteria are sufficient to detect totally wrong structures, establishing the more subtle differences between plausible structures remains more challenging. Results A new criterion, called TAP score, measuring local sequence to structure fitness based on torsion angle propensities normalized against the global minimum and maximum is introduced. It is shown to be more accurate than previous methods at estimating the validity of a protein model in terms of commonly used experimental quality parameters on two test sets representing the full PDB database and a subset of obsolete PDB structures. Highly selective TAP thresholds are derived to recognize over 90% of the top experimental structures in the absence of experimental information. Both a web server and an executable version of the TAP score are available at . Conclusion A novel procedure for energy normalization (TAP) has significantly improved the possibility to recognize the best experimental structures. It will allow the user to more reliably isolate problematic structures in the context of automated experimental structure determination. PMID:17504537

Does Matching Quality Matter in Mode Comparison Studies?

ERIC Educational Resources Information Center

Zeng, Ji; Yin, Ping; Shedden, Kerby A.

2015-01-01

This article provides a brief overview and comparison of three matching approaches in forming comparable groups for a study comparing test administration modes (i.e., computer-based tests [CBT] and paper-and-pencil tests [PPT]): (a) a propensity score matching approach proposed in this article, (b) the propensity score matching approach used by…

Using Propensity Score Matching to Test the Community College Penalty Assumption

ERIC Educational Resources Information Center

Dietrich, Cecile C.; Lichtenberger, Eric J.

2015-01-01

Research studies have been ambivalent about whether enrolling in community college makes completing a bachelor's degree less likely than directly enrolling in a four-year institution. This study uses propensity score matching with a posttreatment adjustment to determine the treatment effect associated with taking the community college to four-year…

Assessing Student Achievement in Large-Scale Educational Programs Using Hierarchical Propensity Scores

ERIC Educational Resources Information Center

Vaughan, Angela L.; Lalonde, Trent L.; Jenkins-Guarnieri, Michael A.

2014-01-01

Many researchers assessing the efficacy of educational programs face challenges due to issues with non-randomization and the likelihood of dependence between nested subjects. The purpose of the study was to demonstrate a rigorous research methodology using a hierarchical propensity score matching method that can be utilized in contexts where…

Understanding Foster Youth Outcomes: Is Propensity Scoring Better than Traditional Methods?

ERIC Educational Resources Information Center

Berzin, Stephanie Cosner

2010-01-01

Objectives: This study seeks to examine the relationship between foster care and outcomes using multiple comparison methods to account for factors that put foster youth at risk independent of care. Methods: Using the National Longitudinal Survey of Youth 1997, matching, propensity scoring, and comparisons to the general population are used to…

The Use of Propensity Scores as a Matching Strategy

ERIC Educational Resources Information Center

John, Lindsay; Wright, Robin; Duku, Eric K.; Willms, J. Douglas

2008-01-01

Objectives: This study reports on the concept and method of linear propensity scores used to obtain a comparison group from the National Longitudinal Survey of Children and Youth to assess the effects of a longitudinal, structured arts program for Canadian youth (aged 9 to 15 years) from low-income, multicultural communities. Method: This study…

Graphic report of the results from propensity score method analyses.

PubMed

Shrier, Ian; Pang, Menglan; Platt, Robert W

2017-08-01

To increase transparency in studies reporting propensity scores by using graphical methods that clearly illustrate (1) the number of participant exclusions that occur as a consequence of the analytic strategy and (2) whether treatment effects are constant or heterogeneous across propensity scores. We applied graphical methods to a real-world pharmacoepidemiologic study that evaluated the effect of initiating statin medication on the 1-year all-cause mortality post-myocardial infarction. We propose graphical methods to show the consequences of trimming and matching on the exclusion of participants from the analysis. We also propose the use of meta-analytical forest plots to show the magnitude of effect heterogeneity. A density plot with vertical lines demonstrated the proportion of subjects excluded because of trimming. A frequency plot with horizontal lines demonstrated the proportion of subjects excluded because of matching. An augmented forest plot illustrates the amount of effect heterogeneity present in the data. Our proposed techniques present additional and useful information that helps readers understand the sample that is analyzed with propensity score methods and whether effect heterogeneity is present. Copyright © 2017 Elsevier Inc. All rights reserved.

Analysis of threats to research validity introduced by audio recording clinic visits: Selection bias, Hawthorne effect, both, or neither?

PubMed Central

Henry, Stephen G.; Jerant, Anthony; Iosif, Ana-Maria; Feldman, Mitchell D.; Cipri, Camille; Kravitz, Richard L.

2015-01-01

Objective To identify factors associated with participant consent to record visits; to estimate effects of recording on patient-clinician interactions Methods Secondary analysis of data from a randomized trial studying communication about depression; participants were asked for optional consent to audio record study visits. Multiple logistic regression was used to model likelihood of patient and clinician consent. Multivariable regression and propensity score analyses were used to estimate effects of audio recording on 6 dependent variables: discussion of depressive symptoms, preventive health, and depression diagnosis; depression treatment recommendations; visit length; visit difficulty. Results Of 867 visits involving 135 primary care clinicians, 39% were recorded. For clinicians, only working in academic settings (P=0.003) and having worked longer at their current practice (P=0.02) were associated with increased likelihood of consent. For patients, white race (P=0.002) and diabetes (P=0.03) were associated with increased likelihood of consent. Neither multivariable regression nor propensity score analyses revealed any significant effects of recording on the variables examined. Conclusion Few clinician or patient characteristics were significantly associated with consent. Audio recording had no significant effect on any dependent variables. Practice Implications Benefits of recording clinic visits likely outweigh the risks of bias in this setting. PMID:25837372

Double-adjustment in propensity score matching analysis: choosing a threshold for considering residual imbalance.

PubMed

Nguyen, Tri-Long; Collins, Gary S; Spence, Jessica; Daurès, Jean-Pierre; Devereaux, P J; Landais, Paul; Le Manach, Yannick

2017-04-28

Double-adjustment can be used to remove confounding if imbalance exists after propensity score (PS) matching. However, it is not always possible to include all covariates in adjustment. We aimed to find the optimal imbalance threshold for entering covariates into regression. We conducted a series of Monte Carlo simulations on virtual populations of 5,000 subjects. We performed PS 1:1 nearest-neighbor matching on each sample. We calculated standardized mean differences across groups to detect any remaining imbalance in the matched samples. We examined 25 thresholds (from 0.01 to 0.25, stepwise 0.01) for considering residual imbalance. The treatment effect was estimated using logistic regression that contained only those covariates considered to be unbalanced by these thresholds. We showed that regression adjustment could dramatically remove residual confounding bias when it included all of the covariates with a standardized difference greater than 0.10. The additional benefit was negligible when we also adjusted for covariates with less imbalance. We found that the mean squared error of the estimates was minimized under the same conditions. If covariate balance is not achieved, we recommend reiterating PS modeling until standardized differences below 0.10 are achieved on most covariates. In case of remaining imbalance, a double adjustment might be worth considering.

Blinatumomab vs historical standard therapy of adult relapsed/refractory acute lymphoblastic leukemia.

PubMed

Gökbuget, N; Kelsh, M; Chia, V; Advani, A; Bassan, R; Dombret, H; Doubek, M; Fielding, A K; Giebel, S; Haddad, V; Hoelzer, D; Holland, C; Ifrah, N; Katz, A; Maniar, T; Martinelli, G; Morgades, M; O'Brien, S; Ribera, J-M; Rowe, J M; Stein, A; Topp, M; Wadleigh, M; Kantarjian, H

2016-09-23

We compared outcomes from a single-arm study of blinatumomab in adult patients with B-precursor Ph-negative relapsed/refractory acute lymphoblastic leukemia (R/R ALL) with a historical data set from Europe and the United States. Estimates of complete remission (CR) and overall survival (OS) were weighted by the frequency distribution of prognostic factors in the blinatumomab trial. Outcomes were also compared between the trial and historical data using propensity score methods. The historical cohort included 694 patients with CR data and 1112 patients with OS data compared with 189 patients with CR and survival data in the blinatumomab trial. The weighted analysis revealed a CR rate of 24% (95% CI: 20-27%) and a median OS of 3.3 months (95% CI: 2.8-3.6) in the historical cohort compared with a CR/CRh rate of 43% (95% CI: 36-50%) and a median OS of 6.1 months (95% CI: 4.2-7.5) in the blinatumomab trial. Propensity score analysis estimated increased odds of CR/CRh (OR=2.68, 95% CI: 1.67-4.31) and improved OS (HR=0.536, 95% CI: 0.394-0.730) with blinatumomab. The analysis demonstrates the application of different study designs and statistical methods to compare novel therapies for R/R ALL with historical data.

New steps of robot-assisted radical prostatectomy using the extraperitoneal approach: a propensity-score matched comparison between extraperitoneal and transperitoneal approach in Japanese patients.

PubMed

Kurokawa, Satoshi; Umemoto, Yukihiro; Mizuno, Kentaro; Okada, Atsushi; Nakane, Akihiro; Nishio, Hidenori; Hamamoto, Shuzo; Ando, Ryosuke; Kawai, Noriyasu; Tozawa, Keiichi; Hayashi, Yutaro; Yasui, Takahiro

2017-11-21

Robot-assisted radical prostatectomy (RARP) is commonly performed using the transperitoneal (TP) approach with six trocars over an 8-cm distance in the steep Trendelenburg position. In this study, we investigated the feasibility and the benefit of using the extraperitoneal (EP) approach with six trocars over a 4-cm distance in a flat or 5° Trendelenburg position. We also introduced four new steps to the surgical procedure and compared the surgical results and complications between the EP and TP approach using propensity score matching. Between August 2012 and August 2016, 200 consecutive patients without any physical restrictions underwent RARP with the EP approach in a less than 5° Trendelenburg position, and 428 consecutive patients underwent RARP with the TP approach in a steep Trendelenburg position. Four new steps to RARP using the EP approach were developed: 1) arranging six trocars; 2) creating the EP space using laparoscopic forceps; 3) holding the separated prostate in the EP space outside the robotic view; and 4) preventing a postoperative inguinal hernia. Clinicopathological results and complications were compared between the EP and TP approaches using propensity score matching. Propensity scores were calculated for each patient using multivariate logistic regression based on the preoperative covariates. All 200 patients safely underwent RARP using the EP approach. The mean volume of estimated blood loss and duration of indwelling urethral catheter use were significantly lower with the EP approach than the TP approach (139.9 vs 184.9 mL, p = 0.03 and 5.6 vs 7.7 days, p < 0.01, respectively). No significant differences in the positive surgical margin were observed. None of the patients developed an inguinal hernia postoperatively after we introduced this technique. The EP approach to RARP was safely performed regardless of patient physique or contraindications to a steep Trendelenburg position. Our method, which involved using the EP approach to perform RARP, can decrease the amount of perioperative blood loss, the duration of indwelling urethral catheter use, and the incidence of postoperative inguinal hernia development.

The Association of Statin Use with Age-Related Macular Degeneration Progression: The Age-Related Eye Disease Study 2 Report Number 9.

PubMed

Al-Holou, Shaza N; Tucker, William R; Agrón, Elvira; Clemons, Traci E; Cukras, Catherine; Ferris, Frederick L; Chew, Emily Y

2015-12-01

To evaluate the association of statin use with progression of age-related macular degeneration (AMD). Preplanned, prospective cohort study within a controlled clinical trial of oral supplementation for age-related eye diseases. Age-Related Eye Disease Study 2 (AREDS2) participants, aged 50 to 85 years. Factors, including age, gender, smoking status, aspirin use, and history of diabetes, hypertension, heart disease, angina, and stroke-all known to be associated with statin use-were included in a logistic regression model to estimate propensity scores for each participant. Age-adjusted proportional hazards regression models, with and without propensity score matching, were performed to evaluate the association of statin use with progression to late AMD. Analyses adjusting for the competing risk of death were also performed. Baseline and annual stereoscopic fundus photographs were assessed centrally by masked graders for the development of late AMD, either neovascular AMD or geographic atrophy (GA). Of the 3791 participants (2462 with bilateral large drusen and 1329 with unilateral late AMD at baseline), 1659 (43.8%) were statin users. The overall analysis, with no matching of propensity scores and no adjustment for death as a competing risk, showed that statin use was not associated with progression to late AMD (hazard ratio [HR], 1.08; 95% confidence interval [CI], 0.83-1.41; P = 0.56). When matched for propensity scores and adjusted for death as a competing risk, the result was not statistically significant (HR, 0.81; 95% CI, 0.55-1.20; P = 0.29). Furthermore, subgroup analyses of persons with or without late AMD at baseline and the various components of late AMD (neovascular AMD, central GA, or any GA) also showed no statistically significant association of statin use with progression to AMD. Statin use was not statistically significantly associated with progression to late AMD in the AREDS2 participants, and these findings are consistent with findings in the majority of previous studies. Statins have been demonstrated to reduce the risk of cardiovascular disease, but our data do not provide evidence of a beneficial effect on slowing AMD progression. Published by Elsevier Inc.

Statin use and kidney cancer outcomes: A propensity score analysis.

PubMed

Nayan, Madhur; Finelli, Antonio; Jewett, Michael A S; Juurlink, David N; Austin, Peter C; Kulkarni, Girish S; Hamilton, Robert J

2016-11-01

Studies evaluating the association between statin use and survival outcomes in renal cell carcinoma have demonstrated conflicting results. Our objective was to evaluate this association in a large clinical cohort by using propensity score methods to reduce confounding from measured covariates. We performed a retrospective review of 893 patients undergoing nephrectomy for unilateral, M0 renal cell carcinoma between 2000 and 2014 at a tertiary academic center. Inverse probability of treatment weights were derived from a propensity score model based on clinical, surgical, and pathological characteristics. We used Cox proportional hazard models to evaluate the association between statin use and disease-free survival, cancer-specific survival, and overall survival in the sample weighted by the inverse probability of treatment weights. A secondary analysis was performed matching statin users 1:1 to statin nonusers on the propensity score. Of the 893 patients, 259 (29%) were on statins at the time of surgery. Median follow-up was 47 months (interquartile range: 20-80). Statin use was not significantly associated with disease-free survival (hazard ratio [HR] = 1.09, 95% CI: 0.65-1.81), cancer-specific survival (HR = 0.90, 95% CI: 0.40-2.01), or overall survival (HR = 0.89, 95% CI: 0.55-1.44). Similar results were observed when using propensity score matching. The present study found no significant association between statin use and kidney cancer outcomes. Population-based studies are needed to further evaluate the role of statins in kidney cancer therapy. Copyright © 2016 Elsevier Inc. All rights reserved.

Impacts of age of onset of substance use disorders on risk of adult incarceration among disadvantaged urban youth: a propensity score matching approach.

PubMed

Slade, Eric P; Stuart, Elizabeth A; Salkever, David S; Karakus, Mustafa; Green, Kerry M; Ialongo, Nicholas

2008-05-01

Age of onset of substance use disorders in adolescence and early adulthood could be associated with higher rates of adult criminal incarceration in the U.S., but evidence of these associations is scarce. Propensity score matching was used to estimate the association between adolescent-onset substance use disorders and the rate of incarceration, as well as incarceration costs and self-reported criminal arrests and convictions, of young men predominantly from African American, lower income, urban households. Age of onset was differentiated by whether onset of the first disorder occurred by age 16. Onset of a substance use disorder by age 16, but not later onset, was associated with a fourfold greater risk of adult incarceration for substance related offenses as compared to no disorder (0.35 vs. 0.09, P=0.044). Onset by age 16 and later onset were both positively associated with incarceration costs and risk of arrest and conviction, though associations with crime outcomes were more consistent with respect to onset by age 16. Results were robust to propensity score adjustment for observable predictors of substance use in adolescence and involvement in crime as an adult. Among young men in this high risk minority sample, having a substance use disorder by age 16 was associated with higher risk of incarceration for substance related offenses in early adulthood and with more extensive criminal justice system involvement as compared to having no disorder or having a disorder beginning at a later age.

Multisystemic Therapy and Functional Family Therapy Compared on their Effectiveness Using the Propensity Score Method.

PubMed

Eeren, Hester V; Goossens, Lucas M A; Scholte, Ron H J; Busschbach, Jan J V; van der Rijken, Rachel E A

2018-01-09

Multisystemic Therapy (MST) and Functional Family Therapy (FFT) have overlapping target populations and treatment goals. In this study, these interventions were compared on their effectiveness using a quasi-experimental design. Between October, 2009 and June, 2014, outcome data were collected from 697 adolescents (mean age 15.3 (SD 1.48), 61.9% male) assigned to either MST or FFT (422 MST; 275 FFT). Data were gathered during Routine Outcome Monitoring. The primary outcome was externalizing problem behavior (Child Behavior Checklist and Youth Self Report). Secondary outcomes were the proportion of adolescents living at home, engaged in school or work, and who lacked police contact during treatment. Because of the non-random assignment, a propensity score method was used to control for observed pre-treatment differences. Because the risk-need-responsivity (RNR) model guided treatment assignment, effectiveness was also estimated in youth with and without a court order as an indicator of their risk level. Looking at the whole sample, no difference in effect was found with regard to externalizing problems. For adolescents without a court order, effects on externalizing problems were larger after MST. Because many more adolescents with a court order were assigned to MST compared to FFT, the propensity score method could not balance the treatment groups in this subsample. In conclusion, few differences between MST and FFT were found. In line with the RNR model, higher risk adolescents were assigned to the more intensive treatment, namely MST. In the group with lower risk adolescents, this more intensive treatment was more effective in reducing externalizing problems.

Comparison of safety effect estimates obtained from empirical Bayes before-after study, propensity scores-potential outcomes framework, and regression model with cross-sectional data.

PubMed

Wood, Jonathan S; Donnell, Eric T; Porter, Richard J

2015-02-01

A variety of different study designs and analysis methods have been used to evaluate the performance of traffic safety countermeasures. The most common study designs and methods include observational before-after studies using the empirical Bayes method and cross-sectional studies using regression models. The propensity scores-potential outcomes framework has recently been proposed as an alternative traffic safety countermeasure evaluation method to address the challenges associated with selection biases that can be part of cross-sectional studies. Crash modification factors derived from the application of all three methods have not yet been compared. This paper compares the results of retrospective, observational evaluations of a traffic safety countermeasure using both before-after and cross-sectional study designs. The paper describes the strengths and limitations of each method, focusing primarily on how each addresses site selection bias, which is a common issue in observational safety studies. The Safety Edge paving technique, which seeks to mitigate crashes related to roadway departure events, is the countermeasure used in the present study to compare the alternative evaluation methods. The results indicated that all three methods yielded results that were consistent with each other and with previous research. The empirical Bayes results had the smallest standard errors. It is concluded that the propensity scores with potential outcomes framework is a viable alternative analysis method to the empirical Bayes before-after study. It should be considered whenever a before-after study is not possible or practical. Copyright © 2014 Elsevier Ltd. All rights reserved.

A comparison of propensity score-based approaches to health service evaluation: a case study of a preoperative physician-led clinic for high-risk surgical patients.

PubMed

Pham, Clarabelle T; Gibb, Catherine L; Mittinty, Murthy N; Fitridge, Robert A; Marshall, Villis R; Karnon, Jonathan D

2016-10-01

A physician-led clinic for the preoperative optimization and management of high-risk surgical patients was implemented in a South Australian public hospital in 2008. This study aimed to estimate the costs and effects of the clinic using a mixed retrospective and prospective observational study design. Alternative propensity score estimation methods were applied to retrospective routinely collected administrative and clinical data, using weighted and matched cohorts. Supplementary survey-based prospective data were collected to inform the analysis of the retrospective data and reduce potential unmeasured confounding. Using weighted cohorts, clinic patients had a significantly longer mean length of stay and higher mean cost. With the matched cohorts, reducing the calliper width resulted in a shorter mean length of stay in the clinic group, but the costs remained significantly higher. The prospective data indicated potential unmeasured confounding in all analyses other than in the most tightly matched cohorts. The application of alternative propensity-based approaches to a large sample of retrospective data, supplemented with a smaller sample of prospective data, informed a pragmatic approach to reducing potential observed and unmeasured confounding in an evaluation of a physician-led preoperative clinic. The need to generate tightly matched cohorts to reduce the potential for unmeasured confounding indicates that significant uncertainty remains around the effects of the clinic. This study illustrates the value of mixed retrospective and prospective observational study designs but also underlines the need to prospectively plan for the evaluation of costs and effects alongside the implementation of significant service innovations. © 2016 John Wiley & Sons, Ltd.

The importance of extent of choroid plexus cauterization in addition to endoscopic third ventriculostomy for infantile hydrocephalus: a retrospective North American observational study using propensity score-adjusted analysis.

PubMed

Fallah, Aria; Weil, Alexander G; Juraschka, Kyle; Ibrahim, George M; Wang, Anthony C; Crevier, Louis; Tseng, Chi-Hong; Kulkarni, Abhaya V; Ragheb, John; Bhatia, Sanjiv

2017-12-01

OBJECTIVE Combined endoscopic third ventriculostomy (ETC) and choroid plexus cauterization (CPC)-ETV/CPC- is being investigated to increase the rate of shunt independence in infants with hydrocephalus. The degree of CPC necessary to achieve improved rates of shunt independence is currently unknown. METHODS Using data from a single-center, retrospective, observational cohort study involving patients who underwent ETV/CPC for treatment of infantile hydrocephalus, comparative statistical analyses were performed to detect a difference in need for subsequent CSF diversion procedure in patients undergoing partial CPC (describes unilateral CPC or bilateral CPC that only extended from the foramen of Monro [FM] to the atrium on one side) or subtotal CPC (describes CPC extending from the FM to the posterior temporal horn bilaterally) using a rigid neuroendoscope. Propensity scores for extent of CPC were calculated using age and etiology. Propensity scores were used to perform 1) case-matching comparisons and 2) Cox multivariable regression, adjusting for propensity score in the unmatched cohort. Cox multivariable regression adjusting for age and etiology, but not propensity score was also performed as a third statistical technique. RESULTS Eighty-four patients who underwent ETV/CPC had sufficient data to be included in the analysis. Subtotal CPC was performed in 58 patients (69%) and partial CPC in 26 (31%). The ETV/CPC success rates at 6 and 12 months, respectively, were 49% and 41% for patients undergoing subtotal CPC and 35% and 31% for those undergoing partial CPC. Cox multivariate regression in a 48-patient cohort case-matched by propensity score demonstrated no added effect of increased extent of CPC on ETV/CPC survival (HR 0.868, 95% CI 0.422-1.789, p = 0.702). Cox multivariate regression including all patients, with adjustment for propensity score, demonstrated no effect of extent of CPC on ETV/CPC survival (HR 0.845, 95% CI 0.462-1.548, p = 0.586). Cox multivariate regression including all patients, with adjustment for age and etiology, but not propensity score, demonstrated no effect of extent of CPC on ETV/CPC survival (HR 0.908, 95% CI 0.495-1.664, p = 0.755). CONCLUSIONS Using multiple comparative statistical analyses, no difference in need for subsequent CSF diversion procedure was detected between patients in this cohort who underwent partial versus subtotal CPC. Further investigation regarding whether there is truly no difference between partial versus subtotal extent of CPC in larger patient populations and whether further gain in CPC success can be achieved with complete CPC is warranted.

Propensity Score Techniques and the Assessment of Measured Covariate Balance to Test Causal Associations in Psychological Research

ERIC Educational Resources Information Center

Harder, Valerie S.; Stuart, Elizabeth A.; Anthony, James C.

2010-01-01

There is considerable interest in using propensity score (PS) statistical techniques to address questions of causal inference in psychological research. Many PS techniques exist, yet few guidelines are available to aid applied researchers in their understanding, use, and evaluation. In this study, the authors give an overview of available…

An Introduction to Propensity Scores: What, When, and How

ERIC Educational Resources Information Center

Beal, Sarah J.; Kupzyk, Kevin A.

2014-01-01

The use of propensity scores as a method to promote causality in studies that cannot use random assignment has increased dramatically since its original publication in 1983. While the utility of these approaches is important, the concepts underlying their use are complex. The purpose of this article is to provide a basic tutorial for conducting…

Impacts of Playing after School on Academic Performance: A Propensity Score Matching Approach

ERIC Educational Resources Information Center

Li, Yajuan; Palma, Marco A.; Xu, Zhicheng Phil

2017-01-01

We present a plausible causal analysis of the impact of playing after school on academic performance and investigate parental support as a potential channel. We exploit the data from the 2011 Trends in International Mathematics and Science Survey to evaluate the effects by using a propensity score matching approach. The results show that playing…

Using Propensity Score Analysis for Making Causal Claims in Research Articles

ERIC Educational Resources Information Center

Bai, Haiyan

2011-01-01

The central role of the propensity score analysis (PSA) in observational studies is for causal inference; as such, PSA is often used for making causal claims in research articles. However, there are still some issues for researchers to consider when making claims of causality using PSA results. This summary first briefly reviews PSA, followed by…

Are There Adverse Consequences to Being a Sibling of a Person with a Disability? A Propensity Score Analysis

ERIC Educational Resources Information Center

Neely-Barnes, Susan L.; Graff, J. Carolyn

2011-01-01

This study examined whether siblings of children with disabilities have increased mental health problems, behavioral difficulties, or greater mental health service use as compared to siblings of children without disabilities. Data come from the 2006 National Health Interview Survey. Propensity score matching was used to complete the analysis.…

Automatic Promotion and Student Dropout: Evidence from Uganda, Using Propensity Score in Difference in Differences Model

ERIC Educational Resources Information Center

Okurut, Jeje Moses

2018-01-01

The impact of automatic promotion practice on students dropping out of Uganda's primary education was assessed using propensity score in difference in differences analysis technique. The analysis strategy was instrumental in addressing the selection bias problem, as well as biases arising from common trends over time, and permanent latent…

Nonstandard Work Schedules and Developmentally Generative Parenting Practices: An Application of Propensity Score Techniques

ERIC Educational Resources Information Center

Grzywacz, Joseph G.; Daniel, Stephanie S.; Tucker, Jenna; Walls, Jill; Leerkes, Esther

2011-01-01

Data from the National Institute for Child Health and Human Development Study of Early Child Care (Phase I) and propensity score techniques were used to determine whether working full time in a nonstandard schedule job during the child's first year predicted parenting practices over 3 years. Results indicated that women who worked full time in a…

Understanding Student Success and Institutional Outcomes in Service-Learning Coursework at a North Carolina Community College: A Propensity Score Study

ERIC Educational Resources Information Center

Marts, Jennifer Leigh

2016-01-01

Service-learning has roots deep in higher education. Community colleges and service-learning have an organic relationship as they both strive to represent and support their local communities. This study implemented propensity score matching to study the impact of service-learning on student outcomes for community college students. Much of the…

Propensity Score Matching Helps to Understand Sources of DIF and Mathematics Performance Differences of Indonesian, Turkish, Australian, and Dutch Students in PISA

ERIC Educational Resources Information Center

Arikan, Serkan; van de Vijver, Fons J. R.; Yagmur, Kutlay

2018-01-01

We examined Differential Item Functioning (DIF) and the size of cross-cultural performance differences in the Programme for International Student Assessment (PISA) 2012 mathematics data before and after application of propensity score matching. The mathematics performance of Indonesian, Turkish, Australian, and Dutch students on released items was…

Evaluating Phase II of a New York City-Wide STEM Initiative Using Propensity Score Methods: A Replication Study

ERIC Educational Resources Information Center

Thomas, Ally S.; Bonner, Sarah M.; Everson, Howard T.

2014-01-01

Recently, the authors have been exploring the use of propensity score methods for developing evidence of program impact. Specifically, they have been developing evidence (after one year of implementation) of the effects of the Math Science Partnership in New York City ("MSPinNYC2") on high school students' achievement--both in terms of…

Efficacy of Antenatal Corticosteroid Treatment on Neurodevelopmental Outcome according to Head Circumference at Birth.

PubMed

Basset, Helene; Nusinovici, Simon; Huetz, Noémie; Sentilhes, Loic; Berlie, Isabelle; Flamant, Cyril; Roze, Jean-Christophe; Gascoin, Geraldine

2018-01-01

There are concerns about the efficacy of antenatal corticosteroid treatment (ACT) in the growth-restricted fetus. To evaluate the effect of ACT on neurodevelopmental outcome at 2 years of corrected age according to the z score of birth head circumference (ZS HC) in a large prospective cohort of preterm infants. This study was conducted as a population-based, prospective, multicenter study, including 4,965 infants born between 24 and 33 weeks' gestation and whose status regarding ACT and the measurement of head circumference at birth were available. They were evaluated at 2 years of corrected age to assess neurological outcome. Three approaches were considered to estimate the effect of ACT on neurodevelopment: (i) logistic regression with adjustment on propensity score, (ii) weighted logistic regression using the inverse probability of treatment weighting method, and (iii) 1:1 matching of gestational age, ZS HC, and propensity score between treated and nontreated infants. ACT was documented in 60% of infants. Three groups of infants were considered according to their ZS HC: between -3 and -1 standard deviation (SD), -1 and +1 SD, and +1 and +3 SD, respectively. ACT was associated with a significant improvement of neurodevelopmental outcome only for infants with an ZS HC of between +1 and +3 SD (adjusted OR 1.72; 95% CI 1.06-2.79). Moreover, ORs estimated in the -3 to -1 and +1 to +3 categories were significantly different. We found beneficial effects of ACT on neurodevelopmental outcomes at 2 years of corrected age only in preterm infants with a ZS HC >1 SD. © 2017 S. Karger AG, Basel.

Improved False Discovery Rate Estimation Procedure for Shotgun Proteomics.

PubMed

Keich, Uri; Kertesz-Farkas, Attila; Noble, William Stafford

2015-08-07

Interpreting the potentially vast number of hypotheses generated by a shotgun proteomics experiment requires a valid and accurate procedure for assigning statistical confidence estimates to identified tandem mass spectra. Despite the crucial role such procedures play in most high-throughput proteomics experiments, the scientific literature has not reached a consensus about the best confidence estimation methodology. In this work, we evaluate, using theoretical and empirical analysis, four previously proposed protocols for estimating the false discovery rate (FDR) associated with a set of identified tandem mass spectra: two variants of the target-decoy competition protocol (TDC) of Elias and Gygi and two variants of the separate target-decoy search protocol of Käll et al. Our analysis reveals significant biases in the two separate target-decoy search protocols. Moreover, the one TDC protocol that provides an unbiased FDR estimate among the target PSMs does so at the cost of forfeiting a random subset of high-scoring spectrum identifications. We therefore propose the mix-max procedure to provide unbiased, accurate FDR estimates in the presence of well-calibrated scores. The method avoids biases associated with the two separate target-decoy search protocols and also avoids the propensity for target-decoy competition to discard a random subset of high-scoring target identifications.

Improved False Discovery Rate Estimation Procedure for Shotgun Proteomics

PubMed Central

2016-01-01

Interpreting the potentially vast number of hypotheses generated by a shotgun proteomics experiment requires a valid and accurate procedure for assigning statistical confidence estimates to identified tandem mass spectra. Despite the crucial role such procedures play in most high-throughput proteomics experiments, the scientific literature has not reached a consensus about the best confidence estimation methodology. In this work, we evaluate, using theoretical and empirical analysis, four previously proposed protocols for estimating the false discovery rate (FDR) associated with a set of identified tandem mass spectra: two variants of the target-decoy competition protocol (TDC) of Elias and Gygi and two variants of the separate target-decoy search protocol of Käll et al. Our analysis reveals significant biases in the two separate target-decoy search protocols. Moreover, the one TDC protocol that provides an unbiased FDR estimate among the target PSMs does so at the cost of forfeiting a random subset of high-scoring spectrum identifications. We therefore propose the mix-max procedure to provide unbiased, accurate FDR estimates in the presence of well-calibrated scores. The method avoids biases associated with the two separate target-decoy search protocols and also avoids the propensity for target-decoy competition to discard a random subset of high-scoring target identifications. PMID:26152888

The Quality of Toddler Child Care and Cognitive Skills at 24 Months: Propensity Score Analysis Results from the ECLS-B.

PubMed

Ruzek, Erik; Burchinal, Margaret; Farkas, George; Duncan, Greg J

2014-01-01

Over half of the toddlers in the U.S. experience routine nonparental care, but much less is known about early care than about preschool care. This study analyzed 2-year-old child care and child outcome data from the nationally representative ECLS-B sample of children born in 2001. At two-years of age, 51% of children experienced exclusive parental care, 18% relative care, 15% family child care, and 16% center care. More children in nonparental care were in medium quality care (61%) than in high quality (26%) or low quality (13%) care. Low-income children were more likely than non-low income children to be cared for by their parents and, when in care, were more often in lower quality care. The impact of toddler care quality on cognitive skills was estimated using propensity score adjustments to account for potential selection confounds due to family and child characteristics. Children's cognitive scores were higher in high or medium quality care than in low quality care, but no evidence emerged suggesting that poverty moderated the quality effects. Nevertheless, this suggests that increasing the proportion of low-income children in high quality care could reduce the achievement gap because low-income children are very unlikely to experience high quality care.

The Quality of Toddler Child Care and Cognitive Skills at 24 Months: Propensity Score Analysis Results from the ECLS-B

PubMed Central

Ruzek, Erik; Burchinal, Margaret; Farkas, George; Duncan, Greg J.

2013-01-01

Over half of the toddlers in the U.S. experience routine nonparental care, but much less is known about early care than about preschool care. This study analyzed 2-year-old child care and child outcome data from the nationally representative ECLS-B sample of children born in 2001. At two-years of age, 51% of children experienced exclusive parental care, 18% relative care, 15% family child care, and 16% center care. More children in nonparental care were in medium quality care (61%) than in high quality (26%) or low quality (13%) care. Low-income children were more likely than non-low income children to be cared for by their parents and, when in care, were more often in lower quality care. The impact of toddler care quality on cognitive skills was estimated using propensity score adjustments to account for potential selection confounds due to family and child characteristics. Children’s cognitive scores were higher in high or medium quality care than in low quality care, but no evidence emerged suggesting that poverty moderated the quality effects. Nevertheless, this suggests that increasing the proportion of low-income children in high quality care could reduce the achievement gap because low-income children are very unlikely to experience high quality care. PMID:24347815

High school dropout and long-term sickness and disability in young adulthood: a prospective propensity score stratified cohort study (the Young-HUNT study).

PubMed

De Ridder, Karin A A; Pape, Kristine; Cuypers, Koenraad; Johnsen, Roar; Holmen, Turid Lingaas; Westin, Steinar; Bjørngaard, Johan Håkon

2013-10-09

High school dropout and long-term sickness absence/disability pension in young adulthood are strongly associated. We investigated whether common risk factors in adolescence may confound this association. Data from 6612 school-attending adolescents (13-20 years old) participating in the Norwegian Young-HUNT1 Survey (1995-1997) was linked to long-term sickness absence or disability pension from age 24-29 years old, recorded in the Norwegian Labour and Welfare Organisation registers (1998-2008). We used logistic regression to estimate risk differences of sickness or disability for school dropouts versus completers, adjusting for health, health-related behaviours, psychosocial factors, school problems, and parental socioeconomic position. In addition, we stratified the regression models of sickness and disability following dropout across the quintiles of the propensity score for high school dropout. The crude absolute risk difference for long-term sickness or disability for a school dropout compared to a completer was 0.21% or 21% points (95% confidence interval (CI), 17 to 24). The adjusted risk difference was reduced to 15% points (95% CI, 12 to 19). Overall, high school dropout increased the risk for sickness or disability regardless of the risk factor level present for high school dropout. High school dropouts have a strongly increased risk for sickness and disability in young adulthood across all quintiles of the propensity score for dropout, i.e. independent of own health, family and socioeconomic factors in adolescence. These findings reveal the importance of early prevention of dropout where possible, combined with increased attention to labour market integration and targeted support for those who fail to complete school.

Emergency coronary artery bypass grafting using minimized versus standard extracorporeal circulation – a propensity score analysis

PubMed Central

2013-01-01

Background The impact of minimized extracorporeal circulation (MECC) for emergency revascularization remains controversial. Methods A total of 348 patients underwent emergency CABG with MECC (n=146) or conventional extracorporeal circulation (CECC; n=175) between January 2005 and December 2010. Using propensity score matching after binary logistic regression, 100 patients, who underwent CABG with MECC could be matched with 100 patients, who underwent CABG with CECC. Primary outcome was 30-day mortality. Results Unadjusted 30-day mortality was 14.8% in patients with CECC and 6.9% in those with MECC (mean difference −7.9%; p=0.03). The adjusted mean difference (average treatment effect of the treated, ATT) after matching was −1.0% (95% CI −8.6 to 7.6; p=1.0). Intensive care unit stay (adjusted mean difference 1.0; 95% CI −0.2 to 3.2; p=0.70) and hospital stay (adjusted mean difference 1.0; 95% CI −2.0 to 3.6; p=0.40) did not show significant differences between both groups. The adjusted mean difference for postoperative low cardiac output syndrome was −1.1% (95% CI −7.3 to 7.1; p=0.83) without significant differences between CECC and MECC. Postoperative mechanical ventilation time, drain loss, postoperative rethoracotomy, postoperative neurological events, new onset renal replacement therapy and respiratory failure also had insignificant average treatment effects of the treated. In addition, all average treatment effects (ATEs) did not significantly differ between both groups. Conclusion Using propensity score estimation and matching, we did not observe significant differences in terms of survival and further outcomes in patients who undergo emergency CABG with CECC or MECC, but our results call for further analysis. PMID:23547910

Impact of Colic Pain as a Significant Factor for Predicting the Stone Free Rate of One-Session Shock Wave Lithotripsy for Treating Ureter Stones: A Bayesian Logistic Regression Model Analysis

PubMed Central

Chung, Doo Yong; Cho, Kang Su; Lee, Dae Hun; Han, Jang Hee; Kang, Dong Hyuk; Jung, Hae Do; Kown, Jong Kyou; Ham, Won Sik; Choi, Young Deuk; Lee, Joo Yong

2015-01-01

Purpose This study was conducted to evaluate colic pain as a prognostic pretreatment factor that can influence ureter stone clearance and to estimate the probability of stone-free status in shock wave lithotripsy (SWL) patients with a ureter stone. Materials and Methods We retrospectively reviewed the medical records of 1,418 patients who underwent their first SWL between 2005 and 2013. Among these patients, 551 had a ureter stone measuring 4–20 mm and were thus eligible for our analyses. The colic pain as the chief complaint was defined as either subjective flank pain during history taking and physical examination. Propensity-scores for established for colic pain was calculated for each patient using multivariate logistic regression based upon the following covariates: age, maximal stone length (MSL), and mean stone density (MSD). Each factor was evaluated as predictor for stone-free status by Bayesian and non-Bayesian logistic regression model. Results After propensity-score matching, 217 patients were extracted in each group from the total patient cohort. There were no statistical differences in variables used in propensity- score matching. One-session success and stone-free rate were also higher in the painful group (73.7% and 71.0%, respectively) than in the painless group (63.6% and 60.4%, respectively). In multivariate non-Bayesian and Bayesian logistic regression models, a painful stone, shorter MSL, and lower MSD were significant factors for one-session stone-free status in patients who underwent SWL. Conclusions Colic pain in patients with ureter calculi was one of the significant predicting factors including MSL and MSD for one-session stone-free status of SWL. PMID:25902059

Comparison of the effect of endodontic-periodontal combined lesion on the outcome of endodontic microsurgery with that of isolated endodontic lesion: survival analysis using propensity score analysis.

PubMed

Song, Minju; Kang, Minji; Kang, Dae Ryong; Jung, Hoi In; Kim, Euiseong

2018-05-01

The purpose of this retrospective clinical study was to evaluate the effect of lesion types related to endodontic microsurgery on the clinical outcome. Patients who underwent endodontic microsurgery between March 2001 and March 2014 with a postoperative follow-up period of at least 1 year were included in the study. Survival analyses were conducted to compare the clinical outcomes between isolated endodontic lesion group (endo group) and endodontic-periodontal combined lesion group (endo-perio group) and to evaluate other clinical variables. To reduce the effect of selection bias in this study, the estimated propensity scores were used to match the cases of the endo group with those of the endo-perio group. Among the 414 eligible cases, the 83 cases in the endo-perio group were matched to 166 out of the 331 cases in the endo group based on propensity score matching (PSM). The cumulated success rates of the endo and endo-perio groups were 87.3 and 72.3%, respectively. The median success period of the endo-perio group was 12 years (95% CI: 5.507, 18.498). Lesion type was found to be significant according to both Log-rank test (P = 0.002) and Cox proportional hazard regression analysis (P = 0.001). Among the other clinical variables, sex (female or male), age, and tooth type (anterior, premolar, or molar) were determined to be significant in Cox regression analysis (P < 0.05). Endodontic-periodontal combined lesions had a negative effect on the clinical outcome based on an analysis that utilized PSM, a useful statistical matching method for observational studies. Lesion type is a significant predictor of the outcome of endodontic microsurgery.

Impact of warm ischaemia time on postoperative renal function after partial nephrectomy for clinical T1 renal cell carcinoma: a propensity score-matched study.

PubMed

Lee, Hakmin; Song, Byung D; Byun, Seok-Soo; Lee, Sang E; Hong, Sung K

2018-01-01

To analyse the effect of prolonged warm ischaemia time (WIT) on long-term renal function after partial nephrectomy (PN), as controversy still exists as to whether prolonged WIT adversely affects the incidence of chronic kidney disease (CKD) after PN. We reviewed data from 1816 patients who underwent PN for a clinical T1 renal tumour. The propensity scores for prolonged WIT were calculated with the shorter WIT group (<30 min) matched to the longer WIT group (≥30 min) in a 2:1 ratio. Multivariate analysis was used to determine independent predictors for occurrence of postoperative CKD [defined as an estimated glomerular filtration rate (eGFR) of <60 mL/min/1.73 m 2 ] and major renal function deterioration (MRFD; defined as an eGFR decrease of ≥25% postoperatively). After propensity score matching, there was no significant difference in CKD-free survival between the two WIT groups (P = 0.787). Furthermore, longer WIT did not show any significant associations with postoperative CKD-free survival [hazard ratio (HR) 1.002, 95% confidence interval (CI) 0.989-1.015; P = 0.765) and MRFD-free survival (HR 1.014, 95% CI 1.000-1.028; P = 0.055). From further subgroup analyses using more specific WIT thresholds (≤20, 21-30, 31-40, 41-50, ≥50 min) and status of preoperative CKD, no significant differences were noted in CKD and MRFD-free survival amongst the subgroups (all P > 0.05). Prolonged WIT was not associated with increased incidence of CKD or MRFD after PN. © 2017 The Authors BJU International © 2017 BJU International Published by John Wiley & Sons Ltd.

The significant influence of having children on the postoperative prognosis of patients with nonsmall cell lung cancer: A propensity score-matched analysis.

PubMed

Takamori, Shinkichi; Tagawa, Tetsuzo; Toyokawa, Gouji; Ueo, Hiroki; Shimokawa, Mototsugu; Kinoshita, Fumihiko; Matsubara, Taichi; Kozuma, Yuka; Haratake, Naoki; Akamine, Takaki; Katsura, Masakazu; Takada, Kazuki; Hirai, Fumihiko; Shoji, Fumihiro; Okamoto, Tatsuro; Oda, Yoshinao; Maehara, Yoshihiko

2018-05-29

The aim of this study was to elucidate the relationship between family-associated factors and the postoperative prognosis in patients with nonsmall cell lung cancer (NSCLC). Additionally, we investigated whether having children was associated with the postoperative maintenance of the nutritional status. We selected 438 NSCLC patients who had undergone curative lung resection between 2004 and 2011 at Kyushu University (Fukuoka, Japan), whose family-associated factors were available. Nutritional indices, including the prognostic nutritional index (PNI), were used to estimate the change in the nutritional status for 1 year after surgery. A propensity score analysis was conducted after adjusting the following variables: sex, age, smoking history, performance status, pathological stage, and histological type. Three hundred patients (68.5%) had both children and partners. Forty-nine patients (11.2%) only had children, and 56 (12.8%) patients only had a partner. Thirty-three patients (7.5%) did not have a partner or children. The overall survival (OS) and disease-free survival (DFS) of the partner-present and partner-absent patients did not differ to a statistically significant extent (P = .862 and P = .712, respectively). However, childless patients showed significantly shorter OS and DFS in comparison with patients with children (P = .005 and P = .002, respectively). The postoperative exacerbation of PNI was significantly greater in childless patients than in patients with children (P = .003). These results remained after propensity score matching. Childless patients had a significantly poorer postoperative prognosis than those with children. Surgeons caring for childless NSCLC patients should be aware of the poorer postoperative outcomes in this population. © 2018 The Authors. Cancer Medicine published by John Wiley & Sons Ltd.

What is the effect of unemployment on all-cause mortality? A cohort study using propensity score matching.

PubMed

Clemens, Tom; Popham, Frank; Boyle, Paul

2015-02-01

There is a strong association between unemployment and mortality, but whether this relationship is causal remains debated. This study utilizes population-level administrative data from Scotland within a propensity score framework to explore whether the association between unemployment and mortality may be causal. The study examined a sample of working men and women aged 25-54 in 1991. Subsequent employment status in 2001 was observed (in work or unemployed) and the relative all-cause mortality risk of unemployment between 2001 and 2010 was estimated. To account for potential selection into unemployment of those in poor health, a propensity score matching approach was used. Matching variables were observed prior to unemployment and included health status up to the year of unemployment (hospital admissions and self-reported limiting long-term illness), as well as measures of socioeconomic position. Unemployment was associated with a significant all-cause mortality risk relative to employment for men (hazard ratio [HR] 1.85; 95% confidence interval [CI] 1.33-2.55). This effect was robust to controlling for prior health and sociodemographic characteristics. Effects for women were smaller and statistically insignificant (HR 1.51; 95% CI 0.68-3.37). For men, the findings support the notion that the often-observed association between unemployment and mortality may contain a significant causal component; although for women, there is less support for this conclusion. However, female employment status, as recorded in the census, is more complex than for men and may have served to underestimate any mortality effect of unemployment. Future work should examine this issue further. © The Author 2014. Published by Oxford University Press on behalf of the European Public Health Association. All rights reserved.

The Influence of the Japanese Nationwide Cardiovascular Prevention System Health Guidance on Smoking Cessation Among Smokers: A Propensity Score Matching Analysis.

PubMed

Nakamura, Koshi; Watanabe, Makoto; Okuda, Nagako; Yoshita, Katsushi; Kabayama, Mai; Torii, Sayuki; Kuribayashi, Toru; Itai, Kazuyoshi; Kamide, Kei; Miura, Katsuyuki; Okayama, Akira

2018-04-01

We investigated whether 2 types of personalized health guidance (repeated and single counseling) in the Japanese nationwide cardiovascular prevention system promoted smoking cessation among smokers. The study included 47,745 Japanese smokers aged 40 to 74 years classified into 2 personalized health guidance schemes. After a 1-year follow-up, we compared the rates of smoking cessation between individuals who had received counseling ("supported") and those who had not received counseling ("unsupported"). Using propensity score matching analysis, we estimated the average treatment effect (ATE) of each approach on smoking cessation after balancing out the characteristics between the supported and unsupported groups. The propensity score regression model included age, medical insurance type, weight gain since the age of 20 years, exercise, eating habits, alcohol intake, quality of sleep, readiness to modify lifestyle, willingness to receive support, and body mass index. In the repeated counseling scheme, the age-adjusted rates of smoking cessation in the supported and unsupported groups were 8.8% and 6.3% for males, and 9.8% and 9.1% for females respectively. In the single counseling scheme, the corresponding rates were 8.4% and 7.3% for supported and unsupported males, and 11.0% and 11.7% for supported and unsupported females respectively. The ATE of repeated counseling was ＋2.64% (95% confidence interval: ＋1.51% to ＋3.77%) for males and ＋3.11% (－1.85% to ＋8.07%) for females. The ATE of single counseling was ＋0.61% (－1.17% to ＋2.38%) for males and －1.06% (－5.96% to ＋3.85%) for females. In the Japanese cardiovascular prevention system, repeated counseling may promote smoking cessation among male smokers.

Type A Behavior Pattern, Impulsiveness, Risk Propensity, and Empathy as Predictors of Dyspnea and Number of Infections in Men with Chronic Obstructive Pulmonary Disease: A Cross-Sectional Study.

PubMed

Witusik, Andrzej; Mokros, Łukasz; Kuna, Piotr; Nowakowska-Domagała, Katarzyna; Antczak, Adam; Pietras, Tadeusz

2018-06-06

BACKGROUND Stress and psychological factors can induce dyspnea in patients with chronic obstructive pulmonary disease (COPD). The aim of this study was to assess selected elements of the clinical presentation of COPD in the context of the severity of type A pattern of behavior, impulsiveness, and tendency for empathy. MATERIAL AND METHODS This was a cross-sectional study. The study group consisted of 179 men with COPD and the control group consisted of 31 healthy male smokers. In all patients, the number of infectious exacerbations over the past year, the result on the dyspnea scale (MRC), and the FEV1-to- predicted FEV1 ratio was assessed. The A pattern of behavior was measured using the Type A scale. To measure impulsivity, risk propensity, and empathy, the IVE impulsivity questionnaire was used. RESULTS An increase in the number of infectious exacerbations was associated with an increased score on the Type A scale, an increase in risk propensity, and a decrease in impulsivity score. Increased severity of dyspnea was associated with an increase in Type A behavior pattern score and an increase in the risk propensity score. CONCLUSIONS Type A behavior pattern and risk propensity are independent predictors of the number of infections in the last year and of the subjective severity of dyspnea among men with COPD and healthy male smokers.

Ulinastatin administration is associated with a lower incidence of acute kidney injury after cardiac surgery: a propensity score matched study.

PubMed

Wan, Xin; Xie, Xiangcheng; Gendoo, Yasser; Chen, Xin; Ji, Xiaobing; Cao, Changchun

2016-02-17

Systemic inflammation is involved in the development of acute kidney injury (AKI) after cardiac surgery with cardiopulmonary bypass (CPB). Ulinastatin, a urinary trypsin inhibitor (UTI), possesses a variety of anti-inflammatory effects. Therefore, we hypothesized that the administration of ulinastatin would reduce the occurrence of AKI in patients undergoing cardiac surgery with CPB. A retrospective propensity score matched analysis was used to evaluate the effect of ulinastatin on the development of AKI in patients undergoing first documented cardiac surgery with CPB between January 2008 and December 2012 in our hospital. Multiple logistic regression models were also employed to identify the association between UTI administration and development of AKI. A total of 2072 patients who underwent cardiac surgery with CPB met the inclusion criteria. Before propensity score matching, variables such as age, baseline creatinine, CPB duration, red blood cells transfused, and hematocrit were statistically different between the ulinastatin (UTI) group and the control group. On the basis of propensity scores, 409 UTI patients were successfully matched to the 409 patients from among those 1663 patients without UTI administration. After propensity score matching, no statistically significant differences in the baseline characteristics were found between the UTI group and the control group. The propensity score matched cohort analysis revealed that AKI and the need for renal replacement therapy occurred more frequently in the control group than in the UTI group (40.83% vs. 30.32%, P = 0.002; 2.44% vs. 0.49%, P = 0.02, respectively). However, there were no significant differences in mortality, length of intensive care unit stay, and length of hospital stay between the UTI group and the control group. Using multivariate logistic regression analysis, we found ulinastatin played a protective role in the development of AKI after cardiac surgery (odds ratio 0.71, 95% confidence interval 0.56-0.90, P = 0.005). This study shows that ulinastatin was associated with a lower incidence of AKI after cardiac surgery, suggesting that the administration of ulinastatin may be favorable for those patients undergoing cardiac surgery with CPB.

