A comparison of five recursive partitioning methods to find person subgroups involved in meaningful treatment–subgroup interactions

In case multiple treatment alternatives are available for some medical problem, the detection of treatment–subgroup interactions (i.e., relative treatment effectiveness varying over subgroups of persons) is of key importance for personalized medicine and the development of optimal treatment assignment strategies. Randomized Clinical Trials (RCT) often go without clear a priori hypotheses on the subgroups involved in treatment–subgroup interactions, and with a large number of pre-treatment characteristics in the data. In such situations, relevant subgroups (defined in terms of pre-treatment characteristics) are to be induced during the actual data analysis. This comes down to a problem of cluster analysis, with the goal of this analysis being to find clusters of persons that are involved in meaningful treatment–person cluster interactions. For such a cluster analysis, five recently proposed methods can be used, all being of a recursive partitioning type. However, these five methods have been developed almost independently, and the relations between them are not yet understood. The present paper closes this gap. It starts by outlining the basic principles behind each method, and by illustrating it with an application on an RCT data set on two treatment strategies for substance abuse problems. Next, it presents a comparison of the methods, hereby focusing on major similarities and differences. The discussion concludes with practical advice for end users with regard to the selection of a suitable method, and with an important challenge for future research in this area.

[1]  Claudio Conversano,et al.  Combining an Additive and Tree-Based Regression Model Simultaneously: STIMA , 2010 .

[2]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[3]  Claudio Conversano,et al.  Simultaneous Threshold Interaction Detection in Binary Classification , 2010 .

[4]  C. Sudlow,et al.  Improving medication adherence in stroke survivors: mediators and moderators of treatment effects. , 2014, Health psychology : official journal of the Division of Health Psychology, American Psychological Association.

[5]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[6]  Jacqueline J. Meulman,et al.  The regression trunk approach to discover treatment covariate interaction , 2004 .

[7]  Hansheng Wang,et al.  Subgroup Analysis via Recursive Partitioning , 2009, J. Mach. Learn. Res..

[8]  D. Rubin.  Estimating causal effects of treatments in randomized and nonrandomized studies. , 1974 .

[9]  R. Simon,et al.  Bayesian subset analysis. , 1991, Biometrics.

[10]  Xiaogang Su,et al.  Subgroup Analysis via Recursive Partitioning , 2009 .

[11]  A. Alterman,et al.  A New Measure of Substance Abuse Treatment Initial Studies of the Treatment Services Review , 1992, The Journal of nervous and mental disease.

[12]  J. Meulman,et al.  Prediction in Medicine by Integrating Regression Trees into Regression Analysis with Optimal Scaling , 2001, Methods of Information in Medicine.

[13]  G. Woody,et al.  Motivational interviewing to improve treatment engagement and outcome in individuals seeking treatment for substance abuse: a multisite effectiveness study. , 2006, Drug and alcohol dependence.

[14]  G. Guyatt,et al.  Randomized trials published in higher vs. lower impact journals differ in design, conduct, and analysis. , 2013, Journal of clinical epidemiology.

[15]  Xiaogang Su,et al.  Interaction Trees with Censored Survival Data , 2008, The international journal of biostatistics.

[16]  J. Shaffer.  Probability of directional errors with disordinal (qualitative) interaction , 1991 .

[17]  David M Kent,et al.  Multivariable risk prediction can greatly enhance the statistical power of clinical trial subgroup analysis , 2006, BMC medical research methodology.

[18]  Claudio Conversano,et al.  Simultaneous Threshold Interaction Modeling Algorithm , 2013 .

[19]  K. Hornik,et al.  Model-Based Recursive Partitioning , 2008 .

[20]  Maurizio Vichi,et al.  Studies in Classification Data Analysis and knowledge Organization , 2011 .

[21]  Mark McClellan,et al.  Comparative effectiveness research: Policy context, methods development and research infrastructure , 2010, Statistics in medicine.

[22]  G. Woody,et al.  Addiction Severity Index , 2012 .

[23]  Rajeev Dehejia,et al.  Program Evaluation as a Decision Problem , 1999 .

[24]  J. M. Taylor,et al.  Subgroup identification from randomized clinical trial data , 2011, Statistics in medicine.

[25]  H. Kraemer,et al.  Mediators and moderators of treatment effects in randomized clinical trials. , 2002, Archives of general psychiatry.

[26]  M. LeBlanc,et al.  Survival Trees by Goodness of Split , 1993 .

[27]  A. Alterman,et al.  Addiction Severity Index composite scores: Contribution of objective vs. subjective items to post‐treatment change , 2004 .

[28]  I. Lipkovich,et al.  Subgroup identification based on differential effect search—A recursive partitioning method for establishing response to treatment in patient subpopulations , 2011, Statistics in medicine.

[29]  A. Hoes,et al.  American Journal of Epidemiology Practice of Epidemiology a Comparison of Subgroup Analyses in Grant Applications and Publications , 2022 .