Open Application of Statistical and Machine Learning Models to Explore the Impact of Environmental Exposures on Health and Disease: An Asthma Use Case

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

ICEES (Integrated Clinical and Environmental Exposures Service) provides a disease-agnostic, regulatory-compliant approach for openly exposing and analyzing clinical data that have been integrated at the patient level with environmental exposures data. ICEES is equipped with basic features to support exploratory analysis using statistical approaches, such as bivariate chi-square tests. We recently developed a method for using ICEES to generate multivariate tables for subsequent application of machine learning and statistical models. The objective of the present study was to use this approach to identify predictors of asthma exacerbations through the application of three multivariate methods: conditional random forest, conditional tree, and generalized linear model. Among seven potential predictor variables, we found five to be of significant importance using both conditional random forest and conditional tree: prednisone, race, airborne particulate exposure, obesity, and sex. The conditional tree method additionally identified several significant two-way and three-way interactions among the same variables. When we applied a generalized linear model, we identified four significant predictor variables, namely prednisone, race, airborne particulate exposure, and obesity. When ranked in order by effect size, the results were in agreement with the results from the conditional random forest and conditional tree methods as well as the published literature. Our results suggest that the open multivariate analytic capabilities provided by ICEES are valid in the context of an asthma use case and likely will have broad value in advancing open research in environmental and public health.

Related collections

Most cited references 25

Record: found
Abstract: not found
Article: not found

Estimating the Dimension of a Model

Gideon Schwarz (1978)

0 comments Cited 2722 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

An introduction to recursive partitioning: rationale, application, and characteristics of classification and regression trees, bagging, and random forests.

Carolin Strobl, James Malley, Gerhard Tutz (2009)

Recursive partitioning methods have become popular and widely used tools for nonparametric regression and classification in many scientific fields. Especially random forests, which can deal with large numbers of predictor variables even in the presence of complex interactions, have been applied successfully in genetics, clinical medicine, and bioinformatics within the past few years. High-dimensional problems are common not only in genetics, but also in some areas of psychological research, where only a few subjects can be measured because of time or cost constraints, yet a large amount of data is generated for each subject. Random forests have been shown to achieve a high prediction accuracy in such applications and to provide descriptive variable importance measures reflecting the impact of each variable in both main effects and interactions. The aim of this work is to introduce the principles of the standard recursive partitioning methods as well as recent methodological improvements, to illustrate their usage for low and high-dimensional data exploration, but also to point out limitations of the methods and potential pitfalls in their practical application. Application of the methods is illustrated with freely available implementations in the R system for statistical computing. (c) 2009 APA, all rights reserved.

0 comments Cited 588 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: found

Is Open Access

Bias in random forest variable importance measures: Illustrations, sources and a solution

Carolin Strobl, Anne-Laure Boulesteix, Achim Zeileis … (2007)

Background Variable importance measures for random forests have been receiving increased attention as a means of variable selection in many classification tasks in bioinformatics and related scientific fields, for instance to select a subset of genetic markers relevant for the prediction of a certain disease. We show that random forest variable importance measures are a sensible means for variable selection in many applications, but are not reliable in situations where potential predictor variables vary in their scale of measurement or their number of categories. This is particularly important in genomics and computational biology, where predictors often include variables of different types, for example when predictors include both sequence data and continuous variables such as folding energy, or when amino acid sequence data show different numbers of categories. Results Simulation studies are presented illustrating that, when random forest variable importance measures are used with data of varying types, the results are misleading because suboptimal predictor variables may be artificially preferred in variable selection. The two mechanisms underlying this deficiency are biased variable selection in the individual classification trees used to build the random forest on one hand, and effects induced by bootstrap sampling with replacement on the other hand. Conclusion We propose to employ an alternative implementation of random forests, that provides unbiased variable selection in the individual classification trees. When this method is applied using subsampling without replacement, the resulting variable importance measures can be used reliably for variable selection even in situations where the potential predictor variables vary in their scale of measurement or their number of categories. The usage of both random forest algorithms and their variable importance measures in the R system for statistical computing is illustrated and documented thoroughly in an application re-analyzing data from a study on RNA editing. Therefore the suggested method can be applied straightforwardly by scientists in bioinformatics research.