Using instrumental variables to estimate a Cox's proportional hazards regression subject to additive confounding

PubMed Central

Tosteson, Tor D.; Morden, Nancy E.; Stukel, Therese A.; O'Malley, A. James

2014-01-01

The estimation of treatment effects is one of the primary goals of statistics in medicine. Estimation based on observational studies is subject to confounding. Statistical methods for controlling bias due to confounding include regression adjustment, propensity scores and inverse probability weighted estimators. These methods require that all confounders are recorded in the data. The method of instrumental variables (IVs) can eliminate bias in observational studies even in the absence of information on confounders. We propose a method for integrating IVs within the framework of Cox's proportional hazards model and demonstrate the conditions under which it recovers the causal effect of treatment. The methodology is based on the approximate orthogonality of an instrument with unobserved confounders among those at risk. We derive an estimator as the solution to an estimating equation that resembles the score equation of the partial likelihood in much the same way as the traditional IV estimator resembles the normal equations. To justify this IV estimator for a Cox model we perform simulations to evaluate its operating characteristics. Finally, we apply the estimator to an observational study of the effect of coronary catheterization on survival. PMID:25506259

Using instrumental variables to estimate a Cox's proportional hazards regression subject to additive confounding.

PubMed

MacKenzie, Todd A; Tosteson, Tor D; Morden, Nancy E; Stukel, Therese A; O'Malley, A James

2014-06-01

The estimation of treatment effects is one of the primary goals of statistics in medicine. Estimation based on observational studies is subject to confounding. Statistical methods for controlling bias due to confounding include regression adjustment, propensity scores and inverse probability weighted estimators. These methods require that all confounders are recorded in the data. The method of instrumental variables (IVs) can eliminate bias in observational studies even in the absence of information on confounders. We propose a method for integrating IVs within the framework of Cox's proportional hazards model and demonstrate the conditions under which it recovers the causal effect of treatment. The methodology is based on the approximate orthogonality of an instrument with unobserved confounders among those at risk. We derive an estimator as the solution to an estimating equation that resembles the score equation of the partial likelihood in much the same way as the traditional IV estimator resembles the normal equations. To justify this IV estimator for a Cox model we perform simulations to evaluate its operating characteristics. Finally, we apply the estimator to an observational study of the effect of coronary catheterization on survival.

Blinatumomab vs historical standard therapy of adult relapsed/refractory acute lymphoblastic leukemia

PubMed Central

Gökbuget, N; Kelsh, M; Chia, V; Advani, A; Bassan, R; Dombret, H; Doubek, M; Fielding, A K; Giebel, S; Haddad, V; Hoelzer, D; Holland, C; Ifrah, N; Katz, A; Maniar, T; Martinelli, G; Morgades, M; O'Brien, S; Ribera, J-M; Rowe, J M; Stein, A; Topp, M; Wadleigh, M; Kantarjian, H

2016-01-01

We compared outcomes from a single-arm study of blinatumomab in adult patients with B-precursor Ph-negative relapsed/refractory acute lymphoblastic leukemia (R/R ALL) with a historical data set from Europe and the United States. Estimates of complete remission (CR) and overall survival (OS) were weighted by the frequency distribution of prognostic factors in the blinatumomab trial. Outcomes were also compared between the trial and historical data using propensity score methods. The historical cohort included 694 patients with CR data and 1112 patients with OS data compared with 189 patients with CR and survival data in the blinatumomab trial. The weighted analysis revealed a CR rate of 24% (95% CI: 20–27%) and a median OS of 3.3 months (95% CI: 2.8–3.6) in the historical cohort compared with a CR/CRh rate of 43% (95% CI: 36–50%) and a median OS of 6.1 months (95% CI: 4.2–7.5) in the blinatumomab trial. Propensity score analysis estimated increased odds of CR/CRh (OR=2.68, 95% CI: 1.67–4.31) and improved OS (HR=0.536, 95% CI: 0.394–0.730) with blinatumomab. The analysis demonstrates the application of different study designs and statistical methods to compare novel therapies for R/R ALL with historical data. PMID:27662202

Non-Elective Paraesophageal Hernia Repair Portends Worse Outcomes in Comparable Patients: a Propensity-Adjusted Analysis.

PubMed

Tam, Vernissia; Luketich, James D; Winger, Daniel G; Sarkaria, Inderpal S; Levy, Ryan M; Christie, Neil A; Awais, Omar; Shende, Manisha R; Nason, Katie S

2017-01-01

Patients undergoing non-elective paraesophageal hernia repair (PEHR) have worse perioperative outcomes. Because they are usually older and sicker, however, these patients may be more prone to adverse events, independent of surgical urgency. Our study aimed to determine whether non-elective PEHR is associated with differential postoperative outcome compared to elective repair, using propensity-score weighting. We abstracted data for patients undergoing PEHR (n = 924; non-elective n = 171 (19 %); 1997-2010). Using boosted regression, we generated a propensity-weighted dataset. Odds of 30-day/in-hospital mortality and major complications after non-elective surgery were determined. Patients undergoing non-elective repair were significantly older, had more adverse prognostic factors, and significantly more major complications (38 versus 18 %; p < 0.001) and death (8 versus 1 %; p < 0.001). After propensity weighting, median absolute percentage bias across 28 propensity-score variables improved from 19 % (significant imbalance) to 5.6 % (well-balanced). After adjusting propensity-weighted data for age and comorbidity score, odds of major complications were still nearly two times greater (OR 1.67, CI 1.07-2.61) and mortality nearly three times greater (OR 2.74, CI 0.93-8.1) than for elective repair. Even after balancing significant differences in baseline characteristics, non-elective PEHR was associated with worse outcomes than elective repair. Symptomatic patients should be referred for elective repair by experienced surgeons.

Comparison of Core-Needle Biopsy and Fine-Needle Aspiration for Evaluating Thyroid Incidentalomas Detected by 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography: A Propensity Score Analysis.

PubMed

Suh, Chong Hyun; Choi, Young Jun; Lee, Jong Jin; Shim, Woo Hyun; Baek, Jung Hwan; Chung, Han Cheol; Shong, Young Kee; Song, Dong Eun; Sung, Tae Yon; Lee, Jeong Hyun

2017-10-01

This study used a propensity score analysis to assess the roles of core-needle biopsy (CNB) and fine-needle aspiration (FNA) in the evaluation of thyroid incidentalomas detected on 18 F-fluorodeoxyglucose positron emission tomography/computed tomography ( 18 F-FDG PET/CT). The study population was obtained from a historical cohort who underwent 18 F-FDG PET/CT between October 2008 and September 2015. Patients were included who underwent ultrasound-guided CNB or FNA for incidental focal uptake of 18 F-FDG in the thyroid gland on PET/CT. The primary study outcomes included the inconclusive result rates in the CNB and FNA groups. The secondary outcome measures included the non-diagnostic result rate and the diagnostic performance for neoplasms. Multivariate analysis, propensity score matching, and inverse probability weighting were conducted. A total of 1360 nodules from 1338 patients were included in this study: 859 nodules from 850 patients underwent FNA, and 501 nodules from 488 patients underwent CNB. Compared to FNA, CNB demonstrated a significantly lower inconclusive result rate in the pooled cohort (23.8% vs. 35.4%; p < 0.001), propensity score-matched cohorts (22.9% vs. 36.6%; p < 0.001), and with inverse probability weighting (22.4% vs. 35.2%; p < 0.001). Non-diagnostic result rates were also significantly lower in CNB than in FNA. The diagnostic performance of the two groups in the pooled and matched cohorts was similar, with no significant differences found. The significantly lower inconclusive result rates in CNB than in FNA were consistent within the propensity score-matched cohorts. Therefore, CNB appears to be a promising diagnostic tool for patients with thyroid incidentalomas detected on 18 F-FDG PET/CT.

Impact of non-anticoagulant therapy on patients with sepsis-induced disseminated intravascular coagulation: A multicenter, case-control study.

PubMed

Kudo, Daisuke; Hayakawa, Mineji; Ono, Kota; Yamakawa, Kazuma

2018-03-01

Anticoagulant therapy for patients with sepsis is not recommended in the latest Surviving Sepsis Campaign guidelines, and non-anticoagulant therapy is the global standard treatment approach at present. We aimed at elucidating the effect of non-anticoagulant therapy on patients with sepsis-induced disseminated intravascular coagulation (DIC), as evidence on this topic has remained inconclusive. Data from 3195 consecutive adult patients admitted to 42 intensive care units for the treatment of severe sepsis were retrospectively analyzed via propensity score analyses with and without multiple imputation. The primary outcome was in-hospital all-cause mortality. Among 1784 patients with sepsis-induced DIC, 745 (41.8%) were not treated with anticoagulants. The inverse probability of treatment-weighted (with and without multiple imputation) and quintile-stratified propensity score analyses (without multiple imputation) indicated a significant association between non-anticoagulant therapy and higher in-hospital all-cause mortality (odds ratio [95% confidence interval]: 1.59 [1.19-2.12], 1.32 [1.02-1.81], and 1.32 [1.03-1.69], respectively). However, quintile-stratified propensity score analyses with multiple imputation and propensity score matching analysis with and without multiple imputation did not show this association. Survival duration was not significantly different between patients in the propensity score-matched non-anticoagulant therapy group and those in the anticoagulant therapy group (Cox regression analysis with and without multiple imputation: hazard ratio [95% confidence interval]: 1.26 [1.00-1.60] and 1.22 [0.93-1.59], respectively). It remains controversial if non-anticoagulant therapy is harmful, equivalent, or beneficial compared with anticoagulant therapy in the treatment of patients with sepsis-induced DIC. Copyright © 2018 Elsevier Ltd. All rights reserved.

Do observational studies using propensity score methods agree with randomized trials? A systematic comparison of studies on acute coronary syndromes

PubMed Central

Dahabreh, Issa J.; Sheldrick, Radley C.; Paulus, Jessica K.; Chung, Mei; Varvarigou, Vasileia; Jafri, Haseeb; Rassen, Jeremy A.; Trikalinos, Thomas A.; Kitsios, Georgios D.

2012-01-01

Aims Randomized controlled trials (RCTs) are the gold standard for assessing the efficacy of therapeutic interventions because randomization protects from biases inherent in observational studies. Propensity score (PS) methods, proposed as a potential solution to confounding of the treatment–outcome association, are widely used in observational studies of therapeutic interventions for acute coronary syndromes (ACS). We aimed to systematically assess agreement between observational studies using PS methods and RCTs on therapeutic interventions for ACS. Methods and results We searched for observational studies of interventions for ACS that used PS methods to estimate treatment effects on short- or long-term mortality. Using a standardized algorithm, we matched observational studies to RCTs based on patients’ characteristics, interventions, and outcomes (‘topics’), and we compared estimates of treatment effect between the two designs. When multiple observational studies or RCTs were identified for the same topic, we performed a meta-analysis and used the summary relative risk for comparisons. We matched 21 observational studies investigating 17 distinct clinical topics to 63 RCTs (median = 3 RCTs per observational study) for short-term (7 topics) and long-term (10 topics) mortality. Estimates from PS analyses differed statistically significantly from randomized evidence in two instances; however, observational studies reported more extreme beneficial treatment effects compared with RCTs in 13 of 17 instances (P = 0.049). Sensitivity analyses limited to large RCTs, and using alternative meta-analysis models yielded similar results. Conclusion For the treatment of ACS, observational studies using PS methods produce treatment effect estimates that are of more extreme magnitude compared with those from RCTs, although the differences are rarely statistically significant. PMID:22711757

Propensity Score-based Comparison of Long-term Outcomes With 3-Dimensional Conformal Radiotherapy vs Intensity-Modulated Radiotherapy for Esophageal Cancer

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

Lin, Steven H., E-mail: SHLin@mdanderson.org; Wang Lu; Myles, Bevan

2012-12-01

Purpose: Although 3-dimensional conformal radiotherapy (3D-CRT) is the worldwide standard for the treatment of esophageal cancer, intensity modulated radiotherapy (IMRT) improves dose conformality and reduces the radiation exposure to normal tissues. We hypothesized that the dosimetric advantages of IMRT should translate to substantive benefits in clinical outcomes compared with 3D-CRT. Methods and Materials: An analysis was performed of 676 nonrandomized patients (3D-CRT, n=413; IMRT, n=263) with stage Ib-IVa (American Joint Committee on Cancer 2002) esophageal cancers treated with chemoradiotherapy at a single institution from 1998-2008. An inverse probability of treatment weighting and inclusion of propensity score (treatment probability) as amore » covariate were used to compare overall survival time, interval to local failure, and interval to distant metastasis, while accounting for the effects of other clinically relevant covariates. The propensity scores were estimated using logistic regression analysis. Results: A fitted multivariate inverse probability weighted-adjusted Cox model showed that the overall survival time was significantly associated with several well-known prognostic factors, along with the treatment modality (IMRT vs 3D-CRT, hazard ratio 0.72, P<.001). Compared with IMRT, 3D-CRT patients had a significantly greater risk of dying (72.6% vs 52.9%, inverse probability of treatment weighting, log-rank test, P<.0001) and of locoregional recurrence (P=.0038). No difference was seen in cancer-specific mortality (Gray's test, P=.86) or distant metastasis (P=.99) between the 2 groups. An increased cumulative incidence of cardiac death was seen in the 3D-CRT group (P=.049), but most deaths were undocumented (5-year estimate, 11.7% in 3D-CRT vs 5.4% in IMRT group, Gray's test, P=.0029). Conclusions: Overall survival, locoregional control, and noncancer-related death were significantly better after IMRT than after 3D-CRT. Although these results need confirmation, IMRT should be considered for the treatment of esophageal cancer.« less

Assessing the Impact of School-Based Health Centers on Academic Achievement and College Preparation Efforts: Using Propensity Score Matching to Assess School-Level Data in California

ERIC Educational Resources Information Center

Bersamin, Melina; Garbers, Samantha; Gaarde, Jenna; Santelli, John

2016-01-01

This study examines the association between school-based health center (SBHC) presence and school-wide measures of academic achievement and college preparation efforts. Publicly available educational and demographic data from 810 California public high schools were linked to a list of schools with an SBHC. Propensity score matching, a method to…

Are Two Years Better than One Year? A Propensity Score Analysis of the Impact of Head Start Program Duration on Children's School Performance in Kindergarten

ERIC Educational Resources Information Center

Wen, Xiaoli; Leow, Christine; Hahs-Vaughn, Debbie L.; Korfmacher, Jon; Marcus, Sue M.

2012-01-01

Using data from a nationally representative sample, this study examined Head Start children's school outcome differences by the end of Kindergarten between children who attended Head Start program for two years and the ones who attended for one year. Propensity scores were used to match children who experienced different durations of the program…

Improving participant selection in disease management programmes: insights gained from propensity score stratification.

PubMed

Linden, Ariel; Adams, John L

2008-10-01

While the randomized controlled trial (RCT) remains the gold-standard study design for evaluating treatment effect, outcomes researchers turn to powerful quasi-experimental designs when only observational studies can be conducted. Within these designs, propensity score matching is one of the most popular to evaluate disease management (DM) programme effectiveness. Given that DM programmes generally have a much smaller number of participants than non-participants in the population, propensity score matching will typically result in all or nearly all participants finding successful matches, while most of the non-participants in the population remain unmatched and thereby excluded from the analysis. By excluding data from the unmatched population, the effect of non-treatment in the remaining population with the disease is not captured. In the present study, we examine changes in hospitalization rates stratified by propensity score quintiles across the entire population allowing us to gain insight as to how well the programme chose its participants, or if the programme could have been effective on those individuals not explicitly targeted for the intervention. These data indicate the presence of regression to the mean, and suggest that the DM programme may be overly limited to only the highest strata when there is evidence of a potential benefit for those in all the lower strata as well.

Using ecological propensity score to adjust for missing confounders in small area studies.

PubMed

Wang, Yingbo; Pirani, Monica; Hansell, Anna L; Richardson, Sylvia; Blangiardo, Marta

2017-11-09

Small area ecological studies are commonly used in epidemiology to assess the impact of area level risk factors on health outcomes when data are only available in an aggregated form. However, the resulting estimates are often biased due to unmeasured confounders, which typically are not available from the standard administrative registries used for these studies. Extra information on confounders can be provided through external data sets such as surveys or cohorts, where the data are available at the individual level rather than at the area level; however, such data typically lack the geographical coverage of administrative registries. We develop a framework of analysis which combines ecological and individual level data from different sources to provide an adjusted estimate of area level risk factors which is less biased. Our method (i) summarizes all available individual level confounders into an area level scalar variable, which we call ecological propensity score (EPS), (ii) implements a hierarchical structured approach to impute the values of EPS whenever they are missing, and (iii) includes the estimated and imputed EPS into the ecological regression linking the risk factors to the health outcome. Through a simulation study, we show that integrating individual level data into small area analyses via EPS is a promising method to reduce the bias intrinsic in ecological studies due to unmeasured confounders; we also apply the method to a real case study to evaluate the effect of air pollution on coronary heart disease hospital admissions in Greater London. © The Author 2017. Published by Oxford University Press.

The Association of Statin Use with Age-Related Macular Degeneration Progression The Age-Related Eye Disease Study 2 Report Number 9

PubMed Central

Al-Holou, Shaza N.; Tucker, William R.; Agrón, Elvira; Clemons, Traci E.; Cukras, Catherine; Ferris, Frederick L.; Chew, Emily Y.

2015-01-01

Objective/purpose To evaluate the association of statin use with progression of age-related macular degeneration (AMD). Design Preplanned, prospective cohort study within a controlled clinical trial of oral supplementation for age-related eye diseases. Subjects Age-Related Eye Disease Study 2 participants, aged 50 to 85 years. Methods Factors, including age, gender, smoking status, aspirin use, and history of diabetes, hypertension, heart disease, angina, and stroke, all known to be associated with statin use, were included in a logistic regression model to estimate propensity scores for each participant. Age-adjusted proportional hazards regression models, with and without propensity score matching, were performed to evaluate the association of statin use with progression to late AMD. Analyses were also performed adjusting for the competing risk of death. Main Outcome Measures Baseline and annual stereoscopic fundus photographs were assessed centrally by masked graders for the development of late AMD, either neovascular AMD or geographic atrophy (GA). Results Of the 3791 participants (2462 with bilateral large drusen and 1329 with unilateral late AMD at baseline), 1659 (43.8%) were statin users. The overall analysis, with no matching of propensity scores and no adjustment for death as a competing risk, showed that statin use was not associated with progression to late AMD (hazard ratios [HR] of 1.08, 95% confidence intervals [CI] of 0.83–1.41, P=0.56). When matched for propensity scores and adjusted for death as a competing risk, the result was not statistically significant with HR: 0.81, 95% CI: 0.55–1.20, P=0.29. Further subgroup analyses of persons with or without late AMD at baseline to the various components of late AMD (neovascular, central geographic atrophy, or any geographic atrophy) also showed no statistically significant association of statin use with progression to AMD. Conclusions Statin use was not statistically significantly associated with the progression to late AMD in the AREDS2 participants, and these findings are consistent with the findings in the majority of previous studies. Statins have been demonstrated to reduce the risks of cardiovascular disease, but our data do not provide evidence of a beneficial effect on slowing AMD progression. PMID:26435335

Performance of the disease risk score in a cohort study with policy-induced selection bias.

PubMed

Tadrous, Mina; Mamdani, Muhammad M; Juurlink, David N; Krahn, Murray D; Lévesque, Linda E; Cadarette, Suzanne M

2015-11-01

To examine the performance of the disease risk score (DRS) in a cohort study with evidence of policy-induced selection bias. We examined two cohorts of new users of bisphosphonates. Estimates for 1-year hip fracture rates between agents using DRS, exposure propensity scores and traditional multivariable analysis were compared. The results for the cohort with no evidence of policy-induced selection bias showed little variation across analyses (-4.1-2.0%). Analysis of the cohort with evidence of policy-induced selection bias showed greater variation (-13.5-8.1%), with the greatest difference seen with DRS analyses. Our findings suggest that caution may be warranted when using DRS methods in cohort studies with policy-induced selection bias, further research is needed.

The Use of Propensity Scores and Observational Data to Estimate Randomized Controlled Trial Generalizability Bias

PubMed Central

Pressler, Taylor R.; Kaizar, Eloise E.

2014-01-01

While randomized controlled trials (RCT) are considered the “gold standard” for clinical studies, the use of exclusion criteria may impact the external validity of the results. It is unknown whether estimators of effect size are biased by excluding a portion of the target population from enrollment. We propose to use observational data to estimate the bias due to enrollment restrictions, which we term generalizability bias. In this paper we introduce a class of estimators for the generalizability bias and use simulation to study its properties in the presence of non-constant treatment effects. We find the surprising result that our estimators can be unbiased for the true generalizability bias even when all potentially confounding variables are not measured. In addition, our proposed doubly robust estimator performs well even for mis-specified models. PMID:23553373

The Effects of Runaway-Homeless Episodes on High School Dropout

PubMed Central

Aratani, Yumiko; Cooper, Janice L.

2013-01-01

This article uses data from the National Longitudinal Survey of Youth 1997 to examine the relationship between running away from home between the ages of 12 and 14 and dropping from high school among youth. Propensity score matching was conducted in estimating the effect of running away on high school dropout while controlling for confounding factors, such as familial instability and socioemotional health risks. The findings suggest that having runaway-homeless episodes have a detrimental effect on academic achievement. PMID:25641997

Novel immunological and nutritional-based prognostic index for gastric cancer.

PubMed

Sun, Kai-Yu; Xu, Jian-Bo; Chen, Shu-Ling; Yuan, Yu-Jie; Wu, Hui; Peng, Jian-Jun; Chen, Chuang-Qi; Guo, Pi; Hao, Yuan-Tao; He, Yu-Long

2015-05-21

To assess the prognostic significance of immunological and nutritional-based indices, including the prognostic nutritional index (PNI), neutrophil-lymphocyte ratio (NLR), and platelet-lymphocyte ratio in gastric cancer. We retrospectively reviewed 632 gastric cancer patients who underwent gastrectomy between 1998 and 2008. Areas under the receiver operating characteristic curve were calculated to compare the predictive ability of the indices, together with estimating the sensitivity, specificity and agreement rate. Univariate and multivariate analyses were performed to identify risk factors for overall survival (OS). Propensity score analysis was performed to adjust variables to control for selection bias. Each index could predict OS in gastric cancer patients in univariate analysis, but only PNI had independent prognostic significance in multivariate analysis before and after adjustment with propensity scoring (hazard ratio, 1.668; 95% confidence interval: 1.368-2.035). In subgroup analysis, a low PNI predicted a significantly shorter OS in patients with stage II-III disease (P = 0.019, P < 0.001), T3-T4 tumors (P < 0.001), or lymph node metastasis (P < 0.001). Canton score, a combination of PNI, NLR, and platelet, was a better indicator for OS than PNI, with the largest area under the curve for 12-, 36-, 60-mo OS and overall OS (P = 0.022, P = 0.030, P < 0.001, and P = 0.024, respectively). The maximum sensitivity, specificity, and agreement rate of Canton score for predicting prognosis were 84.6%, 34.9%, and 70.1%, respectively. PNI is an independent prognostic factor for OS in gastric cancer. Canton score can be a novel preoperative prognostic index in gastric cancer.

Effects of edaravone on early outcomes in acute ischemic stroke patients treated with recombinant tissue plasminogen activator.

PubMed

Wada, Tomoki; Yasunaga, Hideo; Inokuchi, Ryota; Horiguchi, Hiromasa; Fushimi, Kiyohide; Matsubara, Takehiro; Nakajima, Susumu; Yahagi, Naoki

2014-10-15

We investigated whether edaravone could improve early outcomes in acute ischemic stroke patients treated with recombinant tissue plasminogen activator (rtPA). We conducted a retrospective cohort study using the Japanese Diagnosis Procedure Combination database. We identified patients admitted with a primary diagnosis of ischemic stroke from 1 July 2010 to 31 March 2012 and treated with rtPA on the same day of stroke onset or the following day. Thereafter, we selected those who received edaravone on the same day of rtPA administration (edaravone group), and those who received rtPA without edaravone (control group). The primary outcomes were modified Rankin Scale (mRS) scores at discharge. One-to-one propensity-score matching was performed between the edaravone and control groups. An ordinal logistic regression analysis for mRS scores at discharge was performed with adjustment for possible variables as well as clustering of patients within hospitals using a generalized estimating equation. We identified 6336 eligible patients for inclusion in the edaravone group (n=5979; 94%) and the control group (n=357; 6%) as the total population. In 356 pairs of the propensity-matched population, the ordinal logistic regression analysis showed that edaravone was significantly associated with lower mRS scores of patients at discharge (adjusted odds ratio: 0.74; 95% confidence interval: 0.57-0.96). Edaravone may improve early outcomes in acute ischemic stroke patients treated with rtPA. Copyright © 2014 Elsevier B.V. All rights reserved.

The effects of police contact on trajectories of violence: a group-based, propensity score matching analysis.

PubMed

Ward, Jeffrey T; Krohn, Marvin D; Gibson, Chris L

2014-02-01

This study uses a life course framework to investigate how police contacts may serve as a potential turning point in a violent crime trajectory. Drawing on the central ideas from deterrence and labeling theories, we determine whether individuals on different violent offending trajectories increase or decrease their offending following a police contact. Analyzing nine waves of data from the Rochester Youth Development Study, an integrated propensity score matching and latent class growth model was used. First, three violent trajectory groups emerged including high offenders, non-offenders, and low offenders. Second, after accounting for selection bias using propensity score matching procedures, experiencing a police contact increased the likelihood of future violent offending for the entire sample and for those who were on a low violent-offending trajectory specifically. These findings are interpreted as partial support for labeling theory. Limitations of the study and directions for future research are discussed.

Effect of Chronic Diseases on Work Productivity: A Propensity Score Analysis.

PubMed

Fouad, Ahmed Mahmoud; Waheed, Amani; Gamal, Amira; Amer, Shaimaa Ahmed; Abdellah, Rasha Farouk; Shebl, Fatma Mohamed

2017-05-01

The aim of this study was to evaluate the effect of chronic disease(s) on work productivity. Using the Health & Work Performance Questionnaire, information was collected from 516 workers on chronic disease status and work productivity. Propensity-score matching was performed to identify matched-pairs of workers. In the propensity-score matched sample, workers with chronic diseases were more likely to have increased absenteeism and presenteeism rates, 6.34 and 2.36 times the rates if no chronic diseases, respectively. In addition, they had greater odds for getting negative critical work incidents and less odds for positive incidents than none or balanced status. Multimorbidity showed more significant increase in absenteeism and presenteeism rates, as well as increased odds for excess negative critical work incidents. Chronic disease(s) can significantly reduce work productivity by increasing absenteeism, presenteeism, and net negative critical incidents.

Moving to a Highly Walkable Neighborhood and Incidence of Hypertension: A Propensity-Score Matched Cohort Study.

PubMed

Chiu, Maria; Rezai, Mohammad-Reza; Maclagan, Laura C; Austin, Peter C; Shah, Baiju R; Redelmeier, Donald A; Tu, Jack V

2016-06-01

The impact of moving to a neighborhood more conducive to utilitarian walking on the risk of incident hypertension is uncertain. Our study aimed to examine the effect of moving to a highly walkable neighborhood on the risk of incident hypertension. A population-based propensity-score matched cohort study design was used based on the Ontario population from the Canadian Community Health Survey (2001-2010). Participants were adults ≥ 20 years of age who moved from a low-walkability neighborhood (defined as any neighborhood with a Walk Score < 90) to either a high- (Walk Score ≥ 90) or another low-walkability neighborhood. The incidence of hypertension was assessed by linking the cohort to administrative health databases using a validated algorithm. Propensity-score matched Cox proportional hazard models were used. Annual health examination was used as a control event. Among the 1,057 propensity-score matched pairs there was a significantly lower risk of incident hypertension in the low to high vs. the low to low-walkability groups [hazard ratio = 0.46; 95% CI, 0.26, 0.81, p < 0.01]. The crude hypertension incidence rates were 18.0 per 1,000 person-years (95% CI: 11.6, 24.8) among the low- to low-walkability movers compared with 8.6 per 1,000 person-years (95% CI: 5.3, 12.7) among the low- to high-walkability movers (p < 0.001). There were no significant differences in the hazard of annual health examination between the two mover groups. Moving to a highly walkable neighborhood was associated with a significantly lower risk of incident hypertension. Future research should assess whether specific attributes of walkable neighborhoods (e.g., amenities, density, land-use mix) may be driving this relationship. Chiu M, Rezai MR, Maclagan LC, Austin PC, Shah BR, Redelmeier DA, Tu JV. 2016. Moving to a highly walkable neighborhood and incidence of hypertension: a propensity-score matched cohort study. Environ Health Perspect 124:754-760; http://dx.doi.org/10.1289/ehp.1510425.

Validating the EXCEL hypothesis: a propensity score matched 3-year comparison of percutaneous coronary intervention versus coronary artery bypass graft in left main patients with SYNTAX score ≤32.

PubMed

Capodanno, Davide; Caggegi, Anna; Capranzano, Piera; Cincotta, Glauco; Miano, Marco; Barrano, Gionbattista; Monaco, Sergio; Calvo, Francesco; Tamburino, Corrado

2011-06-01

The aim of this study is to verify the study hypothesis of the EXCEL trial by comparing percutaneous coronary intervention (PCI) and coronary artery bypass graft (CABG) in an EXCEL-like population of patients. The upcoming EXCEL trial will test the hypothesis that left main patients with SYNTAX score ≤ 32 experience similar rates of 3-year death, myocardial infarction (MI), or cerebrovascular accidents (CVA) following revascularization by PCI or CABG. We compared the 3-year rates of death/MI/CVA and death/MI/CVA/target vessel revascularization (MACCE) in 556 patients with left main disease and SYNTAX score ≤ 32 undergoing PCI (n = 285) or CABG (n = 271). To account for confounders, outcome parameters underwent extensive statistical adjustment. The unadjusted incidence of death/MI/CVA was similar between PCI and CABG (12.7% vs. 8.4%, P = 0.892), while MACCE were higher in the PCI group compared to the CABG group (27.0% vs. 11.8%, P < 0.001). After propensity score matching, PCI was not associated with a significant increase in the rate of death/MI/CVA (11.8% vs. 10.7%, P = 0.948), while MACCE were more frequently noted among patients treated with PCI (28.8% vs. 14.1%, P = 0.002). Adjustment by means of SYNTAX score and EUROSCORE, covariates with and without propensity score, and propensity score alone did not change significantly these findings. In an EXCEL-like cohort of patients with left main disease, there seems to be a clinical equipoise between PCI and CABG in terms of death/MI/CVA. However, even in patients with SYNTAX score ≤ 32, CABG is superior to PCI when target vessel revascularization is included in the combined endpoint. Copyright © 2011 Wiley-Liss, Inc.

Cancer Recurrence After Esophagectomy: Impact of Postoperative Infection in Propensity-Matched Cohorts.

PubMed

Tam, Vernissia; Luketich, James D; Winger, Daniel G; Sarkaria, Inderpal S; Levy, Ryan M; Christie, Neil A; Awais, Omar; Shende, Manisha R; Nason, Katie S

2016-11-01

Postoperative infection increases cancer recurrence and worsens survival in colorectal cancer, but the relationship for esophagogastric adenocarcinoma after esophagectomy is not well defined. We aimed to determine whether recurrence and survival after minimally invasive esophagectomy for esophagogastric adenocarcinoma were influenced by postoperative infection using propensity-matched analysis. We abstracted data for 810 patients (1997-2010) and defined exposure as at least 1 in-hospital or 30-day infectious complication (n = 206 [25%]). Using 29 pretreatment/intraoperative variables, patients were propensity-score matched (caliper = 0.05). Time to cancer recurrence and survival (Kaplan-Meier curves and the Breslow test), and associated factors (Cox regression with shared frailty) were assessed. After propensity matching (n = 167 pairs), median bias across propensity-score variables was reduced from 12.9% (p < 0.001) to 4.4% (p = 1.000). Postoperative infection was not associated with rate (n = 60 versus 63; McNemar p = 0.736) or time to recurrence in those in whom disease recurred (median, 10.7 versus 11.1 months; Wilcoxon signed-rank p = 0.455) but was associated with shorter overall survival (n = 124 versus 102 deaths; median, 26 versus 41 months; Breslow p = 0.002). After adjusting for age, body mass index, neoadjuvant therapy, sex, comorbidity score, positive resection margins, pathologic stage, R0 resection, and recurrence, postoperative infection was associated with a 44% greater hazard for death (hazard ratio, 1.44; 95% confidence interval, 1.10-1.89). In patients with esophagogastric adenocarcinoma, infections after esophagectomy were not associated with an increased rate or earlier time to recurrence when baseline characteristics associated with infection risk were balanced using propensity-score matching. Despite this, overall survival was shorter in patients with infectious complications. After adjusting for other important survival predictors, infections after esophagectomy continued to be independently associated with worse survival. Copyright © 2016 The Society of Thoracic Surgeons. Published by Elsevier Inc. All rights reserved.

Out-of-Home Care and the Educational Achievement, Attendance, and Suspensions of Maltreated Children: A Propensity-Matched Study.

PubMed

Maclean, Miriam J; Taylor, Catherine L; O'Donnell, Melissa

2018-04-30

To estimate the influence of out-of-home care on reading scores, attendance, and suspensions by comparing a matched sample of maltreated children who entered out-of-home care and maltreated children who remained at home. Linked administrative data for all children born in Western Australia between 1990 and 2010 was used, focusing on those with substantiated maltreatment before year 9 achievement tests (n = 3297). Propensity score modelling was used to address differences in preexisting risk factors (child, family, neighborhood characteristics, maltreatment history, and reading scores) and compare outcomes for children placed in out-of-home care and those remaining in in-home care. Both groups of maltreated children had poor educational outcomes. After accounting for group differences in risk characteristics, there was no difference in year 9 reading achievement for the out-of-home care and in-home care groups. There was no difference in suspensions for the groups. The only significant difference was children in out-of-home care had fewer school absences than children in in-home care. Out-of-home care was not found to be a significant factor in the adverse educational outcomes of these children; however, there is a clear need for further educational support to address poor outcomes for children involved with child protection services. Copyright © 2018 Elsevier Inc. All rights reserved.

Single Motherhood, Alcohol Dependence, and Smoking During Pregnancy: A Propensity Score Analysis.

PubMed

Waldron, Mary; Bucholz, Kathleen K; Lian, Min; Lessov-Schlaggar, Christina N; Miller, Ruth Huang; Lynskey, Michael T; Knopik, Valerie S; Madden, Pamela A F; Heath, Andrew C

2017-09-01

Few studies linking single motherhood and maternal smoking during pregnancy consider correlated risk from problem substance use beyond history of smoking and concurrent use of alcohol. In the present study, we used propensity score methods to examine whether the risk of smoking during pregnancy associated with single motherhood is the result of potential confounders, including alcohol dependence. Data were drawn from mothers participating in a birth cohort study of their female like-sex twin offspring (n = 257 African ancestry; n = 1,711 European or other ancestry). We conducted standard logistic regression models predicting smoking during pregnancy from single motherhood at twins' birth, followed by propensity score analyses comparing single-mother and two-parent families stratified by predicted probability of single motherhood. In standard models, single motherhood predicted increased risk of smoking during pregnancy in European ancestry but not African ancestry families. In propensity score analyses, rates of smoking during pregnancy were elevated in single-mother relative to two-parent European ancestry families across much of the spectrum a priori risk of single motherhood. Among African ancestry families, within-strata comparisons of smoking during pregnancy by single-mother status were nonsignificant. These findings highlight single motherhood as a unique risk factor for smoking during pregnancy in European ancestry mothers, over and above alcohol dependence. Additional research is needed to identify risks, beyond single motherhood, associated with smoking during pregnancy in African ancestry mothers.

A Propensity Score Analysis of the Impact of Dexamethasone Use on Delayed Cerebral Ischemia and Poor Functional Outcomes After Subarachnoid Hemorrhage.

PubMed

Mohney, Nathaniel; Williamson, Craig A; Rothman, Edward; Ball, Ron; Sheehan, Kyle M; Pandey, Aditya S; Fletcher, Jeffrey J; Jacobs, Teresa L; Thompson, B Gregory; Rajajee, Venkatakrishna

2018-01-01

An inflammatory response occurs after aneurysmal subarachnoid hemorrhage (aSAH) and predicts poor outcomes. Glucocorticoids suppress inflammation and promote fluid retention. Dexamethasone is often administered after aSAH for postoperative cerebral edema and refractory headache. Our objective was to examine the impact of dexamethasone use on functional outcomes and delayed cerebral ischemia (DCI) after aSAH. Patients with aSAH admitted between 2010 and 2015 were included; the data source was a single-center subarachnoid hemorrhage registry. The intervention of interest was a dexamethasone taper used <7 days from ictus. The primary outcome was poor discharge functional outcome, with a modified Rankin Scale score >3. Other outcomes included DCI and infection. A propensity score for use of dexamethasone was calculated using a logistic regression model that included potential predictors of dexamethasone use and outcome. The impact of dexamethasone on outcomes of interest was calculated and the propensity score was controlled for. A total of 440 patients with subarachnoid hemorrhage were admitted during the study period and 309 met eligibility criteria. Dexamethasone was administered in 101 patients (33%). A total of 127 patients (41%) had a discharge modified Rankin Scale score >3, 105 (34%) developed DCI, and 94 (30%) developed an infection. After propensity score analysis, dexamethasone use was associated with a significant reduction in poor functional outcomes (odds ratio [OR], 0.35; 95% confidence interval [CI], 0.19-0.66) but showed no significant association with DCI (OR, 0.93; 95% CI, 0.53-1.64) or infection (OR, 0.60; 95% CI, 0.34-1.06). Dexamethasone use after aSAH was associated with a reduction in poor functional outcomes at discharge but not DCI, controlling for predictors of dexamethasone use. Copyright © 2017 Elsevier Inc. All rights reserved.

Optimal case-control matching in practice.

PubMed

Cologne, J B; Shibata, Y

1995-05-01

We illustrate modern matching techniques and discuss practical issues in defining the closeness of matching for retrospective case-control designs (in which the pool of subjects already exists when the study commences). We empirically compare matching on a balancing score, analogous to the propensity score for treated/control matching, with matching on a weighted distance measure. Although both methods in principle produce balance between cases and controls in the marginal distributions of the matching covariates, the weighted distance measure provides better balance in practice because the balancing score can be poorly estimated. We emphasize the use of optimal matching based on efficient network algorithms. An illustration is based on the design of a case-control study of hepatitis B virus infection as a possible confounder and/or effect modifier of radiation-related primary liver cancer in atomic bomb survivors.

Use of an online smoking cessation community promotes abstinence: Results of propensity score weighting.

PubMed

Graham, Amanda L; Papandonatos, George D; Erar, Bahar; Stanton, Cassandra A

2015-12-01

We estimated the causal effects of use of an online smoking cessation community on 30-day point prevalence abstinence at 3 months. Participants (N = 492) were adult current smokers in the enhanced Internet arm of The iQUITT Study, a randomized trial of Internet and telephone treatment for smoking cessation. All participants accessed a Web-based smoking-cessation program that included a large, established online community. Automated tracking metrics of passive (e.g., reading forum posts, viewing member profiles) and active (e.g., writing forum posts, sending private messages) community use were extracted from the site at 3 months. Self-selected community use defines the groups of interest: "None," "Passive," and "Both" (passive + active). Inverse probability of treatment weighting corrected for baseline imbalances on demographic, smoking, psychosocial, and medical history variables. Propensity weights estimated via generalized boosted models were used to calculate Average Treatment Effects (ATE) and Average Treatment effects on the Treated (ATT). Patterns of community use were: None = 198 (40.2%), Passive = 110 (22.4%), and Both = 184 (37.4%). ATE-weighted abstinence rates were: None = 4.2% (95% CI = 1.5-6.9); Passive = 15.1% (95% CI = 8.4-21.9); Both = 20.4% (95% CI = 13.9-26.8). ATT-weighted abstinence rates indicated even greater benefits of community use. Community users were more likely to quit smoking at 3 months than nonusers. The estimated benefit from use of online community resources was even larger among subjects with high propensity to use them. No differences in abstinence emerged between passive and passive/active users. Results suggest that lurking in online communities confers specific abstinence benefits. Implications of these findings for online cessation communities are discussed. (PsycINFO Database Record (c) 2015 APA, all rights reserved).

National Costs Associated with Methicillin-susceptible and Methicillin-resistant S. aureus Hospitalizations in the United States, 2010-2014.

PubMed

Klein, Eili Y; Jiang, Wendi; Mojica, Nestor; Tseng, Katie K; McNeill, Ryan; Cosgrove, Sara E; Perl, Trish M

2018-05-12

Infections caused by methicillin-resistant Staphylococcus aureus (MRSA) have been associated with worse patient outcomes and higher costs of care than susceptible (MSSA) infections. However, the healthcare landscape has changed since prior studies found these differences, including widespread dissemination of community-associated strains of MRSA. Our objective was to provide updated estimates of the excess costs of resistant S. aureus infections. We conducted a retrospective analysis using data from the National Inpatient Sample from the Agency for Healthcare Research and Quality for the years 2010 to 2014. We calculated costs for hospitalizations including MRSA- and MSSA-related septicemia and pneumonia infections, as well as MRSA- and MSSA-related infections from conditions classified elsewhere and of an unspecified site ("other infections"). Differences in the costs of hospitalization were estimated using propensity score adjusted mortality outcomes for 2010 through 2014. In 2014, estimated costs were highest for pneumonia and sepsis-related hospitalizations. Propensity score-adjusted costs were significantly higher for MSSA-related pneumonia ($40,725 vs $38,561; p=0.045) and other hospitalizations ($15,578 vs $14,792; p<0.001) than for MRSA-related hospitalizations. Similar patterns were observed from 2010 to 2013, though crude cost differences between MSSA- and MRSA-related pneumonia hospitalizations rose from 25.8% in 2010 to 31.0% in 2014. MRSA-related hospitalizations had a higher adjusted mortality rate than MSSA-related hospitalizations. Though MRSA infections had been previously associated with higher hospitalization costs, our results suggest that in recent years, costs associated with MSSA-related infections have converged with and may surpass costs of similar MRSA-related hospitalizations.

Estimating the "impact" of out-of-home placement on child well-being: approaching the problem of selection bias.

PubMed

Berger, Lawrence M; Bruch, Sarah K; Johnson, Elizabeth I; James, Sigrid; Rubin, David

2009-01-01

This study used data on 2,453 children aged 4-17 from the National Survey of Child and Adolescent Well-Being and 5 analytic methods that adjust for selection factors to estimate the impact of out-of-home placement on children's cognitive skills and behavior problems. Methods included ordinary least squares (OLS) regressions and residualized change, simple change, difference-in-difference, and fixed effects models. Models were estimated using the full sample and a matched sample generated by propensity scoring. Although results from the unmatched OLS and residualized change models suggested that out-of-home placement is associated with increased child behavior problems, estimates from models that more rigorously adjust for selection bias indicated that placement has little effect on children's cognitive skills or behavior problems.

Hospital consolidation and costs: another look at the evidence.

PubMed

Dranove, David; Lindrooth, Richard

2003-11-01

We investigate whether pairwise hospital consolidation leads to cost savings. We use a unified empirical methodology to assess both systems and mergers. Our comparison group for each consolidation consists of 10 'pseudo-mergers' chosen based on propensity scores. Cost function estimates reveal that consolidation into systems does not generate savings, even after 4 years. Mergers in which hospitals consolidate financial reporting and licenses generate savings of approximately 14%: 2, 3, and 4 years after merger. The system consolidation and merger results are very robust to changes in the specification and the sample.

Confronting ‘confounding by health system use’ in Medicare Part D: Comparative effectiveness of propensity score approaches to confounding adjustment

PubMed Central

Polinski, Jennifer M.; Schneeweiss, Sebastian; Glynn, Robert J.; Lii, Joyce; Rassen, Jeremy

2012-01-01

Purpose Under Medicare Part D, patient characteristics influence plan choice, which in turn influences Part D coverage gap entry. We compared pre-defined propensity score (PS) and high-dimensional propensity score (hdPS) approaches to address such ‘confounding by health system use’ in assessing whether coverage gap entry is associated with cardiovascular events or death. Methods We followed 243,079 Medicare patients aged 65+ with linked prescription, medical, and plan-specific data in 2005–2007. Patients reached the coverage gap and were followed until an event or year’s end. Exposed patients were responsible for drug costs in the gap; unexposed patients (patients with non-Part D drug insurance and Part D patients receiving a low-income subsidy (LIS)) received financial assistance. Exposed patients were 1:1 PS- or hdPS-matched to unexposed patients. The PS model included 52 predefined covariates; the hdPS model added 400 empirically identified covariates. Hazard ratios for death and any of five cardiovascular outcomes were compared. In sensitivity analyses, we explored residual confounding using only LIS patients in the unexposed group. Results In unadjusted analyses, exposed patients had no greater hazard of death (HR=1.00; 95% CI, 0.84–1.20) or other outcomes. PS- (HR=1.29;0.99–1.66) and hdPS- (HR=1.11;0.86–1.42) matched analyses showed elevated but non-significant hazards of death. In sensitivity analyses, the PS analysis showed a protective effect (HR=0.78;0.61–0.98), while the hdPS analysis (HR=1.06;0.82–1.37) confirmed the main hdPS findings. Conclusion Although the PS-matched analysis suggested elevated though non-significant hazards of death among patients with no financial assistance during the gap, the hdPS analysis produced lower estimates that were stable across sensitivity analyses. PMID:22552984

Methamphetamine Users Have Increased Dental Disease: A Propensity Score Analysis.

PubMed

Shetty, V; Harrell, L; Clague, J; Murphy, D A; Dye, B A; Belin, T R

2016-07-01

Methamphetamine (MA) users are assumed to have a high burden of tooth decay. Less clear is how the distribution and severity of dental caries in MA users differ from the general population. Using a covariate-balancing propensity score strategy, we investigated the differential effects of MA use on dental caries by comparing the patterns of decayed, missing, and filled teeth in a community sample of 571 MA users with a subset of 2,755 demographically similar control individuals selected from a National Health and Nutrition Examination Survey (NHANES) cohort. Recruited over a 2-y period with a stratified sampling protocol, the MA users underwent comprehensive dental examinations by 3 trained and calibrated dentists using NHANES protocols. Propensity scores were estimated with logistic regression based on background characteristics, and a subset of closely matched subjects was stratified into quintiles for comparisons. MA users were twice as likely to have untreated caries (odds ratio [OR] = 2.08; 95% confidence interval [95% CI]: 1.55 to 2.78) and 4 times more likely to have caries experience (OR = 4.06; 95% CI: 2.24 to 7.34) than the control group of NHANES participants. Additionally, MA users were twice as likely to have 2 more decayed, missing, or filled teeth (OR = 2.08; 95% CI: 1.29 to 2.79) than the NHANES participants. The differential involvement of the teeth surfaces in MA users was quite distinctive, with carious surface involvement being highest for the maxillary central incisors, followed by maxillary posterior premolars and molars. Users injecting MA had significantly higher rates of tooth decay compared with noninjectors (P = 0.04). Although MA users experienced decayed and missing dental surfaces more frequently than NHANES participants, NHANES participants had more restored surfaces, especially on molars. The high rates and distinctive patterns of dental caries observed could be used 1) to alert dentists to covert MA use in their patients and 2) as the basis for comprehensive management strategies. © International & American Associations for Dental Research 2016.

Impact of chest radiography for children with lower respiratory tract infection: a propensity score approach.

PubMed

Ecochard-Dugelay, Emmanuelle; Beliah, Muriel; Boisson, Caroline; Perreaux, Francis; de Laveaucoupet, Jocelyne; Labrune, Philippe; Epaud, Ralph; Ducou-Lepointe, Hubert; Bouyer, Jean; Gajdos, Vincent

2014-01-01

Management of acute respiratory tract infection varies substantially despite this being a condition frequently encountered in pediatric emergency departments. Previous studies have suggested that the use of antibiotics was higher when chest radiography was performed. However none of these analyses had considered the inherent indication bias of observational studies. The aim of this work was to assess the relationship between performing chest radiography and prescribing antibiotics using a propensity score analysis to address the indication bias due to non-random radiography assignment. We conducted a prospective study of 697 children younger than 2 years of age who presented during the winter months of 2006-2007 for suspicion of respiratory tract infection at the Pediatric Emergency Department of an urban general hospital in France (Paris suburb). We first determined the individual propensity score (probability of having a chest radiography according to baseline characteristics). Then we assessed the relation between radiography and antibiotic prescription using two methods: adjustment and matching on the propensity score. We found that performing a chest radiography lead to more frequent antibiotic prescription that may be expressed as OR = 2.3, CI [1.3-4.1], or as an increased use of antibiotics of 18.6% [0.08-0.29] in the group undergoing chest radiography. Chest radiography has a significant impact on the management of infants admitted for suspicion of respiratory tract infection in a pediatric emergency department and may lead to unnecessary administration of antibiotics.

Proton pump inhibitor use and risk of adverse cardiovascular events in aspirin treated patients with first time myocardial infarction: nationwide propensity score matched study

PubMed Central

Grove, Erik L; Hansen, Peter Riis; Olesen, Jonas B; Ahlehoff, Ole; Selmer, Christian; Lindhardsen, Jesper; Madsen, Jan Kyst; Køber, Lars; Torp-Pedersen, Christian; Gislason, Gunnar H

2011-01-01

Objective To examine the effect of proton pump inhibitors on adverse cardiovascular events in aspirin treated patients with first time myocardial infarction. Design Retrospective nationwide propensity score matched study based on administrative data. Setting All hospitals in Denmark. Participants All aspirin treated patients surviving 30 days after a first myocardial infarction from 1997 to 2006, with follow-up for one year. Patients treated with clopidogrel were excluded. Main outcome measures The risk of the combined end point of cardiovascular death, myocardial infarction, or stroke associated with use of proton pump inhibitors was analysed using Kaplan-Meier analysis, Cox proportional hazard models, and propensity score matched Cox proportional hazard models. Results 3366 of 19 925 (16.9%) aspirin treated patients experienced recurrent myocardial infarction, stroke, or cardiovascular death. The hazard ratio for the combined end point in patients receiving proton pump inhibitors based on the time dependent Cox proportional hazard model was 1.46 (1.33 to 1.61; P<0.001) and for the propensity score matched model based on 8318 patients it was 1.61 (1.45 to 1.79; P<0.001). A sensitivity analysis showed no increase in risk related to use of H2 receptor blockers (1.04, 0.79 to 1.38; P=0.78). Conclusion In aspirin treated patients with first time myocardial infarction, treatment with proton pump inhibitors was associated with an increased risk of adverse cardiovascular events. PMID:21562004

Effectiveness of penicillin, dicloxacillin and cefuroxime for penicillin-susceptible Staphylococcus aureus bacteraemia: a retrospective, propensity-score-adjusted case-control and cohort analysis.

PubMed

Nissen, Jette Lindbjerg; Skov, Robert; Knudsen, Jenny Dahl; Ostergaard, Christian; Schønheyder, Henrik Carl; Frimodt-Møller, Niels; Benfield, Thomas

2013-08-01

Penicillin-susceptible Staphylococcus aureus isolates account for a fifth of cases of S. aureus bacteraemia (SAB) in Denmark, but little is known about treatment outcomes with penicillins or other antimicrobials. Here we compare penicillin, dicloxacillin and cefuroxime as definitive treatments in relation to 30 day mortality. A retrospective chart review of 588 penicillin-susceptible S. aureus cases at five centres from January 1995 to December 2010. Data on demographics, antimicrobial treatment, clinical signs and symptoms, and mortality at day 30 were collected. Hazard ratios (HRs) with 95% CIs associated with mortality were modelled using propensity-score-adjusted Cox proportional hazards regression analysis. Propensity-score-matched case-control studies were carried out. Definitive therapy with cefuroxime was associated with an increased risk of 30 day mortality compared with penicillin (adjusted HR 2.54, 95% CI 1.49-4.32). Other variables that were statistically significantly associated with 30 day mortality included increasing age, disease severity and a primary respiratory focus. Osteomyelitis/arthritis was associated with a lower risk of death than were other secondary manifestations. Propensity-score-matched case-control studies confirmed an increased risk of 30 day mortality: cefuroxime treatment (39%) versus penicillin treatment (20%), P = 0.037; and cefuroxime treatment (38%) versus dicloxacillin treatment (10%), P = 0.004. Definitive therapy for penicillin-susceptible SAB with cefuroxime was associated with a significantly higher mortality than was seen with therapy with penicillin or dicloxacillin.

Statins use and risk of new-onset diabetes in hypertensive patients: a population-based retrospective cohort study in Yinzhou district, Ningbo city, People's Republic of China.

PubMed

Li, Hailong; Lin, Hongbo; Zhao, Houyu; Xu, Yang; Cheng, Yinchu; Shen, Peng; Zhan, Siyan

2018-01-01

Reports have suggested that statin use is associated with an increased incidence of type 2 diabetes mellitus (T2DM). Guidelines suggested that statins should be prescribed in hypertensive patients for primary prevention. However, there were very few studies on the risk of T2DM associated with statin use among patients with hypertension in mainland People's Republic of China. To determine the association between statin use and new-onset diabetes mellitus among patients with hypertension in mainland People's Republic of China. We performed a retrospective cohort study of hypertensive patients using the Yinzhou regional health care database from January 1, 2010, to August 31, 2016. Patients aged 30-90 years old without T2DM were eligible for inclusion. We identified new statin initiators and nonusers by using prescription records of inpatients and outpatients. Multivariate Cox model and propensity score methods were used to adjust potential confounders, including age, sex, body mass index, comorbidities, lifestyle characteristics, and baseline antihypertensive drug use. The risk of incident T2DM among statin initiators compared to nonusers was estimated by the Cox proportional hazards model. Propensity scores for statin use were then developed using logistic regression, statin initiators were matched 1:1 with nonusers according to propensity scores with the nearest neighbor matching method within 0.2 caliper width, and Cox regression was again conducted. Among 67,993 patients (21,551 statin initiators; 46,442 nonusers), the unadjusted incidence rate of incident T2DM was higher in statin initiators than nonusers (25.68 versus 14.19 events/1,000 person-years; adjusted hazard ratio: 1.55; 95% confidence interval: 1.44-1.66). After propensity score 1:1 matching (19,818 statin initiators; 19,818 nonusers), baseline characteristics between 2 groups were balanced except that the nonusers group was 0.53 years older on average ( P <0.001). Then statin use was still associated with a significant increased risk for T2DM in the matched cohort (adjusted hazard ratio: 1.54; 95% confidence interval: 1.41-1.67). Subgroup analyses also demonstrated similar findings. Our study indicated an association between statin use and an increased risk of new-onset diabetes mellitus. It provides better understanding of statin and new-onset diabetes mellitus association among hypertensive patients in real-word setting. As an observational study, our findings were prone to unmeasured confounding and bias.

Alternative approaches for studying humanitarian interventions: propensity score methods to evaluate reintegration packages impact on depression, PTSD, and function impairment among child soldiers in Nepal.

PubMed

Kohrt, B A; Burkey, M; Stuart, E A; Koirala, S

2015-01-01

Ethical, logistical, and funding approaches preclude conducting randomized control trials (RCTs) in some humanitarian crises. A lack of RCTs and other intervention research has contributed to a limited evidence-base for mental health and psychosocial support (MHPS) programs after disasters, war, and disease outbreaks. Propensity score methods (PSMs) are an alternative analysis technique with potential application for evaluating MHPS programs in humanitarian emergencies. PSMs were used to evaluate impacts of education reintegration packages (ERPs) and other (vocational or economic) reintegration packages (ORPs) v. no reintegration programs on mental health of child soldiers. Propensity scores were used to determine weighting of child soldiers in each of the three treatment arms. Multiple linear regression was used to estimate adjusted changes in symptom score severity on culturally validated measures of depression, post-traumatic stress disorder (PTSD), and functional impairment from baseline to 1-year follow-up. Among 258 Nepali child soldiers participating in reintegration programs, 54.7% completed ERP and 22.9% completed ORP. There was a non-significant reduction in depression by 0.59 (95% CI -1.97 to 0.70) for ERP and by 0.60 (95% CI -2.16 to 0.96) for ORP compared with no treatment. There were non-significant increases in PTSD (1.15, 95% CI -1.55 to 3.86) and functional impairment (0.91, 95% CI -0.31 to 2.14) associated with ERP and similar findings for ORP (PTSD: 0.66, 95% CI -2.24 to 3.57; functional impairment (1.05, 95% CI -0.71 to 2.80). In a humanitarian crisis in which a non-randomized intervention assignment protocol was employed, the statistical technique of PSMs addressed differences in covariate distribution between child soldiers who received different integration packages. Our analysis did not demonstrate significant changes in psychosocial outcomes for ERPs and ORPs. We suggest the use of PSMs in evaluating non-randomized interventions in humanitarian crises when non-randomized conditions are not utilized.

Combination of post-operative radiotherapy and cetuximab for high-risk cutaneous squamous cell cancer of the head and neck: A propensity score analysis.

PubMed

Palmer, Joshua D; Schneider, Charles J; Hockstein, Neil; Hanlon, Alexandra L; Silberg, Jordan; Strasser, Jon; Mauer, Elizabeth A; Dzeda, Michael; Witt, Robert; Raben, Adam

2018-03-01

The objective of this study was to investigate the safety, tolerability and preliminary efficacy of radiotherapy plus cetuximab in high risk CSCC patients. Patients with high-risk CSCC diagnosed between 2006 and 2013 were analyzed. Patients were divided into two groups: radiotherapy alone versus radiotherapy plus cetuximab. Among 68 patients meeting study criteria, we identified 29 treated with cetuximab plus RT and 39 with RT alone. Primary analysis examined disease-free and overall survival, freedom from local and distant recurrence in the propensity score matched cohort. Propensity score analysis was performed with weighted factors including: Charlson Comorbidity Index score, age. KPS, primary location, T and N stage, recurrent status, margin status, LVSI, PNI and grade. Toxicity was assessed using the CTCAE v4.0. Median follow-up for living patients was 30 months. Patients in the cetuximab group were more likely to have advanced N stage, positive margins and recurrent disease. After propensity score matching the groups were well balanced. Six patients experienced ≥ grade 3 acute toxicity in the cetuximab group. The 1-year, 2-year and 5-year progression free survival (PFS) for patients in the cetuximab group were 86%, 72% and 66%, respectively. The 1-year, 2-year and 5-year overall survival (OS) for patients in the cetuximab group was 98%, 80% and 80%, respectively. Although limited by small numbers, the combination of cetuximab and radiotherapy in CSCC appears well tolerated there were more long-term survivors and less distant metastasis in the cetuximab group. These promising finding warrant further studies. Copyright © 2018 Elsevier Ltd. All rights reserved.

Ticagrelor versus clopidogrel in real-world patients with ST elevation myocardial infarction: 1-year results by propensity score analysis.

PubMed

Vercellino, Matteo; Sànchez, Federico Ariel; Boasi, Valentina; Perri, Dino; Tacchi, Chiara; Secco, Gioel Gabrio; Cattunar, Stefano; Pistis, Gianfranco; Mascelli, Giovanni

2017-04-05

European guidelines recommend the use of ticagrelor versus clopidogrel in patients with ST elevation myocardial infarction (STEMI). This recommendation is based on inconclusive results and subanalyses from clinical trials. Few data are available on the effects of ticagrelor in a real-world population. To compare the effects of ticagrelor and clopidogrel in a real-world STEMI population, we conducted a pre-post case-control study examining all patients with STEMI included in the Cardio-STEMI Sanremo registry between February 2011 and June 2013. Cases and controls were defined according to P2Y 12 inhibitors, correcting the bias due to lack of randomization by propensity score analysis. Ticagrelor was introduced in 2012 in both in-hospital and pre-hospital settings independently of this study. Of the 416 patients enrolled in the Cardio-STEMI registry, 401 with a definite diagnosis of STEMI were included in this study. One hundred forty-two patients received ticagrelor and 259 received clopidogrel. Regarding clinical presentation and procedural data, those in the ticagrelor group had lower CRUSADE scores (23 [14-36] vs 27 [18-38]; p = 0.015] but a higher proportion of radial access (33% vs 14%; p < 0.001), percutaneous coronary intervention (PCI; 92% vs 81 %; p = 0.002) and primary PCI ≤ 12 h (82% vs 66%; p = 0.001). The patients in the ticagrelor group had a higher procedural success rate (100% vs. 96%; p = 0.044). There was no difference in Bleeding Academic Research Consortium bleeding and in unadjusted incidence of hospital major adverse cardiovascular events (MACE; cardiac death, myocardial infarction, or stroke) but there was a significant reduction in unadjusted cardiac hospital death in the ticagrelor group (0.7% vs 5.4%; p = 0.024). After correcting for propensity score, hospital death (p = 0.22) and hospital MACE (p = 0.96) did not differ in both groups. The unadjusted survival at 1 year after STEMI was higher in the ticagrelor group (97.8% vs 87.8%; p = 0.024), and this result was confirmed by propensity score analysis (hazard ratio = 0.29 [0.08-0.99]; p = 0.048). In this real-word propensity score analysis, ticagrelor did not affect the risk of MACE during the hospital phase, or the incidence of hospital bleeding in patients with STEMI. However, in this mono-centric experience, ticagrelor resulted in improved 1-year survival, even after correction by propensity score.

Estimating the incidence and the economic burden of third and fourth-degree obstetric tears in the English NHS: an observational study using propensity score matching.

PubMed

Orlovic, Martina; Carter, Alexander William; Marti, Joachim; Mossialos, Elias

2017-06-12

Obstetric care is a high-risk area in healthcare delivery, so it is essential to have up-to-date quantitative evidence in this area to inform policy decisions regarding these services. In light of this, the objective of this study is to investigate the incidence and economic burden of third and fourth-degree lacerations in the English National Health Service (NHS) using recent national data. We used coded inpatient data from Hospital Episode Statistics (HES) for the financial years from 2010/2011 to 2013/2014 for all females that gave birth during that period in the English NHS. Using HES, we used pre-existing safety indicator algorithms to calculate the incidence of third and fourth-degree obstetric tears and employed a propensity score matching method to estimate the excess length of stay and economic burden associated with these events. Observed rates per 1000 inpatient episodes in 2010/2011 and 2013/2014, respectively: Patient Safety Indicator-trauma during vaginal delivery with instrument (PSI 18)=84.16 and 91.24; trauma during vaginal delivery without instrument (PSI 19)=29.78 and 33.43; trauma during caesarean delivery (PSI 20)=3.61 and 4.56. Estimated overall (all PSIs) economic burden for 2010/2011=£10.7 million and for 2013/2014=£14.5 million, expressed in 2013/2014 prices. Despite many initiatives targeting the quality of maternity care in the NHS, the incidence of third and fourth-degree lacerations has increased during the observed period which signals that quality improvement efforts in obstetric care may not be reducing incidence rates. Our conservative estimates of the financial burden of these events appear low relative to total NHS expenditure for these years. © Article author(s) (or their employer(s) unless otherwise stated in the text of the article) 2017. All rights reserved. No commercial use is permitted unless otherwise expressly granted.

Estimating the incidence and the economic burden of third and fourth-degree obstetric tears in the English NHS: an observational study using propensity score matching

PubMed Central

Orlovic, Martina; Carter, Alexander William; Marti, Joachim; Mossialos, Elias

2017-01-01

Objective Obstetric care is a high-risk area in healthcare delivery, so it is essential to have up-to-date quantitative evidence in this area to inform policy decisions regarding these services. In light of this, the objective of this study is to investigate the incidence and economic burden of third and fourth-degree lacerations in the English National Health Service (NHS) using recent national data. Methods We used coded inpatient data from Hospital Episode Statistics (HES) for the financial years from 2010/2011 to 2013/2014 for all females that gave birth during that period in the English NHS. Using HES, we used pre-existing safety indicator algorithms to calculate the incidence of third and fourth-degree obstetric tears and employed a propensity score matching method to estimate the excess length of stay and economic burden associated with these events. Results Observed rates per 1000 inpatient episodes in 2010/2011 and 2013/2014, respectively: Patient Safety Indicator—trauma during vaginal delivery with instrument (PSI 18)=84.16 and 91.24; trauma during vaginal delivery without instrument (PSI 19)=29.78 and 33.43; trauma during caesarean delivery (PSI 20)=3.61 and 4.56. Estimated overall (all PSIs) economic burden for 2010/2011=£10.7 million and for 2013/2014=£14.5 million, expressed in 2013/2014 prices. Conclusions Despite many initiatives targeting the quality of maternity care in the NHS, the incidence of third and fourth-degree lacerations has increased during the observed period which signals that quality improvement efforts in obstetric care may not be reducing incidence rates. Our conservative estimates of the financial burden of these events appear low relative to total NHS expenditure for these years. PMID:28606903

The flaws in the detail of an observational study on transcatheter aortic valve implantation versus surgical aortic valve replacement in intermediate-risks patients.

PubMed

Barili, Fabio; Freemantle, Nick; Folliguet, Thierry; Muneretto, Claudio; De Bonis, Michele; Czerny, Martin; Obadia, Jean Francois; Al-Attar, Nawwar; Bonaros, Nikolaos; Kluin, Jolanda; Lorusso, Roberto; Punjabi, Prakash; Sadaba, Rafael; Suwalski, Piotr; Benedetto, Umberto; Böning, Andreas; Falk, Volkmar; Sousa-Uva, Miguel; Kappetein, Pieter A; Menicanti, Lorenzo

2017-06-01

The PARTNER group recently published a comparison between the latest generation SAPIEN 3 transcatheter aortic valve implantation (TAVI) system (Edwards Lifesciences, Irvine, CA, USA) and surgical aortic valve replacement (SAVR) in intermediate-risk patients, apparently demonstrating superiority of the TAVI and suggesting that TAVI might be the preferred treatment method in this risk class of patients. Nonetheless, assessment of the non-randomized methodology used in this comparison reveals challenges that should be addressed in order to elucidate the validity of the results. The study by Thourani and colleagues showed several major methodological concerns: suboptimal methods in propensity score analysis with evident misspecification of the propensity scores (PS; no adjustment for the most significantly different covariates: left ventricular ejection fraction, moderate-severe mitral regurgitation and associated procedures); use of PS quintiles rather than matching; inference on not-adjusted Kaplan-Meier curves, although the authors correctly claimed for the need of balancing score adjusting for confounding factors in order to have unbiased estimates of the treatment effect; evidence of poor fit; lack of data on valve-related death.These methodological flaws invalidate direct comparison between treatments and cannot support authors' conclusions that TAVI with SAPIEN 3 in intermediate-risk patients is superior to surgery and might be the preferred treatment alternative to surgery. © The Author 2017. Published by Oxford University Press on behalf of the European Association for Cardio-Thoracic Surgery. All rights reserved.

Outcomes After Direct Thrombectomy or Combined Intravenous and Endovascular Treatment Are Not Different.

PubMed

Abilleira, Sònia; Ribera, Aida; Cardona, Pedro; Rubiera, Marta; López-Cancio, Elena; Amaro, Sergi; Rodríguez-Campello, Ana; Camps-Renom, Pol; Cánovas, David; de Miquel, Maria Angels; Tomasello, Alejandro; Remollo, Sebastian; López-Rueda, Antonio; Vivas, Elio; Perendreu, Joan; Gallofré, Miquel

2017-02-01

Whether intravenous thrombolysis adds a further benefit when given before endovascular thrombectomy (EVT) is unknown. Furthermore, intravenous thrombolysis delays time to groin puncture, mainly among drip and ship patients. Using region-wide registry data, we selected cases that received direct EVT or combined intravenous thrombolysis+EVT for anterior circulation strokes between January 2011 and October 2015. Treatment effect was estimated by stratification on a propensity score. The average odds ratios for the association of treatment with good outcome and death at 3 months and symptomatic bleedings at 24 hours were calculated with the Mantel-Haenszel test statistic. We included 599 direct EVT patients and 567 patients with combined treatment. Stratification through propensity score achieved balance of baseline characteristics across treatment groups. There was no association between treatment modality and good outcome (odds ratio, 0.97; 95% confidence interval, 0.74-1.27), death (odds ratio, 1.07; 95% confidence interval, 0.74-1.54), or symptomatic bleedings (odds ratio, 0.56; 95% confidence interval, 0.25-1.27). This observational study suggests that outcomes after direct EVT or combined intravenous thrombolysis+EVT are not different. If confirmed by a randomized controlled trial, it may have a significant impact on organization of stroke systems of care. © 2017 American Heart Association, Inc.

The impact of the Bolsa Família Program on food consumption: a comparative study of the southeast and northeast regions of Brazil.

PubMed

Sperandio, Naiara; Rodrigues, Cristiana Tristão; Franceschini, Sylvia do Carmo Castro; Priore, Silvia Eloiza

2017-06-01

The aim of this study was to evaluate the impact of the Bolsa Família Program (PBF) on food consumption in the northeast and southeast regions of Brazil. The database was obtained from the individual food consumption module of the Household Budget Survey conducted in 2008-09. Consumption was assessed through two food records. The food was categorized into four groups: fresh or minimally processed food; culinary ingredients; processed food; and ultra-processed food. To analyze the impact, the propensity score matching method was used, which compares the individual recipients and non-recipients of the PBF in relation to a group of socioeconomic characteristics. After the propensity score was calculated, the impact of the PBF was estimated through the nearest-neighbor matching algorithm. In both regions, more than 60% of the daily total calories consumed by PBF recipients came from foods that had not undergone industrial processing. The recipients of PBF had a low level of consumption of processed and ultra-processed food in both regions, and an increased level of consumption of fresh or minimally processed food in the northeast. The results indicate the importance of adopting intersectoral policies in parallel to the PBF in order to strengthen healthy eating practices.

Case matching and the reduction of selection bias in quasi-experiments: The relative importance of pretest measures of outcome, of unreliable measurement, and of mode of data analysis.

PubMed

Cook, Thomas D; Steiner, Peter M

2010-03-01

In this article, we note the many ontological, epistemological, and methodological similarities between how Campbell and Rubin conceptualize causation. We then explore 3 differences in their written emphases about individual case matching in observational studies. We contend that (a) Campbell places greater emphasis than Rubin on the special role of pretest measures of outcome among matching variables; (b) Campbell is more explicitly concerned with unreliability in the covariates; and (c) for analyzing the outcome, only Rubin emphasizes the advantages of using propensity score over regression methods. To explore how well these 3 factors reduce bias, we reanalyze and review within-study comparisons that contrast experimental and statistically adjusted nonexperimental causal estimates from studies with the same target population and treatment content. In this context, the choice of covariates counts most for reducing selection bias, and the pretest usually plays a special role relative to all the other covariates considered singly. Unreliability in the covariates also influences bias reduction but by less. Furthermore, propensity score and regression methods produce comparable degrees of bias reduction, though these within-study comparisons may not have met the theoretically specified conditions most likely to produce differences due to analytic method.

Using Length of Stay to Control for Unobserved Heterogeneity When Estimating Treatment Effect on Hospital Costs with Observational Data: Issues of Reliability, Robustness, and Usefulness.

PubMed

May, Peter; Garrido, Melissa M; Cassel, J Brian; Morrison, R Sean; Normand, Charles

2016-10-01

To evaluate the sensitivity of treatment effect estimates when length of stay (LOS) is used to control for unobserved heterogeneity when estimating treatment effect on cost of hospital admission with observational data. We used data from a prospective cohort study on the impact of palliative care consultation teams (PCCTs) on direct cost of hospital care. Adult patients with an advanced cancer diagnosis admitted to five large medical and cancer centers in the United States between 2007 and 2011 were eligible for this study. Costs were modeled using generalized linear models with a gamma distribution and a log link. We compared variability in estimates of PCCT impact on hospitalization costs when LOS was used as a covariate, as a sample parameter, and as an outcome denominator. We used propensity scores to account for patient characteristics associated with both PCCT use and total direct hospitalization costs. We analyzed data from hospital cost databases, medical records, and questionnaires. Our propensity score weighted sample included 969 patients who were discharged alive. In analyses of hospitalization costs, treatment effect estimates are highly sensitive to methods that control for LOS, complicating interpretation. Both the magnitude and significance of results varied widely with the method of controlling for LOS. When we incorporated intervention timing into our analyses, results were robust to LOS-controls. Treatment effect estimates using LOS-controls are not only suboptimal in terms of reliability (given concerns over endogeneity and bias) and usefulness (given the need to validate the cost-effectiveness of an intervention using overall resource use for a sample defined at baseline) but also in terms of robustness (results depend on the approach taken, and there is little evidence to guide this choice). To derive results that minimize endogeneity concerns and maximize external validity, investigators should match and analyze treatment and comparison arms on baseline factors only. Incorporating intervention timing may deliver results that are more reliable, more robust, and more useful than those derived using LOS-controls. © Health Research and Educational Trust.

Assessing the effectiveness of a hybrid-flipped model of learning on fluid mechanics instruction: overall course performance, homework, and far- and near-transfer of learning

NASA Astrophysics Data System (ADS)

Harrison, David J.; Saito, Laurel; Markee, Nancy; Herzog, Serge

2017-11-01

To examine the impact of a hybrid-flipped model utilising active learning techniques, the researchers inverted one section of an undergraduate fluid mechanics course, reduced seat time, and engaged in active learning sessions in the classroom. We compared this model to the traditional section on four performance measures. We employed a propensity score method entailing a two-stage regression analysis that considered eight covariates to address the potential bias of treatment selection. First, we estimated the probability score based on the eight covariates, and second, we used the inverse of the probability score as a regression weight on the performance of learners who did not select into the hybrid course. Results suggest that enrolment in the hybrid-flipped section had a marginally significant negative impact on the total course score and a significant negative impact on homework performance, possibly because of poor video usage by the hybrid-flipped learners. Suggested considerations are also discussed.

Preschool motor skills following physical and occupational therapy services among non-disabled very low birth weight children.

PubMed

Watkins, Stephanie; Jonsson-Funk, Michele; Brookhart, M Alan; Rosenberg, Steven A; O'Shea, T Michael; Daniels, Julie

2014-05-01

Children born very low birth weight (VLBW) are at an increased risk of delayed development of motor skills. Physical and occupational therapy services may reduce this risk. Among VLBW children, we evaluated whether receipt of physical or occupational therapy services between 9 months and 2 years of age is associated with improved preschool age motor ability. Using data from the Early Childhood Longitudinal Study Birth Cohort we estimated the association between receipt of therapy and the following preschool motor milestones: skipping eight consecutive steps, hopping five times, standing on one leg for 10 seconds, walking backwards six steps on a line, and jumping distance. We used propensity score methods to adjust for differences in baseline characteristics between children who did and did not receive physical or occupational therapy, since children receiving therapy may be at higher risk of impairment. We applied propensity score weights and modeled the estimated effect of therapy on the distance that the child jumped using linear regression. We modeled all other end points using logistic regression. Treated VLBW children were 1.70 times as likely to skip eight steps (RR 1.70, 95 % CI 0.84, 3.44) compared to the untreated group and 30 % more likely to walk six steps backwards (RR 1.30, 95 % CI 0.63, 2.71), although these differences were not statistically significant. We found little effect of therapy on other endpoints. Providing therapy to VLBW children during early childhood may improve select preschool motor skills involving complex motor planning.

Are tuition-free primary education policies associated with lower infant and neonatal mortality in low- and middle-income countries?

PubMed

Quamruzzaman, Amm; Mendoza Rodríguez, José M; Heymann, Jody; Kaufman, Jay S; Nandi, Arijit

2014-11-01

Robust evidence from low- and middle-income countries (LMICs) suggests that maternal education is associated with better child health outcomes. However, whether or not policies aimed at increasing access to education, including tuition-free education policies, contribute to lower infant and neonatal mortality has not been empirically tested. We joined country-level data on national education policies for 37 LMICs to information on live births to young mothers aged 15-21 years, who were surveyed as part of the population-based Demographic and Health Surveys. We used propensity scores to match births to mothers who were exposed to a tuition-free primary education policy with births to mothers who were not, based on individual-level, household, and country-level characteristics, including GDP per capita, urbanization, and health expenditures per capita. Multilevel logistic regression models, fitted using generalized estimating equations, were used to estimate the effect of exposure to tuition-free primary education policies on the risk of infant and neonatal mortality. We also tested whether this effect was modified by household socioeconomic status. The propensity score matched samples for analyses of infant and neonatal mortality comprised 24,396 and 36,030 births, respectively, from 23 countries. Multilevel regression analyses showed that, on average, exposure to a tuition-free education policy was associated with 15 (95% CI=-32, 1) fewer infant and 5 (95% CI=-13, 4) fewer neonatal deaths per 1000 live births. We found no strong evidence of heterogeneity of this effect by socioeconomic level. Copyright © 2014. Published by Elsevier Ltd.

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

VanderWalde, Noam A.; Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina; Meyer, Anne Marie

Purpose: The purpose of this study was to compare chemoradiation therapy (CRT) with radiation therapy (RT) only in an older patient population with head and neck squamous cell carcinoma (HNSCC). Methods and Materials: Using the Surveillance, Epidemiology, and End Results (SEER)-Medicare linked database (1992-2007), we identified a retrospective cohort of nonmetastatic HNSCC patients and divided them into treatment groups. Comparisons were made between CRT and RT cohorts. Propensity scores for CRT were estimated from covariates associated with receipt of treatment using multivariable logistic regression. Standardized mortality ratio weights (SMRW) were created from the propensity scores and used to balance groupsmore » on measured confounders. Multivariable and SMR-weighted Cox proportional hazard models were used to estimate the hazard ratio (HR) of death for receipt of CRT versus RT among the whole group and for separate patient and tumor categories. Results: The final cohort of 10,599 patients was 68% male and 89% white. Median age was 74 years. Seventy-four percent were treated with RT, 26% were treated with CRT. Median follow-up points for CRT and RT survivors were 4.6 and 6.3 years, respectively. On multivariable analysis, HR for death with CRT was 1.13 (95% confidence interval [CI]: 1.07-1.20; P<.01). Using the SMRW model, the HR for death with CRT was 1.08 (95% CI: 1.02-1.15; P=.01). Conclusions: Although the addition of chemotherapy to radiation has proven efficacious in many randomized controlled trials, it may be less effective in an older patient population treated outside of a controlled trial setting.« less

Outcomes for youth receiving intensive in-home therapy or residential care: a comparison using propensity scores.

PubMed

Barth, Richard P; Greeson, Johanna K P; Guo, Shenyang; Green, Rebecca L; Hurley, Sarah; Sisson, Jocelyn

2007-10-01

This study compares outcomes for behaviorally troubled children receiving intensive in-home therapy (IIHT) and those receiving residential care (RC). Propensity score matching is used to identify matched pairs of youth (n = 786) with equivalent propensity for IIHT. The majority of pretreatment differences between the IIHT and RC groups are eliminated following matching. Logistic regression is then conducted on outcome differences at 1 year postdischarge. Results show that IIHT recipients had a greater tendency (.615) toward living with family, making progress in school, not experiencing trouble with the law, and placement stability compared with RC youth (.558; p < .10). This suggests that IIHT is at least as effective for achieving positive outcomes. Given IIHT's reduced restrictiveness and cost, intensive in-home services should be the preferred treatment over RC in most cases.

Propensity Score Matching: Retrospective Randomization?

PubMed

Jupiter, Daniel C

Randomized controlled trials are viewed as the optimal study design. In this commentary, we explore the strength of this design and its complexity. We also discuss some situations in which these trials are not possible, or not ethical, or not economical. In such situations, specifically, in retrospective studies, we should make every effort to recapitulate the rigor and strength of the randomized trial. However, we could be faced with an inherent indication bias in such a setting. Thus, we consider the tools available to address that bias. Specifically, we examine matching and introduce and explore a new tool: propensity score matching. This tool allows us to group subjects according to their propensity to be in a particular treatment group and, in so doing, to account for the indication bias. Copyright © 2017 American College of Foot and Ankle Surgeons. Published by Elsevier Inc. All rights reserved.

A reappraisal of the benefit-risk profile of hydroxyurea in polycythemia vera: A propensity-matched study.

PubMed

Barbui, Tiziano; Vannucchi, Alessandro Maria; Finazzi, Guido; Finazzi, Maria Chiara; Masciulli, Arianna; Carobbio, Alessandra; Ghirardi, Arianna; Tognoni, Gianni

2017-11-01

The use of hydroxyurea (HU) as first line therapy in polycythemia vera (PV) has been criticized because no solid demonstration that this drug prevents thrombosis or prolongs survival has been so far produced. Here we present the outcomes of a large cohort of patients with PV included in the European Collaborative Low-dose Aspirin (ECLAP) study. We selected 1,042 patients who, during the follow-up, had received only phlebotomy (PHL) or HU to maintain the hematocrit level < 45%. To assure comparability, we conducted a propensity score matching analysis. The two groups (PHL n = 342 and HU n = 681) were well balanced for the parameters included in the propensity score (overall balance: χ 2  = 2.44, P = 0.964). Over a comparable period of follow-up (PHL = 29.9 vs. HU = 34.7 months), we documented an advantage of HU over PHL consistently significant with respect to the incidence of fatal/non-fatal cardiovascular (CV) events (5.8 vs. 3.0 per 100 person-years in PHL vs. HU group, P = 0.002) and myelofibrosis transformation that was only experienced by patients of PHL group. Evolution to acute leukemia was registered in three patients (two in PHL and one in HU group). The excess of mortality and total CV events in the PHL patients was restricted to the high-risk group, and, compared with HU cases, was significant higher in the PHL patients who failed to reach the hematocrit target < 0.45% (P = 0.000). In conclusion, this analysis provides reliable and qualified estimates of the therapeutic profile of HU and PHL treatments for future experimental studies and for the management of PV in clinical practice. © 2017 Wiley Periodicals, Inc.

Anesthesia Technique and Mortality after Total Hip or Knee Arthroplasty: A Retrospective, Propensity Score-matched Cohort Study.

PubMed

Perlas, Anahi; Chan, Vincent W S; Beattie, Scott

2016-10-01

This propensity score-matched cohort study evaluates the effect of anesthetic technique on a 30-day mortality after total hip or knee arthroplasty. All patients who had hip or knee arthroplasty between January 1, 2003, and December 31, 2014, were evaluated. The principal exposure was spinal versus general anesthesia. The primary outcome was 30-day mortality. Secondary outcomes were (1) perioperative myocardial infarction; (2) a composite of major adverse cardiac events that includes cardiac arrest, myocardial infarction, or newly diagnosed arrhythmia; (3) pulmonary embolism; (4) major blood loss; (5) hospital length of stay; and (6) operating room procedure time. A propensity score-matched-pair analysis was performed using a nonparsimonious logistic regression model of regional anesthetic use. We identified 10,868 patients, of whom 8,553 had spinal anesthesia and 2,315 had general anesthesia. Ninety-two percent (n = 2,135) of the patients who had general anesthesia were matched to similar patients who did not have general anesthesia. In the matched cohort, the 30-day mortality rate was 0.19% (n = 4) in the spinal anesthesia group and 0.8% (n = 17) in the general anesthesia group (risk ratio, 0.42; 95% CI, 0.21 to 0.83; P = 0.0045). Spinal anesthesia was also associated with a shorter hospital length of stay (5.7 vs. 6.6 days; P < 0.001). The results of this observational, propensity score-matched cohort study suggest a strong association between spinal anesthesia and lower 30-day mortality, as well as a shorter hospital length of stay, after elective joint replacement surgery.

Matching weights to simultaneously compare three treatment groups: Comparison to three-way matching

PubMed Central

Yoshida, Kazuki; Hernández-Díaz, Sonia; Solomon, Daniel H.; Jackson, John W.; Gagne, Joshua J.; Glynn, Robert J.; Franklin, Jessica M.

2017-01-01

BACKGROUND Propensity score matching is a commonly used tool. However, its use in settings with more than two treatment groups has been less frequent. We examined the performance of a recently developed propensity score weighting method in the three treatment group setting. METHODS The matching weight method is an extension of inverse probability of treatment weighting (IPTW) that reweights both exposed and unexposed groups to emulate a propensity score matched population. Matching weights can generalize to multiple treatment groups. The performance of matching weights in the three-group setting was compared via simulation to three-way 1:1:1 propensity score matching and IPTW. We also applied these methods to an empirical example that compared the safety of three analgesics. RESULTS Matching weights had similar bias, but better mean squared error (MSE) compared to three-way matching in all scenarios. The benefits were more pronounced in scenarios with a rare outcome, unequally sized treatment groups, or poor covariate overlap. IPTW’s performance was highly dependent on covariate overlap. In the empirical example, matching weights achieved the best balance for 24 out of 35 covariates. Hazard ratios were numerically similar to matching. However, the confidence intervals were narrower for matching weights. CONCLUSIONS Matching weights demonstrated improved performance over three-way matching in terms of MSE, particularly in simulation scenarios where finding matched subjects was difficult. Given its natural extension to settings with even more than three groups, we recommend matching weights for comparing outcomes across multiple treatment groups, particularly in settings with rare outcomes or unequal exposure distributions. PMID:28151746

Chronic Azithromycin Use in Cystic Fibrosis and Risk of Treatment-Emergent Respiratory Pathogens.

PubMed

Cogen, Jonathan D; Onchiri, Frankline; Emerson, Julia; Gibson, Ronald L; Hoffman, Lucas R; Nichols, David P; Rosenfeld, Margaret

2018-02-23

Azithromycin has been shown to improve lung function and reduce the number of pulmonary exacerbations in cystic fibrosis patients. Concerns remain, however, regarding the potential emergence of treatment-related respiratory pathogens. To determine if chronic azithromycin use (defined as thrice weekly administration) is associated with increased rates of detection of eight specific respiratory pathogens. We performed a new-user, propensity-score matched retrospective cohort study utilizing data from the Cystic Fibrosis Foundation Patient Registry. Incident azithromycin users were propensity-score matched 1:1 with contemporaneous non-users. Kaplan-Meier curves and Cox proportional hazards regression were used to evaluate the association between chronic azithromycin use and incident respiratory pathogen detection. Analyses were performed separately for each pathogen, limited to patients among whom that pathogen had not been isolated in the two years prior to cohort entry. After propensity score matching, mean age of the cohorts was ~12 years. Chronic azithromycin users had a significantly lower risk of detection of new methicillin-resistant Staphylococcus aureus, non-tuberculous mycobacteria, and Burkholderia cepacia complex compared to non-users. The risk of acquiring the remaining five pathogens was not significantly different between users and non-users. Using an innovative new-user, propensity-score matched study design to minimize indication and selection biases, we found in a predominantly pediatric cohort that chronic azithromycin users had a lower risk of acquiring several cystic fibrosis-related respiratory pathogens. These results may ease concerns that chronic azithromycin exposure increases the risk of acquiring new respiratory pathogens among pediatric cystic fibrosis patients.

[The impact of subsidized healthcare insurance on access to cervical cytology in Medellin, Colombia].

PubMed

Atehortúa, Sara C; Palacio-Mejía, Lina S

2014-01-01

Assessing the impact of subsidized healthcare insurance on access to cervical cytology in Medellin, Colombia. Propensity score matching (PSM) was used with 2008 Life Quality Survey in Colombia figures to obtain a control group comparable to a treatment group. This involved using stratification estimates, the k-nearest-neighbor algorithm and kernel density for calculating impact size Access to cytology for 19 to 49 year-old women having subsidized healthcare insurance were 2.2 % to 2.9 % lower compared to women who did not have any healthcare insurance. Estimates were not statistically significant for women over 50 years-old. Women lacking healthcare insurance having increased access to cytology could be explained by charities or social programs aiding the population lacking healthcare insurance.

Oncological and functional outcomes of elderly men treated with HIFU vs. minimally invasive radical prostatectomy: A propensity score analysis.

PubMed

Capogrosso, Paolo; Barret, Eric; Sanchez-Salas, Rafael; Nunes-Silva, Igor; Rozet, François; Galiano, Marc; Ventimiglia, Eugenio; Briganti, Alberto; Salonia, Andrea; Montorsi, Francesco; Cathelineau, Xavier

2018-01-01

To assess outcomes of whole gland high-intensity focused ultrasound (HIFU) as compared with minimally-invasive radical prostatectomy (MIRP) in elderly patients. Patients aged ≥70 years with, cT1-cT2 disease, biopsy Gleason score (GS) 3 + 3 or 3 + 4 and preoperative PSA ≤10 ng/mL were submitted to either whole-gland HIFU or MIRP. Propensity-score matching analysis was performed to ensure the baseline equivalence of groups. Follow-up visits were routinely performed assessing PSA and urinary function according to the International Continence Score (ICS) and the International Prostatic Symptoms Score (IPSS) questionnaires. Estimated rates of salvage-treatment free survival (SFS) overall-survival (OS), cancer-specific survival (CSS) and metastasis-free survival (MTS) were assessed and compared. Overall, 84 (33.3%) and 168 (66.7%) patients were treated with HIFU and MIRP, respectively. MIRP was associated with a 5-yrs SFS of 93.4% compared to 74.8% for HIFU (p < 0.01). The two groups did not differ in terms of OS and MTS. No cancer-related deaths were registered. Patients treated with HIFU showed better short-term (6-mos) continence outcomes [mean-ICS: 1.7 vs. 4.8; p = 0.005] but higher IPSS mean scores at 12-mos assessment. A comparable rate of patients experiencing post-treatment Clavien-Dindo grade ≥III complications was observed within the two groups. Whole-gland HIFU is a feasible treatment in elderly men with low-to intermediate-risk PCa and could be considered for patients either unfit for surgery, or willing a non-invasive treatment with a low morbidity burden, although a non-negligible risk of requiring subsequent treatment for recurrence should be expected. Copyright © 2017 Elsevier Ltd, BASO ~ The Association for Cancer Surgery, and the European Society of Surgical Oncology. All rights reserved.

Improved knowledge of and difficulties in palliative care among physicians during 2008 and 2015 in Japan: Association with a nationwide palliative care education program.

PubMed

Nakazawa, Yoko; Yamamoto, Ryo; Kato, Masashi; Miyashita, Mitsunori; Kizawa, Yoshiyuki; Morita, Tatsuya

2018-02-01

Palliative care education for health care professionals is a key element in improving access to quality palliative care. The Palliative Care Emphasis Program on Symptom Management and Assessment for Continuous Medical Education (PEACE) was designed to provide educational opportunities for all physicians in Japan. As of 2015, 57,764 physicians had completed it. The objective of this study was to estimate the effects of the program. This study was an analysis of 2 nationwide observational studies from 2008 and 2015. We conducted 2 questionnaire surveys for representative samples of physicians. The measurements used were the Palliative Care Knowledge Test (range, 0-100) and the Palliative Care Difficulties Scale (range, 1-4). Comparisons were made with the unpaired Student t test and with a multivariate linear regression model using 2 cohorts and a propensity score-matched sample. This study analyzed a total of 48,487 physicians in 2008 and a total of 2720 physicians in 2015. Between 2008 and 2015, physicians' knowledge and difficulties significantly improved on the Palliative Care Knowledge Test with total scores of 68 and 78, respectively (P < .001; effect size, 0.40) and on the Palliative Care Difficulties Scale with total scores of 2.65 and 2.49, respectively (P < .001; effect size, 0.29). Propensity-score matching resulted in 619 untrained physicians matched to 619 trained physicians, and physicians who trained with the PEACE program had a higher knowledge score (74 vs 86; P < .001; effect size, 0.64) and a lower difficulties score (2.6 vs 2.3; P < .001; effect size, 0.42). Physicians' knowledge of and difficulties with palliative care improved on a national level. The PEACE program may have contributed to these improvements. Cancer 2018;124:626-35. © 2017 American Cancer Society. © 2017 American Cancer Society.

Serum calcification propensity is independently associated with disease activity in systemic lupus erythematosus

PubMed Central

Chalikias, George; Tziakas, Dimitrios; Chizzolini, Carlo; Ribi, Camillo; Trendelenburg, Marten; Eisenberger, Ute; Hauser, Thomas; Pasch, Andreas; Huynh-Do, Uyen; Arampatzis, Spyridon

2018-01-01

Background Systemic lupus erythematosus (SLE) is associated with severe cardiovascular complications. The T50 score is a novel functional blood test quantifying calcification propensity in serum. High calcification propensity (or low T50) is a strong and independent determinant of all-cause mortality in various patient populations. Methods A total of 168 patients with ≥ 4 American College of Rheumatology (ACR) diagnostic criteria from the Swiss Systemic lupus erythematosus Cohort Study (SSCS) were included in this analysis. Serum calcification propensity was assessed using time-resolved nephelometry. Results The cohort mainly consisted of female (85%), middle-aged (43±14 years) Caucasians (77%). The major determinants of T50 levels included hemoglobin, serum creatinine and serum protein levels explaining 43% of the variation at baseline. Integrating disease activity (SELENA-SLEDAI) into this multivariate model revealed a significant association between disease activity and T50 levels. In a subgroup analysis considering only patients with active disease (SELENA-SLEDAI score ≥4) we found a negative association between T50 and SELENA-SLEDAI score at baseline (Spearman’s rho -0.233, P = 0.02). Conclusions Disease activity and T50 are closely associated. Moreover, T50 levels identify a subgroup of SLE patients with ongoing systemic inflammation as mirrored by increased disease activity. T50 could be a promising biomarker reflecting SLE disease activity and might offer an earlier detection tool for high-risk patients. PMID:29364894

Association between spironolactone added to beta-blockers and ACE inhibition and survival in heart failure patients with reduced ejection fraction: a propensity score-matched cohort study.

PubMed

Frankenstein, L; Katus, H A; Grundtvig, M; Hole, T; de Blois, J; Schellberg, D; Atar, D; Zugck, C; Agewall, S

2013-10-01

Heart failure (CHF) guidelines recommend mineralocorticoid receptor antagonists for all symptomatic patients treated with a combination of ACE inhibitors/angiotensin receptor blockers (ARBs) and beta-blockers. As opposed to both eplerenone trials, patients in RALES (spironolactone) received almost no beta-blockers. Since pharmacological properties differ between eplerenone and spironolactone, the prognostic benefit of spironolactone added to this baseline combination therapy needs clarification. We included 4,832 CHF patients with chronic systolic dysfunction from the Norwegian Heart Failure Registry and the heart failure outpatients' clinic of the University of Heidelberg. Propensity scores for spironolactone receipt were calculated for each patient and used for matching to patients without spironolactone. During a total follow-up of 17,869 patient-years, 881 patients (27.0 %) died in the non-spironolactone group and 445 (28.4 %) in the spironolactone group. Spironolactone was not associated with improved survival, neither in the complete sample (HR 0.82; 95 % CI 0.64-1.07; HR 1.03; 95 % CI 0.88-1.20; multivariate and propensity score adjusted respectively), nor in the propensity-matched cohort (HR 0.98; 95 % CI 0.82-1.18). In CHF outpatients we were unable to observe an association between the use of spironolactone and improved survival when administered in addition to a combination of ACE/ARB and beta-blockers.

Effect of Radiotherapy Planning Complexity on Survival of Elderly Patients With Unresected Localized Lung Cancer

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

Park, Chang H.; Bonomi, Marcelo; Cesaretti, Jamie

2011-11-01

Purpose: To evaluate whether complex radiotherapy (RT) planning was associated with improved outcomes in a cohort of elderly patients with unresected Stage I-II non-small-cell lung cancer (NSCLC). Methods and Materials: Using the Surveillance, Epidemiology, and End Results registry linked to Medicare claims, we identified 1998 patients aged >65 years with histologically confirmed, unresected stage I-II NSCLC. Patients were classified into an intermediate or complex RT planning group using Medicare physician codes. To address potential selection bias, we used propensity score modeling. Survival of patients who received intermediate and complex simulation was compared using Cox regression models adjusting for propensity scoresmore » and in a stratified and matched analysis according to propensity scores. Results: Overall, 25% of patients received complex RT planning. Complex RT planning was associated with better overall (hazard ratio 0.84; 95% confidence interval, 0.75-0.95) and lung cancer-specific (hazard ratio 0.81; 95% confidence interval, 0.71-0.93) survival after controlling for propensity scores. Similarly, stratified and matched analyses showed better overall and lung cancer-specific survival of patients treated with complex RT planning. Conclusions: The use of complex RT planning is associated with improved survival among elderly patients with unresected Stage I-II NSCLC. These findings should be validated in prospective randomized controlled trials.« less

Preoperative Angiotensin Blocking Drug Therapy Is not Associated with Atrial Fibrillation after Cardiac Surgery

PubMed Central

Rader, Florian; Van Wagoner, David R.; Gillinov, A. Marc; Blackstone, Eugene H.

2010-01-01

Background Preoperative use of angiotensin blocking drug therapy (ABDT) with ACE-inhibitors or Angiotensin II receptor blockers (ARBs) and its link to occurrence of postoperative atrial fibrillation (POAF), a common marker of poor outcomes after cardiac surgery, remains controversial. Methods From 1997-2003 10,552 patients underwent coronary artery bypass grafting (CABG) with or without valve surgery. To adjust for differences of clinical characteristics between patients receiving ABDT within 24 hours prior to surgery compared to those who did not, propensity score analyses were conducted. Results ABDT was prescribed in 4,795 (45%) prior to surgery of which 1,725 (36%) developed POAF prior to discharge vs. 1908 (33%) of 5,757 patients who have not received ABDT (unadjusted odds ratio [OR] of 1.13 (95% Confidence Interval [CI] 1.05-1.25, p<0.01). In 6744 propensity score matched patients with well balanced co-morbidity profiles, ABDT was not associated with POAF (OR 1.05, CI 0.95-1.16, p=0.38). Stratified analysis within quintiles of propensity score and propensity-adjusted logistic multivariable regression confirmed these findings. Conclusions In this large observational study we found no evidence of an association between preoperative angiotensin blockade and the occurrence of postoperative atrial fibrillation. Adequately powered randomized studies are needed to clarify the best strategy of perioperative angiotensin blocking drug therapy in patients with and without guideline-based indications. PMID:20691840

The impacts of speed cameras on road accidents: an application of propensity score matching methods.

PubMed

Li, Haojie; Graham, Daniel J; Majumdar, Arnab

2013-11-01

This paper aims to evaluate the impacts of speed limit enforcement cameras on reducing road accidents in the UK by accounting for both confounding factors and the selection of proper reference groups. The propensity score matching (PSM) method is employed to do this. A naïve before and after approach and the empirical Bayes (EB) method are compared with the PSM method. A total of 771 sites and 4787 sites for the treatment and the potential reference groups respectively are observed for a period of 9 years in England. Both the PSM and the EB methods show similar results that there are significant reductions in the number of accidents of all severities at speed camera sites. It is suggested that the propensity score can be used as the criteria for selecting the reference group in before-after control studies. Speed cameras were found to be most effective in reducing accidents up to 200 meters from camera sites and no evidence of accident migration was found. Copyright © 2013 Elsevier Ltd. All rights reserved.

[Influence of surgeon specialization upon the results of colon cancer surgery. Usefulness of propensity scores].

PubMed

Martínez-Ramos, D; Escrig-Sos, J; Miralles-Tena, J M; Rivadulla-Serrano, M I; Daroca-José, J M; Salvador Sanchís, J L

2008-07-01

surgeon influence on colorectal cancer surgery outcomes has been repeatedly studied in the scientific literature, but conclusions have been contradictory. Here we study whether surgeon specialization is a determinant factor for outcome in these patients. The importance of propensity scores (PS) in surgical research is also studied. a retrospective study was performed and medical records were reviewed for 236 patients who were intervened for colon cancer in Castellon General Hospital (Spain). Cases were divided into two groups (specialist and non-specialist surgeons), and both 5-year surveillance and disease free survival were compared. Comparisons were first made with no adjustments, and then subsequently using PS analysis. the initial (non-adjusted) analysis was clearly favourable for the specialist surgeon group (5-year surveillance, 64.3 vs. 79.3%, p = 0.028). After adjusting for PS no statistical significance was obtained. surgeon specialization had no significant impact on patient outcome after colon cancer surgery. Propensity score analysis is an important tool in the analysis of surgical non-randomized studies, particularly when events under scrutiny are rare.

The Effect of Latent Binary Variables on the Uncertainty of the Prediction of a Dichotomous Outcome Using Logistic Regression Based Propensity Score Matching.

PubMed

Szekér, Szabolcs; Vathy-Fogarassy, Ágnes

2018-01-01

Logistic regression based propensity score matching is a widely used method in case-control studies to select the individuals of the control group. This method creates a suitable control group if all factors affecting the output variable are known. However, if relevant latent variables exist as well, which are not taken into account during the calculations, the quality of the control group is uncertain. In this paper, we present a statistics-based research in which we try to determine the relationship between the accuracy of the logistic regression model and the uncertainty of the dependent variable of the control group defined by propensity score matching. Our analyses show that there is a linear correlation between the fit of the logistic regression model and the uncertainty of the output variable. In certain cases, a latent binary explanatory variable can result in a relative error of up to 70% in the prediction of the outcome variable. The observed phenomenon calls the attention of analysts to an important point, which must be taken into account when deducting conclusions.

Marital Dissolution and Major Depression in Midlife: A Propensity Score Analysis.

PubMed

Sbarra, David A; Emery, Robert E; Beam, Christopher R; Ocker, Bailey L

2014-05-01

Marital dissolution is commonly assumed to cause increased depression among adults, but causality can be questioned based on directionality and third variable concerns. The present study improves upon past research by using a propensity score matching algorithm to identify a sub-sample of continuously married participants equivalent in divorce risk to participants who actually experienced separation/divorce between two waves of the nationally representative study, Midlife Development in the United States (MIDUS). After correcting for participants' propensity to separate/divorce, increased rates of depression at the second assessment were observed only among participants who were (a) depressed at the initial assessment, and (b) experienced a separation/divorce. Participants who were not depressed at the initial assessment but who experienced a separation/divorce were not at increased risk for a later major depressive disorder (MDE). Thus, both social selection and social causation contribute to the increased risk for a MDE found among separated/divorced adults.

Estimating local costs associated with Clostridium difficile infection using machine learning and electronic medical records

PubMed Central

Pak, Theodore R.; Chacko, Kieran; O’Donnell, Timothy; Huprikar, Shirish; van Bakel, Harm; Kasarskis, Andrew; Scott, Erick R.

2018-01-01

Background Reported per-patient costs of Clostridium difficile infection (CDI) vary by two orders of magnitude among different hospitals, implying that infection control officers need precise, local analyses to guide rational decision-making between interventions. Objective We sought to comprehensively estimate changes in length of stay (LOS) attributable to CDI at one urban tertiary-care facility using only data automatically extractable from the electronic medical record (EMR). Methods We performed a retrospective cohort study of 171,938 visits spanning a 7-year period. 23,968 variables were extracted from EMR data recorded within 24 hours of admission to train elastic net regularized logistic regression models for propensity score matching. To address time-dependent bias (reverse causation), we separately stratified comparisons by time-of-infection and fit multistate models. Results The estimated difference in median LOS for propensity-matched cohorts varied from 3.1 days (95% CI, 2.2–3.9) to 10.1 days (95% CI, 7.3–12.2) depending on the case definition; however, dependency of the estimate on time-to-infection was observed. Stratification by time to first positive toxin assay, excluding probable community-acquired infections, showed a minimum excess LOS of 3.1 days (95% CI, 1.7–4.4). Under the same case definition, the multistate model averaged an excess LOS of 3.3 days (95% CI, 2.6–4.0). Conclusions Two independent time-to-infection adjusted methods converged on similar excess LOS estimates. Changes in LOS can be extrapolated to a marginal dollar costs by multiplying by average costs of an inpatient-day. Infection control officers can leverage automatically extractable EMR data to estimate costs of CDI at their own institution. PMID:29103378

Sublobar resection is equivalent to lobectomy for clinical stage 1A lung cancer in solid nodules.

PubMed

Altorki, Nasser K; Yip, Rowena; Hanaoka, Takaomi; Bauer, Thomas; Aye, Ralph; Kohman, Leslie; Sheppard, Barry; Thurer, Richard; Andaz, Shahriyour; Smith, Michael; Mayfield, William; Grannis, Fred; Korst, Robert; Pass, Harvey; Straznicka, Michaela; Flores, Raja; Henschke, Claudia I

2014-02-01

A single randomized trial established lobectomy as the standard of care for the surgical treatment of early-stage non-small cell lung cancer. Recent advances in imaging/staging modalities and detection of smaller tumors have once again rekindled interest in sublobar resection for early-stage disease. The objective of this study was to compare lung cancer survival in patients with non-small cell lung cancer with a diameter of 30 mm or less with clinical stage 1 disease who underwent lobectomy or sublobar resection. We identified 347 patients diagnosed with lung cancer who underwent lobectomy (n = 294) or sublobar resection (n = 53) for non-small cell lung cancer manifesting as a solid nodule in the International Early Lung Cancer Action Program from 1993 to 2011. Differences in the distribution of the presurgical covariates between sublobar resection and lobectomy were assessed using unadjusted P values determined by logistic regression analysis. Propensity scoring was performed using the same covariates. Differences in the distribution of the same covariates between sublobar resection and lobectomy were assessed using adjusted P values determined by logistic regression analysis with adjustment for the propensity scores. Lung cancer-specific survival was determined by the Kaplan-Meier method. Cox survival regression analysis was used to compare sublobar resection with lobectomy, adjusted for the propensity scores, surgical, and pathology findings, when adjusted and stratified by propensity quintiles. Among 347 patients, 10-year Kaplan-Meier for 53 patients treated by sublobar resection compared with 294 patients treated by lobectomy was 85% (95% confidence interval, 80-91) versus 86% (confidence interval, 75-96) (P = .86). Cox survival analysis showed no significant difference between sublobar resection and lobectomy when adjusted for propensity scores or when using propensity quintiles (P = .62 and P = .79, respectively). For those with cancers 20 mm or less in diameter, the 10-year rates were 88% (95% confidence interval, 82-93) versus 84% (95% confidence interval, 73-96) (P = .45), and Cox survival analysis showed no significant difference between sublobar resection and lobectomy using either approach (P = .42 and P = .52, respectively). Sublobar resection and lobectomy have equivalent survival for patients with clinical stage IA non-small cell lung cancer in the context of computed tomography screening for lung cancer. Copyright © 2014 The American Association for Thoracic Surgery. Published by Mosby, Inc. All rights reserved.

Early High-Frequency Oscillatory Ventilation in Pediatric Acute Respiratory Failure. A Propensity Score Analysis.

PubMed

Bateman, Scot T; Borasino, Santiago; Asaro, Lisa A; Cheifetz, Ira M; Diane, Shelley; Wypij, David; Curley, Martha A Q

2016-03-01

The use of high-frequency oscillatory ventilation (HFOV) for acute respiratory failure in children is prevalent despite the lack of efficacy data. To compare the outcomes of patients with acute respiratory failure managed with HFOV within 24-48 hours of endotracheal intubation with those receiving conventional mechanical ventilation (CMV) and/or late HFOV. This is a secondary analysis of data from the RESTORE (Randomized Evaluation of Sedation Titration for Respiratory Failure) study, a prospective cluster randomized clinical trial conducted between 2009 and 2013 in 31 U.S. pediatric intensive care units. Propensity score analysis, including degree of hypoxia in the model, compared the duration of mechanical ventilation and mortality of patients treated with early HFOV matched with those treated with CMV/late HFOV. Among 2,449 subjects enrolled in RESTORE, 353 patients (14%) were ever supported on HFOV, of which 210 (59%) had HFOV initiated within 24-48 hours of intubation. The propensity score model predicting the probability of receiving early HFOV included 1,064 patients (181 early HFOV vs. 883 CMV/late HFOV) with significant hypoxia (oxygenation index ≥ 8). The degree of hypoxia was the most significant contributor to the propensity score model. After adjusting for risk category, early HFOV use was associated with a longer duration of mechanical ventilation (hazard ratio, 0.75; 95% confidence interval, 0.64-0.89; P = 0.001) but not with mortality (odds ratio, 1.28; 95% confidence interval, 0.92-1.79; P = 0.15) compared with CMV/late HFOV. In adjusted models including important oxygenation variables, early HFOV was associated with a longer duration of mechanical ventilation. These analyses make supporting the current approach to HFOV less convincing.

Efficacy of a Self-expanding Tract Sealant Device in the Reduction of Pneumothorax and Chest Tube Placement Rates After Percutaneous Lung Biopsy: A Matched Controlled Study Using Propensity Score Analysis.

PubMed

Ahrar, Judy U; Gupta, Sanjay; Ensor, Joe E; Mahvash, Armeen; Sabir, Sharjeel H; Steele, Joseph R; McRae, Stephen E; Avritscher, Rony; Huang, Steven Y; Odisio, Bruno C; Murthy, Ravi; Ahrar, Kamran; Wallace, Michael J; Tam, Alda L

2017-02-01

To evaluate the use of a self-expanding tract sealant device (BioSentry™) on the rates of pneumothorax and chest tube insertion after percutaneous lung biopsy. In this retrospective study, we compared 318 patients who received BioSentry™ during percutaneous lung biopsy (treated group) with 1956 patients who did not (control group). Patient-, lesion-, and procedure-specific variables, and pneumothorax and chest tube insertion rates were recorded. To adjust for potential selection bias, patients in the treated group were matched 1:1 to patients in the control group using propensity score matching based on the above-mentioned variables. Patients were considered a match if the absolute difference in their propensity scores was ≤equal to 0.02. Before matching, the pneumothorax and chest tube rates were 24.5 and 13.1% in the control group, and 21.1 and 8.5% in the treated group, respectively. Using propensity scores, a match was found for 317 patients in the treatment group. Chi-square contingency matched pair analysis showed the treated group had significantly lower pneumothorax (20.8 vs. 32.8%; p = 0.001) and chest tube (8.2 vs. 20.8%; p < 0.0001) rates compared to the control group. Sub-analysis including only faculty who had >30 cases of both treatment and control cases demonstrated similar findings: the treated group had significantly lower pneumothorax (17.6 vs. 30.2%; p = 0.002) and chest tube (7.2 vs. 18%; p = 0.001) rates. The self-expanding tract sealant device significantly reduced the pneumothorax rate, and more importantly, the chest tube placement rate after percutaneous lung biopsy.

Propensity Score Analysis Comparing Videothoracoscopic Lobectomy With Thoracotomy: A French Nationwide Study.

PubMed

Pagès, Pierre-Benoit; Delpy, Jean-Philippe; Orsini, Bastien; Gossot, Dominique; Baste, Jean-Marc; Thomas, Pascal; Dahan, Marcel; Bernard, Alain

2016-04-01

Video-assisted thoracoscopic surgery (VATS) lobectomy has recently become the recommended approach for stage I non-small cell lung cancer. However, these guidelines are not based on any large randomized control trial. Our study used propensity scores and a sensitivity analysis to compare VATS lobectomy with open thoracotomy. From 2005 to 2012, 24,811 patients (95.1%) were operated on by open thoracotomy and 1,278 (4.9%) by VATS. The end points were 30-day postoperative death, postoperative complications, hospital stay, overall survival, and disease-free survival. Two propensity scores analyses were performed: matching and inverse probability of treatment weighting, and one sensitivity analysis to unmask potential hidden bias. A subgroup analysis was performed to compare "high-risk" with "low-risk" patients. Results are reported by odds ratios or hazard ratios and their 95% confidence intervals. Postoperative death was not significantly reduced by VATS whatever the analysis. Concerning postoperative complications, VATS significantly decreased the occurrence of atelectasis and pneumopathy with both analysis methods, but there were no differences in the occurrence of other postoperative complications. VATS did not provide a benefit for high-risk patients. The VATS approach decreased the hospital length of stay from 2.4 days (95% confidence interval, -1.7 to -3 days) to -4.68 days (95% confidence interval, -8.5 to 0.9 days). Overall survival and disease-free survival were not influenced by the surgical approach. The sensitivity analysis showed potential biases. The results must be interpreted carefully because of the differences observed according to the propensity scores method used. A multicenter randomized controlled trial is necessary to limit the biases. Copyright © 2016 The Society of Thoracic Surgeons. Published by Elsevier Inc. All rights reserved.

One-year clinical outcomes of patients treated with everolimus-eluting bioresorbable vascular scaffolds versus everolimus-eluting metallic stents: a propensity score comparison of patients enrolled in the ABSORB EXTEND and SPIRIT trials.

PubMed

de Ribamar Costa, José; Abizaid, Alexandre; Bartorelli, Antonio L; Whitbourn, Robert; Jepson, Nigel; Perin, Marco; Steinwender, Clemens; Stuteville, Marrianne; Ediebah, Divine; Sudhir, Krishnankutty; Serruys, Patrick W

2016-11-20

We sought to compare the outcomes of low/moderate complexity patients treated with the Absorb BVS from the ABSORB EXTEND trial with patients treated with the XIENCE everolimus-eluting stent (EES), using propensity score (PS) matching of pooled data from the SPIRIT trials (SPIRIT II, SPIRIT III, SPIRIT IV) and the XIENCE V USA trial. ABSORB EXTEND was a prospective, single-arm, open-label clinical study in which 812 patients were enrolled at 56 sites. This study allowed the treatment of lesions ≤28 mm in length and with a reference vessel diameter of 2.0-3.8 mm (as assessed by online QCA). The propensity score was obtained by fitting a logistic regression model with the cohort indicator as the binary outcome and other variables as the predictor variables. At one-year clinical follow-up, there was no statistical difference between groups with regard to MACE (5.0% vs. 4.8%, p=0.83), target lesion failure (5.0% vs. 4.7%, p=0.74), ischaemia-driven target vessel revascularisation (2.3% vs. 3.0%, p=0.38) and device thrombosis (1.0% vs. 0.3%, p=0.11). Myocardial infarction was higher with Absorb (3.3% vs. 1.5%, p=0.02), at the expense of periprocedural CK-MB elevation. Independent predictors of MACE among patients receiving Absorb BVS were treatment of multivessel disease, insulin-dependent diabetes and performance of post-dilation. At one-year follow-up, propensity score-matched analysis demonstrated that the clinical safety and effectiveness of Absorb are comparable to those of XIENCE EES among non-complex patients treated with PCI.

Observation Versus Embolization in Patients with Blunt Splenic Injury After Trauma: A Propensity Score Analysis.

PubMed

Olthof, Dominique C; Joosse, Pieter; Bossuyt, Patrick M M; de Rooij, Philippe P; Leenen, Loek P H; Wendt, Klaus W; Bloemers, Frank W; Goslings, J Carel

2016-05-01

Non-operative management (NOM) is the standard of care in hemodynamically stable patients with blunt splenic injury after trauma. Splenic artery embolization (SAE) is reported to increase observation success rate. Studies demonstrating improved splenic salvage rates with SAE primarily compared SAE with historical controls. The aim of this study was to investigate whether SAE improves success rate compared to observation alone in contemporaneous patients with blunt splenic injury. We included adult patients with blunt splenic injury admitted to five Level 1 Trauma Centers between January 2009 and December 2012 and selected for NOM. Successful treatment was defined as splenic salvage and no splenic re-intervention. We calculated propensity scores, expressing the probability of undergoing SAE, using multivariable logistic regression and created five strata based on the quintiles of the propensity score distribution. A weighted relative risk (RR) was calculated across strata to express the chances of success with SAE. Two hundred and six patients were included in the study. Treatment was successful in 180 patients: 134/146 (92 %) patients treated with observation and 48/57 (84 %) patients treated with SAE. The weighted RR for success with SAE was 1.17 (0.94-1.45); for complications, the weighted RR was 0.71 (0.41-1.22). The mean number of transfused blood products was 4.4 (SD 9.9) in the observation group versus 9.1 (SD 17.2) in the SAE group. After correction for confounders with propensity score stratification technique, there was no significant difference between embolization and observation alone with regard to successful treatment in patients with blunt splenic injury after trauma.

Safety and Long-Term Outcomes of Catheter Ablation of Atrial Fibrillation Using Magnetic Navigation versus Manual Conventional Ablation: A Propensity-Score Analysis.

PubMed

Adragão, Pedro Pulido; Cavaco, Diogo; Ferreira, António Miguel; Costa, Francisco Moscoso; Parreira, Leonor; Carmo, Pedro; Morgado, Francisco Bello; Santos, Katya Reis; Santos, Pedro Galvão; Carvalho, Maria Salomé; Durazzo, Anai; Marques, Hugo; Gonçalves, Pedro Araújo; Raposo, Luís; Mendes, Miguel

2016-03-01

Whether or not the potential advantages of using a magnetic navigation system (MNS) translate into improved outcomes in patients undergoing atrial fibrillation (AF) ablation is a question that remains unanswered. In this observational registry study, we used propensity-score matching to compare the outcomes of patients with symptomatic drug-refractory AF who underwent catheter ablation using MNS with the outcomes of those who underwent catheter ablation using conventional manual navigation. Among 1,035 eligible patients, 287 patients in each group had similar propensity scores and were included in the analysis. The primary efficacy outcome was the rate of AF relapse after a 3-month blanking period. At a mean follow-up of 2.6 ± 1.5 years, AF ablation with MNS was associated with a similar risk of AF relapse as compared with manual navigation (18.4% per year and 22.3% per year, respectively; hazard ratio 0.81, 95% CI 0.63-1.05; P = 0.108). Major complications occurred in two patients (0.7%) using MNS, and in six patients (2.1%) undergoing manually navigated ablation (P = 0.286). Fluoroscopy times were 21 ± 10 minutes in the manual navigation group, and 12 ± 9 minutes in the MNS group (P < 0.001), whereas total procedure times were 152 ± 52 minutes and 213 ± 58 minutes, respectively (P < 0.001). In this propensity-score matched comparison, magnetic navigation and conventional manual AF ablations seem to have similar relapse rates and a similar risk of complications. AF ablations with magnetic navigation take longer to perform but expose patients to significantly shorter fluoroscopy times. © 2015 Wiley Periodicals, Inc.

Does knee replacement surgery for osteoarthritis improve survival? The jury is still out.

PubMed

Misra, Devyani; Lu, Na; Felson, David; Choi, Hyon K; Seeger, John; Einhorn, Thomas; Neogi, Tuhina; Zhang, Yuqing

2017-01-01

The relation of knee replacement (KR) surgery to all-cause mortality has not been well established owing to potential biases in previous studies. Thus, we aimed to examine the relation of KR to mortality risk among patients with knee osteoarthritis (OA) focusing on identifying biases that may threaten the validity of prior studies. We included knee OA subjects (ages 50-89 years) from The Health Improvement Network, an electronic medical records database in the UK. Risk of mortality among KR subjects was compared with propensity score-matched non-KR subjects. To explore residual confounding bias, subgroup analyses stratified by age and propensity scores were performed. Subjects with KR had 28% lower risk of mortality than non-KR subjects (HR 0.72, 95% CI 0.66 to 0.78). However, when stratified by age, protective effect was noted only in older age groups (>63 years) but not in younger subjects (≤63 years). Further, the mortality rate among KR subjects decreased as candidacy (propensity score) for KR increased among subjects with KR, but no such consistent trend was noted among non-KR subjects. While a protective effect of KR on mortality cannot be ruled out, findings of lower mortality among older KR subjects and those with higher propensity scores suggest that prognosis-based selection for KR may lead to intractable confounding by indication; hence, the protective effect of KR on all-cause mortality may be overestimated. 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/.

Evaluation of the US Food and Drug Administration sentinel analysis tools in confirming previously observed drug-outcome associations: The case of clindamycin and Clostridium difficile infection.

PubMed

Carnahan, Ryan M; Kuntz, Jennifer L; Wang, Shirley V; Fuller, Candace; Gagne, Joshua J; Leonard, Charles E; Hennessy, Sean; Meyer, Tamra; Archdeacon, Patrick; Chen, Chih-Ying; Panozzo, Catherine A; Toh, Sengwee; Katcoff, Hannah; Woodworth, Tiffany; Iyer, Aarthi; Axtman, Sophia; Chrischilles, Elizabeth A

2018-03-13

The Food and Drug Administration's Sentinel System developed parameterized, reusable analytic programs for evaluation of medical product safety. Research on outpatient antibiotic exposures, and Clostridium difficile infection (CDI) with non-user reference groups led us to expect a higher rate of CDI among outpatient clindamycin users vs penicillin users. We evaluated the ability of the Cohort Identification and Descriptive Analysis and Propensity Score Matching tools to identify a higher rate of CDI among clindamycin users. We matched new users of outpatient dispensings of oral clindamycin or penicillin from 13 Data Partners 1:1 on propensity score and followed them for up to 60 days for development of CDI. We used Cox proportional hazards regression stratified by Data Partner and matched pair to compare CDI incidence. Propensity score models at 3 Data Partners had convergence warnings and a limited range of predicted values. We excluded these Data Partners despite adequate covariate balance after matching. From the 10 Data Partners where these models converged without warnings, we identified 807 919 new clindamycin users and 8 815 441 new penicillin users eligible for the analysis. The stratified analysis of 807 769 matched pairs included 840 events among clindamycin users and 290 among penicillin users (hazard ratio 2.90, 95% confidence interval 2.53, 3.31). This evaluation produced an expected result and identified several potential enhancements to the Propensity Score Matching tool. This study has important limitations. CDI risk may have been related to factors other than the inherent properties of the drugs, such as duration of use or subsequent exposures. Copyright © 2018 John Wiley & Sons, Ltd.

Assessing the independent contribution of maternal educational expectations to children's educational attainment in early adulthood: a propensity score matching analysis.

PubMed

Pingault, Jean Baptiste; Côté, Sylvana M; Petitclerc, Amélie; Vitaro, Frank; Tremblay, Richard E

2015-01-01

Parental educational expectations have been associated with children's educational attainment in a number of long-term longitudinal studies, but whether this relationship is causal has long been debated. The aims of this prospective study were twofold: 1) test whether low maternal educational expectations contributed to failure to graduate from high school; and 2) compare the results obtained using different strategies for accounting for confounding variables (i.e. multivariate regression and propensity score matching). The study sample included 1,279 participants from the Quebec Longitudinal Study of Kindergarten Children. Maternal educational expectations were assessed when the participants were aged 12 years. High school graduation—measuring educational attainment—was determined through the Quebec Ministry of Education when the participants were aged 22-23 years. Findings show that when using the most common statistical approach (i.e. multivariate regressions to adjust for a restricted set of potential confounders) the contribution of low maternal educational expectations to failure to graduate from high school was statistically significant. However, when using propensity score matching, the contribution of maternal expectations was reduced and remained statistically significant only for males. The results of this study are consistent with the possibility that the contribution of parental expectations to educational attainment is overestimated in the available literature. This may be explained by the use of a restricted range of potential confounding variables as well as the dearth of studies using appropriate statistical techniques and study designs in order to minimize confounding. Each of these techniques and designs, including propensity score matching, has its strengths and limitations: A more comprehensive understanding of the causal role of parental expectations will stem from a convergence of findings from studies using different techniques and designs.

Analgesic Choice in Management of Rib Fractures: Paravertebral Block or Epidural Analgesia?

PubMed

Malekpour, Mahdi; Hashmi, Ammar; Dove, James; Torres, Denise; Wild, Jeffrey

2017-06-01

Rib fractures are commonly encountered in the setting of trauma. The aim of this study was to assess the association between the clinical outcome of rib fracture and epidural analgesia (EA) versus paravertebral block (PVB) using the National Trauma Data Bank (NTDB). Using the 2011 and 2012 versions of the NTDB, we retrieved completed records for all patients above 18 years of age who were admitted with rib fractures. Primary outcome was in-hospital mortality. Secondary outcomes were length of stay (LOS), intensive care unit (ICU) admission, ICU LOS, mechanical ventilation, duration of mechanical ventilation, development of pneumonia, and development of any other complication. Clinical outcomes were first compared between propensity score-matched EA and PVB patients. Then, EA and PVB patients were combined into the procedure group and the outcomes were compared with propensity score-matched patients that received neither intervention (no-procedure group). A total of 194,766 patients were included in the study with 1073 patients having EA, 1110 patients having PVB, and 192,583 patients having neither procedure. After propensity score matching, comparison of primary and secondary outcomes between EA and PVB patients showed no difference. Comparison of propensity score-matched procedure and no-procedure patients showed prolonged LOS and more frequent ICU admissions in patients receiving a procedure (both P < .0001), yet having no procedure was associated with a significantly increased odds of mortality (odds ratio: 2.25; 95% confidence interval, 1.14-3.84; P = .002). Using the NTDB, EA and PVB were not found to be significantly different in management of rib fractures. There was an association between use of a block and improved outcome, but this could be explained by selection of healthier patients to receive a block. Prospective study of this association is recommended.

Hemiarch Reconstruction Vs Clamped Aortic Anastomosis for Concomitant Ascending Aortic Aneurysm.

PubMed

Sultan, Ibrahim; Bianco, Valentino; Yajzi, Ibrahim; Kilic, Arman; Dufendach, Keith; Cardounel, Arturo; Althouse, Andrew D; Masri, Ahmad; Navid, Forozan; Gleason, Thomas G

2018-05-03

Deep hypothermic circulatory arrest (DHCA) is often avoided in patients with concomitant ascending aortic pathology when treating other cardiac disease to avoid increased risk of morbidity and mortality. We hypothesized that the use of DHCA with retrograde cerebral perfusion (RCP) does not add incremental risk to ascending aortic replacement alone in the setting of concomitant cardiac surgery. 408 ascending aortic ± hemiarch replacements and aortic (root)/mitral/tricuspid valve(s), CABG, or MAZE procedures were performed for concomitant cardiac disease. DHCA with RCP was used for all hemiarch replacements or the ascending aorta was replaced with an aortic cross-clamp proximal to the innominate artery. Propensity-score matching was used to match similar ascending patients vs. hemiarch patients; the final propensity score matched patients on age, gender, BMI, previous heart surgery, pre-op aortic insufficiency, pre-op aortic stenosis, pre-op EF, and operative variables. Propensity-score matching yielded 116 pairs of Non-hemiarch patients vs. 116 hemiarch patients. Within the propensity-score matched cohort, there were no differences in postoperative stroke (1.7% vs. 3.4%, p = 0.41), new postoperative dialysis (6.0% vs. 5.2%, p = 0.78), postoperative renal insufficiency (27.6% vs. 19.8%, p = 0.16), 30-day mortality (2.6% vs. 3.4%, p = 0.701), or 1-year mortality (4.3% vs. 4.3%, p = 1.00) CONCLUSIONS: Hemiarch replacement using DHCA with RCP does not increase the risk of operative complications compared to a normothermic, clamped-distal aortic anastomosis, and therefore its use should not be limited when planning complex multi-procedural reconstructions during elective ascending thoracic aortic replacement with concomitant cardiac surgery. Copyright © 2018. Published by Elsevier Inc.

Patients with type 2 diabetes benefit from primary care-based disease management: a propensity score matched survival time analysis.

PubMed

Drabik, Anna; Büscher, Guido; Thomas, Karsten; Graf, Christian; Müller, Dirk; Stock, Stephanie

2012-08-01

This study aimed to assess the impact of a nationwide German diabetes mellitus disease management program (DMP) on survival time and costs in comparison to routine care. The authors conducted a retrospective observational cohort study using routine administration data from Germany's largest sickness fund to identify insured suffering from diabetes in 2002. A total of 95,443 insured with type 2 diabetes mellitus who were born before January 1, 1962 met the defined inclusion criteria, resulting in 19,888 pairs of DMP participants and nonparticipants matched for socioeconomic and health status using propensity score matching methods. This is the first time propensity score matching has been used to evaluate a survival benefit of DMPs. In the time frame analyzed (3 years), mean survival time for the DMP group was 1045 days vs. 985 days for the routine care group (P<0.001). Mean daily hospital and total costs (including DMP administration and medical costs) were lower for the DMP group in the case of deceased insureds (92€ vs. 139€ and 122€ vs. 169€, respectively) as well as for censored observations (6€ vs. 7€ and 12.9€ vs. 13.4€, respectively). Mean daily drug costs were slightly lower for deceased insured in the DMP group (difference 0.6€), while no identifiable difference was found for censored observations. In this study, insured who were enrolled in a DMP for diabetes mellitus in the German Statutory Health Insurance showed a significant benefit in survival time. They also incurred lower costs compared to propensity score matched insured in routine care.

The Incidence of Complications in Single-stage Endoscopic Stone Removal for Patients with Common Bile Duct Stones: A Propensity Score Analysis.

PubMed

Saito, Hirokazu; Kadono, Yoshihiro; Kamikawa, Kentaro; Urata, Atsushi; Imamura, Haruo; Matsushita, Ikuo; Kakuma, Tatsuyuki; Tada, Shuji

2018-02-15

Objective Single-stage endoscopic stone removal for choledocholithiasis is an advantageous approach because it is associated with a shorter hospital stay; however, few studies have reported the incidence of complications related to this procedure in detail. The aim of this study was to examine the incidence of complications and efficacy of this procedure. Methods This retrospective study investigated the incidence of complications in 345 patients with naive papilla who underwent therapeutic endoscopic retrograde cholangiopancreatography (ERCP) for choledocholithiasis at three institutions between April 2014 and March 2016 by a propensity score analysis. The efficacy of single-stage endoscopic stone removal was assessed based on a hospital stay of within 7 days and the number of ERCP attempts. Results Among 114 patients who underwent single-stage endoscopic stone removal, 15 patients (13.2%) experienced complications. Among the remaining 231 patients in the two-stage endoscopic stone removal group, complications were observed in 17 patients (7.4%). The propensity score analysis, which was adjusted for confounding factors, revealed that single-stage endoscopic stone removal was not a significant risk factor for complications (p=0.52). In patients in whom >10 min was required for deep cannulation, single-stage endoscopic stone removal was not a significant risk factor for complications in the propensity score analysis (p=0.37). In the single-stage group, the proportion of patients with a hospital stay of within 7 days was significantly higher and the number of ERCP attempts was significantly lower in comparison to the two-stage group (p <0.0001 and <0.0001, respectively). Conclusion Single-stage endoscopic stone removal did not increase the incidence of complications associated with ERCP and was effective for reducing the hospital stay and the number of ERCP attempts.

The Incidence of Complications in Single-stage Endoscopic Stone Removal for Patients with Common Bile Duct Stones: A Propensity Score Analysis

PubMed Central

Saito, Hirokazu; Kadono, Yoshihiro; Kamikawa, Kentaro; Urata, Atsushi; Imamura, Haruo; Matsushita, Ikuo; Kakuma, Tatsuyuki; Tada, Shuji

2017-01-01

Objective Single-stage endoscopic stone removal for choledocholithiasis is an advantageous approach because it is associated with a shorter hospital stay; however, few studies have reported the incidence of complications related to this procedure in detail. The aim of this study was to examine the incidence of complications and efficacy of this procedure. Methods This retrospective study investigated the incidence of complications in 345 patients with naive papilla who underwent therapeutic endoscopic retrograde cholangiopancreatography (ERCP) for choledocholithiasis at three institutions between April 2014 and March 2016 by a propensity score analysis. The efficacy of single-stage endoscopic stone removal was assessed based on a hospital stay of within 7 days and the number of ERCP attempts. Results Among 114 patients who underwent single-stage endoscopic stone removal, 15 patients (13.2%) experienced complications. Among the remaining 231 patients in the two-stage endoscopic stone removal group, complications were observed in 17 patients (7.4%). The propensity score analysis, which was adjusted for confounding factors, revealed that single-stage endoscopic stone removal was not a significant risk factor for complications (p=0.52). In patients in whom >10 min was required for deep cannulation, single-stage endoscopic stone removal was not a significant risk factor for complications in the propensity score analysis (p=0.37). In the single-stage group, the proportion of patients with a hospital stay of within 7 days was significantly higher and the number of ERCP attempts was significantly lower in comparison to the two-stage group (p <0.0001 and <0.0001, respectively). Conclusion Single-stage endoscopic stone removal did not increase the incidence of complications associated with ERCP and was effective for reducing the hospital stay and the number of ERCP attempts. PMID:29151506

Atrial natriuretic peptide therapy and in-hospital mortality in acute myocardial infarction patients undergoing percutaneous coronary intervention.

PubMed

Isogai, Toshiaki; Matsui, Hiroki; Tanaka, Hiroyuki; Fushimi, Kiyohide; Yasunaga, Hideo

2016-11-01

Atrial natriuretic peptide (ANP) therapy has been reported to have beneficial effects in patients with acute myocardial infarction (AMI); however, its impact on in-hospital mortality remains unclear. This study aimed to investigate the effects of ANP therapy on in-hospital mortality in AMI patients undergoing percutaneous coronary intervention (PCI). This was a retrospective cohort study using the Diagnosis Procedure Combination inpatient database in Japan. We identified AMI patients who underwent PCI with stent implantation on the day of admission, between 2010 and 2014. We compared 30-day in-hospital mortality between patients who started ANP therapy on the day of admission (ANP group) and those who received no ANP therapy during hospitalization (control group), using propensity score and instrumental variable methods. Of 60,592 eligible patients (8189 ANP group, 52,403 control group) from 850 hospitals, 1:1 propensity score matching created 8027 pairs. There was no significant difference in 30-day in-hospital mortality between the ANP and control groups (3.4% vs. 3.8%, respectively; p=0.162; risk difference, -0.42%; 95% confidence interval [CI], -1.00% to 0.15%) in the propensity score-matched cohort. Logistic regression analysis with adjustment for propensity score deciles found no significant association between ANP therapy and 30-day in-hospital mortality (odds ratio, 0.99; 95% CI, 0.82 to 1.19). Instrumental variable analysis also showed no significant association between ANP therapy and 30-day in-hospital mortality (risk difference, -0.59%; 95% CI, -1.24% to 0.05%). This study found no significant association between ANP therapy and in-hospital mortality in AMI patients undergoing PCI. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Weight Loss Surgery Reduces Healthcare Resource Utilization and All-Cause Inpatient Mortality in Morbid Obesity: a Propensity-Matched Analysis.

PubMed

Krishna, Somashekar G; Rawal, Varun; Durkin, Claire; Modi, Rohan M; Hinton, Alice; Cruz-Monserrate, Zobeida; Conwell, Darwin L; Hussan, Hisham

2018-06-21

There is a lack of population studies evaluating the impact of bariatric surgery (BRS) on all-cause inpatient mortality. We sought to determine the impact of prior BRS on all-cause mortality and healthcare utilization in hospitalized patients. We analyzed the National Inpatient Sample database from 2007 to 2013. Participants were adult (≥ 18 years) inpatients admitted with a diagnosis of morbid obesity or a history of BRS. Propensity score-matched analyses were performed to compare mortality and healthcare resource utilization (hospital length of stay and cost). There were 9,044,103 patient admissions with morbid obesity and 1,066,779 with prior BRS. A propensity score-matched cohort analysis demonstrated that prior BRS was associated with decreased mortality (OR = 0.58; 95% CI [0.54, 0.63]), shorter length of stay (0.59 days; P < 0.001), and lower hospital costs ($2152; P < 0.001) compared to morbid obesity. A subgroup of propensity score-matched analysis among patients with high-risk of mortality (leading ten causes of mortality in morbid obesity) revealed a consistently significant reduction in odds of mortality for patients with prior BRS (OR = 0.82; 95% CI [0.72, 0.92]). Hospitalized patients with a history of BRS have lower all-cause mortality and healthcare resource utilization compared to those who are morbidly obese. These observations support the continued application of BRS as an effective and resource-conscious treatment for morbid obesity.

Prehospital amiodarone may increase the incidence of acute respiratory distress syndrome among patients at risk.

PubMed

Karnatovskaia, Lioudmila V; Festic, Emir; Gajic, Ognjen; Carter, Rickey E; Lee, Augustine S

2012-10-01

Amiodarone has been implicated as a risk factor for acute lung injury (ALI) and acute respiratory distress syndrome (ARDS) when used in the hospital. This study aims to estimate whether prehospital amiodarone also increases the risk of ALI/ARDS. Adult patients admitted to 22 centers with at least 1 risk factor for developing ALI were recruited. In a secondary analysis of this cohort, the prehospital use of amiodarone was documented on admission, and the patients followed for the primary outcome of ALI and secondary outcomes of ARDS, the need for invasive ventilation, and mortality. Dose/duration of amiodarone therapy was not available. Propensity matching was performed to account for imbalances in being assigned to amiodarone. The adjusted risk for ALI/ARDS was then estimated from a conditional logistic regression model of this propensity-matched set. Forty of 5584 patients were on amiodarone at the time of hospitalization; of those, 6 developed ALI, with 5 progressing to ARDS. In comparison, 371 patients not on amiodarone developed ALI, with 224 having ARDS. After propensity score matching, the prehospital use of amiodarone was not statistically associated with an increased risk for all ALI (odds ratio [OR], 1.8; 95% confidence interval [CI], 0.7-5.0; P = .25), invasive ventilation (OR, 1.9; 95% CI, 1.0-3.6; P = .059), or in-hospital mortality (OR, 1.2; 95% CI, 0.5-2.9; P = .75); but its use appeared to significantly increase the risk for ARDS (OR 3.8; 95% CI, 1.1-13.1; P = .036). Prehospital use of amiodarone may independently increase the risk for ARDS in patients who have at least 1 predisposing condition for ALI. Copyright © 2012 Elsevier Inc. All rights reserved.

Short-Term Effects of Grade Retention on the Growth Rate of Woodcock-Johnson III Broad Math and Reading Scores

PubMed Central

Wu, Wei; West, Stephen G.; Hughes, Jan N.

2008-01-01

We investigated the effects of grade retention in first grade on the growth of the Woodcock-Johnson broad mathematics and reading scores over three years using linear growth curve modeling on an academically at-risk sample. A large sample (n = 784) of first grade children who were at risk for retention were initially identified based on low literacy scores. Scores representing propensity for retention were constructed based on 72 variables collected in comprehensive baseline testing in first grade. We closely matched 97 pairs of retained and promoted children based on their propensity scores using optimal matching procedures. This procedure adjusted for baseline differences between the retained and promoted children. We found that grade retention decreased the growth rate of mathematical skills but had no significant effect on reading skills. In addition, several potential moderators of the effect of retention on growth of mathematical and reading skills were identified including limited English language proficiency and children's conduct problems. PMID:19083352

Short-term effects of grade retention on the growth rate of Woodcock-Johnson III broad math and reading scores.

PubMed

Wu, Wei; West, Stephen G; Hughes, Jan N

2008-02-01

We investigated the effects of grade retention in first grade on the growth of the Woodcock-Johnson broad mathematics and reading scores over three years using linear growth curve modeling on an academically at-risk sample. A large sample (n=784) of first grade children who were at risk for retention was initially identified based on low literacy scores. Scores representing propensity for retention were constructed based on 72 variables collected in comprehensive baseline testing in first grade. We closely matched 97 pairs of retained and promoted children based on their propensity scores using optimal matching procedures. This procedure adjusted for baseline differences between the retained and promoted children. We found that grade retention decreased the growth rate of mathematical skills but had no significant effect on reading skills. In addition, several potential moderators of the effect of retention on growth of mathematical and reading skills were identified including limited English language proficiency and children's conduct problems.

Validation of the Australian Propensity for Angry Driving Scale (Aus-PADS).

PubMed

Leal, Nerida L; Pachana, Nancy A

2009-09-01

The present study used a university sample to assess the test-retest reliability and validity of the Australian Propensity for Angry Driving Scale (Aus-PADS). The scale has stability over time, and convergent validity was established, as Aus-PADS scores correlated significantly with established anger and impulsivity measures. Discriminant validity was also established, as Aus-PADS scores did not correlate with Venturesomeness scores. The Aus-PADS has demonstrated criterion validity, as scores were correlated with behavioural measures, such as yelling at other drivers, gesturing at other drivers, and feeling angry but not doing anything. Aus-PADS scores reliably predicted the frequency of these behaviours over and above other study variables. No significant relationship between aggressive driving and crash involvement was observed. It was concluded that the Aus-PADS is a reliable and valid tool appropriate for use in Australian research, and that the potential relationship between aggressive driving and crash involvement warrants further investigation with a more representative (and diverse) driver sample.

Mannitol and Outcome in Intracerebral Hemorrhage: Propensity Score and Multivariable Intensive Blood Pressure Reduction in Acute Cerebral Hemorrhage Trial 2 Results.

PubMed

Wang, Xia; Arima, Hisatomi; Yang, Jie; Zhang, Shihong; Wu, Guojun; Woodward, Mark; Muñoz-Venturelli, Paula; Lavados, Pablo M; Stapf, Christian; Robinson, Thompson; Heeley, Emma; Delcourt, Candice; Lindley, Richard I; Parsons, Mark; Chalmers, John; Anderson, Craig S

2015-10-01

Mannitol is often used to reduce cerebral edema in acute intracerebral hemorrhage but without strong supporting evidence of benefit. We aimed to determine the impact of mannitol on outcome among participants of the Intensive Blood Pressure Reduction in Acute Cerebral Hemorrhage Trial (INTERACT2). INTERACT2 was an international, open, blinded end point, randomized controlled trial of 2839 patients with spontaneous intracerebral hemorrhage (<6 hours) and elevated systolic blood pressure allocated to intensive (target systolic blood pressure, <140 mm Hg within 1 hour) or guideline-recommended (target systolic blood pressure, <180 mm Hg) blood pressure-lowering treatment. Propensity score and multivariable analyses were performed to investigate the relationship between mannitol treatment (within 7 days) and poor outcome, defined by death or major disability on the modified Rankin Scale score (3-6) at 90 days. There was no significant difference in poor outcome between mannitol (n=1533) and nonmannitol (n=993) groups: propensity score-matched odds ratio of 0.90 (95% confidence interval, 0.75-1.09; P=0.30) and multivariable odds ratio of 0.87 (95% confidence interval, 0.71-1.07; P=0.18). Although a better outcome was suggested in patients with larger (≥15 mL) than those with smaller (<15 mL) baseline hematomas who received mannitol (odds ratio, 0.52 [95% confidence interval, 0.35-0.78] versus odds ratio, 0.91 [95% confidence interval, 0.72-1.15]; P homogeneity<0.03 in propensity score analyses), the association was not consistent in analyses across other cutoff points (≥10 and ≥20 mL) and for differing grades of neurological severity. Mannitol was not associated with excess serious adverse events. Mannitol seems safe but might not improve outcome in patients with acute intracerebral hemorrhage. URL: http://www.clinicaltrials.gov. Unique identifier: NCT00716079. © 2015 American Heart Association, Inc.

Attributable Healthcare Resource Utilization and Costs for Patients With Primary and Recurrent Clostridium difficile Infection in the United States.

PubMed

Zhang, Dongmu; Prabhu, Vimalanand S; Marcella, Stephen W

2018-04-17

The economic burden of Clostridium difficile infection (CDI), the leading cause of nosocomial infectious diarrhea, is not well understood. The objective of this study was to estimate the healthcare resource utilization (HCRU) and costs attributable to primary CDI and recurrent CDI (rCDI). This is a database (MarketScan) study. Patients without CDI were matched 1:1 by propensity score to those with primary CDI but no recurrences to obtain HCRU and costs attributable to primary CDI. Patients with primary CDI but no recurrences were matched 1:1 by propensity score to those with primary CDI plus 1 recurrence in order to obtain HCRU and costs attributable to rCDI. Adjusted estimates for incremental cumulative hospitalized days and healthcare costs over a 6-month follow-up period were obtained by generalized linear models with a Poisson or gamma distribution and a log link. Bootstrapping was used to obtain 95% confidence intervals (CIs). A total of 55504 eligible CDI patients were identified. Approximately 25% of these CDI patients had rCDI. The cumulative hospitalized days attributable to primary CDI and rCDI over the 6-month follow-up period were 5.20 days (95% CI, 5.01-5.39) and 1.95 days (95% CI, 1.48-2.43), respectively. The healthcare costs attributable to primary CDI and rCDI over the 6-month follow-up period were $24205 (95% CI, $23436-$25013) and $10580 (95% CI, $8849-$12446), respectively. The HCRU and costs attributable to primary CDI and rCDI are quite substantial. It is necessary to reduce the burden of CDI, especially rCDI.

Attributable cost and length of stay for central line-associated bloodstream infections.

PubMed

Goudie, Anthony; Dynan, Linda; Brady, Patrick W; Rettiganti, Mallikarjuna

2014-06-01

Central line-associated bloodstream infections (CLABSI) are common types of hospital-acquired infections associated with high morbidity. Little is known about the attributable cost and length of stay (LOS) of CLABSI in pediatric inpatient settings. We determined the cost and LOS attributable to pediatric CLABSI from 2008 through 2011. A propensity score-matched case-control study was performed. Children <18 years with inpatient discharges in the Nationwide Inpatient Sample databases from the Healthcare Cost and Utilization Project from 2008 to 2011 were included. Discharges with CLABSI were matched to those without CLABSI by age, year, and high dimensional propensity score (obtained from a logistic regression of CLABSI status on patient characteristics and the presence or absence of 262 individual clinical classification software diagnoses). Our main outcome measures were estimated costs obtained from cost-to-charge ratios and LOS for pediatric discharges. The mean attributable cost and LOS between matched CLABSI cases (1339) and non-CLABSI controls (2678) was $55 646 (2011 dollars) and 19 days, respectively. Between 2008 and 2011, the rate of pediatric CLABSI declined from 1.08 to 0.60 per 1000 (P < .001). Estimates of mean costs of treating patients with CLABSI declined from $111 852 to $98 621 (11.8%; P < .001) over this period, but cost of treating matched non-CLABSI patients remained constant at ∼$48 000. Despite significant improvement in rates, CLABSI remains a burden on patients, families, and payers. Continued attention to CLABSI-prevention initiatives and lower-cost CLABSI care management strategies to support high-value pediatric care delivery is warranted. Copyright © 2014 by the American Academy of Pediatrics.

Anticoagulant vs. antiplatelet therapy in patients with cryptogenic stroke and patent foramen ovale: an individual participant data meta-analysis.

PubMed

Kent, David M; Dahabreh, Issa J; Ruthazer, Robin; Furlan, Anthony J; Weimar, Christian; Serena, Joaquín; Meier, Bernhard; Mattle, Heinrich P; Di Angelantonio, Emanuele; Paciaroni, Maurizio; Schuchlenz, Herwig; Homma, Shunichi; Lutz, Jennifer S; Thaler, David E

2015-09-14

The preferred antithrombotic strategy for secondary prevention in patients with cryptogenic stroke (CS) and patent foramen ovale (PFO) is unknown. We pooled multiple observational studies and used propensity score-based methods to estimate the comparative effectiveness of oral anticoagulation (OAC) compared with antiplatelet therapy (APT). Individual participant data from 12 databases of medically treated patients with CS and PFO were analysed with Cox regression models, to estimate database-specific hazard ratios (HRs) comparing OAC with APT, for both the primary composite outcome [recurrent stroke, transient ischaemic attack (TIA), or death] and stroke alone. Propensity scores were applied via inverse probability of treatment weighting to control for confounding. We synthesized database-specific HRs using random-effects meta-analysis models. This analysis included 2385 (OAC = 804 and APT = 1581) patients with 227 composite endpoints (stroke/TIA/death). The difference between OAC and APT was not statistically significant for the primary composite outcome [adjusted HR = 0.76, 95% confidence interval (CI) 0.52-1.12] or for the secondary outcome of stroke alone (adjusted HR = 0.75, 95% CI 0.44-1.27). Results were consistent in analyses applying alternative weighting schemes, with the exception that OAC had a statistically significant beneficial effect on the composite outcome in analyses standardized to the patient population who actually received APT (adjusted HR = 0.64, 95% CI 0.42-0.99). Subgroup analyses did not detect statistically significant heterogeneity of treatment effects across clinically important patient groups. We did not find a statistically significant difference comparing OAC with APT; our results justify randomized trials comparing different antithrombotic approaches in these patients. Published on behalf of the European Society of Cardiology. All rights reserved. © The Author 2015. For permissions please email: journals.permissions@oup.com.

Medication persistence and discontinuation of rivaroxaban and dabigatran etexilate among patients with non-valvular atrial fibrillation.

PubMed

Nelson, Winnie W; Song, Xue; Thomson, Erin; Smith, David M; Coleman, Craig I; Damaraju, C V; Schein, Jeffrey R

2015-01-01

To compare real-world persistence and discontinuation among non-valvular atrial fibrillation (NVAF) patients on rivaroxaban and dabigatran in the US. A large nationally representative US claims database was used to conduct a retrospective cohort analysis of patients with NVAF on rivaroxaban or dabigatran between October 2010 and March 2013. The index date was the date of the first prescription of rivaroxaban or dabigatran. All patients had ≥6 months of data prior to the index date and were followed until the earliest of inpatient death, end of continuous enrollment, or end of the study period. Rivaroxaban patients were matched 1:1 with dabigatran patients using the propensity score matching technique. Cox proportional hazards models were employed to estimate the adjusted hazard ratios (aHRs) of non-persistence and discontinuation. Persistence was defined as absence of a refill gap of ≥60 days. Discontinuation was defined as no additional refill for at least 90 days and until the end of follow-up. A total of 30,337 NVAF patients on rivaroxaban or dabigatran met the study criteria. All 7259 rivaroxaban patients were matched 1:1 to dabigatran patients. Compared with dabigatran users, rivaroxaban patients were 11% less likely to become non-persistent with therapy (aHR: 0.89, 95% CI 0.84-0.95) and 29% less likely to discontinue therapy (aHR: 0.71, 95% CI 0.66-0.77). Claims data are subject to miscoding and inaccuracies. Refill data may not fully reflect actual medication taken. Confounding may remain even after propensity score matching and additional adjustments in model. Longer follow-up may produce more precise estimates of persistence and discontinuation. This matched cohort analysis indicated that, compared to dabigatran, rivaroxaban was associated with better persistence and lower rates of discontinuation.

Medication persistence and discontinuation of rivaroxaban versus warfarin among patients with non-valvular atrial fibrillation.

PubMed

Nelson, Winnie W; Song, Xue; Coleman, Craig I; Thomson, Erin; Smith, David M; Damaraju, C V; Schein, Jeffrey R

2014-12-01

To compare real-world persistence and discontinuation among non-valvular atrial fibrillation (NVAF) patients on rivaroxaban and warfarin in the US. A large nationally representative US claims database was used to conduct a retrospective cohort analysis of patients with NVAF treated with rivaroxaban or warfarin from 1 July 2010 through 31 March 2013. Index date was the date of the first prescription of rivaroxaban or warfarin. All patients were followed until the earliest of inpatient death, end of continuous enrollment, or end of study period. Rivaroxaban patients were matched 1:1 by propensity scores. Medication persistence was defined as absence of refill gap of ≥ 60 days. Discontinuation was defined as no additional refill for at least 90 days and until the end of follow-up. Cox proportional hazards models were estimated to examine the adjusted hazard ratios (aHRs) of rivaroxaban vs. warfarin on non-persistence and discontinuation. A total of 32,886 NVAF patients on rivaroxaban or warfarin met the study inclusion criteria. Each of the 7259 rivaroxaban patients identified were matched 1:1 to warfarin patients. Patients on rivaroxaban had a significantly better rate of persistence (aHR: 0.63, 95% CI 0.59-0.68) and lower rate of discontinuation (aHR: 0.54, 95% CI 0.49-0.58) compared to warfarin recipients. Claims data may have contained inaccuracies and miscoding. Confounding may remain even after propensity score matching and additional adjustments in model. Refill data may not fully reflect actual medication use. Longer follow-up may produce more precise estimates of persistence and discontinuation. This matched cohort analysis indicated that rivaroxaban was associated with significantly higher medication persistence and lower discontinuation rates compared to warfarin.

Statins Reduces the Risk of Dementia in Patients with Late-Onset Depression: A Retrospective Cohort Study.

PubMed

Yang, Ya-Hsu; Teng, Hao-Wei; Lai, Yen-Ting; Li, Szu-Yuan; Lin, Chih-Ching; Yang, Albert C; Chan, Hsiang-Lin; Hsieh, Yi-Hsuan; Lin, Chiao-Fan; Hsu, Fu-Ying; Liu, Chih-Kuang; Liu, Wen-Sheng

2015-01-01

Patients with late-onset depression (LOD) have been reported to run a higher risk of subsequent dementia. The present study was conducted to assess whether statins can reduce the risk of dementia in these patients. We used the data from National Health Insurance of Taiwan during 1996-2009. Standardized Incidence Ratios (SIRs) were calculated for LOD and subsequent dementia. The criteria for LOD diagnoses included age ≥65 years, diagnosis of depression after 65 years of age, at least three service claims, and treatment with antidepressants. The time-dependent Cox proportional hazards model was applied for multivariate analyses. Propensity scores with the one-to-one nearest-neighbor matching model were used to select matching patients for validation studies. Kaplan-Meier curve estimate was used to measure the group of patients with dementia living after diagnosis of LOD. Totally 45,973 patients aged ≥65 years were enrolled. The prevalence of LOD was 12.9% (5,952/45,973). Patients with LOD showed to have a higher incidence of subsequent dementia compared with those without LOD (Odds Ratio: 2.785; 95% CI 2.619-2.958). Among patients with LOD, lipid lowering agent (LLA) users (for at least 3 months) had lower incidence of subsequent dementia than non-users (Hazard Ratio = 0.781, 95% CI 0.685-0.891). Nevertheless, only statins users showed to have reduced risk of dementia (Hazard Ratio = 0.674, 95% CI 0.547-0.832) while other LLAs did not, which was further validated by Kaplan-Meier estimates after we used the propensity scores with the one-to-one nearest-neighbor matching model to control the confounding factors. Statins may reduce the risk of subsequent dementia in patients with LOD.

Mortality of Department of Veterans Affairs patients undergoing coronary revascularization in private sector hospitals.

PubMed

Vaughan-Sarrazin, Mary S; Wakefield, Bonnie; Rosenthal, Gary E

2007-10-01

A limitation of studies comparing outcomes of Veterans Affairs (VA) and private sector hospitals is uncertainty about the methods of accounting for risk factors in VA populations. This study estimates whether use of VA services is a marker for increased risk by comparing outcomes of VA users and other patients undergoing coronary revascularization in private sector hospitals. Males 67 years and older undergoing coronary artery bypass graft (CABG; n=687,936) surgery or percutaneous coronary intervention (PCI; n=664,124) during 1996-2002 were identified from Medicare administrative data. Patients using VA services during the 2 years preceding the Medicare admission were identified using VA administrative files. Thirty-, 90-, and 365-day mortality were compared in patients who did and did not use VA services, adjusting for demographic and clinical risk factors using generalized estimating equations and propensity score analysis. Adjusted mortality after CABG was higher (p<.001) in VA users compared with nonusers at 30, 90, and 365 days: odds ratio (OR)=1.07 (95 percent confidence interval [CI], 1.03-1.11), 1.07 (95 percent CI, 1.04-1.10), and 1.09 (95 percent CI, 1.06-1.12), respectively. For PCI, mortality at 30 and 90 days was similar (p>.05) for VA users and nonusers, but was higher at 365 days (OR=1.09; 95 percent CI, 1.06-1.12). The increased risk of death in VA users was limited to patients with service-connected disabilities or low incomes. Odds of death for VA users were slightly lower using samples matched by propensity scores. A small difference in risk-adjusted outcomes for VA users and nonusers undergoing revascularization in private sector hospitals was found. This difference reflects unmeasured severity in VA users undergoing revascularization in private sector hospitals.

Repeated Vaccination Does Not Appear to Impact Upon Influenza Vaccine Effectiveness Against Hospitalization With Confirmed Influenza.

PubMed

Cheng, Allen C; Macartney, Kristine K; Waterer, Grant W; Kotsimbos, Tom; Kelly, Paul M; Blyth, Christopher C

2017-06-01

Annual influenza vaccine is recommended for those at greatest risk of severe influenza infection. Recent reports of a negative impact of serial influenza vaccination on vaccine effectiveness (VE) raises concerns about the recommendation for annual influenza vaccines, particularly in persons at greatest risk. The Influenza Complications Alert Network (FluCAN) is an Australian hospital-based sentinel surveillance program. In this observational study, cases were defined as subjects aged >9 years admitted with influenza confirmed by polymerase chain reaction. Controls were subjects with acute respiratory illness testing negative for influenza. Propensity scores were used to adjust for the likelihood of being vaccinated. VE was calculated as 1 - adjusted odds ratio of vaccination in cases compared with test-negative controls. Over 2010-2015, 6223 cases and 6505 controls were hospitalized with confirmed influenza and influenza test-negative acute respiratory illness, respectively. Following stratification by quintile of propensity score, site, and year, VE was estimated to be 43% (95% confidence interval [CI], 37%-49%) overall. VE was estimated to be 51% (95% CI, 45%-57%) in those vaccinated in both the current and previous season, compared with 33% (95% CI, 17%-47%) vaccinated in the current season only and 35% (95% CI, 21%-46%) in the previous season only. Similar results were observed for influenza A/H1N1, influenza A/H3N2, and influenza B strains. Vaccination in both the current and previous seasons was associated with a higher VE against hospitalization with influenza than vaccination in either single season. These findings reinforce current recommendations for annual influenza vaccination, particularly those at greatest risk of influenza disease. © The Author 2017. Published by Oxford University Press for the Infectious Diseases Society of America. All rights reserved. For permissions, e-mail: journals.permissions@oup.com

Fluoroquinolone use and risk of aortic aneurysm and dissection: nationwide cohort study

PubMed Central

Inghammar, Malin; Svanström, Henrik

2018-01-01

Abstract Objective To investigate whether oral fluoroquinolone use is associated with an increased risk of aortic aneurysm or dissection. Design Nationwide historical cohort study using linked register data on patient characteristics, filled prescriptions, and cases of aortic aneurysm or dissection. Setting Sweden, July 2006 to December 2013. Participants 360 088 treatment episodes of fluoroquinolone use (78%ciprofloxacin) and propensity score matched comparator episodes of amoxicillin use (n=360 088). Main outcome measures Cox regression was used to estimate hazard ratios for a first diagnosis of aortic aneurysm or dissection, defined as admission to hospital or emergency department for, or death due to, aortic aneurysm or dissection, within 60 days from start of treatment. Results Within the 60 day risk period, the rate of aortic aneurysm or dissection was 1.2 cases per 1000 person years among fluoroquinolone users and 0.7 cases per 1000 person years among amoxicillin users. Fluoroquinolone use was associated with an increased risk of aortic aneurysm or dissection (hazard ratio 1.66 (95% confidence interval 1.12 to 2.46)), with an estimated absolute difference of 82 (95% confidence interval 15 to 181) cases of aortic aneurysm or dissection by 60 days per 1 million treatment episodes. In a secondary analysis, the hazard ratio for the association with fluoroquinolone use was 1.90 (1.22 to 2.96) for aortic aneurysm and 0.93 (0.38 to 2.29) for aortic dissection. Conclusions In a propensity score matched cohort, fluoroquinolone use was associated with an increased risk of aortic aneurysm or dissection. This association appeared to be largely driven by aortic aneurysm. PMID:29519881

Attributable Healthcare Resource Utilization and Costs for Patients With Primary and Recurrent Clostridium difficile Infection in the United States

PubMed Central

Zhang, Dongmu; Prabhu, Vimalanand S; Marcella, Stephen W

2018-01-01

Abstract Background The economic burden of Clostridium difficile infection (CDI), the leading cause of nosocomial infectious diarrhea, is not well understood. The objective of this study was to estimate the healthcare resource utilization (HCRU) and costs attributable to primary CDI and recurrent CDI (rCDI). Methods This is a database (MarketScan) study. Patients without CDI were matched 1:1 by propensity score to those with primary CDI but no recurrences to obtain HCRU and costs attributable to primary CDI. Patients with primary CDI but no recurrences were matched 1:1 by propensity score to those with primary CDI plus 1 recurrence in order to obtain HCRU and costs attributable to rCDI. Adjusted estimates for incremental cumulative hospitalized days and healthcare costs over a 6-month follow-up period were obtained by generalized linear models with a Poisson or gamma distribution and a log link. Bootstrapping was used to obtain 95% confidence intervals (CIs). Results A total of 55504 eligible CDI patients were identified. Approximately 25% of these CDI patients had rCDI. The cumulative hospitalized days attributable to primary CDI and rCDI over the 6-month follow-up period were 5.20 days (95% CI, 5.01–5.39) and 1.95 days (95% CI, 1.48–2.43), respectively. The healthcare costs attributable to primary CDI and rCDI over the 6-month follow-up period were $24205 (95% CI, $23436–$25013) and $10580 (95% CI, $8849–$12446), respectively. Conclusions The HCRU and costs attributable to primary CDI and rCDI are quite substantial. It is necessary to reduce the burden of CDI, especially rCDI. PMID:29360950

Costs of accountable care organization participation for primary care providers: early stage results.

PubMed

Hofler, Richard A; Ortiz, Judith

2016-07-28

Little is known about the impact of joining an Accountable Care Organization (ACO) on primary care provider organization's costs. The purpose of this study was to determine whether joining an ACO is associated with an increase in a Rural Health Clinic's (RHC's) cost per visit. The analyses focused on cost per visit in 2012 and 2013 for RHCs that joined an ACO in 2012 and cost per visit in 2013 for RHCs that joined an ACO in 2013. The RHCs were located in nine states. Data were obtained from Medicare Cost Reports. The analysis was conducted taking a treatment effects approach where the treatment is joining an ACO. Propensity-score matching was employed to provide multiple single and pooled estimates of the average treatment effect on the treated. Four-hundred thirty four to 544 RHCs (depending on the type of analysis and the variables used) were used in the several analyses. Seven of the RHCs joined an ACO in 2012 and 14 joined an ACO in 2013. The mean cost per visit for RHCs that did not join an ACO rose 4.40 % from 2011 to 2012 whereas the mean cost per visit for RHCs that joined an ACO rose by triple: 13.5 %. All of the pooled estimates of the average treatment effect on the treated from the propensity-score matching showed that joining an ACO was associated with higher mean cost per visit. The range of the estimated mean cost per visit differences was $17.19 (p value = 0.00) to $25.19 (p value = 0.00). This study is one of the first to describe the cost of ACO participation from the perspective of primary care provider organizations. It appears that for at least one type of primary care provider - the RHC - there are substantial costs associated with ACO participation during the first two years.

Comparative effectiveness of switching to alternative tumour necrosis factor (TNF) antagonists versus switching to rituximab in patients with rheumatoid arthritis who failed previous TNF antagonists: the MIRAR Study.

PubMed

Gomez-Reino, Juan J; Maneiro, Jose Ramon; Ruiz, Jorge; Roselló, Rosa; Sanmarti, Raimon; Romero, Ana Belen

2012-11-01

To compare the effectiveness of switching to rituximab (RTX) with switching to alternative tumour necrosis factor (TNF) antagonists in patients with rheumatoid arthritis (RA) failing on TNF antagonists. A multicentre prospective 3-year observational study was performed in patients with RA treated with RTX or an alternative TNF antagonist. The baseline 28-joint disease activity score (DAS28) and Health Assessment Questionnaire (HAQ) score were compared with 6, 9 and 12 month values, adjusting for propensity score quintiles. Propensity scores were estimated for each patient using logistic regression with treatment as the dependent variable and baseline prior number of TNFs >1, years from diagnosis >5, extra-articular manifestations, previous toxicity, use of ≥2 disease-modifying antirheumatic drugs, age and sex as independent variables. 1124 patients were treated with either RTX (n=591, 52.6%) or alternative TNF antagonists (n=533, 47.4%). RTX-treated patients had longer disease duration (p=0.0001), larger numbers of previous TNF antagonists (p<0.0001) and tender and swollen joints (p<0.0001). There was no significant difference in the reduction in DAS28 at 6, 9 and 12 months between RTX-treated patients and those treated with TNF antagonists. However, the reduction in DAS28 was significantly different between RTX-treated patients and adalimumab/infliximab-treated patients (p=0.001 and p=0.05, respectively). There was a marginally significant difference at any time period in the proportion of patients achieving an improvement in the HAQ score of >0.22 (p=0.06). Optimal treatment for patients with RA failing on treatment with TNF antagonists may include RTX. This study suggests that the improvement in DAS28 is larger in patients treated with RTX than in those treated with monoclonal anti-TNF agents.

Improving employee productivity through improved health.

PubMed

Mitchell, Rebecca J; Ozminkowski, Ronald J; Serxner, Seth

2013-10-01

The objective of this study was to estimate productivity-related savings associated with employee participation in health promotion programs. Propensity score weighting and multiple regression techniques were used to estimate savings. These techniques were adjusted for demographic and health status differences between participants who engaged in one or more telephonic health management programs and nonparticipants who were eligible for but did not engage in these programs. Employees who participated in a program and successfully improved their health care or lifestyle showed significant improvements in lost work time. These employees saved an average of $353 per person per year. This reflects about 10.3 hours in additional productive time annually, compared with similar, but nonparticipating employees. Participating in health promotion programs can help improve productivity levels among employees and save money for their employers.

Risk of poor neonatal outcome at term after medically assisted reproduction: a propensity score-matched study.

PubMed

Ensing, Sabine; Abu-Hanna, Ameen; Roseboom, Tessa J; Repping, Sjoerd; van der Veen, Fulco; Mol, Ben Willem J; Ravelli, Anita C J

2015-08-01

To study risk of birth asphyxia and related morbidity among term singletons born after medically assisted reproduction (MAR). Population cohort study. Not applicable. A total of 1,953,932 term singleton pregnancies selected from a national registry for 1999-2011. None. Primary outcome Apgar score <4; secondary outcomes Apgar score <7, intrauterine fetal death, perinatal mortality, congenital anomalies, small for gestational age, asphyxia related morbidity, and cesarean delivery. The risks of birth asphyxia and related morbidity were calculated in women who conceived either through MAR or spontaneously (SC), with a subgroup analysis for in vitro fertilization (IVF). An additional propensity score matching analysis was performed with matching on multiple maternal baseline covariates (maternal age, ethnicity, socioeconomic status, parity, year of birth, and preexistent diseases). Each MAR pregnancy was matched to three SC controls. Relative to SC, the MAR singletons had an increased risk of adverse neonatal outcomes including Apgar score <4 (adjusted odds ratio [OR] 1.29; 95% CI, 1.14-1.46) and intrauterine fetal death (adjusted OR 1.61; 95% CI, 1.35-1.91). After propensity score matching, the risk of an Apgar score <4 was comparable between MAR and SC singletons (OR 0.99; 95% CI, 0.87-1.14). Cesarean delivery for both fetal distress and nonprogressive labor occurred more among MAR pregnancies compared with SC pregnancies. Term singletons conceived after MAR have an increased risk of morbidity related to birth asphyxia. Because this is mainly due to maternal characteristics, obstetric caregivers should be aware that the increased rates of cesareans reflect the behavior of women and physicians rather than increased perinatal complications. Copyright © 2015 American Society for Reproductive Medicine. Published by Elsevier Inc. All rights reserved.

MoRFPred-plus: Computational Identification of MoRFs in Protein Sequences using Physicochemical Properties and HMM profiles.

PubMed

Sharma, Ronesh; Bayarjargal, Maitsetseg; Tsunoda, Tatsuhiko; Patil, Ashwini; Sharma, Alok

2018-01-21

Intrinsically Disordered Proteins (IDPs) lack stable tertiary structure and they actively participate in performing various biological functions. These IDPs expose short binding regions called Molecular Recognition Features (MoRFs) that permit interaction with structured protein regions. Upon interaction they undergo a disorder-to-order transition as a result of which their functionality arises. Predicting these MoRFs in disordered protein sequences is a challenging task. In this study, we present MoRFpred-plus, an improved predictor over our previous proposed predictor to identify MoRFs in disordered protein sequences. Two separate independent propensity scores are computed via incorporating physicochemical properties and HMM profiles, these scores are combined to predict final MoRF propensity score for a given residue. The first score reflects the characteristics of a query residue to be part of MoRF region based on the composition and similarity of assumed MoRF and flank regions. The second score reflects the characteristics of a query residue to be part of MoRF region based on the properties of flanks associated around the given residue in the query protein sequence. The propensity scores are processed and common averaging is applied to generate the final prediction score of MoRFpred-plus. Performance of the proposed predictor is compared with available MoRF predictors, MoRFchibi, MoRFpred, and ANCHOR. Using previously collected training and test sets used to evaluate the mentioned predictors, the proposed predictor outperforms these predictors and generates lower false positive rate. In addition, MoRFpred-plus is a downloadable predictor, which makes it useful as it can be used as input to other computational tools. https://github.com/roneshsharma/MoRFpred-plus/wiki/MoRFpred-plus:-Download. Copyright © 2017 Elsevier Ltd. All rights reserved.

Paternal Race/Ethnicity and Birth Outcomes

PubMed Central

2008-01-01

Objectives. I sought to identify whether there were associations between paternal race/ethnicity and birth outcomes among infants with parents of same- and mixed-races/ethnicities. Methods. Using the National Center for Health Statistics 2001 linked birth and infant death file, I compared birth outcomes of infants of White mothers and fathers of different races/ethnicities by matching and weighting racial/ethnic groups following a propensity scoring approach so other characteristics were distributed identically. I applied the same analysis to infants of Black parents and infants with a Black mother and White father. Results. Variation in risk factors and outcomes was found in infants of White mothers by paternal race/ethnicity. After propensity score weighting, the disparities in outcomes by paternal or parental race/ethnicity could be largely attributed to nonracial parental characteristics. Infants whose paternal race/ethnicity was unreported on their birth certificates had the worst outcomes. Conclusions. The use of maternal race/ethnicity to refer to infant race/ethnicity in research is problematic. The effects of maternal race/ethnicity on birth outcomes are estimated to be much larger than that of paternal race/ethnicity after I controlled for all covariates. Not listing a father on the birth certificate had a strong association with outcomes, which might be a source of bias in existing data and a marker for identifying infants at risk. PMID:18445802

Adding moxifloxacin is associated with a shorter time to culture conversion in pulmonary tuberculosis.

PubMed

Wang, J-Y; Wang, J-T; Tsai, T-H; Hsu, C-L; Yu, C-J; Hsueh, P-R; Lee, L-N; Yang, P-C

2010-01-01

To investigate whether adding moxifloxacin (MXF) to the standard anti-tuberculosis regimen can shorten the time to sputum culture conversion in pulmonary tuberculosis (PTB). Adults with culture-positive PTB were divided into two treatment groups by their choice: standard regimen alone (HERZ group) and standard regimen plus daily 400 mg MXF in the first 2 months (MXF group). Sputum samples were collected thrice weekly in the first 8 weeks. The propensity score was calculated to estimate the conditional probability of entering the MXF group. Factors influencing time to culture conversion were investigated using Cox proportional hazards regression analysis stratified by propensity score. Sixty-two patients were enrolled in the MXF group and 88 in the HERZ group; respectively 51 and 72 completed the study. The regimen was modified before culture conversion in respectively 6 (12%) and 12 (16%; P = 0.47) patients, due to adverse effects. The time to culture conversion was shorter in the MXF group (HR 2.1, 95%CI 1.4-3.2). The culture conversion rate after 6 weeks of treatment was respectively 82% and 61% (P = 0.011, <0.05/4, calculated using the modified Bonferroni method). Adding MXF to the standard anti-tuberculosis regimen in the first 2 months was associated with a shorter time to culture conversion, a higher 6-week culture conversion rate and reduced transmission of tuberculosis.

Complementarity in dietary supplements and foods: are supplement users vegetable eaters?

PubMed

Kang, Hyoung-Goo; Joo, Hailey Hayeon; Choi, Kyong Duk; Lee, Dongmin; Moon, Junghoon

2017-01-01

Background : The consumption of fruits, vegetables, and dietary supplements correlate. Most previous studies have aimed to identify the determinants of supplement uses or the distinct features of supplement users; this literature lacks a discussion on dietary supplement consumption as a predictor of fruit and vegetable consumption. Objective : This study examines how dietary supplement consumption correlates with fruit and vegetable consumption by combining scanner data and surveys of Korean household grocery shopping. Methods : Propensity score matching (PSM) is used to identify the relationship between dietary supplement consumption and fruit and vegetable consumption in a household. A logit regression using supplement consumption as the dependent variable is used. Then, the supplement takers (the treatment group) are matched with non-takers (the control group) based on the propensity scores estimated in the logit regression. The fruit and vegetable consumption levels of the groups are then compared. Results : We found that dietary supplement use is associated with higher fruit and vegetable consumption. This supports the health consciousness hypothesis based on attention bias, availability heuristics, the focusing effect, and the consumption episode effect. It rejects the health substitute hypothesis based on economic substitutes and mental accounting. Conclusions : Future research on the health benefits of dietary supplements should address the complementary consumption of fruits/vegetables and their health benefits to avoid misstating the health effects of supplements.

Disaster loss and social media: Can online information increase flood resilience?

NASA Astrophysics Data System (ADS)

Allaire, Maura C.

2016-09-01

When confronted with natural disasters, individuals around the world increasingly use online resources to become informed of forecasted conditions and advisable actions. This study tests the effectiveness of online information and social media in enabling households to reduce disaster losses. The 2011 Bangkok flood is utilized as a case study since it was one of the first major disasters to affect a substantial population connected to social media. The role of online information is investigated with a mixed methods approach. Both quantitative (propensity score matching) and qualitative (in-depth interviews) techniques are employed. The study relies on two data sources—survey responses from 469 Bangkok households and in-depth interviews with internet users who were a subset of the survey participants. Propensity score matching indicates that social media enabled households to reduce flood losses by an average of 37% (USD 3708 per household), using a nearest neighbor estimator. This reduction is substantial when considering that household flood losses for the matched sample averaged USD 8278. Social media offered information not available from other sources, such as localized and nearly real-time updates of flood location and depth. With this knowledge, households could move belongings to higher ground before floodwaters arrived. These findings suggest that utilizing social media users as sensors could better inform populations during disasters. Overall, the study reveals that online information can enable effective disaster preparedness and reduce losses.

Disaster Loss and Social Media: Can Online Information Increase Flood Resilience?

NASA Astrophysics Data System (ADS)

Allaire, M.

2016-12-01

When confronted with natural disasters, individuals around the world increasingly use online resources to become informed of forecasted conditions and advisable actions. This study tests the effectiveness of online information and social media in enabling households to reduce disaster losses. The 2011 Bangkok flood is utilized as a case study since it was one of the first major disasters to affect a substantial population connected to social media. The role of online information is investigated with a mixed methods approach. Both quantitative (propensity score matching) and qualitative (in-depth interviews) techniques are employed. The study relies on two data sources - survey responses from 469 Bangkok households and in-depth interviews with twenty-three internet users who are a subset of the survey participants. Propensity score matching indicates that social media enabled households to reduce flood losses by an average of 37% (USD 3,708), using a nearest neighbor estimator. This reduction is massive when considering that total flood losses for the full sample averaged USD 4,903. Social media offered information not available from other sources, such as localized and nearly real-time updates of flood location and depth. With this knowledge, households could move belongings to higher ground before floodwaters arrived. These findings suggest that utilizing social media users as sensors could better inform populations during disasters. Overall, the study reveals that online information can enable effective disaster preparedness and reduce losses.

Complementarity in dietary supplements and foods: are supplement users vegetable eaters?

PubMed Central

Kang, Hyoung-Goo; Joo, Hailey Hayeon; Choi, Kyong Duk; Lee, Dongmin; Moon, Junghoon

2017-01-01

ABSTRACT Background: The consumption of fruits, vegetables, and dietary supplements correlate. Most previous studies have aimed to identify the determinants of supplement uses or the distinct features of supplement users; this literature lacks a discussion on dietary supplement consumption as a predictor of fruit and vegetable consumption. Objective: This study examines how dietary supplement consumption correlates with fruit and vegetable consumption by combining scanner data and surveys of Korean household grocery shopping. Methods: Propensity score matching (PSM) is used to identify the relationship between dietary supplement consumption and fruit and vegetable consumption in a household. A logit regression using supplement consumption as the dependent variable is used. Then, the supplement takers (the treatment group) are matched with non-takers (the control group) based on the propensity scores estimated in the logit regression. The fruit and vegetable consumption levels of the groups are then compared. Results: We found that dietary supplement use is associated with higher fruit and vegetable consumption. This supports the health consciousness hypothesis based on attention bias, availability heuristics, the focusing effect, and the consumption episode effect. It rejects the health substitute hypothesis based on economic substitutes and mental accounting. Conclusions: Future research on the health benefits of dietary supplements should address the complementary consumption of fruits/vegetables and their health benefits to avoid misstating the health effects of supplements. PMID:28904529

Incidence of opioid-managed pelvic pain after hysteroscopic sterilization versus laparoscopic sterilization, U.S. 2005-2012

PubMed Central

Conover, Mitchell M.; Howell, Jennifer O.; Wu, Jennifer M.; Kinlaw, Alan C.; Dasgupta, Nabarun; Funk, Michele Jonsson

2015-01-01

Objective Compare incidence of opioid-managed pelvic pain within 12-months after hysteroscopic and laparoscopic sterilization. Methods Using administrative claims, we identified women age 18-49 without recent history of childbirth who underwent hysteroscopic or laparoscopic sterilization between 2005-2012. We defined the outcome as ≥2 diagnoses for pelvic pain and ≥2 prescription fills for opioids. We calculated adjusted hazard ratios (HR) using Cox models and propensity score methods (matching and inverse-probability-of-treatment-weighting [IPTW]). Results We identified 71,875 eligible women (hysteroscopic n=26,927 [37.5%], laparoscopic n=44,948 [62.5%]). Of those, 236 (0.88%) hysteroscopic patients and 420 (0.93%) laparoscopic patients experienced the outcome (crude HR=0.97, [95%CI: 0.83, 1.14]). Adjusted analyses also yielded near-null results (matched HR=1.08 [95%CI: 0.90, 1.31]; IPTW HR=0.97 [95%CI: 0.80, 1.18]). While most sensitivity analyses generated results close to the null, hazard ratios estimated using propensity score matching ranged from 0.65 to 1.53. Conclusions Among women without recent history of childbirth, we did not find compelling evidence of a clinically meaningful increase in the incidence of pelvic pain requiring opioids during the year after hysteroscopic sterilization. However, effects observed in sensitivity analyses may merit further investigation. PMID:25832014

Cell-Free DNA Analysis in Maternal Blood: Differences in Estimates between Laboratories with Different Methodologies Using a Propensity Score Approach.

PubMed

Bevilacqua, Elisa; Jani, Jacques C; Letourneau, Alexandra; Duiella, Silvia F; Kleinfinger, Pascale; Lohmann, Laurence; Resta, Serena; Cos Sanchez, Teresa; Fils, Jean-François; Mirra, Marilyn; Benachi, Alexandra; Costa, Jean-Marc

2018-06-13

To evaluate the failure rate and performance of cell-free DNA (cfDNA) testing, mainly in terms of detection rates for trisomy 21, performed by 2 laboratories using different analytical methods. cfDNA testing was performed on 2,870 pregnancies with the HarmonyTM Prenatal Test using the targeted digital analysis of selected regions (DANSR) method, and on 2,635 pregnancies with the "Cerba test" using the genome-wide massively parallel sequencing (GW-MPS) method, with available outcomes. Propensity score analysis was used to match patients between the 2 groups. A comparison of the detection rates for trisomy 21 between the 2 laboratories was made. In all, 2,811 patients in the Harmony group and 2,530 patients in the Cerba group had no trisomy 21, 18, or 13. Postmatched comparisons of the patient characteristics indicated a higher no-result rate in the Harmony group (1.30%) than in the Cerba group (0.75%; p = 0.039). All 41 cases of trisomy 21 in the Harmony group and 93 cases in the Cerba group were detected. Both methods of cfDNA testing showed low no-result rates and a comparable performance in detecting trisomy 21; yet GW-MPS had a slightly lower no-result rate than the DANSR method. © 2018 S. Karger AG, Basel.

Estimating Causal Effects in Observational Studies using Electronic Health Data: Challenges and (Some) Solutions

PubMed Central

Stuart, Elizabeth A.; DuGoff, Eva; Abrams, Michael; Salkever, David; Steinwachs, Donald

2013-01-01

Electronic health data sets, including electronic health records (EHR) and other administrative databases, are rich data sources that have the potential to help answer important questions about the effects of clinical interventions as well as policy changes. However, analyses using such data are almost always non-experimental, leading to concerns that those who receive a particular intervention are likely different from those who do not in ways that may confound the effects of interest. This paper outlines the challenges in estimating causal effects using electronic health data and offers some solutions, with particular attention paid to propensity score methods that help ensure comparisons between similar groups. The methods are illustrated with a case study describing the design of a study using Medicare and Medicaid administrative data to estimate the effect of the Medicare Part D prescription drug program on individuals with serious mental illness. PMID:24921064

Advanced age does not affect abdominal wall reconstruction outcomes using acellular dermal matrix: A comparative study using propensity score analysis.

PubMed

Giordano, Salvatore; Schaverien, Mark; Garvey, Patrick B; Baumann, Donald P; Liu, Jun; Butler, Charles E

2017-06-01

We hypothesized that elderly patients (≥65 years) experience worse outcomes following abdominal wall reconstruction (AWR) for hernia or oncologic resection. We included all consecutive patients who underwent complex AWR using acellular dermal matrix (ADM) between 2005 and 2015. Propensity score analysis was performed for risk adjustment in multivariable analysis and for one-to-one matching. The primary outcome was hernia recurrence; the secondary outcomes included surgical site occurrence (SSO) and bulging. Mean follow-up for the 511 patients was 31.4 months; 184 (36%) patients were elderly. The elderly and non-elderly groups had similar rates of hernia recurrence (7.6% vs 10.1%, respectively; p = 0.43) and SSO (24.5% vs 23.5%, respectively; p = 0.82). Bulging occurred significantly more often in elderly patients (6.5% vs 2.8%, respectively; p = 0.04). After adjustment through the propensity score, which included 130 pairs, these results persisted. Contrary to our hypothesis, elderly patients did not have worse outcomes in AWR with ADM. Surgeons should not deny elderly patients AWR solely because of their age. Copyright © 2016 Elsevier Inc. All rights reserved.

Sociodemographic Differences in the Association Between Obesity and Stress: A Propensity Score-Matched Analysis from the Korean National Health and Nutrition Examination Survey (KNHANES).

PubMed

Mak, Kwok-Kei; Kim, Dae-Hwan; Leigh, J Paul

2015-01-01

Few population-based studies have used an econometric approach to understand the association between two cancer risk factors, obesity and stress. This study investigated sociodemographic differences in the association between obesity and stress among Korean adults (6,546 men and 8,473 women). Data were drawn from the Korean National Health and Nutrition Examination Survey for 2008, 2009, and 2010. Ordered logistic regression models and propensity score matching methods were used to examine the associations between obesity and stress, stratified by gender and age groups. In women, the stress level of the obese group was found to be 27.6% higher than the nonobese group in the ordered logistic regression; the obesity effect on stress was statistically significant in the propensity score-matched analysis. Corresponding evidence for the effect of obesity on stress was lacking among men. Participants who were young, well-educated, and working were more likely to report stress. In Korea, obesity causes stress in women but not in men. Young women are susceptible to a disproportionate level of stress. More cancer prevention programs targeting young and obese women are encouraged in developed Asian countries.

Eicosapentaenoic Acid (EPA) Decreases the All-Cause Mortality in Hemodialysis Patients.

PubMed

Inoue, Tomoko; Okano, Kazuhiro; Tsuruta, Yuki; Tsuruta, Yukio; Tsuchiya, Ken; Akiba, Takashi; Nitta, Kosaku

2015-01-01

Atherosclerosis, which causes cardiovascular disease, is a major cause of death in hemodialysis (HD) patients. Eicosapentaenoic acid (EPA), an anti-hyperlipidemic agent, is known to have antioxidative or anti-inflammatory effects, resulting in improvements in atherosclerosis. In the present study, we examined whether EPA improves the all-cause mortality in patients receiving regular HD therapy. We enrolled 176 patients treated with maintenance HD therapy and performed a longitudinal observational cohort study for three years. We divided the patients into two groups based on whether or not the received EPA treatment [EPA(+) and EPA(-), respectively]. The primary end-point was all-cause death. We also matched the two groups using propensity score matching and examined the effect of EPA. Before matching, the all-cause mortality rates were 24.0% in the EPA(+) and 11.8% in the EPA(-) groups, which were significantly different (p=0.044). After propensity score matching, the EPA(+) group still showed a significantly better prognosis than the EPA(-) group (p=0.038). A multivariate analysis showed that EPA treatment significantly reduced the risk of all-cause mortality both before and after propensity score matching. EPA treatment is independently associated with lower mortality in HD patients.

Cost effectiveness of drug-eluting stents in acute myocardial infarction patients in Germany: results from administrative data using a propensity score-matching approach.

PubMed

Bäumler, Michael; Stargardt, Tom; Schreyögg, Jonas; Busse, Reinhard

2012-07-01

The high number of patients with acute myocardial infarction (AMI) has facilitated greater research, resulting in the development of innovative medical devices. So far, results from economic evaluations that compared drug-eluting stents (DES) and bare-metal stents (BMS) have not shown clear evidence that one intervention is more cost effective than the other. The aim of this study was to measure the cost effectiveness of DES compared with BMS in routine care. We used administrative data from a large German sickness fund to compare the costs and effectiveness of DES and BMS in patients with AMI. Patients with hospital admission after AMI in 2004 and 2005 were followed up for 1 year after hospital discharge. The cost of treatment and survival after 365 days were compared for patients treated with DES and BMS. We adjusted for covariates defined according to the Ontario Acute Myocardial Infarction Mortality Prediction Rules using propensity score matching. After matching, we calculated incremental cost-effectiveness ratios (ICERs) by (i) using sample means based on bootstrapping procedures and (ii) estimating generalized linear mixed models for costs and survival. After propensity score matching, the sample included 719 patients treated with DES and 719 patients treated with BMS. A comparison of sample means resulted in average costs of € 12 714 and € 11 714 for DES and BMS, respectively, in 2005 German euros. Difference in 365-day survival was not statistically significant (700 patients with DES and 701 with BMS). The ICER of DES versus BMS was -€ 718 709 per life saved. Bootstrapping resulted in DES being dominated by BMS in 54.5% of replications and DES being a dominant strategy in 2.7% of replications. Results from regression models and sensitivity analyses confirm these results. Treatment with DES after admission with AMI is less cost effective than treatment with BMS. Our results are in line with other cost-effectiveness analyses that used administrative data, i.e. under routine care conditions. However, our results do not preclude that DES may be cost effective in specific patient subgroups.

Poverty and gender perspective in productive projects for rural women in Mexico: impact evaluation of a pilot project.

PubMed

Urquieta-Salomón, José E; Tepichin-Valle, Ana María; Téllez-Rojo, Martha María

2009-02-01

The objective of this study is to evaluate the impact of a pilot study that promoted productive and capacity-building activities among deprived rural women of Mexico. The evaluation design is observational; 1,278 women are interviewed, and the comparison group is estimated by propensity score matching. The results show a positive impact on the carrying out of agricultural activities, in the autonomy of women in decision making, as does their perception of their role in the household. However, the project does not decrease the number of hours set aside for household chores or improve the women's technical and administrative skills.

The impact of spousal bereavement on hospitalisations: Evidence from the Scottish Longitudinal Study.

PubMed

Tseng, Fu-Min; Petrie, Dennis; Wang, Shaolin; Macduff, Colin; Stephen, Audrey I

2018-02-01

This paper estimates the impact of spousal bereavement on hospital inpatient use for the surviving bereaved by following the experience of 94,272 married Scottish individuals from 1991 until 2009 using a difference-in-difference model. We also consider the sample selection issues related to differences in survival between the bereaved and non-bereaved using a simple Cox Proportional-Hazard model. Before conducting these estimations, propensity score approaches are used to re-weight the non-bereaved to generate a more random-like comparison sample for the bereaved. We find that those bereaved who survive are both more likely to be admitted and to stay longer in hospital than a comparable non-bereaved cohort. Bereavement is estimated to induce on average an extra 0.24 (95% CI [0.15, 0.33]) hospital inpatient days per year. Similar to previous studies, we estimate the bereaved have a 19.2% (95% CI [12.5%, 26.3%]) higher mortality rate than the comparable non-bereaved cohort. Copyright © 2017 John Wiley & Sons, Ltd.

Primary tumor resection in metastatic breast cancer: A propensity-matched analysis, 1988-2011 SEER data base.

PubMed

Vohra, Nasreen A; Brinkley, Jason; Kachare, Swapnil; Muzaffar, Mahvish

2018-03-02

Primary tumor resection (PTR) in metastatic breast cancer is not a standard treatment modality, and its impact on survival is conflicting. The primary objective of this study was to analyze impact of PTR on survival in metastatic patients with breast cancer. A retrospective study of metastatic patients with breast cancer was conducted using the 1988-2011 Surveillance, Epidemiology, and End Results (SEER) data base. Cox proportional hazards regression models were used to evaluate the relationship between PTR and survival and to adjust for the heterogeneity between the groups, and a propensity score-matched analysis was also performed. A total of 29 916 patients with metastatic breast cancer were included in the study, and 15 129 (51%) of patients underwent primary tumor resection, and 14 787 (49%) patients did not undergo surgery. Overall, decreasing trend in PTR for metastatic breast cancer in last decades was noted. Primary tumor resection was associated with a longer median OS (34 vs 18 months). In a propensity score-matched analysis, prognosis was also more favorable in the resected group (P = .0017). Primary tumor resection in metastatic breast cancer was associated with survival improvement, and the improvement persisted in propensity-matched analysis. © 2018 Wiley Periodicals, Inc.

Effectiveness of early administration of tranexamic acid in patients with severe trauma.

PubMed

Shiraishi, A; Kushimoto, S; Otomo, Y; Matsui, H; Hagiwara, A; Murata, K

2017-05-01

A reduction in mortality with the early use of tranexamic acid has been demonstrated in severely injured patients who are bleeding. However, the modest treatment effect with no reduction in blood transfusion has raised concerns. The aim of the present study was to estimate the effectiveness of regular use of tranexamic acid in severely injured patients. This multicentre observational study used retrospectively collected data from consecutive injured patients (Injury Severity Score at least 16) treated in 15 Japanese academic institutions in 2012. A propensity score-matched analysis compared patients who did or did not receive tranexamic acid administration within 3 h of injury. Study outcomes included 28-day all-cause and cause-specific mortality, and need for blood transfusion. Of 796 eligible subjects, 281 were treated with tranexamic acid. Propensity score matching selected a total of 500 matched subjects (250 in each group). Tranexamic acid administration was associated with lower 28-day mortality (10·0 versus 18·4 per cent; difference -8·4 (95 per cent c.i. -14·5 to -2·3) per cent) and lower 28-day mortality from primary brain injury (6·0 versus 13·2 per cent; difference -7·2 (-12·3 to -2·1) per cent). However, there was no significant difference between groups in the need for blood transfusion (33·2 versus 34·8 per cent; difference -1·6 (-9·9 to 6·7) per cent). Early tranexamic acid use was associated with reduced mortality in severely injured patients, in particular those with a primary brain injury. © 2017 BJS Society Ltd Published by John Wiley & Sons Ltd.

Healthcare resource utilization and related financial costs associated with glucose lowering with either exenatide or basal insulin: A retrospective cohort study.

PubMed

Holden, Sarah E; Morgan, Christopher Ll; Qiao, Qing; Jenkins-Jones, Sara; Berni, Ellen R; Currie, Craig J

2017-08-01

Type 2 diabetes is a major health problem placing increasing demands on healthcare systems. Our objective was to estimate healthcare resource use and related financial costs following treatment with exenatide-based regimens prescribed as once-weekly (EQW) or twice-daily (EBID) formulations, compared with regimens based on basal insulin (BI). This retrospective cohort study used data from the UK Clinical Practice Research Datalink (CPRD) linked to Hospital Episode Statistics (HES). Patients with type 2 diabetes who received exenatide or BI between 2009 and 2014 as their first recorded exposure to injectable therapy were selected. Costs were attributed to primary care contacts, diabetes-related prescriptions and inpatient admissions using standard UK healthcare costing methods (2014 prices). Frequency and costs were compared between cohorts before and after matching by propensity score using Poisson regression. Groups of 8723, 218 and 2180 patients receiving BI, EQW and EBID, respectively, were identified; 188 and 1486 patients receiving EQW and EBID, respectively, were matched 1:1 to patients receiving BI by propensity score. Among unmatched cohorts, total crude mean costs per patient-year were £2765 for EQW, £2549 for EBID and £4080 for BI. Compared with BI, the adjusted annual cost ratio (aACR) was 0.92 (95% CI, 0.91-0.92) for EQW and 0.82 (95% CI, 0.82-0.82) for EBID. Corresponding costs for the propensity-matched subgroups were £2646 vs £3283 (aACR, 0.80, 0.80-0.81) for EQW vs BI and £2532 vs £3070 (aACR, 0.84, 0.84-0.84) for EBID vs BI. Overall, exenatide once-weekly and twice-daily-based regimens were associated with reduced healthcare resource use and costs compared with basal-insulin-based regimens. © 2017 John Wiley & Sons Ltd.

Long-term Outcomes of Laparoscopic Versus Open Surgery for Clinical Stage II/III Gastric Cancer: A Multicenter Cohort Study in Japan (LOC-A Study).

PubMed

Kinoshita, Takahiro; Uyama, Ichiro; Terashima, Masanori; Noshiro, Hirokazu; Nagai, Eishi; Obama, Kazutaka; Tamamori, Yutaka; Nabae, Toshinaga; Honda, Michitaka; Abe, Takayuki

2018-04-24

A large-scale multicenter historical cohort study was conducted to investigate the efficacy of laparoscopic gastrectomy (LG) in comparison to open gastrectomy (OG) for locally advanced gastric cancer. LG is now practiced widely, but its applicability for advanced gastric cancer is still controversial. As oncologic outcomes of randomized trials are still pending, there is an urgent need for information that would be relevant to current practice. Through a consensus meeting involving surgeons and biostatisticians, 30 preoperative variables possibly influencing the choice of surgical approach and associated with outcome were identified to enable rigorous estimation of propensity scores. A total of 1948 consecutive patients who underwent gastrectomy for clinical stage II/III gastric adenocarcinoma between 2008 and 2014 were identified, and their clinical data were collected from 8 participating hospitals. After propensity score matching, 610 cases (OG = 305, LG = 305) were finally selected for comparison of long-term outcomes. In the propensity-matched OG and LG populations, the mean observation period was 3.5 and 3.4 years, and the 5-year overall survival was 53.0% and 54.2%, respectively. The hazard ratio (LG/OG) for overall survival was 1.01 (95% confidence interval, 0.80-1.29), and noninferiority of LG was demonstrated statistically as the upper 95% confidence limit was less than the prespecified margin (1.33). The recurrence rate was 30.8% and 29.8% for OG and LG, respectively, and the hazard ratio for recurrence was 0.98 (95% confidence interval, 0.74-1.31). The patterns of recurrence in the 2 groups were similar. This observational study strictly adjusted for confounding factors has provided evidence to suggest that LG is oncologically comparable to OG for locally advanced gastric cancer. The validity of this result will be examined in ongoing randomized trials.

Effects of breast and colorectal cancer on labour market outcomes-average effects and educational gradients.

PubMed

Heinesen, Eskil; Kolodziejczyk, Christophe

2013-12-01

We estimate causal effects of breast and colorectal cancer on labour market outcomes 1-3 years after the diagnosis. Based on Danish administrative data we estimate average treatment effects on the treated by propensity score weighting methods using persons with no cancer diagnosis as control group. We conduct robustness checks using matching, difference-in-differences methods and an alternative control group of later cancer patients. The different methods give approximately the same results. Cancer increases the risks of leaving the labour force and receiving disability pension, and the effects are larger for the less educated. Effects on income are small and mostly insignificant. We investigate some of the mechanisms which may be important in explaining the educational gradient in effects of cancer on labour market attachment. Copyright © 2013 Elsevier B.V. All rights reserved.

The effects of breastfeeding on childhood BMI: a propensity score matching approach.

PubMed

Gibson, Laura A; Hernández Alava, Mónica; Kelly, Michael P; Campbell, Michael J

2017-12-01

Many studies have found a statistical association between breastfeeding and childhood adiposity. This paper investigates whether breastfeeding has an effect on subsequent childhood body mass index (BMI) using propensity scores to account for confounding. We use data from the Millennium Cohort Study, a nationally representative UK cohort survey, which contains detailed information on infant feeding and childhood BMI. Propensity score matching is used to investigate the mean BMI in children breastfed exclusively and partially for different durations of time. We find statistically significant influences of breastfeeding on childhood BMI, particularly in older children, when breastfeeding is prolonged and exclusive. At 7 years, children who were exclusively breastfed for 16 weeks had a BMI 0.28 kg/m2 (95% confidence interval 0.07 to 0.49) lower than those who were never breastfed, a 2% reduction from the mean BMI of 16.6 kg/m2. For this young cohort, even small effects of breastfeeding on BMI could be important. In order to reduce BMI, breastfeeding should be encouraged as part of wider lifestyle intervention. This evidence could help to inform public health bodies when creating public health guidelines and recommendations. © The Author 2016. Published by Oxford University Press on behalf of Faculty of Public Health.

Effect of perioperative oral care on prevention of postoperative pneumonia associated with esophageal cancer surgery: A multicenter case-control study with propensity score matching analysis.

PubMed

Soutome, Sakiko; Yanamoto, Souichi; Funahara, Madoka; Hasegawa, Takumi; Komori, Takahide; Yamada, Shin-Ichi; Kurita, Hiroshi; Yamauchi, Chika; Shibuya, Yasuyuki; Kojima, Yuka; Nakahara, Hirokazu; Oho, Takahiko; Umeda, Masahiro

2017-08-01

The aim of this study was to investigate the effectiveness of oral care in prevention of postoperative pneumonia associated with esophageal cancer surgery.Postoperative pneumonia is a severe adverse event associated with esophageal cancer surgery. It is thought to be caused by aspiration of oropharyngeal fluid containing pathogens. However, the relationship between oral health status and postoperative pneumonia has not been well investigated.This study included 539 patients with esophageal cancer undergoing surgery at 1 of 7 university hospitals. While 306 patients received perioperative oral care, 233 did not. Various clinical factors as well as occurrence of postoperative pneumonia were retrospectively evaluated. Propensity-score matching was performed to minimize selection biases associated with comparison of retrospective data between the oral care and control groups. Factors related to postoperative pneumonia were analyzed by logistic regression analysis.Of the original 539 patients, 103 (19.1%) experienced postoperative pneumonia. The results of multivariate analysis of the 420 propensity score-matched patients revealed longer operation time, postoperative dysphagia, and lack of oral care intervention to be significantly correlated with postoperative pneumonia.The present findings demonstrate that perioperative oral care can reduce the risk of postoperative pneumonia in patients undergoing esophageal cancer surgery.

Effect of intravenous immunoglobulin for fulminant myocarditis on in-hospital mortality: propensity score analyses.

PubMed

Isogai, Toshiaki; Yasunaga, Hideo; Matsui, Hiroki; Tanaka, Hiroyuki; Horiguchi, Hiromasa; Fushimi, Kiyohide

2015-05-01

Fulminant myocarditis (FM) is a rare but life-threatening disease. Intravenous immunoglobulin (IVIG) is not recommended for acute or chronic myocarditis in Western nations owing to the lack of rigorous evidence, but it is widely used in other countries, including Japan. This nationwide retrospective cohort study focused on evaluating the effect of IVIG in FM patients. Using the Diagnosis Procedure Combination database in Japan, we identified 603 FM patients aged ≥16 years who received mechanical circulatory support within 7 days after admission. We performed propensity score analyses to compare the in-hospital mortality and total costs between IVIG users (n = 220; 36.5%) and nonusers (n = 383; 63.5%). Among propensity score-matched patients (164 pairs), there was no significant difference in in-hospital mortality between IVIG users and nonusers (36.6% vs 37.2%; P = .909). A multivariable logistic regression analysis showed no significant association between IVIG use and in-hospital mortality (adjusted odds ratio 0.91; 95% confidence interval 0.52 to 1.58; P = .733). The median total costs were significantly higher for IVIG users than for nonusers (US $44,226 vs $33,280; P < .001). IVIG for FM was not significantly associated with a decrease in in-hospital mortality. Copyright © 2015 Elsevier Inc. All rights reserved.

Efficacy of a Self-expanding Tract Sealant Device in the Reduction of Pneumothorax and Chest Tube Placement Rates After Percutaneous Lung Biopsy: A Matched Controlled Study Using Propensity Score Analysis

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

Ahrar, Judy U., E-mail: judy.ahrar@mdanderson.org; Gupta, Sanjay; Ensor, Joe E.

PurposeTo evaluate the use of a self-expanding tract sealant device (BioSentry™) on the rates of pneumothorax and chest tube insertion after percutaneous lung biopsy.Materials and MethodsIn this retrospective study, we compared 318 patients who received BioSentry™ during percutaneous lung biopsy (treated group) with 1956 patients who did not (control group). Patient-, lesion-, and procedure-specific variables, and pneumothorax and chest tube insertion rates were recorded. To adjust for potential selection bias, patients in the treated group were matched 1:1 to patients in the control group using propensity score matching based on the above-mentioned variables. Patients were considered a match if themore » absolute difference in their propensity scores was ≤equal to 0.02.ResultsBefore matching, the pneumothorax and chest tube rates were 24.5 and 13.1% in the control group, and 21.1 and 8.5% in the treated group, respectively. Using propensity scores, a match was found for 317 patients in the treatment group. Chi-square contingency matched pair analysis showed the treated group had significantly lower pneumothorax (20.8 vs. 32.8%; p = 0.001) and chest tube (8.2 vs. 20.8%; p < 0.0001) rates compared to the control group. Sub-analysis including only faculty who had >30 cases of both treatment and control cases demonstrated similar findings: the treated group had significantly lower pneumothorax (17.6 vs. 30.2%; p = 0.002) and chest tube (7.2 vs. 18%; p = 0.001) rates.ConclusionsThe self-expanding tract sealant device significantly reduced the pneumothorax rate, and more importantly, the chest tube placement rate after percutaneous lung biopsy.« less

Comparative risk of cerebrovascular adverse events in community-dwelling older adults using risperidone, olanzapine and quetiapine: a multiple propensity score-adjusted retrospective cohort study.

PubMed

Chatterjee, Satabdi; Chen, Hua; Johnson, Michael L; Aparasu, Rajender R

2012-10-01

Atypical antipsychotic agents have been associated with cerebrovascular adverse events, particularly in elderly dementia patients. However, limited evidence exists regarding comparative cerebrovascular profiles of individual atypical agents, particularly in community settings. The objective of this study was to evaluate the risk of cerebrovascular events associated with use of risperidone, olanzapine and quetiapine in community-dwelling older adults in the US. A propensity score-adjusted retrospective cohort design involving the IMS LifeLink™ Health Plan Claims Database was used for the study. The study population included all older adults (aged ≥50 years) who initiated risperidone, olanzapine or quetiapine anytime during 1 July 2000 to 30 June 2008. Patients were followed until hospitalization or an emergency room visit for a cerebrovascular event, or the end of the study period, whichever occurred earlier. The Cox proportional hazard regression model with time-varying covariates was used to evaluate the risk of cerebrovascular events during the follow-up period, using olanzapine as the reference. The covariates adjusted for in the final model included multiple propensity scores and exposure to other medications that could be associated with the risk of cerebrovascular events. A total of 2,458 cerebrovascular events were identified in the study cohort: 1,081 (21.38%) for risperidone users, 816 (18.75%) for olanzapine users and 561 (21.05%) for quetiapine users. After adjusting for propensity scores and other covariates, the Cox proportional hazard model revealed that use of quetiapine [hazard ratio (HR) 0.88; 95% CI 0.78, 0.99] but not risperidone (HR 1.05; 95% CI 0.95, 1.16) was associated with a decrease in the risk of cerebrovascular adverse events compared with olanzapine. The study suggested that quetiapine use may be associated with a moderately lower risk of cerebrovascular events than olanzapine in older adults. Prescribers should closely monitor the patients treated with atypical agents for the incidence of cerebrovascular adverse events.

A propensity score-matched comparison of the efficacies of OK-432 and talc slurry for pleurodesis for malignant pleural effusion induced by lung adenocarcinoma.

PubMed

Nohara, Kango; Takada, Kazuto; Kojima, Eiji; Ninomiya, Kiyoko; Miyamatsu, Shoko; Shimizu, Takahiro; Sakurai, Tsutomu; Mizuno, Takaaki; Yamashita, Yuuki

2016-09-01

The choice of an optimal sclerosant for pleurodesis for malignant pleural effusion remains controversial. This retrospective clinical study compared the efficacy and safety of two sclerosants; talc slurry (talc-s) and OK-432. We compared the characteristics, 30/90-day success rates, and adverse events in patients with lung adenocarcinoma who underwent pleurodesis by using either OK-432 or talc-s. Propensity score matching was used to compare the two scelrosants. Ninety-four patients (mean age=71.6±9.6 years) were included in this retrospective study, of whom 64 received OK-432 and 30 received talc-s. Seventy-three patients (77.6%) were initially diagnosed with clinical stage IV lung cancer, with a 28.7% epidermal growth factor receptor mutation frequency. The propensity score-matched cohort included 26 patients from each group. The 30-day success rates for OK-432 and talc-s were 80.7% and 76.9%, respectively (odds ratio: 1.26, 95% confidence interval: 0.33-4.77, p=0.73). Neither the overall incidence of adverse events nor the 90-day success rates differed significantly. Multivariate logistic regression revealed that the predictors of 30-day success were lower drainage volume on the previous day, particularly <250mL/day, the presence of full lung expansion, and pre-therapy with an epidermal growth factor receptor-tyrosine kinase inhibitor. The median post-pleurodesis survival time was 6.9 months, which was not significantly different between the study groups. Propensity score-matched analyses showed that pleurodesis using OK-432 and talc-s demonstrated comparable efficacy and safety profiles in patients with lung adenocarcinoma. This indicated that OK-432 could be a viable alternative to talc-s in this procedure. Copyright © 2016. Published by Elsevier B.V.

Impact of gender on long-term outcomes after surgical repair for acute Stanford A aortic dissection: a propensity score matched analysis.

PubMed

Sabashnikov, Anton; Heinen, Stephanie; Deppe, Antje Christin; Zeriouh, Mohamed; Weymann, Alexander; Slottosch, Ingo; Eghbalzadeh, Kaveh; Popov, Aron-Frederik; Liakopoulos, Oliver; Rahmanian, Parwis B; Madershahian, Navid; Kroener, Axel; Choi, Yeong-Hoon; Kuhn-Régnier, Ferdinand; Simon, André R; Wahlers, Thorsten; Wippermann, Jens

2017-05-01

Previous research suggests that female gender is associated with increased mortality rates after surgery for Stanford A acute aortic dissection (AAD). However, women with AAD usually present with different clinical symptoms that may bias outcomes. Moreover, there is a lack of long-term results regarding overall mortality and freedom from major cerebrovascular events. We analysed the impact of gender on long-term outcomes after surgery for Stanford A AAD by comparing genders with similar risk profiles using propensity score matching. A total of 240 patients operated for Stanford A AAD were included in this study. To control for selection bias and other confounders, propensity score matching was applied to gender groups. After propensity score matching, the gender groups were well balanced in terms of risk profiles. There were no statistically significant differences regarding duration of cardiopulmonary bypass ( P  = 0.165) and duration of aortic cross-clamp time ( P  = 0.111). Female patients received less fresh frozen plasma ( P  = 0.021), had shorter stays in the intensive care unit ( P  = 0.031), lower incidence of temporary neurological dysfunction ( P  < 0.001) and lower incidence of dialysis ( P  = 0.008). There were no significant differences regarding intraoperative mortality ( P  = 1.000), 30-day mortality ( P  = 0.271), long-term overall cumulative survival ( P  = 0.954) and long-term freedom from cerebrovascular events ( P  = 0.235) with up to a 9-year follow-up. Considering patients with similar risk profiles, female gender per se is not associated with worse long-term survival and freedom from stroke after surgical aortic repair. Moreover, female patients might even benefit from a smoother early postoperative course and lower incidence of early postoperative complications. © The Author 2017. Published by Oxford University Press on behalf of the European Association for Cardio-Thoracic Surgery. All rights reserved.

Assessing the Independent Contribution of Maternal Educational Expectations to Children’s Educational Attainment in Early Adulthood: A Propensity Score Matching Analysis

PubMed Central

Pingault, Jean Baptiste; Côté, Sylvana M.; Petitclerc, Amélie; Vitaro, Frank; Tremblay, Richard E.

2015-01-01

Background Parental educational expectations have been associated with children’s educational attainment in a number of long-term longitudinal studies, but whether this relationship is causal has long been debated. The aims of this prospective study were twofold: 1) test whether low maternal educational expectations contributed to failure to graduate from high school; and 2) compare the results obtained using different strategies for accounting for confounding variables (i.e. multivariate regression and propensity score matching). Methodology/Principal Findings The study sample included 1,279 participants from the Quebec Longitudinal Study of Kindergarten Children. Maternal educational expectations were assessed when the participants were aged 12 years. High school graduation – measuring educational attainment – was determined through the Quebec Ministry of Education when the participants were aged 22–23 years. Findings show that when using the most common statistical approach (i.e. multivariate regressions to adjust for a restricted set of potential confounders) the contribution of low maternal educational expectations to failure to graduate from high school was statistically significant. However, when using propensity score matching, the contribution of maternal expectations was reduced and remained statistically significant only for males. Conclusions/Significance The results of this study are consistent with the possibility that the contribution of parental expectations to educational attainment is overestimated in the available literature. This may be explained by the use of a restricted range of potential confounding variables as well as the dearth of studies using appropriate statistical techniques and study designs in order to minimize confounding. Each of these techniques and designs, including propensity score matching, has its strengths and limitations: A more comprehensive understanding of the causal role of parental expectations will stem from a convergence of findings from studies using different techniques and designs. PMID:25803867

Cold snare polypectomy reduced delayed postpolypectomy bleeding compared with conventional hot polypectomy: a propensity score-matching analysis

PubMed Central

Yamashina, Takeshi; Fukuhara, Manabu; Maruo, Takanori; Tanke, Gensho; Marui, Saiko; Sada, Ryota; Taki, Mio; Ohara, Yoshiaki; Sakamoto, Azusa; Henmi, Shinichiro; Sawai, Yugo; Saito, Sumio; Nishijima, Norihiro; Nasu, Akihiro; Komekado, Hideyuki; Sekikawa, Akira; Asada, Masanori; Tumura, Takehiko; Kita, Ryuichi; Kimura, Toru; Osaki, Yukio

2017-01-01

Background and study aims  Cold snare polypectomy (CSP) for small colorectal polyps has lower incidence of adverse events, especially delayed postpolypectomy bleeding (DPPB). However, few data are available on comparisons of the incidence of DPPB of CSP and hot polypectomy (HP). The aim of this study was to evaluate the incidence of DPPB after CSP and compare it with that of HP. A propensity score model was used as a secondary analysis. Patients and methods  This was a retrospective cohort study conducted in a single municipal hospital. We identified 539 patients with colorectal polyps from 2 mm to 11 mm in size who underwent CSP (804 polyps in 330 patients) or HP (530 polyps in 209 patients) between July 2013 and June 2015. Results  There were no cases of DPPB in the CSP group. Conversely, DPPB occurred in 4 patients (1.9 %) after HP, resulting in a significant difference between the CSP and HP groups (0.008 % vs 0 %, P  = 0.02). Propensity score-matching analysis created 402 matched pairs, yielding a significantly higher DPPB rate in the HP group than CSP group (0.02 % vs 0 %, P  = 0.04). However, significantly more patients in the CSP group had unclear horizontal margins that precluded assessment (83 vs 38 cases, P  < 0.001). The retrieval failure rate was significantly higher in the CSP group than in the HP group (3 % vs 0.7 %, P  = 0.01). Conclusions  DPPB was less frequent with CSP than HP, as selected by the propensity score-matching model. Our findings indicate that CSP is recommended polypectomy in daily clinical setting. However, special care should be taken during polyp retrieval and horizontal margin assessment, and these issues could be taken into account in follow-up after CSP. PMID:28670615

Effects of statin therapy on clinical outcomes after acute myocardial infarction in patients with advanced renal dysfunction: A propensity score-matched analysis.

PubMed

Kim, Jin Sug; Kim, Weon; Park, Ji Yoon; Woo, Jong Shin; Lee, Tae Won; Ihm, Chun Gyoo; Kim, Yang Gyun; Moon, Ju-Young; Lee, Sang Ho; Jeong, Myung Ho; Jeong, Kyung Hwan

2017-01-01

Lipid lowering therapy is widely used for the prevention of cardiovascular complications after acute myocardial infarction (AMI). However, some studies show that this benefit is uncertain in patients with renal dysfunction, and the role of statins is based on the severity of renal dysfunction. In this study, we investigated the impact of statin therapy on major adverse cardiac events (MACEs) and all-cause mortality in patients with advanced renal dysfunction undergoing percutaneous coronary intervention (PCI) after AMI. This study was based on the Korea Acute Myocardial Infarction Registry database. We included 861 patients with advanced renal dysfunction from among 33,205 patients who underwent PCI after AMI between November 2005 and July 2012. Patients were divided into two groups: a statin group (n = 537) and a no-statin group (n = 324). We investigated the 12-month MACEs (cardiac death, myocardial infarction, repeated PCI or coronary artery bypass grafting) and all-cause mortality of each group. Subsequently, a propensity score-matched analysis was performed. In the total population studied, no significant differences were observed between the two groups with respect to the rate of recurrent MI, repeated PCI, coronary artery bypass grafting (CABG), or all-cause mortality. However, the cardiac death rate was significantly lower in the statin group (p = 0.009). Propensity score-matched analysis yielded 274 pairs demonstrating, results similar to those obtained from the total population. However, there was no significant difference in the cardiac death rate in the propensity score-matched population (p = 0.103). Cox-regression analysis revealed only left ventricular ejection fraction to be an independent predictor of 12-month MACEs (Hazard ratio [HR] of 0.979, 95% confidence interval [CI], 0962-0.996, p = 0.018). Statin therapy was not significantly associated with a reduction in the 12-month MACEs or all-cause mortality in patients with advanced renal dysfunction undergoing PCI after AMI.

Propensity score-matched analysis of comprehensive local therapy for oligometastatic non-small cell lung cancer that did not progress after front-line chemotherapy.

PubMed

Sheu, Tommy; Heymach, John V; Swisher, Stephen G; Rao, Ganesh; Weinberg, Jeffrey S; Mehran, Reza; McAleer, Mary Frances; Liao, Zhongxing; Aloia, Thomas A; Gomez, Daniel R

2014-11-15

To retrospectively analyze factors influencing survival in patients with non-small cell lung cancer presenting with ≤3 synchronous metastatic lesions. We identified 90 patients presenting between 1998 and 2012 with non-small cell lung cancer and ≤3 metastatic lesions who had received at least 2 cycles of chemotherapy followed by surgery or radiation therapy before disease progression. The median number of chemotherapy cycles before comprehensive local therapy (CLT) (including concurrent chemoradiation as first-line therapy) was 6. Factors potentially affecting overall (OS) or progression-free survival (PFS) were evaluated with Cox proportional hazards regression. Propensity score matching was used to assess the efficacy of CLT. Median follow-up time was 46.6 months. Benefits in OS (27.1 vs 13.1 months) and PFS (11.3 months vs 8.0 months) were found with CLT, and the differences were statistically significant when propensity score matching was used (P ≤ .01). On adjusted analysis, CLT had a statistically significant benefit in terms of OS (hazard ratio, 0.37; 95% confidence interval, 0.20-0.70; P ≤ .01) but not PFS (P=.10). In an adjusted subgroup analysis of patients receiving CLT, favorable performance status (hazard ratio, 0.43; 95% confidence interval, 0.22-0.84; P=.01) was found to predict improved OS. Comprehensive local therapy was associated with improved OS in an adjusted analysis and seemed to favorably influence OS and PFS when factors such as N status, number of metastatic lesions, and disease sites were controlled for with propensity score-matched analysis. Patients with favorable performance status had improved outcomes with CLT. Ultimately, prospective, randomized trials are needed to provide definitive evidence as to the optimal treatment approach for this patient population. Copyright © 2014 Elsevier Inc. All rights reserved.

Is participation in labour market programmes related to mental health? Results from a 14-year follow-up of the Northern Swedish Cohort.

PubMed

Reine, Ieva; Novo, Mehmed; Hammarström, Anne

2011-02-01

There is a lack of empirical studies assessing the possible impact of active labour market programmes (ALMP) on health. The aim of this study was to analyze whether participation in ALMP, in contrast to being unemployed and not participating in ALMP (UNALMP), was related to mental health at different ages. The study was carried out in a medium-sized industrial town in the north of Sweden. The cohort, consisting of all 1,083 pupils who attended or should have attended the last year of compulsory school in 1981, was followed up at the ages of 16, 18, 21 and 30. Data on 381 individuals at age 21, and 281 at age 30 were used in the study. The main health measurement was psychological symptoms among participants of ALMP in contrast to UNALMP at ages 21 and 30, and was analyzed by propensity score matching method (PSM) and multivariate logistic regression. Generally, ALMP had higher scores of psychological symptoms than UNALMP. Nevertheless, participation in ALMP was not related to mental health. Due to methodological shortages our results have to be interpreted with caution. Adjustment for either all background selection variables or the propensity score in multivariate logistic regression showed similar associations, suggesting that propensity score could be used to adjust for background selection variables. There is a need for more well-designed studies, using a theoretical framework, within the field, that are based on larger samples.

Functional outcome after primary endovascular therapy or IV thrombolysis alone for stroke. An observational, comparative effectiveness study.

PubMed

Abilleira, Sònia; Ribera, Aida; Dávalos, Antonio; Ribó, Marc; Chamorro, Angel; Cardona, Pere; Molina, Carlos A; Martínez-Yélamos, Antonio; Urra, Xabier; Dorado, Laura; Roquer, Jaume; Martí-Fàbregas, Joan; Aja, Lucía; Tomasello, Alejandro; Castaño, Carlos; Blasco, Jordi; Cánovas, David; Castellanos, Mar; Krupinski, Jerzy; Guimaraens, Leopoldo; Perendreu, Joan; Ustrell, Xavier; Purroy, Francisco; Gómez-Choco, Manuel; Baiges, Joan Josep; Cocho, Dolores; Saura, Júlia; Gallofré, Miquel

2014-01-01

Among the acute ischemic stroke patients with large vessel occlusions and contraindications for the use of IV thrombolysis, mainly on oral anticoagulation or presenting too late, primary endovascular therapy is often performed as an alternative to the standard therapy even though evidence supporting the use of endovascular reperfusion therapies is not yet established. Using different statistical approaches, we compared the functional independence rates at 3 months among patients undergoing primary endovascular therapy and patients treated only with IV thrombolysis. We used data from a prospective, government-mandated and externally audited registry of reperfusion therapies for ischemic stroke (January 2011 to November 2012). Patients were selected if treated with either IV thrombolysis alone (n = 1,582) or primary endovascular thrombectomy (n = 250). A series of exclusions were made to homogenize the clinical characteristics among the two groups. We then carried out multivariate logistic regression and propensity score matching analyses on the final study sample (n = 1,179) to compare functional independence at 3 months, as measured by the modified Rankin scale scores 0-2, between the two groups. The unadjusted likelihood of good outcome was poorer among the endovascular group (OR: 0.69; 95% CI: 0.47-1.0). After adjustment, no differences by treatment modality were seen (OR: 1.51; 95% CI: 0.93-2.43 for primary endovascular therapy). Patients undergoing endovascular thrombectomy within 180-270 min (OR: 2.89; 95% CI: 1.17-7.15) and patients with severe strokes (OR: 1.84; 95% CI: 1.02-3.35) did better than their intravenous thrombolysis counterparts. The propensity score-matched analyses with and without adjustment by additional covariates showed that endovascular thrombectomy was as effective as intravenous thrombolysis alone in achieving functional independence (OR for unadjusted propensity score matched: 1.35; 95% CI: 0.9-2.02, OR for adjusted propensity score matched: 1.45; 95% CI: 0.91-2.32). This comparative effectiveness study shows that in ischemic stroke patients with contraindications for IV thrombolysis, primary endovascular treatment might be an alternative therapy at least as effective as IV thrombolysis alone. Randomized controlled trials are urgently needed. © 2014 S. Karger AG, Basel.

Early administration of epinephrine (adrenaline) in patients with cardiac arrest with initial shockable rhythm in hospital: propensity score matched analysis

PubMed Central

Andersen, Lars W; Kurth, Tobias; Chase, Maureen; Berg, Katherine M; Cocchi, Michael N; Callaway, Clifton

2016-01-01

Objectives To evaluate whether patients who experience cardiac arrest in hospital receive epinephrine (adrenaline) within the two minutes after the first defibrillation (contrary to American Heart Association guidelines) and to evaluate the association between early administration of epinephrine and outcomes in this population. Design Prospective observational cohort study. Setting Analysis of data from the Get With The Guidelines-Resuscitation registry, which includes data from more than 300 hospitals in the United States. Participants Adults in hospital who experienced cardiac arrest with an initial shockable rhythm, including patients who had a first defibrillation within two minutes of the cardiac arrest and who remained in a shockable rhythm after defibrillation. Intervention Epinephrine given within two minutes after the first defibrillation. Main outcome measures Survival to hospital discharge. Secondary outcomes included return of spontaneous circulation and survival to hospital discharge with a good functional outcome. A propensity score was calculated for the receipt of epinephrine within two minutes after the first defibrillation, based on multiple characteristics of patients, events, and hospitals. Patients who received epinephrine at either zero, one, or two minutes after the first defibrillation were then matched on the propensity score with patients who were “at risk” of receiving epinephrine within the same minute but who did not receive it. Results 2978patients were matched on the propensity score, and the groups were well balanced. 1510 (51%) patients received epinephrine within two minutes after the first defibrillation, which is contrary to current American Heart Association guidelines. Epinephrine given within the first two minutes after the first defibrillation was associated with decreased odds of survival in the propensity score matched analysis (odds ratio 0.70, 95% confidence interval 0.59 to 0.82; P<0.001). Early epinephrine administration was also associated with a decreased odds of return of spontaneous circulation (0.71, 0.60 to 0.83; P<0.001) and good functional outcome (0.69, 0.58 to 0.83; P<0.001). Conclusion Half of patients with a persistent shockable rhythm received epinephrine within two minutes after the first defibrillation, contrary to current American Heart Association guidelines. The receipt of epinephrine within two minutes after the first defibrillation was associated with decreased odds of survival to hospital discharge as well as decreased odds of return of spontaneous circulation and survival to hospital discharge with a good functional outcome. PMID:27053638

Early administration of epinephrine (adrenaline) in patients with cardiac arrest with initial shockable rhythm in hospital: propensity score matched analysis.

PubMed

Andersen, Lars W; Kurth, Tobias; Chase, Maureen; Berg, Katherine M; Cocchi, Michael N; Callaway, Clifton; Donnino, Michael W

2016-04-06

To evaluate whether patients who experience cardiac arrest in hospital receive epinephrine (adrenaline) within the two minutes after the first defibrillation (contrary to American Heart Association guidelines) and to evaluate the association between early administration of epinephrine and outcomes in this population. Prospective observational cohort study. Analysis of data from the Get With The Guidelines-Resuscitation registry, which includes data from more than 300 hospitals in the United States. Adults in hospital who experienced cardiac arrest with an initial shockable rhythm, including patients who had a first defibrillation within two minutes of the cardiac arrest and who remained in a shockable rhythm after defibrillation. Epinephrine given within two minutes after the first defibrillation. Survival to hospital discharge. Secondary outcomes included return of spontaneous circulation and survival to hospital discharge with a good functional outcome. A propensity score was calculated for the receipt of epinephrine within two minutes after the first defibrillation, based on multiple characteristics of patients, events, and hospitals. Patients who received epinephrine at either zero, one, or two minutes after the first defibrillation were then matched on the propensity score with patients who were "at risk" of receiving epinephrine within the same minute but who did not receive it. 2978 patients were matched on the propensity score, and the groups were well balanced. 1510 (51%) patients received epinephrine within two minutes after the first defibrillation, which is contrary to current American Heart Association guidelines. Epinephrine given within the first two minutes after the first defibrillation was associated with decreased odds of survival in the propensity score matched analysis (odds ratio 0.70, 95% confidence interval 0.59 to 0.82; P<0.001). Early epinephrine administration was also associated with a decreased odds of return of spontaneous circulation (0.71, 0.60 to 0.83; P<0.001) and good functional outcome (0.69, 0.58 to 0.83; P<0.001). Half of patients with a persistent shockable rhythm received epinephrine within two minutes after the first defibrillation, contrary to current American Heart Association guidelines. The receipt of epinephrine within two minutes after the first defibrillation was associated with decreased odds of survival to hospital discharge as well as decreased odds of return of spontaneous circulation and survival to hospital discharge with a good functional outcome. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://group.bmj.com/group/rights-licensing/permissions.

The effect of early childhood stunting on children’s cognitive achievements: Evidence from young lives Ethiopia

PubMed Central

Woldehanna, Tassew; Behrman, Jere R.; Araya, Mesele W.

2017-01-01

Background There is little empirical evidence on the effect of childhood malnutrition on children’s cognitive achievements in low income countries like Ethiopia. A longitudinal data is thus vital to understand the factors that influence cognitive development of children over time, particularly how early childhood stunting affects cognitive achievement of children up to the age of 8 years. Objective To examine the effect of early childhood stunting on cognitive achievements of children using longitudinal data that incorporate anthropometric measurements and results of cognitive achievement tests such as Peabody Picture Vocabulary Test and Cognitive Development Assessment quantitative tests. Method Defining stunted children as those having a standardized height for age z-score less than −2; we used a Propensity Score Matching (PSM) to examine the effect of early childhood stunting on measures of cognitive performance of children. The balance of the propensity score matching techniques was checked and found to be satisfied (P<0.01) Results Early childhood stunting is significantly negatively associated with cognitive performance of children. Controlled for confounding variables such as length of breastfeeding, relative size of the child at birth, health problems of early childhood such as acute respiratory illness and malaria, baseline household wealth, child gender, household size and parental education, estimates from PSM show that stunted children scored 16.1% less in the Peabody Picture Vocabulary Test and 48.8% less in the Quantitative Assessment test at the age of eight, both statistically significant at P<0.01. Conclusions It is important to realize the importance of early investment in terms of child health and nutrition until five years for the cognitive performance of children. As household wealth and parental education are particularly found to play an important role in children’s nutritional achievements, policy measures that are directed in improving household’s livelihood may have a spill-over impact in improving child nutritional status, and consequently cognitive development and schooling. PMID:29249889

Application of propensity scores to estimate the association between government subsidy and injection use in primary health care institutions in China.

PubMed

Tang, Yuqing; Zhang, Xiaopeng; Yang, Chunyan; Yang, Lianping; Wang, Hongtao; Zhang, Xinping

2013-05-21

The problem posed by therapeutic injection is a clinical practice issue that influences health care quality and patient safety. Although sufficient government subsidy was one of the 12 key interventions to promote rational drug use initiated by WHO (World Health Organization), limited information is available about the association between government subsidy and injection use in primary health care institutions. In 2009, National Essential Medicines System (NEMS) was implemented in China. The subsidy policy plays an important role in maintaining primary health care institutions. This study explores the impact of government subsidies on the injection use in primary health care institutions in China. 126 primary health institutions were included in this study. Institutions were divided into two groups (intervention and control groups) according to the median GS (General subsidy per personnel). Propensity score matching (PSM) was used to minimize the observed covariate differences in the characteristics of the primary institutions between the two groups. Kappa score was calculated to determine the consistency between the groups. Paired chi-square test and Relative Risk (RR) were calculated to compare the differences in injection use between the groups. Among all the investigated prescriptions, the overall percent of people who received an injection prescribed was 36.96% (n = 12600). PSM showed no significant covariate difference among the 34 groups obtained through this analysis. Kappa score (k = -0.082, p = 0.558) indicated an inconsistency between groups and paired chi-square test revealed a significant difference (p < 0.05) in injection use between the two groups. Relative Risk = 0.679 (95%CI [0.485, 0.950]) indicate that high General subsidy per personnel is a protective factor for primary health care institutions to prescribe injections properly. The intervention group obtained a higher possibility of using injection properly. The overall effect of government subsidy on the use of injection was positively significant. However, the mechanism by which government subsidy influence injection administration remains unclear, and thus requires further study.

Monitoring of the Conformational Space of Dipeptides by Generative Topographic Mapping.

PubMed

Horvath, Dragos; Marcou, Gilles; Varnek, Alexandre

2018-01-01

This work describes a procedure to build generative topographic maps (GTM) as 2D representation of the conformational space (CS) of dipeptides. GTMs with excellent propensities to support highly predictive landscapes of various conformational properties were reported for three dipeptides (AA, KE and KR). CS monitoring via GTMproceeds through the projection of conformer ensembles on the map, producing cumulated responsibility (CR) vectors characteristic of the CS areas covered by the ensemble. Overlap of the CS areas visited by two distinct simulations can be expressed by the Tanimoto coefficient Tc of the associated CRs. This idea was used to monitor the reproducibility of the stochastic evolutionary conformer generation process implemented in S4MPLE. It could be shown that conformers produced by <500 S4MPLE runs reproducibly cover the relevant CS zone at given setup of the driving force field. The propensity of a simulation to visit the native CS zone can thus be quantitatively estimated, as the Tc score with respect to the "native" CR, as defined by the ensemble of dipeptide geometries extracted from PDB proteins. It could be shown that low-energy CS regions were indeed found to fall within the native zone. The Tc overlap score behaved as a smooth function of force field parameters. This opens the perspective of a novel force field parameter tuning procedure, bound to simultaneously optimize the behavior of the in Silico simulations for every possible dipeptide. © 2018 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim.

A Framework for Estimating Causal Effects in Latent Class Analysis: Is There a Causal Link Between Early Sex and Subsequent Profiles of Delinquency?

PubMed Central

Lanza, Stephanie T.; Coffman, Donna L.

2013-01-01

Prevention scientists use latent class analysis (LCA) with increasing frequency to characterize complex behavior patterns and profiles of risk. Often, the most important research questions in these studies involve establishing characteristics that predict membership in the latent classes, thus describing the composition of the subgroups and suggesting possible points of intervention. More recently, prevention scientists have begun to adopt modern methods for drawing causal inference from observational data because of the bias that can be introduced by confounders. This same issue of confounding exists in any analysis of observational data, including prediction of latent class membership. This study demonstrates a straightforward approach to causal inference in LCA that builds on propensity score methods. We demonstrate this approach by examining the causal effect of early sex on subsequent delinquency latent classes using data from 1,890 adolescents in 11th and 12th grade from wave I of the National Longitudinal Study of Adolescent Health. Prior to the statistical adjustment for potential confounders, early sex was significantly associated with delinquency latent class membership for both genders (p=0.02). However, the propensity score adjusted analysis indicated no evidence for a causal effect of early sex on delinquency class membership (p=0.76) for either gender. Sample R and SAS code is included in an Appendix in the ESM so that prevention scientists may adopt this approach to causal inference in LCA in their own work. PMID:23839479

A framework for estimating causal effects in latent class analysis: is there a causal link between early sex and subsequent profiles of delinquency?

PubMed

Butera, Nicole M; Lanza, Stephanie T; Coffman, Donna L

2014-06-01

Prevention scientists use latent class analysis (LCA) with increasing frequency to characterize complex behavior patterns and profiles of risk. Often, the most important research questions in these studies involve establishing characteristics that predict membership in the latent classes, thus describing the composition of the subgroups and suggesting possible points of intervention. More recently, prevention scientists have begun to adopt modern methods for drawing causal inference from observational data because of the bias that can be introduced by confounders. This same issue of confounding exists in any analysis of observational data, including prediction of latent class membership. This study demonstrates a straightforward approach to causal inference in LCA that builds on propensity score methods. We demonstrate this approach by examining the causal effect of early sex on subsequent delinquency latent classes using data from 1,890 adolescents in 11th and 12th grade from wave I of the National Longitudinal Study of Adolescent Health. Prior to the statistical adjustment for potential confounders, early sex was significantly associated with delinquency latent class membership for both genders (p = 0.02). However, the propensity score adjusted analysis indicated no evidence for a causal effect of early sex on delinquency class membership (p = 0.76) for either gender. Sample R and SAS code is included in an Appendix in the ESM so that prevention scientists may adopt this approach to causal inference in LCA in their own work.

Cost and utilization outcomes of patients receiving hospital-based palliative care consultation.

PubMed

Penrod, Joan D; Deb, Partha; Luhrs, Carol; Dellenbaugh, Cornelia; Zhu, Carolyn W; Hochman, Tsivia; Maciejewski, Matthew L; Granieri, Evelyn; Morrison, R Sean

2006-08-01

To compare per diem total direct, ancillary (laboratory and radiology) and pharmacy costs of palliative care (PC) compared to usual care (UC) patients during a terminal hospitalization; to examine the association between PC and ICU admission. Retrospective, observational cost analysis using a VA (payer) perspective. Two urban VA medical centers. Demographic and health characteristics of 314 veterans admitted during two years were obtained from VA administrative data. Hospital costs came from the VA cost accounting system. Generalized linear models (GLM) were estimated for total direct, ancillary and pharmacy costs. Predictors included patient age, principal diagnosis, comorbidity, whether patient stay was medical or surgical, site and whether the patient was seen by the palliative care consultation team. A probit regression was used to analyze probability of ICU admission. Propensity score matching was used to improve balance in observed covariates. PC patients were 42 percentage points (95% CI, -56% [corrected] to -31%) less likely to be admitted to ICU. Total direct costs per day were $239 (95% CI, -387 to -122) lower and ancillary costs were $98 (95% CI, -133 to -57) lower than costs for UC patients. There was no difference in pharmacy costs. The results were similar using propensity score matching. PC was associated with significantly lower likelihood of ICU use and lower inpatient costs compared to UC. Our findings coupled with those indicating better patient and family outcomes with PC suggest both a cost and quality incentive for hospitals to develop PC programs.

Symptom Burden among Latino Patients with End-Stage Renal Disease and Access to Standard or Emergency-Only Hemodialysis.

PubMed

Cervantes, Lilia; Hull, Madelyne; Keniston, Angela; Chonchol, Michel; Hasnain-Wynia, Romana; Fischer, Stacy

2018-05-30

Patients with end-stage renal disease (ESRD) have a high symptom burden and this negatively impacts health-related quality of life. Little is known about the symptom burden of Latinos with ESRD and variable access to hemodialysis. To estimate the symptom burden of Latinos with ESRD and access to standard or emergency-only hemodialysis. Observational descriptive study of Latino adults with ESRD receiving standard or emergency-only hemodialysis. Patients completed the Edmonton Symptom Assessment System Revised: Renal (ESAS-r:Renal). We used descriptive statistics and propensity score adjustment to conduct the analysis. ESAS-r:Renal. Participants (N = 67) had a mean age of 58 years (standard deviation [SD] ±13) and a mean Charlson Comorbidity Index of 6.6 ± 2.5, and had been on hemodialysis a mean of 42 months (SD ±43). On average, Latinos with ESRD experienced 7 (SD ±3) symptoms with a mean of 5 ± 3 symptoms reported as moderate or severe. After adjusting for propensity score, emergency-only hemodialysis patients reported experiencing more nausea compared to standard hemodialysis patients (odds ratio 8.95, 95% confidence interval: 1.17-68.31, p = 0.03). Latinos with ESRD have a high symptom burden and compared to patients with standard hemodialysis, patients who rely on emergency-only hemodialysis report more nausea. A national treatment strategy that provides standard hemodialysis for undocumented immigrants with ESRD is an important next step.

Novel Longitudinal and Propensity Score Matched Analysis of Hands-On Cooking and Nutrition Education versus Traditional Clinical Education among 627 Medical Students

PubMed Central

Monlezun, Dominique J.; Leong, Benjamin; Joo, Esther; Birkhead, Andrew G.; Sarris, Leah; Harlan, Timothy S.

2015-01-01

Background. Physicians are inadequately equipped to respond to the global obesity and nutrition-associated chronic disease epidemics. We investigated superiority of simulation-based medical education with deliberate practice (SBME-DP) hands-on cooking and nutrition elective in a medical school-based teaching kitchen versus traditional clinical education for medical students. Materials and Methods. A 59-question panel survey was distributed to an entire medical school twice annually from September 2012 to May 2014. Student diet and attitudes and competencies (DACs) counseling patients on nutrition were compared using conditional multivariate logistic regression, propensity score-weighted, and longitudinal panel analyses. Inverse-variance weighted meta-analysis (IVWM) was used for planned subgroup analysis by year and treatment estimates across the three methods. Results. Of the available 954 students, 65.72% (n = 627) unique students were followed to produce 963 responses. 11.32% (n = 109) of responses were from 84 subjects who participated in the elective. SBME-DP versus traditional education significantly improved fruit and vegetable diet (OR = 1.38, 95% CI: 1.07–1.79, p = 0.013) and attitudes (OR = 1.81, 95% CI: 1.40–2.35, p < 0.001) and competencies (OR = 1.72, 95% CI: 1.54–1.92, p < 0.001). Conclusions. This study reports for the first time superiority longitudinally for SBME-DP style nutrition education for medical students which has since expanded to 13 schools. PMID:26435851

Long-term mortality from cardiac causes after adjuvant hypofractionated vs. conventional radiotherapy for localized left-sided breast cancer.

PubMed

Chan, Elisa K; Woods, Ryan; Virani, Sean; Speers, Caroline; Wai, Elaine S; Nichol, Alan; McBride, Mary L; Tyldesley, Scott

2015-01-01

Ongoing concern remains regarding cardiac injury with hypofractionated whole breast/chest-wall radiotherapy (HF-WBI) compared to conventional radiotherapy (CF-WBI) in left-sided breast cancer patients. The purpose was to determine if cardiac mortality increases with HF-WBI relative to CF-WBI. Between 1990 and 1998, 5334 women with early-stage breast cancer received post-operative radiotherapy to the breast/chest wall alone. A population-based database recorded baseline patient, tumor and treatment factors. Baseline cardiovascular risk factors were identified from hospital administrative records. A propensity-score model balanced risk factors between radiotherapy groups. Cause of death was coded as breast cancer, cardiac or other cause. Cumulative mortality from each cause after radiotherapy was estimated using a competing risk approach. For left-sided cases, median follow-up was 14.2 years. 485 women received CF-WBI, 2221 women received HF-WBI. There was no difference in 15-year mortality from cardiac causes: 4.8% with HF-WBI and 4.2% with CF-WBI (p=0.74), even after propensity-score adjustment (p=0.45). There was no difference in breast cancer mortality or other cause mortality. For right-sided cases, there was no difference in mortality for the three causes of death. At 15-years follow-up, cardiac mortality is not statistically different among left-sided breast cancer patients treated with HF-WBI or CF-WBI. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

Periodontal profile classes predict periodontal disease progression and tooth loss.

PubMed

Morelli, Thiago; Moss, Kevin L; Preisser, John S; Beck, James D; Divaris, Kimon; Wu, Di; Offenbacher, Steven

2018-02-01

Current periodontal disease taxonomies have limited utility for predicting disease progression and tooth loss; in fact, tooth loss itself can undermine precise person-level periodontal disease classifications. To overcome this limitation, the current group recently introduced a novel patient stratification system using latent class analyses of clinical parameters, including patterns of missing teeth. This investigation sought to determine the clinical utility of the Periodontal Profile Classes and Tooth Profile Classes (PPC/TPC) taxonomy for risk assessment, specifically for predicting periodontal disease progression and incident tooth loss. The analytic sample comprised 4,682 adult participants of two prospective cohort studies (Dental Atherosclerosis Risk in Communities Study and Piedmont Dental Study) with information on periodontal disease progression and incident tooth loss. The PPC/TPC taxonomy includes seven distinct PPCs (person-level disease pattern and severity) and seven TPCs (tooth-level disease). Logistic regression modeling was used to estimate relative risks (RR) and 95% confidence intervals (CI) for the association of these latent classes with disease progression and incident tooth loss, adjusting for examination center, race, sex, age, diabetes, and smoking. To obtain personalized outcome propensities, risk estimates associated with each participant's PPC and TPC were combined into person-level composite risk scores (Index of Periodontal Risk [IPR]). Individuals in two PPCs (PPC-G: Severe Disease and PPC-D: Tooth Loss) had the highest tooth loss risk (RR = 3.6; 95% CI = 2.6 to 5.0 and RR = 3.8; 95% CI = 2.9 to 5.1, respectively). PPC-G also had the highest risk for periodontitis progression (RR = 5.7; 95% CI = 2.2 to 14.7). Personalized IPR scores were positively associated with both periodontitis progression and tooth loss. These findings, upon additional validation, suggest that the periodontal/tooth profile classes and the derived personalized propensity scores provide clinical periodontal definitions that reflect disease patterns in the population and offer a useful system for patient stratification that is predictive for disease progression and tooth loss. © 2018 American Academy of Periodontology.

Clinical impact of stress dose steroids in patients with septic shock: insights from the PROWESS-Shock trial.

PubMed

Póvoa, Pedro; Salluh, Jorge I F; Martinez, Maria L; Guillamat-Prats, Raquel; Gallup, Dianne; Al-Khalidi, Hussein R; Thompson, B Taylor; Ranieri, V Marco; Artigas, Antonio

2015-04-28

The aim of our study was to evaluate the clinical impact of the administration of intravenous steroids, alone or in conjunction with drotrecogin-alfa (activated) (DrotAA), on the outcomes in septic shock patients. We performed a sub-study of the PROWESS-Shock trial (septic shock patients who received fluids and vasopressors above a predefined threshold for at least 4 hours were randomized to receive either DrotAA or placebo for 96 hours). A propensity score for the administration of intravenous steroids for septic shock at baseline was constructed using multivariable logistic regression. Cox proportional hazards model using inverse probability of treatment weighting of the propensity score was used to estimate the effect of intravenous steroids, alone or in conjunction with DrotAA, on 28-day and 90-day all-cause mortality. A total of 1695 patients were enrolled of which 49.5% received intravenous steroids for treatment of septic shock at baseline (DrotAA + steroids N = 436; DrotAA + no steroids N = 414; placebo + steroids N = 403; placebo + no steroids N = 442). The propensity weighted risk of 28-day as well as 90-day mortality in those treated vs. those not treated with steroids did not differ among those randomized to DrotAA vs. placebo (interaction p-value = 0.38 and p = 0.27, respectively) nor was a difference detected within each randomized treatment. Similarly, the course of vasopressor use and cardiovascular SOFA did not appear to be influenced by steroid therapy. In patients with lung infection (N = 744), abdominal infection (N = 510), Gram-positive sepsis (N = 420) and Gram-negative sepsis (N = 461), the propensity weighted risk of 28-day as well as 90-day mortality in those treated vs. those not treated with steroids did not differ among those randomized to DrotAA vs. placebo nor was a difference detected within each randomized treatment. In the present study of septic shock patients, after adjustment for treatment selection bias, we were unable to find noticeable positive impact from intravenous steroids for treatment of septic shock at baseline either in patients randomized for DrotAA or placebo. Clinicaltrials.gov NCT00604214 . Registered 24 January 2008.

Effect of dextran-70 on outcome in severe sepsis; a propensity-score matching study.

PubMed

Bentzer, Peter; Broman, Marcus; Kander, Thomas

2017-07-06

Albumin may be beneficial in patients with septic shock but availability is limited and cost is high. The objective of the present study was to investigate if the use of dextran-70 in addition to albumin and crystalloids influences organ failure or mortality in patients with severe sepsis or septic shock. Patients with severe sepsis or septic shock (n = 778) admitted to a university hospital intensive care unit (ICU) between 2007 and 2015 that received dextran-70 during resuscitation were propensity score matched to controls at a 1 to 1 ratio. Outcomes were highest acute kidney injury network (AKIN) score the first 10 days in the ICU, use of renal replacement therapy, days alive and free of organ support the first 28 days after admission to ICU, mortality and events of severe bleeding. Outcomes were assessed using paired hypothesis testing. Propensity score matching resulted in two groups of patients with 245 patients in each group. The dextran group received a median volume of 1483 ml (interquartile range, 1000-2000 ml) of dextran-70 during the ICU stay. Highest AKIN score did not differ between the control- and dextran groups (1 (0-3) versus 2 (0-3), p = 0.06). Incidence of renal replacement therapy in the control- and dextran groups was similar (19% versus 22%, p = 0.42, absolute risk reduction -2.9% [95% CI: -9.9 to 4.2]). Days alive and free of renal replacement, vasopressors and mechanical ventilation did not differ between the control- and dextran groups. The 180-day mortality was 50.2% in the control group and 41.6% in the dextran group (p = 0.046, absolute risk reduction 8.6% [-0.2 to 17.4]). Fraction of patients experiencing a severe bleeding in the first 10 days in the ICU did not differ between the control and dextran groups (14% versus 18%, p = 0.21). There is a paucity of high quality data regarding effects of dextran solutions on outcome in sepsis. In the present study, propensity score matching was used in attempt to reduce bias. No evidence to support a detrimental effect of dextran-70 on mortality or on organ failures in patients with severe sepsis or septic shock could be detected.

Continued Inpatient Care After Primary Total Knee Arthroplasty Increases 30-Day Post-Discharge Complications: A Propensity Score-Adjusted Analysis.

PubMed

McLawhorn, Alexander S; Fu, Michael C; Schairer, William W; Sculco, Peter K; MacLean, Catherine H; Padgett, Douglas E

2017-09-01

Discharge destination, either home or skilled care facility, after total knee arthroplasty (TKA) may be associated with significant variation in postacute care outcomes. The purpose of this study was to characterize the 30-day postdischarge outcomes after primary TKA relative to discharge destination. All primary unilateral TKAs performed for osteoarthritis from 2011-2014 were identified in the National Surgical Quality Improvement Program database. Propensity scores based on predischarge characteristics were used to adjust for selection bias in discharge destination. Propensity-adjusted multivariable logistic regressions were used to examine associations between discharge destination and postdischarge complications. Among 101,256 primary TKAs identified, 70,628 were discharged home and 30,628 to skilled care facilities. Patients discharged to facilities were more frequently were female, older, higher body mass index class, higher Charlson comorbidity index and American Society of Anesthesiologists scores, had predischarge complications, received general anesthesia, and classified as nonindependent preoperatively. Propensity adjustment accounted for this selection bias. Patients discharged to skilled care facilities after TKA had higher odds of any major complication (odds ratio = 1.25; 95% confidence interval, 1.13-1.37) and readmission (odds ratio = 1.81; 95% confidence interval, 1.50-2.18). Skilled care was associated with increased odds for respiratory, septic, thromboembolic, and urinary complications. Associations with death, cardiac, and wound complications were not significant. After controlling for predischarge characteristics, discharge to skilled care facilities vs home after primary TKA is associated with higher odds of numerous complications and unplanned readmission. These results support coordination of care pathways to facilitate home discharge after hospitalization for TKA whenever possible. Copyright © 2017 Elsevier Inc. All rights reserved.

Can You Party Your Way to Better Health? A Propensity Score Analysis of Block Parties and Health

PubMed Central

Dean, Lorraine T.; Hillier, Amy; Chau-Glendinning, Hang; Subramanian, SV; Williams, David R.; Kawachi, Ichiro

2015-01-01

While other indicators of social capital have been linked to health, the role of block parties on health in Black neighborhoods and on Black residents is understudied. Block parties exhibit several features of bonding social capital and are present in nearly 90% of Philadelphia’s predominantly Black neighborhoods. This analysis investigated: (1) whether or not block parties are an indicator of bonding social capital in Black neighborhoods; (2) the degree to which block parties might be related to self-rated health in the ways that other bonding social indicators are related to health; and (3) whether or not block parties are associated with average self-rated health for Black residents particularly. Using census tract-level indicators of bonding social capital and records of block parties from 2003 to 2008 for 381 Philadelphia neighborhoods (defined by census tracts), an ecological-level propensity score was generated to assess the propensity for a block party, adjusting for population demographics, neighborhood characteristics, neighborhood resources and violent crime. Results indicate that in multivariable regression, block parties were associated with increased bonding social capital in Black neighborhoods; however, the calculation of the average effect of the treatment on the treated (ATT) within each propensity score strata showed no effect of block parties on average self-rated health for Black residents. Block parties may be an indicator of bonding social capital in Philadelphia’s predominantly Black neighborhoods, but this analysis did not show a direct association between block parties and self-rated health for Black residents. Further research should consider what other health outcomes or behaviors block parties may be related to and how interventionists can leverage block parties for health promotion. PMID:26117555

Comparing the therapeutic efficacies of third-generation cephalosporins and broader-spectrum β-lactams as appropriate empirical therapy in adults with community-onset monomicrobial Enterobacteriaceae bacteraemia: a propensity score matched analysis.

PubMed

Lee, Chung-Hsun; Hsieh, Chih-Chia; Hong, Ming-Yuan; Hung, Yuan-Pin; Ko, Wen-Chien; Lee, Ching-Chi

2017-05-01

In this study, the therapeutic efficacy of third-generation cephalosporins (3GCs) was compared with that of broader-spectrum β-lactams (BSBLs) [fourth-generation cephalosporins (4GCs) and carbapenems] as empirical therapy in adults with community-onset monomicrobial Enterobacteriaceae bacteraemia. Compared with those in the 3GC group (n = 477), a significantly higher proportion of patients in the BSBL group (n = 141) had initial presentation with severe sepsis or septic shock, critical illness (Pitt bacteraemia score ≥4) at bacteraemia onset and fatal co-morbidities (McCabe classification). For propensity score matching, 318 of the 477 patients in the 3GC group were matched with 106 patients in the BSBL group with the closest propensity scores on the basis of five independent predictors of 28-day mortality. After appropriate matching, no significant differences were observed in major baseline characteristics between the 3GC and BSBL groups in terms of causative micro-organism, bacteraemia severity, major source of bacteraemia, major co-morbidities and severity of co-morbidity. Consequently, the early clinical failure rate (12.9% vs. 12.3%; P = 0.87), bacteraemia severity (Pitt bacteraemia score ≥4; 4.6% vs. 8.2%; P = 0.17) at Day 3, and 3-day (3.8% vs. 7.5%; P = 0.11) and 28-day (13.2% vs. 17.0%; P = 0.33) crude mortality rates between the two groups were similar. These data suggest that the efficacy of 3GCs is similar to that of 4GCs or carbapenems when used as empirical antimicrobial therapy for community-onset Enterobacteriaceae bacteraemia. Copyright © 2017 Elsevier B.V. and International Society of Chemotherapy. All rights reserved.

Data-Adaptive Bias-Reduced Doubly Robust Estimation.

PubMed

Vermeulen, Karel; Vansteelandt, Stijn

2016-05-01

Doubly robust estimators have now been proposed for a variety of target parameters in the causal inference and missing data literature. These consistently estimate the parameter of interest under a semiparametric model when one of two nuisance working models is correctly specified, regardless of which. The recently proposed bias-reduced doubly robust estimation procedure aims to partially retain this robustness in more realistic settings where both working models are misspecified. These so-called bias-reduced doubly robust estimators make use of special (finite-dimensional) nuisance parameter estimators that are designed to locally minimize the squared asymptotic bias of the doubly robust estimator in certain directions of these finite-dimensional nuisance parameters under misspecification of both parametric working models. In this article, we extend this idea to incorporate the use of data-adaptive estimators (infinite-dimensional nuisance parameters), by exploiting the bias reduction estimation principle in the direction of only one nuisance parameter. We additionally provide an asymptotic linearity theorem which gives the influence function of the proposed doubly robust estimator under correct specification of a parametric nuisance working model for the missingness mechanism/propensity score but a possibly misspecified (finite- or infinite-dimensional) outcome working model. Simulation studies confirm the desirable finite-sample performance of the proposed estimators relative to a variety of other doubly robust estimators.

The Sensitivity of Adverse Event Cost Estimates to Diagnostic Coding Error

PubMed Central

Wardle, Gavin; Wodchis, Walter P; Laporte, Audrey; Anderson, Geoffrey M; Baker, Ross G

2012-01-01

Objective To examine the impact of diagnostic coding error on estimates of hospital costs attributable to adverse events. Data Sources Original and reabstracted medical records of 9,670 complex medical and surgical admissions at 11 hospital corporations in Ontario from 2002 to 2004. Patient specific costs, not including physician payments, were retrieved from the Ontario Case Costing Initiative database. Study Design Adverse events were identified among the original and reabstracted records using ICD10-CA (Canadian adaptation of ICD10) codes flagged as postadmission complications. Propensity score matching and multivariate regression analysis were used to estimate the cost of the adverse events and to determine the sensitivity of cost estimates to diagnostic coding error. Principal Findings Estimates of the cost of the adverse events ranged from $16,008 (metabolic derangement) to $30,176 (upper gastrointestinal bleeding). Coding errors caused the total cost attributable to the adverse events to be underestimated by 16 percent. The impact of coding error on adverse event cost estimates was highly variable at the organizational level. Conclusions Estimates of adverse event costs are highly sensitive to coding error. Adverse event costs may be significantly underestimated if the likelihood of error is ignored. PMID:22091908

Development and psychometric evaluation of the Swedish Propensity to Achieve Healthy Lifestyle Scale in patients with hypertension.

PubMed

Broström, Anders; Pakpour, A H; Ulander, Martin; Nilsen, Per

2018-05-18

To develop and validate a Swedish questionnaire to measure propensity for behaviour change regarding food habits, physical activity and weight reduction in patients with hypertension. Cross-sectional design. A total of 270 consecutive patients with hypertension diagnosed at 4 primary care centres in Sweden were included. The 6-item Swedish version of the Propensity to Achieve Healthy Lifestyle Scale (PAHLS) was developed to measure propensity for behaviour change regarding food habits, physical activity and weight reduction. The PAHLS (i.e., including 3 items for preparedness and 3 items for capacity) was developed by 3 multi-professional researchers inspired by the Transtheoretical Model of Behaviour Change in collaboration with clinically active nurses. Data were collected by questionnaires on food habits (i.e., the Food Frequency Questionnaire), physical activity (the International Physical Activity Questionnaire), propensity for a healthy lifestyle (the PHLQ), as well as during a clinical examination. Exploratory (EFA) and confirmatory factor analyses (CFA), as well as Rasch analysis, were used. Of the 270 patients (50% women), 27% scored low levels of physical activity on the International Physical Activity Questionnaire, and 34% of the patients were obese (body mass index ≥30 kg/m 2 ). The EFA (explaining 54% of the variance) showed unidimensionality for the PAHLS that was supported by both CFA and Rasch analyses. No floor and 1.9% ceiling effects were found. Multiple group CFA (an extension of structural equation modelling) showed that the PAHLS operated equivalently across both male and female patients. Internal consistency (Cronbach's alpha 0.83) and composite reliability (0.89) were good. The initial testing of PAHLS provided good validity and reliability scores to measure propensity for behaviour change in patients with hypertension. The PAHLS can be used by nurses as a tool to simplify shared decision making in relation to behavioural changes. This article is protected by copyright. All rights reserved. This article is protected by copyright. All rights reserved.

Thoughts and sensations, twin galaxies of the inner space: The propensity to mind-wander relates to spontaneous sensations arising on the hands.

PubMed

Michael, George A; Tapiero, Isabelle; Gálvez-García, Germán; Jacquot, Laurence

2017-10-01

Sensations and thoughts have been described as potentially related to self-awareness. We therefore asked whether sensations that arise in the absence of external triggers, i.e., spontaneous sensations (SPS), which were shown to relate to interoception and perception of the self, vary as a function of the individual propensity to generate spontaneous thoughts, i.e., mind-wandering. The Mind Wandering Questionnaire (MWQ) was used as a specific tool to assess the frequency and propensity to mind-wander several weeks before completing an SPS task. Correlational analyses between the MWQ score and SPS showed that greater propensity to mind-wander coincided with widespread perception of SPS, while lesser propensity to mind-wander coincided with more spatially restricted perception of SPS. The results are interpreted in light of the role of spontaneous thoughts and sensations in self-awareness. The potential psychological processes and the way they might regulate the relation between mind-wandering and the perception of SPS are discussed. Copyright © 2017 Elsevier Inc. All rights reserved.

Strengthening Causal Estimates for Links Between Spanking and Children's Externalizing Behavior Problems.

PubMed

Gershoff, Elizabeth T; Sattler, Kierra M P; Ansari, Arya

2018-01-01

Establishing causal links when experiments are not feasible is an important challenge for psychology researchers. The question of whether parents' spanking causes children's externalizing behavior problems poses such a challenge because randomized experiments of spanking are unethical, and correlational studies cannot rule out potential selection factors. This study used propensity score matching based on the lifetime prevalence and recent incidence of spanking in a large and nationally representative sample ( N = 12,112) as well as lagged dependent variables to get as close to causal estimates outside an experiment as possible. Whether children were spanked at the age of 5 years predicted increases in externalizing behavior problems by ages 6 and 8, even after the groups based on spanking prevalence or incidence were matched on a range of sociodemographic, family, and cultural characteristics and children's initial behavior problems. These statistically rigorous methods yield the conclusion that spanking predicts a deterioration of children's externalizing behavior over time.

Academic achievement and course taking among language minority youth in U.S. schools: Effects of ESL placement

PubMed Central

Callahan, Rebecca; Wilkinson, Lindsey; Muller, Chandra

2014-01-01

The 1974 Lau decision requires that U.S. public schools ensure a meaningful education for students learning English. English as a Second Language (ESL) placement is an institutional response to the linguistic needs of these students; however, its academic implications remain largely unexplored. Using nationally representative data from the Educational Longitudinal Study (ELS), the effects of ESL placement on college preparatory course enrollment and academic achievement of language minority students are estimated, first with fixed effects regression models and then with multi-level propensity score matching techniques. While numerous school and individual level factors beyond language proficiency predict ESL placement, a significant negative estimated effect of ESL placement on science enrollment and cumulative GPA is consistently found. Perhaps more important, however, no positive effects of ESL placement on the achievement of language minority youth are found when accounting for English proficiency and other potential covariates. PMID:25431506

Academic achievement and course taking among language minority youth in U.S. schools: Effects of ESL placement.

PubMed

Callahan, Rebecca; Wilkinson, Lindsey; Muller, Chandra

2010-03-01

The 1974 Lau decision requires that U.S. public schools ensure a meaningful education for students learning English. English as a Second Language (ESL) placement is an institutional response to the linguistic needs of these students; however, its academic implications remain largely unexplored. Using nationally representative data from the Educational Longitudinal Study (ELS), the effects of ESL placement on college preparatory course enrollment and academic achievement of language minority students are estimated, first with fixed effects regression models and then with multi-level propensity score matching techniques. While numerous school and individual level factors beyond language proficiency predict ESL placement, a significant negative estimated effect of ESL placement on science enrollment and cumulative GPA is consistently found. Perhaps more important, however, no positive effects of ESL placement on the achievement of language minority youth are found when accounting for English proficiency and other potential covariates.

Renal function on admission modifies prognostic impact of diuretics in acute heart failure: a propensity score matched and interaction analysis.

PubMed

Matsue, Yuya; Shiraishi, Atsushi; Kagiyama, Nobuyuki; Yoshida, Kazuki; Kume, Teruyoshi; Okura, Hiroyuki; Suzuki, Makoto; Matsumura, Akihiko; Yoshida, Kiyoshi; Hashimoto, Yuji

2016-12-01

Although intravenous diuretics have been mainstay drugs in patients with acute heart failure (AHF), they have been suggested to have some deleterious effects on prognosis. We postulated that renal function may modify their deleterious effects in AHF patients. The study population consisted of 1094 AHF patients from three hospitals. Renal dysfunction (RD) was defined as estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m 2 on admission, and the cohort was divided into a high-dose furosemide (≥100 mg/48 h) and low-dose furosemide group according to the amount of intravenous furosemide used within 48 h from admission. In the whole cohort, in-hospital mortality rate was higher in the high-dose furosemide group than the low-dose furosemide group (12.5 vs. 6.6 %, respectively, P = 0.001). However, this difference in the in-hospital mortality rates was significant only in the RD subgroup (15.6 vs. 7.0 %, respectively, P < 0.001), and not in the non-RD subgroup (2.5 vs. 5.9 %, respectively, P = 0.384). Propensity score-matched analysis was performed to evaluate the impact of high-dose furosemide on prognosis. After propensity score matching, high-dose furosemide was not associated with in-hospital mortality (OR 1.25, 95 % CI 0.73-2.16, P = 0.408). However, there was a qualitative difference in OR for in-hospital mortality between AHF with RD (OR 1.77, 95 % CI 0.96-3.28, P = 0.068) and without RD (OR 0.23, 95 % CI 0.05-1.10, P = 0.064), and there was a significant interaction between eGFR and prognostic impact of high-dose furosemide (P for OR interaction = 0.013). An inverse relationship was observed between eGFR and OR for in-hospital death in the group treated with high-dose furosemide (decreasing OR with better eGFR). The deleterious effect of diuretics was significantly modified with renal function in AHF. This association may be one reason for poorer prognosis of AHF patients complicated with renal impairment.

Impact of Private Secondary Schooling on Cognitive Skills: Evidence from India

ERIC Educational Resources Information Center

Azam, Mehtabul; Kingdon, Geeta; Wu, Kin Bing

2016-01-01

We examine the effect of attending private secondary school on educational achievement, as measured by students' scores in a comprehensive standardized math test, in two Indian states: Orissa and Rajasthan. We use propensity score matching (PSM) to control for any systematic differences between students attending private secondary schools and…

Evaluation of dystonia in children and adolescents treated with atomoxetine within the Truven MarketScan database: a retrospective cohort study.

PubMed

Meyers, Kristin J; Upadhyaya, Himanshu P; Goodloe, Robert; Kryzhanovskaya, Ludmila A; Liles-Burden, Marie A; Kellier-Steele, Nicole A; Mancini, Michele

2018-05-01

Atomoxetine is a non-stimulant drug indicated for the treatment of attention-deficit/hyperactivity disorder in children aged ≥6 years, adolescents, and adults. In this retrospective cohort study, the incidence and risk of dystonia in children and adolescents treated with atomoxetine was compared to a propensity score-matched cohort of stimulant users. Data between 1 January 2006 and 31 December 2014 from patients aged 6-17 years in the Truven Health Analytics MarketScan database were used to generate two cohorts of patients: (1) atomoxetine users and (2) stimulant (methylphenidates or amphetamines) users. A Cox proportional hazards regression model was used to compare incidence of dystonia across propensity score-matched cohorts. Of the 70,657 atomoxetine users, 70,655 users were propensity score-matched to a stimulant user. In the atomoxetine- and stimulant-treated cohorts, the crude incidence rates of dystonia were 54.9 (95% CI: 27.1-82.7) and 77.9 (95% CI: 49.1-106.8) per 100,000 person-years, respectively. The hazard ratio for occurrence of dystonia with atomoxetine use relative to stimulant use was 0.68 (95% CI: 0.36 - 1.28; P = 0.23). In this large retrospective cohort study, there was no significant difference in incidence or risk of dystonia among patients treated with atomoxetine compared to stimulants.

Luminal-like HER2-negative stage IA breast cancer: a multicenter retrospective study on long-term outcome with propensity score analysis

PubMed Central

De Angelis, Carmine; Di Maio, Massimo; Crispo, Anna; Giuliano, Mario; Schettini, Francesco; Bonotto, Marta; Gerratana, Lorenzo; Iacono, Donatella; Cinausero, Marika; Riccardi, Ferdinando; Ciancia, Giuseppe; De Laurentiis, Michelino; Puglisi, Fabio; De Placido, Sabino; Arpino, Grazia

2017-01-01

The benefit of adding chemotherapy (CT) to adjuvant hormone therapy (HT) in stage IA luminal-like HER2-negative breast cancer (BC) is unclear. We retrospectively evaluated predictive factors and clinical outcome of 1,222 patients from 4 oncologic centers. Three hundred and eighty patients received CT and HT (CT-cohort) and 842 received HT alone (HT-cohort). Disease-free survival (DFS) and overall survival (OS) were evaluated with univariate and multivariate analyses. We also applied the propensity score methodology. Compared with the HT-cohort, patients in the CT-cohort were more likely to be younger, have larger tumors of a higher histological grade that were Ki67-positive, and lower estrogen and progesterone receptor expression. At univariate analysis, a higher histological grade and Ki67 were significantly associated to a lower DFS. At multivariable analysis, only histological grade was predictive of DFS. The CT-cohort had a worse outcome than the HT-cohort in terms of DFS and OS, but differences disappeared when matched according to propensity score. In summary, patients with stage IA luminal-like BC had an excellent prognosis, however relapse and mortality were higher in the CT-cohort than in the HT-cohort. Longer use of adjuvant HT or other therapeutic strategies may be needed to improve outcome. PMID:29348868

Comparison of the Long-Term Outcomes of Mechanical and Bioprosthetic Aortic Valves　- A Propensity Score Analysis.

PubMed

Minakata, Kenji; Tanaka, Shiro; Tamura, Nobushige; Yanagi, Shigeki; Ohkawa, Yohei; Okonogi, Shuichi; Kaneko, Tatsuo; Usui, Akihiko; Abe, Tomonobu; Shimamoto, Mitsuomi; Takahara, Yoshiharu; Yamanaka, Kazuo; Yaku, Hitoshi; Sakata, Ryuzo

2017-07-25

The aim of this study was to assess the long-term outcomes of aortic valve replacement (AVR) with either mechanical or bioprosthetic valves according to age at operation.Methods and Results:A total of 1,002 patients (527 mechanical valves and 475 bioprosthetic valves) undergoing first-time AVR were categorized according to age at operation: group Y, age <60 years; group M, age 60-69 years; and group O, age ≥70 years). Outcomes were compared on propensity score analysis (adjusted for 28 variables). Hazard ratio (HR) was calculated using the Cox regression model with adjustment for propensity score with bioprosthetic valve as a reference (HR=1). There were no significant differences in overall mortality between mechanical and bioprosthetic valves for all age groups. Valve-related mortality was significantly higher for mechanical valves in group O (HR, 2.53; P=0.02). Reoperation rate was significantly lower for mechanical valves in group Y (HR, 0.16; P<0.01) and group M (no events for mechanical valves). Although the rate of thromboembolic events was higher in mechanical valves in group Y (no events for tissue valves) and group M (HR, 9.05; P=0.03), there were no significant differences in bleeding events between all age groups. The type of prosthetic valve used in AVR does not significantly influence overall mortality.

Heart rupture predictors in Spanish myocardial infarction patients: evaluation using propensity score analysis.

PubMed

Ruiz-Bailén, Manuel; Expósito-Ruiz, Manuela; Castillo-Rivera, Ana-María; Rucabado-Aguilar, Luis; Ruiz-García, María Isabel; Ramos-Cuadra, José-Angel; Ruiz-Valverde, Andrés; Gómez-Jiménez, Javier; Benitez-Parejo, José-Luis; Cuñat de la Hoz, José; Abat, Francisco Felices; Valenzuela, Jesús Pérez

2010-05-01

The aim was to evaluate factors associated with the development of heart rupture in a Spanish registry of acute myocardial infarction (AMI) patients. This was a retrospective study of cohorts, including all patients diagnosed with AMI included in the ARIAM Spanish multicenter registry. The study period was from June 1996 to December 2005. The follow-up period was limited to the time of stay in intensive care or coronary care units. Multivariate logistic regression was used to study the factors associated with the development of heart rupture. A propensity score analysis was also performed to determine the involvement of beta blockers, ACE inhibitors, and fibrinolytics in the development of heart rupture. 16,815 AMI patients were included. Heart rupture occurred in 477 (2.8%). Heart rupture was associated with female gender, older age, the absence of previous infarct, and the administration of thrombolysis, while ACE inhibitors and beta blockers acted as protective variables. The propensity score analysis showed that fibrinolysis was a variable associated with heart rupture except in the younger subgroup and in the subgroup with less delay in administration. It was also found that beta blockers and ACE inhibitors are variables providing protection against heart rupture. Heart rupture is associated with older age, female gender, absence of previous infarct, and the administration of thrombolysis, while ACE inhibitors and beta blockers seem to prevent this complication.

Calcium supplementation improves clinical outcome in intensive care unit patients: a propensity score matched analysis of a large clinical database MIMIC-II.

PubMed

Zhang, Zhongheng; Chen, Kun; Ni, Hongying

2015-01-01

Observational studies have linked hypocalcemia with adverse clinical outcome in critically ill patients. However, calcium supplementation has never been formally investigated for its beneficial effect in critically ill patients. To investigate whether calcium supplementation can improve 28-day survival in adult critically ill patients. Secondary analysis of a large clinical database consisting over 30,000 critical ill patients was performed. Multivariable analysis was performed to examine the independent association of calcium supplementation and 28-day morality. Furthermore, propensity score matching technique was employed to investigate the role of calcium supplementation in improving survival. none. Primary outcome was the 28-day mortality. 90-day mortality was used as secondary outcome. A total of 32,551 adult patients, including 28,062 survivors and 4489 non-survivors (28-day mortality rate: 13.8 %) were included. Calcium supplementation was independently associated with improved 28-day mortality after adjusting for confounding variables (hazard ratio: 0.51; 95 % CI 0.47-0.56). Propensity score matching was performed and the after-matching cohort showed well balanced covariates. The results showed that calcium supplementation was associated with improved 28- and 90-day mortality (p < 0.05 for both Log-rank test). In adult critically ill patients, calcium supplementation during their ICU stay improved 28-day survival. This finding supports the use of calcium supplementation in critically ill patients.

Outcome of Intravenous Azithromycin Therapy in Patients with Complicated Scrub Typhus Compared with That of Doxycycline Therapy Using Propensity-Matched Analysis

PubMed Central

Jang, Mi-Ok; Jang, Hee-Chang; Kim, Uh Jin; Ahn, Joon Hwan; Kang, Seung-Ji; Jung, Sook-In; Shin, Hee-Young

2014-01-01

There are no well-matched, controlled studies comparing azithromycin with doxycycline for the treatment of complicated scrub typhus. A retrospective propensity score-matched case-control study was performed for patients who presented with complicated scrub typhus and were treated with doxycycline or azithromycin between 2001 and 2011. Data on comorbidities, clinical manifestations, laboratory studies, treatments, and outcomes were extracted for analysis. The clinical characteristics and outcomes of the azithromycin-treated group (n = 73) were compared to those of the doxycycline-treated group (n = 108). Of 181 patients, 73 from each group were matched by propensity scores. There were no significant differences in baseline characteristics between the matched groups. The treatment success and survival rates were not significantly different (89% [65/73 patients] versus 96% [70/73 patients] and 96% [70/73 patients] versus 96% [70/73 patients], respectively [P > 0.05]). No difference was observed in the time to defervescence or length of hospital stay between the two groups (P > 0.05). In complicated scrub typhus patients (n = 181), multivariate analysis showed that only APACHE II score was an independent risk factor for mortality (95% confidence interval, 1.11 to 1.56; P < 0.001). Our data suggest that outcomes of azithromycin therapy are comparable to those of doxycycline therapy in patients with complicated scrub typhus. PMID:24366734

Home health care and patterns of subsequent VA and medicare health care utilization for veterans.

PubMed

Van Houtven, Courtney Harold; Jeffreys, Amy S; Coffman, Cynthia J

2008-10-01

The Veterans Affairs or VA health care system is in the process of significantly expanding home health care (HHC) nationwide. We describe VA HHC use in 2003 for all VA HHC users from 2002; we examine whether VA utilization across a broad spectrum of services differed for a sample of VA HHC users and their propensity-score-matched controls. We also consider crossover between the VA and Medicare. This is a retrospective study using propensity score and stratified analysis to control for selection bias on observable characteristics. We examined the full cohort of 2002 VA HHC users (n = 24,169) and a 2:1 sample of age- and race-based nonusers (n = 53,356). Utilization measures included VA and Medicare outpatient, inpatient, nursing home, and hospice use, as well as VA home-based primary care, respite care, and adult day health care. VA HHC users had a higher absolute probability of outpatient use by around 3%, of inpatient use by 12%, and nursing home use by 6% than their propensity-score-matched controls. Veterans who used HHC services had a higher rate of VA service use in the subsequent year than controls did, even after we adjusted for differences in observed health status, eligibility advantages, and supplemental insurance status. High utilization for VA home health users spilled over into high Medicare utilization.

Alcohol Use Among Active Duty Women: Analysis AUDIT Scores From the 2011 Health-Related Behavior Survey of Active Duty Military Personnel.

PubMed

Jeffery, Diana D; Mattiko, Mark

2016-01-01

Numerous studies document higher substance use among military men after deployment; similar studies focused on military women are limited. This study examines alcohol use of active duty women and deployment factors, social/environmental/attitudinal factors, and psychological/intrapersonal factors. Secondary data analysis of the 2011 Survey of Health-Related Behavior of active duty military personnel was conducted using bivariate statistics and multiple regression analyses with Alcohol Use Disorders Identification Test scores as the dependent variable. Nearly 94% had low risk for alcohol use disorders. Length of combat experience and extent of combat exposure were unrelated to Alcohol Use Disorders Identification Test scores; noncombat deployment was unrelated after controlling for marital status, age of first drink, pay grade, and branch of service. Significant motivators (p < 0.001) for drinking were "like/enjoy drinking," "drink to cheer up," "drink to forget problems," and significant deterrents were "cost of alcohol" and "fear of upsetting family/friends if used alcohol." Anger propensity, risk propensity, lifetime prevalence of suicidal ideation, and depressed mood were significant predictors in the regression model after controlling for covariates. Findings suggest that some active duty women use alcohol to cope with adverse emotional states, whereas others use alcohol consistent with propensity for high-risk behaviors. Reprint & Copyright © 2016 Association of Military Surgeons of the U.S.

Evaluation of physiotherapy in a prospective cohort of early axial spondyloarthritis. Data from the DESIR cohort.

PubMed

Escalas, Cécile; Dalichampt, Marie; Dougados, Maxime; Poiraudeau, Serge

2016-03-01

To evaluate the effect of physiotherapy on functional limitation in an observational cohort of early axial spondyloarthritis. prospective population-based cohort study. 708 patients with early axial spondyloarthritis between 2007 and 2010 naive of TNF blockers. early physiotherapy defined by at least eight supervised sessions of physical therapy during the first six months. the primary outcome was functional improvement defined by a relative improvement of at least 20% in BASFI at six months. Secondary outcomes were improvement in BASFI at one and two years and ASAS20 response criteria at six months. a propensity score of having physiotherapy was developed and multivariate analysis using propensity score weighting were used to assess the effect of physiotherapy on outcome. Overall, 166 (24%) patients had physiotherapy during the first six months. After using propensity score weighting, there was no functional improvement on the primary outcome in patients treated with early physical therapy (relative risk [IC95%]: 1.15 [0.91-1.45]). No differences were observed on secondary outcomes (relative risk [IC95%]: 0.94 [0.80-1.11]). It seems there is no functional benefit for patients with early spondyloarthritis to be treated early by physiotherapy in daily practice, even though the efficacy of physiotherapy has been shown in several randomized controlled studies. Copyright © 2015 Société française de rhumatologie. Published by Elsevier SAS. All rights reserved.

Assisted reproductive technology has no association with autism spectrum disorders: The Taiwan Birth Cohort Study.

PubMed

Lung, For-Wey; Chiang, Tung-Liang; Lin, Shio-Jean; Lee, Meng-Chih; Shu, Bih-Ching

2018-04-01

The use of assisted reproduction technology has increased over the last two decades. Autism spectrum disorders and assisted reproduction technology share many risk factors. However, previous studies on the association between autism spectrum disorders and assisted reproduction technology have shown inconsistent results. The purpose of this study was to investigate the association between assisted reproduction technology and autism spectrum disorder diagnosis in a national birth cohort database. Furthermore, the results from the assisted reproduction technology and autism spectrum disorder propensity score matching exact matched datasets were compared. For this study, the 6- and 66-month Taiwan Birth Cohort Study datasets were used (N = 20,095). In all, 744 families were propensity score matching exact matched and selected as the assisted reproduction technology sample (ratio of assisted reproduction technology to controls: 1:2) and 415 families as the autism spectrum disorder sample (ratio of autism spectrum disorder to controls: 1:4). Using a national birth cohort dataset, controlling for the confounding factors of assisted reproduction technology conception and autism spectrum disorder diagnosis, both assisted reproduction technology and autism spectrum disorder propensity score matching matched datasets showed the same results of no association between assisted reproduction technology and autism spectrum disorder. Further study on the detailed information regarding the processes and methods of assisted reproduction technology may provide us with more information on the association between assisted reproduction technology and autism spectrum disorder.

Enteral Nutrition for TBI Patients in the Rehabilitation Setting: Associations with Patient Pre-injury and Injury Characteristics and Outcomes

PubMed Central

Horn, Susan D.; Kinikini, Merin; Moore, Linda W.; Hammond, Flora M.; Brandstater, Murray E.; Smout, Randall J.; Barrett, Ryan S.

2015-01-01

Objective To determine the association of enteral nutrition (EN) with patient pre-injury and injury characteristics and outcomes for patients receiving inpatient brain injury rehabilitation. Design Prospective observational study using propensity scores to isolate the effect of EN Setting 9 rehabilitation centers in the US Participants Patients (n=1701) admitted for first full inpatient rehabilitation after a TBI index injury Interventions Not applicable Main Outcome Measures Functional Independence Measure (FIM) at rehabilitation discharge, length of stay (LOS), weight loss, and presence of infections. Results There were many significant differences in pre-injury and injury characteristics for patients who received EN compared to patients who did not. After matching patients with a propensity score >40% for the likely use of EN, patients with greater than 25% of their rehabilitation stay receiving EN with either standard or high protein formulas (greater than 20% of calories coming from protein) had better FIM Motor and FIM Cognitive scores at rehabilitation discharge and less weight loss than similar patients not receiving EN. Conclusions For patients receiving inpatient rehabilitation following TBI and matched on a propensity to use EN of >40%, clinicians should strongly consider, when possible, EN for at least 25% of the patient’s stay and especially with a formula that contains at least 20% protein rather than a standard formula. PMID:26212401

Right anterior mini-thoracotomy vs. conventional sternotomy for aortic valve replacement: a propensity-matched comparison

PubMed Central

Del Giglio, Mauro; Mikus, Elisa; Micari, Antonio; Calvi, Simone; Tripodi, Alberto; Campo, Gianluca; Maietti, Elisa; Castriota, Fausto; Cremonesi, Alberto

2018-01-01

Background Right anterior mini-thoracotomy (MIAVR) is a promising technique for aortic valve replacement. We aimed at comparing its outcomes with those obtained in a propensity-matched group of patients undergoing sternotomy at our two high-volume centers. Methods Main clinical and operative data of patients undergoing aortic valve replacement between January 2010 and May 2016 were retrospectively collected. A total of 678 patients were treated with a standard full sternotomy approach, while MIAVR was performed in 502. Propensity score matching identified 363 patients per each group. Results In-hospital mortality was not significantly different between the propensity-matched groups (1.7% in MIAVR patients vs. 2.2% in conventional sternotomy patients; P=0.79). No significant difference in the incidence of major post-operative complications was observed. Post-operative ventilation times (median 7, range 5–12 hours in MIAVR patients vs. median 7, range 5–12 in conventional sternotomy patients; P=0.72) were not significantly different between the two groups. Cardiopulmonary bypass time (61.0±21.0 vs. 65.9±24.7 min in conventional sternotomy group; P<0.01) and aortic cross-clamping time (48.3±16.7 vs. 53.2±19.6 min in full sternotomy group; P<0.01) were shorter in MIAVR group. EuroSCORE (OR 1.52, 95% CI, 1.12–2.06; P<0.01) was found to be the only independent predictor of intra-hospital mortality in the whole propensity-matched population. Conclusions Our experience shows that mini-access isolated aortic valve surgery is a reproducible, safe and effective procedure with similar outcomes and no longer operative times compared to conventional sternotomy. PMID:29707310

Informing Mitigation of Disaster Loss through Social Media: Evidence from Thailand

NASA Astrophysics Data System (ADS)

Allaire, M.

2015-12-01

This paper is the first to investigate the role of online information and social media in enabling households to reduce natural disaster losses. The historic 2011 Bangkok flood is utilized as a case study to assess how internet use allowed households to mitigate flood losses. This event was one of the first major disasters to affect an urban area with a substantial population connected to social media. The role of online information is investigated with a mixed methods approach, using both quantitative (propensity score matching and multivariate regression analysis) and qualitative (in-depth interviews) techniques. The study relies on two data sources - survey responses from 469 Bangkok households and in-depth interviews with internet users who are a subset of the survey participants. Propensity score matching indicates that social media use enabled households to reduce mean total losses by 37%, using a nearest neighbor estimator. Average loss reductions amounted to USD 3,708 to USD 4,886, depending on the matching estimator. In addition, regression analysis suggests that social media use is associated with lower flood losses (average reduction of USD 2,784). These reductions are notable when considering that total flood losses in 2011 averaged USD 4,903. Social media offered information that was not available from other sources, such as localized and nearly real-time updates of flood location and depth. With knowledge of current flood conditions, Bangkok households could move belongings to higher ground before floodwaters arrived. These findings suggest that utilizing social media users as sensors could better inform populations during natural disasters, particularly in locations that lack real-time, accurate flood monitoring networks. Therefore, expanded access to the internet and social could especially be useful in developing countries, ungagged basins, and highly complex urban environments. There is also an enormous opportunity for disseminating government disaster communication through social media. Overall, the study reveals that online information can enable effective disaster preparedness and reduce flood losses.

Peer Victimization and Sexual Risk Differences Between Lesbian, Gay, Bisexual, Transgender, or Questioning and Nontransgender Heterosexual Youths in Grades 7–12

PubMed Central

Espelage, Dorothy L.

2013-01-01

Objectives. Before and after accounting for peer victimization, we estimated sexual risk disparities between students who self-identified as lesbian, gay, bisexual, transgender, or questioning (LGBTQ) and students who self-identified as nontransgender heterosexual. Methods. Students in grades 7 through 12 in Dane County, Wisconsin, were given the Web-administered Dane County Youth Assessment. One set of analyses was based on a sample that included 11 337 students. Subsequent analyses were based on a sample from which we screened out students who may not have been responding to survey items truthfully. Various multilevel-modeling and propensity-score-matching strategies ensured robustness of the results, examined disparities at lower and higher victimization rates, and explored heterogeneity among LGBTQ-identified youths. Finally, propensity-score-matching strategies estimated LGBTQ–heterosexual disparities in 2 matched samples: a sample that reported higher victimization and one that reported lower victimization. Results. Across 7 sexual risk outcomes, and in middle and high school, LGBTQ-identified youths reported engaging in riskier behavior than did heterosexual-identified youths after we accounted for peer victimization. Risk differentials were present in middle and high school. The LGBTQ group was heterogeneous, with lesbian/gay- and bisexual-identified youths generally appearing most risky, and questioning-identified youths least risky. In the matched sample with lower average victimization rates, LGBTQ-identified youths perceived a greater risk of sexually transmitted infections despite not engaging in sexually risky behavior at significantly higher rates; in the matched sample with higher average victimization rates, all outcomes were significantly different. Conclusions. Demonstrated LGBTQ–heterosexual risk differentials in grades 7 through 8 suggest that interventions need to be implemented during middle school. These interventions should also be differentiated to address the unique risk patterns among LGBTQ subgroups. Finally, models of sexual risk disparities must expand beyond peer victimization. PMID:23947999

Impact of infectious disease consultation on the clinical and economic outcomes of solid organ transplant recipients admitted for infectious complications.

PubMed

Hamandi, Bassem; Husain, Shahid; Humar, Atul; Papadimitropoulos, Emmanuel A

2014-10-15

There has been a paucity of data on the healthcare resource utilization of infectious disease-related complications in solid organ transplant recipients. The aims of this study were to report the clinical and economic burden of infectious disease-related complications, along with the impact of infectious disease consultation. This cohort study evaluated patients requiring admission to a tertiary-care center during 2007, 2008, and 2011. Propensity score matching was used to estimate the effects of patient demographics, comorbidities, and transplant- and infection-related factors on 28-day hospital survival, length of stay (LOS), and medical costs. Infectious disease-related complications occurred in 603 of 1414 (43%) admissions in 306 of 531 (58%) patients. Unadjusted 28-day mortality did not differ between those who received infectious disease consultations vs those who did not (2.9% vs 3.6%, P = .820), however, after propensity score matching, infectious disease consultation resulted in significantly greater 28-day survival estimates (hazard ratio = 0.33; log-rank P = .026), and reduced 30-day rehospitalization rates (16.9% vs 23.9%, P = .036). The median LOS and hospitalization costs were significantly increased for patients receiving an infectious disease consultation than in those managed by the attending team alone (7.0 vs 5.0 days, P = .002, and $9652 vs $6192, P = .003). However, the median LOS (5.5 vs 5.1 days, P = .31) and hospitalization costs ($8106 vs $6912, P = .63) did not differ significantly among those receiving an early infectious disease consultation (<48 hours) vs no consultation, respectively. Infectious disease consultation in recipients of solid organ transplant is associated with increased LOS and hospitalization costs but decreased mortality and reduced rehospitalization rates. Early consultation with infectious disease specialists decreases healthcare resource utilization compared with delayed referrals. © The Author 2014. Published by Oxford University Press on behalf of the Infectious Diseases Society of America. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Outcomes of subsequent non-muscle-invasive bladder cancer treated with intravesical Bacillus Calmette-Guérin after radical nephroureterectomy for upper urinary tract urothelial carcinoma.

PubMed

Miyake, Makito; Tatsumi, Yoshihiro; Matsumoto, Hiroaki; Nagao, Kazuhiro; Matsuyama, Hideyasu; Inamoto, Teruo; Azuma, Haruhito; Yasumoto, Hiroaki; Shiina, Hiroaki; Fujimoto, Kiyohide

2018-05-01

To describe the clinicopathological characteristics and prognosis of subsequent non-muscle-invasive bladder cancer (NMIBC) after radical nephroureterectomy (RNU) for upper urinary tract urothelial carcinoma (UTUC), and particularly its response to intravesical Bacillus Calmette-Guérin (BCG). An observational study was conducted in 1463 patients with UTUC who had undergone RNU and in 1555 patients with primary NMIBC. Of the 1463 patients with UTUC, 256 (17%) subsequently developed NMIBC (UTUC-NMIBC group) and were available for the analysis. The clinicopathological background and outcomes, including intravesical recurrence-free survival and bladder progression-free survival, were compared between the patients with UTUC-NMIBC and the patients with primary NMIBC treated with intravesical BCG. Propensity score matching was performed to adjust for the potential differences in the backgrounds of the two groups. To validate the utility of the CUETO scoring model in the UTUC-NMIBC group, risk scores were calculated and compared with the published probabilities for recurrence and progression. Compared with the unadjusted primary NMIBC group (n = 352), the UTUC-NMIBC group (n = 75) were found to have a worse prognosis for intravesical recurrence and progression, before propensity score matching. After propensity score matching for potential confounding factors, however, a worse prognosis was observed only for intravesical recurrence. The validation test of the CUETO scoring model for the UTUC-NMIBC group showed a significant difference in the rate of intravesical recurrence and progression for the 0-4 and 5-6 score groups between the UTUC-NMIBC group and the CUETO risk table reference data. Compared with the primary NMIBC group, the UTUC-NMIBC group had a worse prognosis after intravesical BCG, especially with regard to intravesical recurrence. This suggests that patients with UTUC-NMIBC are inherently poor responders to BCG exposure. An optimal treatment strategy and risk scoring model to select patients for adjuvant intravesical BCG, chemotherapy or immediate radical cystectomy should be established. © 2017 The Authors BJU International © 2017 BJU International Published by John Wiley & Sons Ltd.

Betahistine plus piracetam dual therapy versus betahistine monotherapy for peripheral vestibular vertigo: a confounder-corrected subanalysis of the OSVaLD study.

PubMed

Melnikov, Oleg A; Lilenko, Sergey V; Nauta, Jos; Ouwens, Mario J N M

2015-11-01

This subanalysis compared the efficacy of betahistine plus piracetam dual therapy versus betahistine monotherapy using data from OSVaLD, a 3 month, open-label, observational study conducted in 2272 patients with peripheral vestibular vertigo. Of the 1898 patients included in the original efficacy population, 1076 were from countries where betahistine plus piracetam dual therapy was prescribed to >1 patient; 114 of these 1076 patients (11%) received the dual therapy and 567 (53%) were treated with betahistine monotherapy; these patients were selected for analysis. Efficacy was assessed using the Dizziness Handicap Inventory (DHI) total and subscale scores. Propensity-score matching was used to correct potential differences in patient baseline characteristics between treatment groups. In addition, a subgroup analysis evaluated 103 patients treated with betahistine because of insufficient efficacy with their existing treatment. In the propensity-score matched, total-population evaluation, improvements in the DHI total and subscale scores were numerically greater in the betahistine plus piracetam group (n = 88) versus the betahistine group (n = 89) (DHI total, -42.9 vs. -37.6, respectively; DHI physical, -12.1 vs. -10.4; DHI emotional, -13.5 vs. -13.2) and statistically significant for the DHI functional score (-17.3 vs. -14.0, respectively, p = 0.01). The percentage of patients with no impairment at final visit was 27% with betahistine and 47% with betahistine plus piracetam; odds ratio: 2.3, 95% confidence interval: 1.3-2.4 (p = 0.007). Similar results were obtained in the subgroup analyses for patients whose current vertigo treatment was insufficient. The overall incidence of adverse events was low and similar in both groups, and there were no discontinuations due to drug-related adverse events. By using propensity-score matching, which controls for potential heterogeneity in patient baseline characteristics and small patient numbers, the results of this analysis suggest that combined betahistine and piracetam may be more effective than betahistine alone in patients with peripheral vestibular vertigo.

A Propensity Score Matching Analysis of the Effects of Special Education Services

PubMed Central

Morgan, Paul L.; Frisco, Michelle; Farkas, George; Hibel, Jacob

2013-01-01

We sought to quantify the effectiveness of special education services as naturally delivered in U.S. schools. Specifically, we examined whether children receiving special education services displayed (a) greater reading or mathematics skills, (b) more frequent learning-related behaviors, or (c) less frequent externalizing or internalizing problem behaviors than closely matched peers not receiving such services. To do so, we used propensity score matching techniques to analyze data from the Early Childhood Longitudinal—Study Kindergarten Cohort, 1998–1999, a large scale, nationally representative sample of U.S. schoolchildren. Collectively, results indicate that receipt of special education services has either a negative or statistically non-significant impact on children’s learning or behavior. However, special education services do yield a small, positive effect on children’s learning-related behaviors. PMID:23606759

Comparative effectiveness from a single-arm trial and real-world data: alectinib versus ceritinib.

PubMed

Davies, Jessica; Martinec, Michael; Delmar, Paul; Coudert, Mathieu; Bordogna, Walter; Golding, Sophie; Martina, Reynaldo; Crane, Gracy

2018-06-26

To compare the overall survival of anaplastic lymphoma kinase-positive non-small-cell lung cancer patients who received alectinib with those who received ceritinib. Two treatment arms (alectinib [n = 183] and ceritinib [n = 67]) were extracted from clinical trials and an electronic health record database, respectively. Propensity scores were applied to balance baseline characteristics. Kaplan-Meier and multivariate Cox regression were conducted. After propensity score adjustment, baseline characteristics were balanced. Alectinib had a prolonged median overall survival (alectinib = 24.3 months and ceritinib = 15.6 months) and lower risk of death (hazard ratio: 0.65; 95% CI: 0.48-0.88). Alectinib was associated with prolonged overall survival versus ceritinib, which is consistent with efficacy evidence from clinical trials.

A Propensity Score Matching Analysis of the Effects of Special Education Services.

PubMed

Morgan, Paul L; Frisco, Michelle; Farkas, George; Hibel, Jacob

2010-02-01

We sought to quantify the effectiveness of special education services as naturally delivered in U.S. schools. Specifically, we examined whether children receiving special education services displayed (a) greater reading or mathematics skills, (b) more frequent learning-related behaviors, or (c) less frequent externalizing or internalizing problem behaviors than closely matched peers not receiving such services. To do so, we used propensity score matching techniques to analyze data from the Early Childhood Longitudinal-Study Kindergarten Cohort, 1998-1999, a large scale, nationally representative sample of U.S. schoolchildren. Collectively, results indicate that receipt of special education services has either a negative or statistically non-significant impact on children's learning or behavior. However, special education services do yield a small, positive effect on children's learning-related behaviors.

Influenza Vaccine Effectiveness in the Elderly Based on Administrative Databases: Change in Immunization Habit as a Marker for Bias

PubMed Central

Hottes, Travis S.; Skowronski, Danuta M.; Hiebert, Brett; Janjua, Naveed Z.; Roos, Leslie L.; Van Caeseele, Paul; Law, Barbara J.; De Serres, Gaston

2011-01-01

Background Administrative databases provide efficient methods to estimate influenza vaccine effectiveness (IVE) against severe outcomes in the elderly but are prone to intractable bias. This study returns to one of the linked population databases by which IVE against hospitalization and death in the elderly was first assessed. We explore IVE across six more recent influenza seasons, including periods before, during, and after peak activity to identify potential markers for bias. Methods and Findings Acute respiratory hospitalization and all-cause mortality were compared between immunized/non-immunized community-dwelling seniors ≥65years through administrative databases in Manitoba, Canada between 2000-01 and 2005-06. IVE was compared during pre-season/influenza/post-season periods through logistic regression with multivariable adjustment (age/sex/income/residence/prior influenza or pneumococcal immunization/medical visits/comorbidity), stratification based on prior influenza immunization history, and propensity scores. Analysis during pre-season periods assessed baseline differences between immunized and unimmunized groups. The study population included ∼140,000 seniors, of whom 50–60% were immunized annually. Adjustment for key covariates and use of propensity scores consistently increased IVE. Estimates were paradoxically higher pre-season and for all-cause mortality vs. acute respiratory hospitalization. Stratified analysis showed that those twice consecutively and currently immunized were always at significantly lower hospitalization/mortality risk with odds ratios (OR) of 0.60 [95%CI0.48–0.75] and 0.58 [0.53–0.64] pre-season and 0.77 [0.69–0.86] and 0.71 [0.66–0.77] during influenza circulation, relative to the consistently unimmunized. Conversely, those forgoing immunization when twice previously immunized were always at significantly higher hospitalization/mortality risk with OR of 1.41 [1.14–1.73] and 2.45 [2.21–2.72] pre-season and 1.21 [1.03–1.43] and 1.78 [1.61–1.96] during influenza circulation. Conclusions The most pronounced IVE estimates were paradoxically observed pre-season, indicating bias tending to over-estimate vaccine protection. Change in immunization habit from that of the prior two years may be a marker for this bias in administrative data sets; however, no analytic technique explored could adjust for its influence. Improved methods to achieve valid interpretation of protection in the elderly are needed. PMID:21818350

[Are Two-Year Vocational Retraining Programs Really Better than One-Year Programs? Findings of a Propensity Score Matched Analysis].

PubMed

Bethge, M; Streibelt, M

2015-12-01

To analyze if one- and 2-year vocational retraining programs achieve similar effects on employment. Analyses were performed with longitudinal administrative data. We included persons aged 18-59 years, who started their retraining between January and June 2005. One- and 2-year program participants were matched by propensity scores. The matched groups were balanced regarding all baseline scores (one-year program: n=514; 2-year program: n=514). 4 and 5 years after start of the vocational retraining program, annual income, the duration of welfare benefits and the risk of a disability pension were comparable in both groups. However, the accumulative income between 2005 and 2009 was 9 294 Euro higher (95% CI: 3 656-14 932 Euro) in one-year retraining participants. Moreover, participants of one-year programs received less welfare benefits. The development of a vocational rehabilitation strategy needs to consider the accumulative advantage of one-year programs. © Georg Thieme Verlag KG Stuttgart · New York.

CADDIS Volume 4. Data Analysis: Advanced Analyses - Controlling for Natural Variability

EPA Pesticide Factsheets

Methods for controlling natural variability, predicting environmental conditions from biological observations method, biological trait data, species sensitivity distributions, propensity scores, Advanced Analyses of Data Analysis references.

Employment during pregnancy and obstetric intervention without medical reason: labor induction and cesarean delivery

PubMed Central

Kozhimannil, Katy Backes; Attanasio, Laura B.; Johnson, Pamela Jo; Gjerdingen, Dwenda K.; McGovern, Patricia M.

2014-01-01

Background Rising rates of labor induction and cesarean delivery, especially when used without a medical reason, have generated concern among clinicians, women, and policymakers. Whether employment status affects pregnant women's childbirth-related care is not known. We estimated the relationship between prenatal employment and obstetric procedures, distinguishing whether women reported that the induction or cesarean was performed for medical reasons. Methods Using data from a nationally-representative sample of women who gave birth in U.S. hospitals (N=1,573), we used propensity score matching to reduce potential bias from non-random selection into employment. Outcomes were cesarean delivery and labor induction, with and without a self-reported medical reason. Exposure was prenatal employment status (full-time employment, not employed). We conducted separate analyses for unmatched and matched cohorts using multivariable regression models. Findings There were no differences in labor induction based on employment status. In unmatched analyses, employed women had higher odds of cesarean delivery overall (adjusted odds ratio (AOR) = 1.45, p=0.046) and cesarean delivery without medical reason (AOR=1.94, p=0.024). Adding an interaction term between employment and college education revealed no significant effects on cesarean without medical reason. There were no significant differences in cesarean delivery by employment status in the propensity score matched analysis. Conclusions Full-time prenatal employment is associated with higher odds of cesarean delivery, but this association was not explained by socio-economic status and no longer existed after accounting for socio-demographic differences by matching women employed full-time with similar women not employed during pregnancy. PMID:25213740

Applying a propensity score-based weighting model to interrupted time series data: improving causal inference in programme evaluation.

PubMed

Linden, Ariel; Adams, John L

2011-12-01

Often, when conducting programme evaluations or studying the effects of policy changes, researchers may only have access to aggregated time series data, presented as observations spanning both the pre- and post-intervention periods. The most basic analytic model using these data requires only a single group and models the intervention effect using repeated measurements of the dependent variable. This model controls for regression to the mean and is likely to detect a treatment effect if it is sufficiently large. However, many potential sources of bias still remain. Adding one or more control groups to this model could strengthen causal inference if the groups are comparable on pre-intervention covariates and level and trend of the dependent variable. If this condition is not met, the validity of the study findings could be called into question. In this paper we describe a propensity score-based weighted regression model, which overcomes these limitations by weighting the control groups to represent the average outcome that the treatment group would have exhibited in the absence of the intervention. We illustrate this technique studying cigarette sales in California before and after the passage of Proposition 99 in California in 1989. While our results were similar to those of the Synthetic Control method, the weighting approach has the advantage of being technically less complicated, rooted in regression techniques familiar to most researchers, easy to implement using any basic statistical software, may accommodate any number of treatment units, and allows for greater flexibility in the choice of treatment effect estimators. © 2010 Blackwell Publishing Ltd.

A method for modeling co-occurrence propensity of clinical codes with application to ICD-10-PCS auto-coding.

PubMed

Subotin, Michael; Davis, Anthony R

2016-09-01

Natural language processing methods for medical auto-coding, or automatic generation of medical billing codes from electronic health records, generally assign each code independently of the others. They may thus assign codes for closely related procedures or diagnoses to the same document, even when they do not tend to occur together in practice, simply because the right choice can be difficult to infer from the clinical narrative. We propose a method that injects awareness of the propensities for code co-occurrence into this process. First, a model is trained to estimate the conditional probability that one code is assigned by a human coder, given than another code is known to have been assigned to the same document. Then, at runtime, an iterative algorithm is used to apply this model to the output of an existing statistical auto-coder to modify the confidence scores of the codes. We tested this method in combination with a primary auto-coder for International Statistical Classification of Diseases-10 procedure codes, achieving a 12% relative improvement in F-score over the primary auto-coder baseline. The proposed method can be used, with appropriate features, in combination with any auto-coder that generates codes with different levels of confidence. The promising results obtained for International Statistical Classification of Diseases-10 procedure codes suggest that the proposed method may have wider applications in auto-coding. © The Author 2016. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Employment during pregnancy and obstetric intervention without medical reason: labor induction and cesarean delivery.

PubMed

Kozhimannil, Katy Backes; Attanasio, Laura B; Johnson, Pamela Jo; Gjerdingen, Dwenda K; McGovern, Patricia M

2014-01-01

Rising rates of labor induction and cesarean delivery, especially when used without a medical reason, have generated concern among clinicians, women, and policymakers. Whether employment status affects pregnant women's childbirth-related care is not known. We estimated the relationship between prenatal employment and obstetric procedures, distinguishing whether women reported that the induction or cesarean was performed for medical reasons. Using data from a nationally representative sample of women who gave birth in U.S. hospitals (n = 1,573), we used propensity score matching to reduce potential bias from nonrandom selection into employment. Outcomes were cesarean delivery and labor induction, with and without a self-reported medical reason. Exposure was prenatal employment status (full-time employment, not employed). We conducted separate analyses for unmatched and matched cohorts using multivariable regression models. There were no differences in labor induction based on employment status. In unmatched analyses, employed women had higher odds of cesarean delivery overall (adjusted odds ratio [AOR], 1.45; p = .046) and cesarean delivery without medical reason (AOR, 1.94; p = .024). Adding an interaction term between employment and college education revealed no effects on cesarean delivery without medical reason. There were no differences in cesarean delivery by employment status in the propensity score-matched analysis. Full-time prenatal employment is associated with higher odds of cesarean delivery, but this association was not explained by socioeconomic status and no longer existed after accounting for sociodemographic differences by matching women employed full time with similar women not employed during pregnancy. Copyright © 2014 Jacobs Institute of Women's Health. Published by Elsevier Inc. All rights reserved.

Impact on postoperative bleeding and cost of recombinant activated factor VII in patients undergoing heart transplantation.

PubMed

Hollis, Allison L; Lowery, Ashleigh V; Pajoumand, Mehrnaz; Pham, Si M; Slejko, Julia F; Tanaka, Kenichi A; Mazzeffi, Michael

2016-01-01

Cardiac transplantation can be complicated by refractory hemorrhage particularly in cases where explantation of a ventricular assist device is necessary. Recombinant activated factor VII (rFVIIa) has been used to treat refractory bleeding in cardiac surgery patients, but little information is available on its efficacy or cost in heart transplant patients. Patients who had orthotopic heart transplantation between January 2009 and December 2014 at a single center were reviewed. Postoperative bleeding and the total costs of hemostatic therapies were compared between patients who received rFVIIa and those who did not. Propensity scores were created and used to control for the likelihood of receiving rFVIIa in order to reduce bias in our risk estimates. Seventy-six patients underwent heart transplantation during the study period. Twenty-one patients (27.6%) received rFVIIa for refractory intraoperative bleeding. There was no difference in postoperative red blood cell transfusion, chest tube output, or surgical re-exploration between patients who received rFVIIa and those who did not, even after adjusting with the propensity score (P = 0.94, P = 0.60, and P = 0.10, respectively). The total cost for hemostatic therapies was significantly higher in the rFVIIa group (median $10,819 vs. $1,985; P < 0.0001). Subgroup analysis of patients who underwent redo-sternotomy with left ventricular assist device explantation did not show any benefit for rFVIIa either. In this relatively small cohort, rFVIIa use was not associated with decreased postoperative bleeding in patients undergoing heart transplantation; however, it led to significantly higher cost.

Naturally occurring workplace facilities to increase the leisure time physical activity of workers: A propensity-score weighted population study.

PubMed

Biswas, Aviroop; Smith, Peter M; Gignac, Monique A M

2018-06-01

The benefit of providing access to physical activity facilities at or near work to support the leisure time physical activity (LTPA) of workers is uncertain. We examined the association between access to physical activity facilities at or near work and the LTPA of workers after adjusting for a range of individual and occupational characteristics. Data was obtained from 60,650 respondents to the 2007-2008 Canadian Community Health Survey. Participants were employed adults ≥18 years of age who had no long-term health condition which reduced their participation in physical activity. Latent class analysis determined naturally occurring combinations of physical activity facilities at or near work. Each combination was balanced by 19 individual and occupational covariate characteristics using inverse probability of treatment weights derived from propensity scores. The association between combinations of physical activity facilities at or near work on LTPA level was estimated by multinomial logistic regression. Five different combinations of physical activity facilities were available to respondents at or near work. Data were analyzed in 2017. All possible physical facilities increased the likelihood for LTPA (OR, 2.08, 95% CI, 1.03-4.20) and other combinations were also positively associated. Respondents with no physical activity facilities were characterized as having a low education, low income, high physically demanding work, poor health and mental health, non-white racial background, and being an immigrant. Access to supportive workplace environments can help workers be physically active. Future research should assess a range of personal, social and environmental factors that may be driving this relationship.

Routine hospital management of self-harm and risk of further self-harm: propensity score analysis using record-based cohort data.

PubMed

Steeg, S; Emsley, R; Carr, M; Cooper, J; Kapur, N

2018-01-01

The care received by people presenting to hospital following self-harm varies and it is unclear how different types of treatment affect risk of further self-harm. Observational cohort data from the Manchester Self-Harm Project, UK, included 16 456 individuals presenting to an Emergency Department with self-harm between 2003 and 2011. Individuals were followed up for 12 months. We also used data from a smaller cohort of individuals presenting to 31 hospitals in England during a 3-month period in 2010/2011, followed up for 6 months. Propensity score (PS) methods were used to address observed confounding. Missing data were imputed using multiple imputation. Following PS stratification, those who received a psychosocial assessment had a lower risk of repeat hospital attendance for self-harm than those who were not assessed [RR 0.87, 95% confidence interval (CI) 0.80-0.95]. The risk was reduced most among people less likely to be assessed. Following PS matching, we found no associations between risks of repeat self-harm and admission to a medical bed, referral to outpatient psychiatry or admission to a psychiatric bed. We did not find a relationship between psychosocial assessment and repeat self-harm in the 31 centre cohort. This study shows the potential value of using novel statistical techniques in large mental health datasets to estimate treatment effects. We found that specialist psychosocial assessment may reduce the risk of repeat self-harm. This type of routine care should be provided for all individuals who present to hospital after self-harm, regardless of perceived risk.

Graduated driver licensing and differential deterrence: The effect of license type on intentions to violate road rules.

PubMed

Poirier, Brigitte; Blais, Etienne; Faubert, Camille

2018-01-01

In keeping with the differential deterrence theory, this article assesses the moderating effect of license type on the relationship between social control and intention to violate road rules. More precisely, the article has two objectives: (1) to assess the effect of license type on intentions to infringe road rules; and (2) to pinpoint mechanisms of social control affecting intentions to violate road rules based on one's type of driver license (a restricted license or a full license). This effect is examined among a sample of 392 young drivers in the province of Quebec, Canada. Drivers taking part in the Graduated Driver Licensing (GDL) program have limited demerit points and there is zero tolerance for drinking-and-driving. Propensity score matching techniques were used to assess the effect of the license type on intentions to violate road rules and on various mechanisms of social control. Regression analyses were then conducted to estimate the moderating effect of license type. Average treatment effects from propensity score matching analyses indicate that respondents with a restricted license have lower levels of intention to infringe road rules. While moral commitment and, to a lesser extent, the perceived risk of arrest are both negatively associated with intentions to violate road rules, the license type moderates the relationship between delinquent peers and intentions to violate road rules. The effect of delinquent peers is reduced among respondents with a restricted driver license. Finally, a diminished capability to resist peer pressure could explain the increased crash risk in months following full licensing. Copyright © 2017 Elsevier Ltd. All rights reserved.

Does breastfeeding help to reduce the risk of childhood overweight and obesity? A propensity score analysis of data from the KiGGS study.

PubMed

Grube, Maike Miriam; von der Lippe, Elena; Schlaud, Martin; Brettschneider, Anna-Kristin

2015-01-01

Current studies suggest that the beneficial effect of breastfeeding on overweight and obesity may have been largely overestimated. We examined the relationship between >4 months of full breastfeeding and overweight/obesity in children living in Germany. We analyzed retrospectively collected data on breastfeeding from children aged 3-17 years who participated in the German Health Interview and Examination Survey for Children and Adolescents (KiGGS baseline study) between 2003 and 2006 (n = 13163). To minimize confounding, we applied propensity score matching and multivariate logistic regression analyses to estimate the effect of breastfeeding on childhood overweight and obesity. Adjusted analyses of the matched dataset (n = 8034) indicated that children who were breastfed for >4 months had a significant reduction in the odds of overweight (OR 0.81 [95% CI 0.71–0.92]) and obesity (OR 0.75 [95% CI 0.61–0.92]) compared to children who were not breastfed or who were breastfed for a shorter duration [corrected].Further analyses stratified by age group showed that the association was strongest in children aged 7-10 years (OR 0.67 [95% CI 0.53-0.84] for overweight and OR 0.56 [95% CI 0.39-0.81] for obesity), while no significant effect could be seen in other age groups. Our findings support the hypothesis that breastfeeding does have a beneficial effect on childhood overweight and obesity, although the effect seems to be strongest in children of primary school age.

Inequality in healthcare costs between residing and non-residing patients: evidence from Vietnam.

PubMed

Nguyen, Hieu M

2017-05-12

Place of residence has been shown to impact health. To date, however, previous studies have only focused on the variability in health outcomes and healthcare costs between urban and rural patients. This study takes a different approach and investigates cost inequality facing non-residing patients - patients who do not reside in the regions in which the hospitals are located. Understanding the sources for this inequality is important, as they are directly related to healthcare accessibility in developing countries. The causal impact of residency status on individual healthcare spending is documented with a quasi-experimental design. The propensity score matching method is applied to a unique patient-level dataset (n = 900) collected at public general and specialist hospitals across North Vietnam. Propensity score matching shows that Vietnamese patients who do not reside in the regions in which the hospitals are located are expected to pay about 15 million Vietnamese dongs (approximately 750 USD) more than those who do, a sizable gap, given the distribution of total healthcare costs for the overall sample. This estimate is robust to alternative matching specifications. The obtained discrepancy is empirically attributable to the differences in three potential contributors, namely spending on accompanying relatives, "courtesy funds," and days of hospitalization. The present study finds that there is significant inequality in healthcare spending between residing and non-residing patients at Vietnamese hospitals and that this discrepancy can be partially explained by both institutional and non-institutional factors. These factors signal practical channels through which policymakers can improve healthcare accessibility.

Outcomes following Kidney transplantation in IgA nephropathy: a UNOS/OPTN analysis.

PubMed

Kadiyala, Aditya; Mathew, Anna T; Sachdeva, Mala; Sison, Cristina P; Shah, Hitesh H; Fishbane, Steven; Jhaveri, Kenar D

2015-10-01

This study updates assessment of post-transplant outcomes in IgAN patients in the modern era of immunosuppression. Using UNOS/OPTN data, patients ≥18 yr of age with first kidney transplant (1/1/1999 to 12/31/2008) were analyzed. Multivariable Cox regression models and propensity score-based matching techniques were used to estimate hazard ratios (HRs) for death-censored allograft survival (DCGS) and patient survival in IgAN compared to non-IgAN. Results of multivariable regression were stratified by donor type (living vs. deceased). A total of 107, 747 recipients were included (4589 with IgAN and 103 158 with non-IgAN). Adjusted HR for DCGS showed no significant difference between IgAN and non-IgAN. IgAN had higher patient survival compared to non-IgAN (HR 0.54, 95% CI 0.47-0.62, p < 0.0001 for deceased donors; HR 0.42, 95% CI 0.33-0.54, p < 0.0001 for living donors). Propensity score-matched analysis was similar, with no significant difference in DCGS between matched groups and higher patient survival in IgAN patients compared to non-IgAN group (HR 0.54, 95% CI 0.47, 0.63; p-value <0.0001). IgAN patients with first kidney transplant have superior patient survival and similar graft survival compared to non-IgAN recipients. Results can be used in prognostication and informed decision-making about kidney transplantation in patients with IgAN. © 2015 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Association between adherence to an antimicrobial stewardship program and mortality among hospitalised cancer patients with febrile neutropaenia: a prospective cohort study

PubMed Central

2014-01-01

Background Initial management of chemotherapy-induced febrile neutropaenia (FN) comprises empirical therapy with a broad-spectrum antimicrobial. Currently, there is sufficient evidence to indicate which antibiotic regimen should be administered initially. However, no randomized trial has evaluated whether adherence to an antimicrobial stewardship program (ASP) results in lower rates of mortality in this setting. The present study sought to assess the association between adherence to an ASP and mortality among hospitalised cancer patients with FN. Methods We conducted a prospective cohort study in a single tertiary hospital from October 2009 to August 2011. All adult patients who were admitted to the haematology ward with cancer and FN were followed up for 28 days. ASP adherence to the initial antimicrobial prescription was determined. The mortality rates of patients who were treated with antibiotics according to the ASP protocol were compared with those of patients treated with other antibiotic regimens. The multivariate Cox proportional hazards model and propensity score were used to estimate 28-day mortality risk. Results A total of 307 FN episodes in 169 subjects were evaluated. The rate of adherence to the ASP was 53%. In a Cox regression analysis, adjusted for propensity scores and other potential confounding factors, ASP adherence was independently associated with lower mortality (hazard ratio, 0.36; 95% confidence interval, 0.14–0.92). Conclusions Antimicrobial selection is important for the initial management of patients with FN, and adherence to the ASP, which calls for the rational use of antibiotics, was associated with lower mortality rates in this setting. PMID:24884397

Association between adherence to an antimicrobial stewardship program and mortality among hospitalised cancer patients with febrile neutropaenia: a prospective cohort study.

PubMed

Rosa, Regis G; Goldani, Luciano Z; dos Santos, Rodrigo P

2014-05-23

Initial management of chemotherapy-induced febrile neutropaenia (FN) comprises empirical therapy with a broad-spectrum antimicrobial. Currently, there is sufficient evidence to indicate which antibiotic regimen should be administered initially. However, no randomized trial has evaluated whether adherence to an antimicrobial stewardship program (ASP) results in lower rates of mortality in this setting. The present study sought to assess the association between adherence to an ASP and mortality among hospitalised cancer patients with FN. We conducted a prospective cohort study in a single tertiary hospital from October 2009 to August 2011. All adult patients who were admitted to the haematology ward with cancer and FN were followed up for 28 days. ASP adherence to the initial antimicrobial prescription was determined. The mortality rates of patients who were treated with antibiotics according to the ASP protocol were compared with those of patients treated with other antibiotic regimens. The multivariate Cox proportional hazards model and propensity score were used to estimate 28-day mortality risk. A total of 307 FN episodes in 169 subjects were evaluated. The rate of adherence to the ASP was 53%. In a Cox regression analysis, adjusted for propensity scores and other potential confounding factors, ASP adherence was independently associated with lower mortality (hazard ratio, 0.36; 95% confidence interval, 0.14-0.92). Antimicrobial selection is important for the initial management of patients with FN, and adherence to the ASP, which calls for the rational use of antibiotics, was associated with lower mortality rates in this setting.

The impact of hepatitis C on labor force participation, absenteeism, presenteeism and non-work activities.

PubMed

DiBonaventura, Marco daCosta; Wagner, Jan-Samuel; Yuan, Yong; L'Italien, Gilbert; Langley, Paul; Ray Kim, W

2011-01-01

Between 2.7 and 3.9 million people are currently infected with the hepatitis C virus (HCV) in the United States. Although many studies have investigated the impact of HCV on direct healthcare costs, few studies have estimated the indirect costs associated with the virus using a nationally-representative dataset. Using data from the 2009 United States (US) National Health and Wellness Survey, patients who reported a hepatitis C diagnosis (n = 695) were compared to controls on labor force participation, productivity loss, and activity impairment after adjusting for demographics, health risk behaviors, and comorbidities. All analyses applied sampling weights to project to the population. Patients with HCV were significantly less likely to be in the labor force than controls and reported significantly higher levels of absenteeism (4.88 vs. 3.03%), presenteeism (16.69 vs. 13.50%), overall work impairment (19.40 vs.15.35%), and activity impairment (25.01 vs. 21.78%). A propensity score matching methodology replicated many of these findings. While much of the work on HCV has focused on direct costs, our results suggest indirect costs should not be ignored when quantifying the societal burden of HCV. To our knowledge, this is the first study which has utilized a large, nationally-representative data source for identifying the impact of HCV on labor force participation and work and activity impairment using both a propensity-score matching and a regression modeling framework. All data were patient-reported (including HCV diagnosis and work productivity), which could have introduced some subjective biases.

Primary fascial closure with biologic mesh reinforcement results in lesser complication and recurrence rates than bridged biologic mesh repair for abdominal wall reconstruction: A propensity score analysis.

PubMed

Giordano, Salvatore; Garvey, Patrick B; Baumann, Donald P; Liu, Jun; Butler, Charles E

2017-02-01

Previous studies suggest that bridged mesh repair for abdominal wall reconstruction may result in worse outcomes than mesh-reinforced, primary fascial closure, particularly when acellular dermal matrix is used. We compared our outcomes of bridged versus reinforced repair using ADM in abdominal wall reconstruction procedures. This retrospective study included 535 consecutive patients at our cancer center who underwent abdominal wall reconstruction either for an incisional hernia or for abdominal wall defects left after excision of malignancies involving the abdominal wall with underlay mesh. A total of 484 (90%) patients underwent mesh-reinforced abdominal wall reconstruction and 51 (10%) underwent bridged repair abdominal wall reconstruction. Acellular dermal matrix was used, respectively, in 98% of bridged and 96% of reinforced repairs. We compared outcomes between these 2 groups using propensity score analysis for risk-adjustment in multivariate analysis and for 1-to-1 matching. Bridged repairs had a greater hernia recurrence rate (33.3% vs 6.2%, P < .001), a greater overall complication rate (59% vs 30%, P = .001), and worse freedom from hernia recurrence (log-rank P <.001) than reinforced repairs. Bridged repairs also had a greater rate of wound dehiscence (26% vs 14%, P = .034) and mesh exposure (10% vs 1%, P = .003) than mesh-reinforced abdominal wall reconstruction. When the treatment method was adjusted for propensity score in the propensity-score-matched pairs (n = 100), we found that the rates of hernia recurrence (32% vs 6%, P = .002), overall complications (32% vs 6%, P = .002), and freedom from hernia recurrence (68% vs 32%, P = .001) rates were worse after bridged repair. We did not observe differences in wound healing and mesh complications between the 2 groups. In our population of primarily cancer patients at MD Anderson Cancer Center bridged repair for abdominal wall reconstruction is associated with worse outcomes than mesh-reinforced abdominal wall reconstruction. Particularly when employing acellular dermal matrix, reinforced repairs should be used for abdominal wall reconstruction whenever possible. Copyright © 2016 Elsevier Inc. All rights reserved.

Tertiary structural propensities reveal fundamental sequence/structure relationships.

PubMed

Zheng, Fan; Zhang, Jian; Grigoryan, Gevorg

2015-05-05

Extracting useful generalizations from the continually growing Protein Data Bank (PDB) is of central importance. We hypothesize that the PDB contains valuable quantitative information on the level of local tertiary structural motifs (TERMs). We show that by breaking a protein structure into its constituent TERMs, and querying the PDB to characterize the natural ensemble matching each, we can estimate the compatibility of the structure with a given amino acid sequence through a metric we term "structure score." Considering submissions from recent Critical Assessment of Structure Prediction (CASP) experiments, we found a strong correlation (R = 0.69) between structure score and model accuracy, with poorly predicted regions readily identifiable. This performance exceeds that of leading atomistic statistical energy functions. Furthermore, TERM-based analysis of two prototypical multi-state proteins rapidly produced structural insights fully consistent with prior extensive experimental studies. We thus find that TERM-based analysis should have considerable utility for protein structural biology. Copyright © 2015 Elsevier Ltd. All rights reserved.

Does parental consent for birth control affect underage pregnancy rates? The case of Texas.

PubMed

Girma, Sourafel; Paton, David

2013-12-01

Previous work based on conjectural responses of minors predicted that the 2003 Texas requirement for parental consent for state-funded birth control to minors would lead to a large increase in underage pregnancies. We use state- and county-level data to test this prediction. The latter allow us to compare the impact of parental consent in counties with and without state-funded family planning clinics. We control for characteristics systematically correlated with the presence of state-funded clinics by combining difference-in-difference estimation with propensity score-weighted regressions. The evidence suggests that the parental consent mandate led to a large decrease in attendance at family planning clinics among teens but did not lead to an increase in underage pregnancies.

Estimating the effect of gang membership on nonviolent and violent delinquency: a counterfactual analysis.

PubMed

Barnes, J C; Beaver, Kevin M; Miller, J Mitchell

2010-01-01

This study reconsiders the well-known link between gang membership and criminal involvement. Recently developed analytical techniques enabled the approximation of an experimental design to determine whether gang members, after being matched with similarly situated nongang members, exhibited greater involvement in nonviolent and violent delinquency. Findings indicated that while gang membership is a function of self-selection, selection effects alone do not account for the greater involvement in delinquency exhibited by gang members. After propensity score matching was employed, gang members maintained a greater involvement in both nonviolent and violent delinquency when measured cross-sectionally, but only violent delinquency when measured longitudinally. Additional analyses using inverse probability of treatment weights reaffirmed these conclusions. © 2010 Wiley-Liss, Inc.

Differential labour market impacts from disability onset.

PubMed

Polidano, Cain; Vu, Ha

2015-03-01

We estimate the causal labour market impacts of disability onset by gender, age and education levels up to 4 years after onset using longitudinal data from the Household Income and Labour Dynamics Australia survey and difference-in-difference propensity score matching techniques. We find lasting negative impacts on employment, especially full-time employment, which is due more to reduced movement into full-time employment than downshifting from full-time to part-time work following onset. Those without post-school education qualifications are particularly vulnerable to the impacts of onset and are more likely to be out of work and on income support than those with qualifications up to 4 years after onset, due in part because they have greater difficulty adjusting. Copyright © 2013 John Wiley & Sons, Ltd.

Five Steps to Successfully Implement and Evaluate Propensity Score Matching in Clinical Research Studies.

PubMed

Staffa, Steven J; Zurakowski, David

2018-01-09

In clinical research, the gold standard level of evidence is the randomized controlled trial (RCT). The availability of nonrandomized retrospective data is growing; however, a primary concern of analyzing such data is comparability of the treatment groups with respect to confounding variables. Propensity score matching (PSM) aims to equate treatment groups with respect to measured baseline covariates to achieve a comparison with reduced selection bias. It is a valuable statistical methodology that mimics the RCT, and it may create an "apples to apples" comparison while reducing bias due to confounding. PSM can improve the quality of anesthesia research and broaden the range of research opportunities. PSM is not necessarily a magic bullet for poor-quality data, but rather may allow the researcher to achieve balanced treatment groups similar to a RCT when high-quality observational data are available. PSM may be more appealing than the common approach of including confounders in a regression model because it allows for a more intuitive analysis of a treatment effect between 2 comparable groups.We present 5 steps that anesthesiologists can use to successfully implement PSM in their research with an example from the 2015 Pediatric National Surgical Quality Improvement Program: a validated, annually updated surgery and anesthesia pediatric database. The first step of PSM is to identify its feasibility with regard to the data at hand and ensure availability of data on any potential confounders. The second step is to obtain the set of propensity scores from a logistic regression model with treatment group as the outcome and the balancing factors as predictors. The third step is to match patients in the 2 treatment groups with similar propensity scores, balancing all factors. The fourth step is to assess the success of the matching with balance diagnostics, graphically or analytically. The fifth step is to apply appropriate statistical methodology using the propensity-matched data to compare outcomes among treatment groups.PSM is becoming an increasingly more popular statistical methodology in medical research. It often allows for improved evaluation of a treatment effect that may otherwise be invalid due to a lack of balance between the 2 treatment groups with regard to confounding variables. PSM may increase the level of evidence of a study and in turn increases the strength and generalizability of its results. Our step-by-step approach provides a useful strategy for anesthesiologists to implement PSM in their future research.

Dysthymia increases the risk of temporomandibular disorder: A population-based cohort study (A STROBE-Compliant Article).

PubMed

Lin, Shang-Lun; Wu, Shang-Liang; Ko, Shun-Yao; Lu, Ching-Hsiang; Wang, Diew-Wei; Ben, Ren-Jy; Horng, Chi-Ting; Yang, Jung-Wu

2016-07-01

Numerous studies have investigated the relationship between depression and temporomandibular disorders (TMD), but the conclusions remain vague. The aim of this study was to examine the causal effect between depression and TMD.The reporting of this study conforms to the STROBE statement. In this retrospective cohort study, all samples were recruited from a representative subdataset of 1 million insured persons for the year 2005 Longitudinal Health Insurance Database, who were randomly selected from all beneficiaries enrolled in the National Health Insurance program of Taiwan. We used a propensity score and stratified 926,560 patients into 2 groups (propensity1 = 588,429 and propensity2 = 338,131) and 4 cohorts (propensity1 with depression = 18,038, propensity1 without depression = 570,391, propensity2 with depression = 38,656, propensity2 without depression = 299,475) to detect the development of TMD among the depressive and nondepressive patients between 2004 and 2013.The positive correlative factors of TMD included female, total number of times seeking medical advice (TTSMA) for anxiety state, TTSMA for generalized anxiety disorder, TTSMA for mandible fracture, and TTSMA for unspecified anomaly of jaw size. The propensity2 group was represented by elder and female-predominant patients who used more psychiatric health resources. Among 3 types of depression, only dysthymia (so-called chronic depression) had a causal impact on TMD in the propensity 2 group. In the propensity 2 group, the hazard ratio of dysthymia for TMD measured by Cox's regression was 1.64 (95% confidence interval 1.28-2.09), after adjusting for demographic factors, psychiatric comorbidities, and maxillofacial confounders. The first-onset mean time of TMD as the consequence of dysthymia was 3.56 years (sd = 2.74, min = 0.08, median = 2.99, max = 9.73).This study demonstrates that dysthymia increases the risk of TMD in elderly and female-predominant patients who use more psychiatric health resources.

Impact of Inadequate Empirical Therapy on the Mortality of Patients with Bloodstream Infections: a Propensity Score-Based Analysis

PubMed Central

Retamar, Pilar; Portillo, María M.; López-Prieto, María Dolores; Rodríguez-López, Fernando; de Cueto, Marina; García, María V.; Gómez, María J.; del Arco, Alfonso; Muñoz, Angel; Sánchez-Porto, Antonio; Torres-Tortosa, Manuel; Martín-Aspas, Andrés; Arroyo, Ascensión; García-Figueras, Carolina; Acosta, Federico; Corzo, Juan E.; León-Ruiz, Laura; Escobar-Lara, Trinidad

2012-01-01

The impact of the adequacy of empirical therapy on outcome for patients with bloodstream infections (BSI) is key for determining whether adequate empirical coverage should be prioritized over other, more conservative approaches. Recent systematic reviews outlined the need for new studies in the field, using improved methodologies. We assessed the impact of inadequate empirical treatment on the mortality of patients with BSI in the present-day context, incorporating recent methodological recommendations. A prospective multicenter cohort including all BSI episodes in adult patients was performed in 15 hospitals in Andalucía, Spain, over a 2-month period in 2006 to 2007. The main outcome variables were 14- and 30-day mortality. Adjusted analyses were performed by multivariate analysis and propensity score-based matching. Eight hundred one episodes were included. Inadequate empirical therapy was administered in 199 (24.8%) episodes; mortality at days 14 and 30 was 18.55% and 22.6%, respectively. After controlling for age, Charlson index, Pitt score, neutropenia, source, etiology, and presentation with severe sepsis or shock, inadequate empirical treatment was associated with increased mortality at days 14 and 30 (odds ratios [ORs], 2.12 and 1.56; 95% confidence intervals [95% CI], 1.34 to 3.34 and 1.01 to 2.40, respectively). The adjusted ORs after a propensity score-based matched analysis were 3.03 and 1.70 (95% CI, 1.60 to 5.74 and 0.98 to 2.98, respectively). In conclusion, inadequate empirical therapy is independently associated with increased mortality in patients with BSI. Programs to improve the quality of empirical therapy in patients with suspicion of BSI and optimization of definitive therapy should be implemented. PMID:22005999

Impact of totally laparoscopic combined management of colorectal cancer with synchronous hepatic metastases on severity of complications: a propensity-score-based analysis.

PubMed

Ratti, Francesca; Catena, Marco; Di Palo, Saverio; Staudacher, Carlo; Aldrighetti, Luca

2016-11-01

Thanks to widespread diffusion of minimally invasive approach in the setting of both colorectal and hepatic surgeries, the interest in combined resections for colorectal cancer and synchronous liver metastases (SCLM) by totally laparoscopic approach (TLA) has increased. Aim of this study was to compare outcome of combined resections for SCLM performed by TLA or by open approach, in a propensity-score-based study. All 25 patients undergoing combined TLA for SCLM at San Raffaele Hospital in Milano were compared in a case-matched analysis with 25 out of 91 patients undergoing totally open approach (TOA group). Groups were matched with 1:2 ratio using propensity scores based on covariates representing disease severity. Main endpoints were postoperative morbidity and long-term outcome. The Modified Accordion Severity Grading System was used to quantify complications. The groups resulted comparable in terms of patients and disease characteristics. The TLA group, as compared to the TOA group, had lower blood loss (350 vs 600 mL), shorter postoperative stay (9 vs 12 days), lower postoperative morbidity index (0.14 vs 0.20) and severity score for complicated patients (0.60 vs 0.85). Colonic anastomosis leakage had the highest fractional complication burden in both groups. In spite of comparable long-term overall survival, the TLA group had better recurrence-free survival. TLA for combined resections is feasible, and its indications can be widened to encompass a larger population of patients, provided its benefits in terms of reduced overall risk and severity of complications, rapid functional recovery and favorable long-term outcomes.

CADDIS Volume 4. Data Analysis: Advanced Analyses - Controlling for Natural Variability: SSD Plot Diagrams

EPA Pesticide Factsheets

Methods for controlling natural variability, predicting environmental conditions from biological observations method, biological trait data, species sensitivity distributions, propensity scores, Advanced Analyses of Data Analysis references.

Retrospective Comparison of Single-Port Sleeve Gastrectomy Versus Three-Port Laparoscopic Sleeve Gastrectomy: a Propensity Score Adjustment Analysis.

PubMed

Mauriello, Claudio; Chouillard, Elie; d'alessandro, Antonio; Marte, Gianpaolo; Papadimitriou, Argyri; Chahine, Elias; Kassir, Radwan

2018-04-16

Evaluate the efficacy of single-port sleeve gastrectomy (SPSG) and then compare it to a less-invasive sleeve approach (three-port) (3PSG) according to a propensity score (PS) matching analysis. We analyzed all patients who underwent SG through a three-port or a single-port laparoscopic approach. After 2 years, the follow-up was completed in 84% patients treated with 3PSG and 95% patients of the SPSG group. Excess weight loss (EWL) was comparable for the first year of follow-up within the two groups except for the controls at 3 months in which the SPSG group showed a higher EWL (p = 0.0243). We demonstrated the efficacy of SPSG in bariatric surgery even compared to another, less invasive, laparoscopic SG approach (three-port).

Hunger and overweight in Canadian school-aged children: A propensity score matching analysis.

PubMed

Sentenac, Mariane; Gariepy, Geneviève; McKinnon, Britt; Elgar, Frank J

2016-12-27

The last decade saw a higher prevalence of overweight reported among food-insecure families in Canada, but no robust evidence exists on the covariate-adjusted association in children. In this study, we examined the association between hunger and overweight in Canadian students, using a propensity score matching analysis to reduce confounding. This research used data from the 2009/2010 Canadian Health Behaviour in School-aged Children study on a representative national sample of students in Grades 6 through 10. Students self-reported their height and weight and how often they have gone to school or to bed hungry due to a lack of food at home. Multivariate logistic regression modeling was conducted on the total sample (N = 17,694) and on the sample matched on propensity scores (n = 7,788). The overall prevalence of overweight among students was 20.2% with a significant difference between students who reported hunger (24.0%; 95% CI: 22.1-26.0) and students who did not (19.0%; 95% CI: 17.9-20.2). Analysis on the matched sample revealed a significant association between hunger and overweight in children (adjusted odds ratio: 1.30; 95% CI: 1.12-1.50). A substantial number of Canadian students have reported being hungry because of a lack of food at home. These students are at increased risk of overweight, regardless of their social class. Child hunger and household food insecurity exist in Canada and constitute a call for policy action at a national level.

Effects of sugammadex vs. pyridostigmine-glycopyrrolate on post-operative nausea and vomiting: propensity score matching.

PubMed

Lee, O H; Choi, G J; Kang, H; Baek, C W; Jung, Y H; Woo, Y C; Oh, J; Park, Y H

2017-01-01

Sugammadex is a new agent that reverses neuromuscular blockade by aminosteroid neuromuscular blocker. This retrospective study compared the effects of sugammadex on post-operative nausea and vomiting (PONV) with those of a pyridostigmine-glycopyrrolate mixture. We reviewed the electronic medical records of 7179 patients who had received fentanyl-based, intravenous, patient-controlled analgesia (IV-PCA) at Chung-Ang University Hospital between January 1, 2010 and December 31, 2015. We categorized the patients into two groups on the basis of the type of reversal agent to neuromuscular blockade that was used: a traditional reversal agent (pyridostigmine-glycopyrrolate mixture; Group R; n = 7059) and sugammadex (Group S; n = 120). The propensity score matching method was then used to select 408 subjects in Group R and 115 subjects in Group S; on the basis of their covariates, these subjects were then matched with a counterpart in the other group. After propensity score matching, the two groups were well balanced with respect to all baseline covariates. In Group S, the numeric rating scale of nausea on day 0, as well as the number of patients who vomited on day 0, was lower than that in group R. Furthermore, Group S used fewer rescue antiemetics on day 0 and had a higher complete response on day 0. Sugammadex might be more beneficial for PONV compared to pyridostigmine-glycopyrrolate mixture for patients who have received opioid-based IV-PCA. © 2016 The Acta Anaesthesiologica Scandinavica Foundation. Published by John Wiley & Sons Ltd.

Acute kidney injury and edaravone in acute ischemic stroke: the Fukuoka Stroke Registry.

PubMed

Kamouchi, Masahiro; Sakai, Hironori; Kiyohara, Yutaka; Minematsu, Kazuo; Hayashi, Kunihiko; Kitazono, Takanari

2013-11-01

A free radical scavenger, edaravone, which has been used for the treatment of ischemic stroke, was reported to cause acute kidney injury (AKI) as a fatal adverse event. The aim of the present study was to clarify whether edaravone is associated with AKI in patients with acute ischemic stroke. From the Fukuoka Stroke Registry database, 5689 consecutive patients with acute ischemic stroke who were hospitalized within 24 hours of the onset of symptoms were included in this study. A logistic regression analysis for the Fukuoka Stroke Registry cohort was done to identify the predictors for AKI. A propensity score-matched nested case-control study was also performed to elucidate any association between AKI and edaravone. Acute kidney injury occurred in 128 of 5689 patients (2.2%) with acute ischemic stroke. A multivariate analysis revealed that the stroke subtype, the basal serum creatinine level, and the presence of infectious complications on admission were each predictors of developing AKI. In contrast, a free radical scavenger, edaravone, reduced the risk of developing AKI (multivariate-adjusted odds ratio [OR] .45, 95% confidence interval [CI] .30-.67). Propensity score-matched case-control study confirmed that edaravone use was negatively associated with AKI (propensity score-adjusted OR .46, 95% CI .29-.74). Although AKI has a significant impact on the clinical outcome of hospital inpatients, edaravone has a protective effect against the development of AKI in patients with acute ischemic stroke. Copyright © 2013 National Stroke Association. Published by Elsevier Inc. All rights reserved.

Positive association between hypertension and urinary bladder cancer: epidemiologic evidence involving 79,236 propensity score-matched individuals.

PubMed

Kok, Victor C; Zhang, Han-Wei; Lin, Chin-Teng; Huang, Shih-Chung; Wu, Ming-Feng

2018-06-18

We hypothesized that hypertensive patients harbor a higher risk of urinary bladder (UB) cancer. We performed a population-based cohort study on adults using a National Health Insurance Research Database (NHIRD) dataset. Hypertension and comparison non-hypertensive (COMP) groups comprising 39,618 patients each were propensity score-matched by age, sex, index date, and medical comorbidities. The outcome was incident UB cancer validated using procedure codes. We constructed multivariable Cox models to derive adjusted hazard ratios (aHRs) and 95% confidence intervals (CIs). Cumulative incidence was compared using a log-rank test. During a total follow-up duration of 380,525 and 372,020 person-years in the hypertension and COMP groups, 248 and 186 patients developed UB cancer, respectively, representing a 32% increase in the risk (aHR, 1.32; 95% CI, 1.09-1.60). Hypertensive women harbored a significantly increased risk of UB cancer (aHR, 1.55; 95% CI, 1.12-2.13) compared with non-hypertensive women, whereas men with hypertension had a statistically non-significant increased risk (aHR, 1.22; 95% CI, 0.96-1.55). The sensitivity analysis demonstrated that the increased risk was sustained throughout different follow-up durations for the entire cohort; a statistical increase in the risk was also noted among hypertensive men. This nationwide population-based propensity score-matched cohort study supports a positive association between hypertension and subsequent UB cancer development.

Duodenal localization is a negative predictor of survival after small bowel adenocarcinoma resection: A population-based, propensity score-matched analysis.

PubMed

Wilhelm, Alexander; Galata, Christian; Beutner, Ulrich; Schmied, Bruno M; Warschkow, Rene; Steffen, Thomas; Brunner, Walter; Post, Stefan; Marti, Lukas

2018-03-01

This study assessed the influence of tumor localization of small bowel adenocarcinoma on survival after surgical resection. Patients with resected small bowel adenocarcinoma, ACJJ stage I-III, were identified from the Surveillance, Epidemiology, and End Results database from 2004 to 2013. The impact of tumor localization on overall and cancer-specific survival was assessed using Cox proportional hazard regression models with and without risk-adjustment and propensity score methods. Adenocarcinoma was localized to the duodenum in 549 of 1025 patients (53.6%). There was no time trend for duodenal localization (P = 0.514). The 5-year cancer-specific survival rate was 48.2% (95%CI: 43.3-53.7%) for patients with duodenal carcinoma and 66.6% (95%CI: 61.6-72.1%) for patients with cancer located in the jejunum or ileum. Duodenal localization was associated with worse overall and cancer-specific survival in univariable (HR = 1.73; HR = 1.81, respectively; both P < 0.001), multivariable (HR = 1.52; HR = 1.65; both P < 0.001), and propensity score-adjusted analyses (HR = 1.33, P = 0.012; HR = 1.50, P = 0.002). Furthermore, young age, retrieval of more than 12 regional lymph nodes, less advanced stage, and married matrimonial status were positive, independent prognostic factors. Duodenal localization is an independent risk factor for poor survival after resection of adenocarcinoma. © 2017 Wiley Periodicals, Inc.

Impact of early human milk on sepsis and health-care costs in very low birth weight infants.

PubMed

Patel, A L; Johnson, T J; Engstrom, J L; Fogg, L F; Jegier, B J; Bigger, H R; Meier, P P

2013-07-01

To study the incidence of sepsis and neonatal intensive care unit (NICU) costs as a function of the human milk (HM) dose received during the first 28 days post birth for very low birth weight (VLBW) infants. Prospective cohort study of 175 VLBW infants. The average daily dose of HM (ADDHM) was calculated from daily nutritional data for the first 28 days post birth (ADDHM-Days 1-28). Other covariates associated with sepsis were used to create a propensity score, combining multiple risk factors into a single metric. The mean gestational age and birth weight were 28.1 ± 2.4 weeks and 1087 ± 252 g, respectively. The mean ADDHM-Days 1-28 was 54 ± 39 ml kg(-1) day(-1) (range 0-135). Binary logistic regression analysis controlling for propensity score revealed that increasing ADDHM-Days 1-28 was associated with lower odds of sepsis (odds ratio 0.981, 95% confidence interval 0.967-0.995, P=0.008). Increasing ADDHM-Days 1-28 was associated with significantly lower NICU costs. A dose-response relationship was demonstrated between ADDHM-Days 1-28 and a reduction in the odds of sepsis and associated NICU costs after controlling for propensity score. For every HM dose increase of 10 ml kg(-1) day(-1), the odds of sepsis decreased by 19%. NICU costs were lowest in the VLBW infants who received the highest ADDHM-Days 1-28.

Long-term survival in laparoscopic vs open resection for colorectal liver metastases: inverse probability of treatment weighting using propensity scores.

PubMed

Lewin, Joel W; O'Rourke, Nicholas A; Chiow, Adrian K H; Bryant, Richard; Martin, Ian; Nathanson, Leslie K; Cavallucci, David J

2016-02-01

This study compares long-term outcomes between intention-to-treat laparoscopic and open approaches to colorectal liver metastases (CLM), using inverse probability of treatment weighting (IPTW) based on propensity scores to control for selection bias. Patients undergoing liver resection for CLM by 5 surgeons at 3 institutions from 2000 to early 2014 were analysed. IPTW based on propensity scores were generated and used to assess the marginal treatment effect of the laparoscopic approach via a weighted Cox proportional hazards model. A total of 298 operations were performed in 256 patients. 7 patients with planned two-stage resections were excluded leaving 284 operations in 249 patients for analysis. After IPTW, the population was well balanced. With a median follow up of 36 months, 5-year overall survival (OS) and recurrence-free survival (RFS) for the cohort were 59% and 38%. 146 laparoscopic procedures were performed in 140 patients, with weighted 5-year OS and RFS of 54% and 36% respectively. In the open group, 138 procedures were performed in 122 patients, with a weighted 5-year OS and RFS of 63% and 38% respectively. There was no significant difference between the two groups in terms of OS or RFS. In the Brisbane experience, after accounting for bias in treatment assignment, long term survival after LLR for CLM is equivalent to outcomes in open surgery. Crown Copyright © 2015. Published by Elsevier Ltd. All rights reserved.

Long-term survival in laparoscopic vs open resection for colorectal liver metastases: inverse probability of treatment weighting using propensity scores

PubMed Central

Lewin, Joel W.; O'Rourke, Nicholas A.; Chiow, Adrian K.H.; Bryant, Richard; Martin, Ian; Nathanson, Leslie K.; Cavallucci, David J.

2015-01-01

Background This study compares long-term outcomes between intention-to-treat laparoscopic and open approaches to colorectal liver metastases (CLM), using inverse probability of treatment weighting (IPTW) based on propensity scores to control for selection bias. Method Patients undergoing liver resection for CLM by 5 surgeons at 3 institutions from 2000 to early 2014 were analysed. IPTW based on propensity scores were generated and used to assess the marginal treatment effect of the laparoscopic approach via a weighted Cox proportional hazards model. Results A total of 298 operations were performed in 256 patients. 7 patients with planned two-stage resections were excluded leaving 284 operations in 249 patients for analysis. After IPTW, the population was well balanced. With a median follow up of 36 months, 5-year overall survival (OS) and recurrence-free survival (RFS) for the cohort were 59% and 38%. 146 laparoscopic procedures were performed in 140 patients, with weighted 5-year OS and RFS of 54% and 36% respectively. In the open group, 138 procedures were performed in 122 patients, with a weighted 5-year OS and RFS of 63% and 38% respectively. There was no significant difference between the two groups in terms of OS or RFS. Conclusion In the Brisbane experience, after accounting for bias in treatment assignment, long term survival after LLR for CLM is equivalent to outcomes in open surgery. PMID:26902138

Impact of Early Human Milk on Sepsis and Health Care Costs in Very Low Birth Weight Infants

PubMed Central

Patel, Aloka L.; Johnson, Tricia J.; Engstrom, Janet L.; Fogg, Louis F.; Jegier, Briana J.; Bigger, Harold R.; Meier, Paula P.

2013-01-01

Objective To study the incidence of sepsis and neonatal intensive care unit (NICU) costs as a function of the human milk (HM) dose received during the first 28 days post-birth for very low birth weight (VLBW) infants. Study Design Prospective cohort study of 175 VLBW infants. Average daily dose of HM (ADDHM) was calculated from daily nutritional data for the first 28 days post-birth (ADDHM-Days1-28). Other covariates associated with sepsis were used to create a propensity score, combining multiple risk factors into a single metric. Result The mean gestational age and birth weight were 28.1 ± 2.4 wk and 1087 ± 252 g, respectively. The mean ADDHM-Days1-28 was 54 ± 39 mL/kg/d (range 0-135). Binary logistic regression analysis controlling for propensity score revealed that increasing ADDHM-Days1-28 was associated with lower odds of sepsis (OR .981, 95%CI .967-.995, p=.008). Increasing ADDHM-Days1-28 was associated with significantly lower NICU costs. Conclusion A dose-response relationship was demonstrated between ADDHM-Days1-28 and a reduction in the odds of sepsis and associated NICU costs after controlling for propensity score. For every HM dose increase of 10 mL/kg/d, the odds of sepsis decreased by 19%. NICU costs were lowest in the VLBW infants who received the highest ADDHM-Days1-28. PMID:23370606

Amiodarone use in patients listed for heart transplant is associated with increased 1-year post-transplant mortality.

PubMed

Cooper, Lauren B; Mentz, Robert J; Edwards, Leah B; Wilk, Amber R; Rogers, Joseph G; Patel, Chetan B; Milano, Carmelo A; Hernandez, Adrian F; Stehlik, Josef; Lund, Lars H

2017-02-01

Pre-transplant amiodarone use has been postulated as a risk factor for morbidity and mortality after orthotopic heart transplantation (OHT). We assessed pre-OHT amiodarone use and tested the hypothesis that it is associated with impaired post-OHT outcomes. We performed a retrospective cohort analysis of adult OHT recipients from the registry of the International Society for Heart and Lung Transplantation (ISHLT). All patients had been transplanted between 2005 and 2013 and were stratified by pre-OHT amiodarone use. We derived propensity scores using logistic regression with amiodarone use as the dependent variable, and assessed the associations between amiodarone use and outcomes with Kaplan-Meier analysis after matching patients 1:1 based on propensity score, and with Cox regression with adjustment for propensity score. Of the 14,944 OHT patients in the study cohort, 32% (N = 4,752) received pre-OHT amiodarone. Amiodarone use was higher in recent years (29% in 2005 to 2007, 32% in 2008 to 2010, 35% in 2011 to 2013). Amiodarone-treated patients were older and more frequently had a history of sudden cardiac death (27% vs 13%) and pre-OHT mechanical circulatory support. Key donor characteristics and allograft ischemia times were similar between groups. In propensity-matched analyses, amiodarone-treated patients had higher rates of cardiac reoperation (15% vs 13%) and permanent pacemaker (5% vs 3%) after OHT and before discharge. Amiodarone-treated patients also had higher 1-year mortality (hazard ratio 1.15, 95% confidence interval 1.02 to 1.30), but the risks of early graft failure, retransplantation and rehospitalization were similar between groups. Amiodarone use before OHT was independently associated with increased 1-year mortality. The need for amiodarone therapy should be carefully and continuously assessed in patients awaiting OHT. Copyright © 2016 International Society for Heart and Lung Transplantation. Published by Elsevier Inc. All rights reserved.

Carvedilol Compared With Metoprolol Succinate in the Treatment and Prognosis of Patients With Stable Chronic Heart Failure: Carvedilol or Metoprolol Evaluation Study.

PubMed

Fröhlich, Hanna; Zhao, Jingting; Täger, Tobias; Cebola, Rita; Schellberg, Dieter; Katus, Hugo A; Grundtvig, Morten; Hole, Torstein; Atar, Dan; Agewall, Stefan; Frankenstein, Lutz

2015-09-01

β-Blockers exert a prognostic benefit in the treatment of chronic heart failure. Their pharmacological properties vary. The only substantial comparative trial to date-the Carvedilol or Metoprolol European Trial-has compared carvedilol with short-acting metoprolol tartrate at different dose equivalents. We therefore addressed the relative efficacy of equal doses of carvedilol and metoprolol succinate on survival in multicenter hospital outpatients with chronic heart failure. Four thousand sixteen patients with stable systolic chronic heart failure who were using either carvedilol or metoprolol succinate were identified in the Norwegian Heart Failure Registry and The Heart Failure Registry of the University of Heidelberg, Germany. Patients were individually matched on both the dose equivalents and the respective propensity scores for β-blocker treatment. During a follow-up for 17 672 patient-years, it was found that 304 (27.2%) patients died in the carvedilol group and 1066 (36.8%) in the metoprolol group. In a univariable analysis of the general sample, metoprolol therapy was associated with higher mortality compared with carvedilol therapy (hazard ratio, 1.49; 95% confidence interval, 1.31-1.69; P<0.001). This difference was not seen after multivariable adjustment (hazard ratio, 0.93; 95% confidence interval, 0.57-1.50; P=0.75) and adjustment for propensity score and dose equivalents (hazard ratio, 1.06; 95% confidence interval, 0.94-1.20; P=0.36) or in the propensity and dose equivalent-matched sample (hazard ratio, 1.00; 95% confidence interval, 0.82-1.23; P=0.99). These results were essentially unchanged for all prespecified subgroups. In outpatients with chronic heart failure, no conclusive association between all-cause mortality and treatment with carvedilol or metoprolol succinate was observed after either multivariable adjustment or multilevel propensity score matching. © 2015 American Heart Association, Inc.

Evaluation of Model Specification, Variable Selection, and Adjustment Methods in Relation to Propensity Scores and Prognostic Scores in Multilevel Data

ERIC Educational Resources Information Center

Yu, Bing; Hong, Guanglei

2012-01-01

This study uses simulation examples representing three types of treatment assignment mechanisms in data generation (the random intercept and slopes setting, the random intercept setting, and a third setting with a cluster-level treatment and an individual-level outcome) in order to determine optimal procedures for reducing bias and improving…

Differential Third-Grade Outcomes Associated with Attending Publicly Funded Preschool Programs for Low-Income Latino Children

ERIC Educational Resources Information Center

Ansari, Arya; L?pez, Michael; Manfra, Louis; Bleiker, Charles; Dinehart, Laura H. B.; Hartman, Suzanne C.; Winsler, Adam

2017-01-01

This study examined the third-grade outcomes of 11,902 low-income Latino children who experienced public school pre-K or child care via subsidies (center-based care) at age 4 in Miami-Dade County, Florida. Regression and propensity score analyses revealed that children who experienced public school pre-K earned higher scores on standardized…

An integrated epidemiological and neural net model of the warfarin effect in managed care patients.

PubMed

Jacobs, David M; Stefanovic, Filip; Wilton, Greg; Gomez-Caminero, Andres; Schentag, Jerome J

2017-01-01

Risk assessment tools are utilized to estimate the risk for stroke and need of anticoagulation therapy for patients with atrial fibrillation (AF). These risk stratification scores are limited by the information inputted into them and a reliance on time-independent variables. The objective of this study was to develop a time-dependent neural net model to identify AF populations at high risk of poor clinical outcomes and evaluate the discriminatory ability of the model in a managed care population. We performed a longitudinal, cohort study within a health-maintenance organization from 1997 to 2008. Participants were identified with incident AF irrespective of warfarin status and followed through their duration within the database. Three clinical outcome measures were evaluated including stroke, myocardial infarction, and hemorrhage. A neural net model was developed to identify patients at high risk of clinical events and defined to be an "enriched" patient. The model defines the enrichment based on the top 10 minimum mean square error output parameters that describe the three clinical outcomes. Cox proportional hazard models were utilized to evaluate the outcome measures. Among 285 patients, the mean age was 74±12 years with a mean follow-up of 4.3±2.6 years, and 154 (54%) were treated with warfarin. After propensity score adjustment, warfarin use was associated with a slightly increased risk of adverse outcomes (including stroke, myocardial infarction, and hemorrhage), though it did not attain statistical significance (adjusted hazard ratio [aHR] =1.22; 95% confidence interval [CI] 0.75-1.97; p =0.42). Within the neural net model, subjects at high risk of adverse outcomes were identified and labeled as "enriched." Following propensity score adjustment, enriched subjects were associated with an 81% higher risk of adverse outcomes as compared to nonenriched subjects (aHR=1.81; 95% CI, 1.15-2.88; p =0.01). Enrichment methodology improves the statistical discrimination of meaningful endpoints when used in a health records-based analysis.

Thoracic irrigation prevents retained hemothorax: A prospective propensity scored analysis.

PubMed

Kugler, Nathan W; Carver, Thomas W; Milia, David; Paul, Jasmeet S

2017-12-01

Thoracic trauma resulting in hemothorax (HTx) is typically managed with thoracostomy tube (TT) placement; however, up to 20% of patients develop retained HTx which may necessitate further intervention for definitive management. Although optimal management of retained HTx has been extensively researched, little is known about prevention of this complication. We hypothesized that thoracic irrigation at the time of TT placement would significantly decrease the rate of retained HTx necessitating secondary intervention. A prospective, comparative study of patients with traumatic HTx who underwent bedside TT placement was conducted. The control group consisted of patients who underwent standard TT placement, whereas the irrigation group underwent standard TT placement with immediate irrigation using 1 L of warmed sterile 0.9% saline. Patients who underwent emergency thoracotomy, those with TTs removed within 24 hours, or those who died within 30 days of discharge were excluded. The primary end point was secondary intervention defined by additional TT placement or operative management for retained HTx. A propensity-matched analysis was performed with scores estimated using a logistic regression model based on age, sex, mechanism of injury, Abbreviated Injury Scale chest score, and TT size. In over a 30-month period, a total of 296 patients underwent TT placement for the management of traumatic HTx. Patients were predominantly male (79.6%) at a median age of 40 years and were evenly split between blunt (48.8%) and penetrating (51.2%) mechanisms. Sixty (20%) patients underwent thoracic irrigation at time of initial TT placement. The secondary intervention rate was significantly lower within the study group (5.6% vs. 21.8%; OR, 0.16; p < 0.001). No significant differences in TT duration, ventilator days, or length of stay were noted between the irrigation and control cohort. Thoracic irrigation at the time of initial TT placement for traumatic HTx significantly reduced the need for secondary intervention for retained HTx. Therapeutic Study, Level III.

High accuracy prediction of beta-turns and their types using propensities and multiple alignments.

PubMed

Fuchs, Patrick F J; Alix, Alain J P

2005-06-01

We have developed a method that predicts both the presence and the type of beta-turns, using a straightforward approach based on propensities and multiple alignments. The propensities were calculated classically, but the way to use them for prediction was completely new: starting from a tetrapeptide sequence on which one wants to evaluate the presence of a beta-turn, the propensity for a given residue is modified by taking into account all the residues present in the multiple alignment at this position. The evaluation of a score is then done by weighting these propensities by the use of Position-specific score matrices generated by PSI-BLAST. The introduction of secondary structure information predicted by PSIPRED or SSPRO2 as well as taking into account the flanking residues around the tetrapeptide improved the accuracy greatly. This latter evaluated on a database of 426 reference proteins (previously used on other studies) by a sevenfold crossvalidation gave very good results with a Matthews Correlation Coefficient (MCC) of 0.42 and an overall prediction accuracy of 74.8%; this places our method among the best ones. A jackknife test was also done, which gave results within the same range. This shows that it is possible to reach neural networks accuracy with considerably less computional cost and complexity. Furthermore, propensities remain excellent descriptors of amino acid tendencies to belong to beta-turns, which can be useful for peptide or protein engineering and design. For beta-turn type prediction, we reached the best accuracy ever published in terms of MCC (except for the irregular type IV) in the range of 0.25-0.30 for types I, II, and I' and 0.13-0.15 for types VIII, II', and IV. To our knowledge, our method is the only one available on the Web that predicts types I' and II'. The accuracy evaluated on two larger databases of 547 and 823 proteins was not improved significantly. All of this was implemented into a Web server called COUDES (French acronym for: Chercher Ou Une Deviation Existe Surement), which is available at the following URL: http://bioserv.rpbs.jussieu.fr/Coudes/index.html within the new bioinformatics platform RPBS.

Effect of a wildlife conservation camp experience in China on student knowledge of animals, care, propensity for environmental stewardship, and compassionate behavior toward animals

NASA Astrophysics Data System (ADS)

Bexell, Sarah M.

The goal of conservation education is positive behavior change toward animals and the environment. This study was conducted to determine whether participation in a wildlife conservation education camp was effective in positively changing 8-12 year old students': (a) knowledge of animals, (b) care about animals, (c) propensity for environmental and wildlife stewardship, and (d) compassionate behavior toward animals. During the summer of 2005, 2 five-day camps were conducted at 2 zoological institutions in Chengdu, China. The camp curriculum was influenced by theory and research on the following: conservation psychology, social learning theory, empathy and moral development theory, socio-biological theory, constructivist theory, and conservation science. Camp activities were sensitive to Chinese culture and included Chinese conservation issues. Activities were designed to help children form bonds with animals and care enough about them to positively change their behavior toward animals and the environment. This mixed methods study triangulated quantitative and qualitative data from six sources to answer the following: (1) Did camp increase student knowledge of animals? (2) Did camp increase student caring about animals? (3) Did camp increase student propensity for environmental and wildlife stewardship? (4) Did camp affect student compassionate behavior toward animals? A conservation stewards survey revealed significant increases on pre-post, self-report of knowledge, care, and propensity. Pre-post, rubric-scored responses to human-animal interaction vignettes indicated a significant increase in knowledge, and stable scores on care and propensity. Qualitative data from student journals, vignettes, and end-of-camp questionnaires demonstrated knowledge, caring, and propensity, and revealed the emergent theme empathy. To address question 4, instructors tallied campers' behavior toward animals using a student behavior ethogram. Occurrence of positive behaviors was inconsistent, but negative behaviors decreased, indicating campers were more conscious of behaviors to avoid. Field notes helped determine that camps were implemented as planned, therefore not interfering with goals of the camp. This study contributes to an emerging and critical knowledge base of effective strategies to promote conservation behavior.

76 FR 30926 - Notice of Proposed Information Collection Requests

Federal Register 2010, 2011, 2012, 2013, 2014

2011-05-27

... North Carolina study will use a quasi-experimental design using propensity score matching. State end-of... student learning will be compared to a traditional FLVS U.S. History online course using an experimental...

Comparison and limitations of DVH-based NTCP models derived from 3D-CRT and IMRT data for prediction of gastrointestinal toxicities in prostate cancer patients by using propensity score matched pair analysis.

PubMed

Troeller, Almut; Yan, Di; Marina, Ovidiu; Schulze, Derek; Alber, Markus; Parodi, Katia; Belka, Claus; Söhn, Matthias

2015-02-01

This study compared normal tissue complication probability (NTCP) modeling of chronic gastrointestinal toxicities following prostate cancer treatment for 2 treatment modalities. Possible factors causing discrepancies in optimal NTCP model parameters between 3-dimensional conformal radiation therapy (3D-CRT) and intensity modulated RT (IMRT) were analyzed and discussed, including the impact of patient characteristics, image guidance, toxicity scoring bias, and NTCP model limitations. Rectal wall dose-volume histograms of 1115 patients treated for prostate cancer under an adaptive radiation therapy protocol were used to model gastrointestinal toxicity grade ≥2 (according to Common Terminology Criteria for Adverse Events). A total of 457 patients were treated with 3D-CRT and 658 with IMRT. 3D-CRT patients were matched to IMRT patients based on various patient characteristics, using a propensity score-based algorithm. Parameters of the Lyman equivalent uniform dose and cut-off dose logistic regression NTCP models were estimated for the 2 matched treatment modalities and the combined group. After they were matched, the 3D-CRT and IMRT groups contained 275 and 550 patients with a large discrepancy of 28.7% versus 7.8% toxicities, respectively (P<.001). For both NTCP models, optimal parameters found for the 3D-CRT groups did not fit the IMRT patients well and vice versa. Models developed for the combined data overestimated NTCP for the IMRT patients and underestimated NTCP for the 3D-CRT group. Our analysis did not reveal a single definitive cause for discrepancies of model parameters between 3D-CRT and IMRT. Patient characteristics and bias in toxicity scoring, as well as image guidance alone, are unlikely causes of the large discrepancy of toxicities. Whether the cause was inherent to the specific NTCP models used in this study needs to be verified by future investigations. Because IMRT is increasingly used clinically, it is important that appropriate NTCP model parameters are determined for this treatment modality. Copyright © 2015 Elsevier Inc. All rights reserved.

[Impact analysis of shuxuetong injection on abnormal changes of ALT based on generalized boosted models propensity score weighting].

PubMed

Yang, Wei; Yi, Dan-Hui; Xie, Yan-Ming; Yang, Wei; Dai, Yi; Zhi, Ying-Jie; Zhuang, Yan; Yang, Hu

2013-09-01

To estimate treatment effects of Shuxuetong injection on abnormal changes on ALT index, that is, to explore whether the Shuxuetong injection harms liver function in clinical settings and to provide clinical guidance for its safe application. Clinical information of traditional Chinese medicine (TCM) injections is gathered from hospital information system (HIS) of eighteen general hospitals. This is a retrospective cohort study, using abnormal changes in ALT index as an outcome. A large number of confounding biases are taken into account through the generalized boosted models (GBM) and multiple logistic regression model (MLRM) to estimate the treatment effects of Shuxuetong injections on abnormal changes in ALT index and to explore possible influencing factors. The advantages and process of application of GBM has been demonstrated with examples which eliminate the biases from most confounding variables between groups. This serves to modify the estimation of treatment effects of Shuxuetong injection on ALT index making the results more reliable. Based on large scale clinical observational data from HIS database, significant effects of Shuxuetong injection on abnormal changes in ALT have not been found.