Comparing algorithms for characterizing treatment effect heterogeneity in randomized trials

Sun, Sophie; Sechidis, Konstantinos; Chen, Yao; Lu, Jiarui; Ma, Chengbin; Mirshani, Ardalan; Ohlssen, David; Vandemeulebroecke, Marc; Bornkamp, Björn

doi:10.1002/bimj.202100337

Cited by 5 publications

(4 citation statements)

References 69 publications

(137 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Participants obtained the protocols for all involved studies, data-set specifications and background material on subgroup identification, that is, three literature references 17,25,26 and example code to get started. Two clinical experts were identified to help with potential questions that participants may have on the compound, disease or subgroup relevance more generally.…”

Section: Further Information Sourcesmentioning

confidence: 99%

Predicting subgroup treatment effects for a new study: Motivations, results and learnings from running a data challenge in a pharmaceutical corporation

Bornkamp,

Zaoli,

Azzarito

et al. 2024

Pharmaceutical Statistics

Self Cite

View full text Add to dashboard Cite

We present the motivation, experience, and learnings from a data challenge conducted at a large pharmaceutical corporation on the topic of subgroup identification. The data challenge aimed at exploring approaches to subgroup identification for future clinical trials. To mimic a realistic setting, participants had access to 4 Phase III clinical trials to derive a subgroup and predict its treatment effect on a future study not accessible to challenge participants. A total of 30 teams registered for the challenge with around 100 participants, primarily from Biostatistics organization. We outline the motivation for running the challenge, the challenge rules, and logistics. Finally, we present the results of the challenge, the participant feedback as well as the learnings. We also present our view on the implications of the results on exploratory analyses related to treatment effect heterogeneity.

show abstract

Section: Further Information Sourcesmentioning

confidence: 99%

Predicting subgroup treatment effects for a new study: Motivations, results and learnings from running a data challenge in a pharmaceutical corporation

Bornkamp,

Zaoli,

Azzarito

et al. 2024

Pharmaceutical Statistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Model-based forests allow simultaneous estimation of μ false( bold-italicx false) and τ false( bold-italicx false) 24–29 in the same forest model and have been demonstrated to perform at least on par with the best competitor in several independent studies evaluating HTE estimation in randomized trials. 30–33 In a nutshell, model-based forests combine the parametric modeling framework with random forests to estimate individual treatment effects. 25 By using generalized linear models and transformation models, model-based forests can be adapted for survival data, 24–26 ordinal data, 27 or clustered data.…”

Section: Introductionmentioning

confidence: 99%

Heterogeneous treatment effect estimation for observational data using model-based forests

Dandl,

Bender,

Hothorn

2024

Stat Methods Med Res

View full text Add to dashboard Cite

The estimation of heterogeneous treatment effects has attracted considerable interest in many disciplines, most prominently in medicine and economics. Contemporary research has so far primarily focused on continuous and binary responses where heterogeneous treatment effects are traditionally estimated by a linear model, which allows the estimation of constant or heterogeneous effects even under certain model misspecifications. More complex models for survival, count, or ordinal outcomes require stricter assumptions to reliably estimate the treatment effect. Most importantly, the noncollapsibility issue necessitates the joint estimation of treatment and prognostic effects. Model-based forests allow simultaneous estimation of covariate-dependent treatment and prognostic effects, but only for randomized trials. In this paper, we propose modifications to model-based forests to address the confounding issue in observational data. In particular, we evaluate an orthogonalization strategy originally proposed by Robinson (1988, Econometrica) in the context of model-based forests targeting heterogeneous treatment effect estimation in generalized linear models and transformation models. We found that this strategy reduces confounding effects in a simulated study with various outcome distributions. We demonstrate the practical aspects of heterogeneous treatment effect estimation for survival and ordinal outcomes by an assessment of the potentially heterogeneous effect of Riluzole on the progress of Amyotrophic Lateral Sclerosis.

show abstract

“…Additionally, the focus of research questions differs, e.g. Sun et al [84] focus on a more general assessment of the treatment heterogeneity, whereas in my research I focused on the identification of a biomarkerpositive and biomarker-negative subgroup with differential treatment effects. My research on subgroup identification based on IPD meta-analysis considers data from multiple trials [43].…”

Section: Discussionmentioning

confidence: 99%

“…the methods investigated in my comparison study [42], the application of post-selection inference [4,8] remains a topic of future research. The identification of subgroups and neutral comparisons of the different proposed methods is still a relevant topic as publications in the past few years [1,19,42,59,79] and the recent publication by Sun et al [84] demonstrate. Although all studies focus on the comparison of subgroup identification methods, the results differ because of the study-specific properties of the investigated data, the included methods, and the underlying scientific questions of interest.…”

Section: Discussionmentioning

confidence: 99%

Identification of biomarker-defined populations in precision medicine

Huber¹

View full text Add to dashboard Cite

I would also like to thank Prof. Heike Bickeböller, who kindly agreed to be my second assessor. Furthermore, my sincere thanks are due to PD Dr. Norbert Benda for being a member of my thesis committee, for co-authoring my publications, and for supervising my internships at the Federal Institute for Drugs and Medical Devices (BfArM). In addition, I would like to express my gratitude to Prof. Jürgen Brockmöller for being a further member of my thesis committee. Moreover, I am also very grateful to Prof. Julia Stingl for co-authoring one of my papers and to Prof. Matthias Schmid for his valuable suggestions and ideas on my fourth paper. Besides my advisors, I would like to thank all my (former) colleagues, and fellow PhD students, especially Burak, for the conducive working atmosphere on the top floor and the many cheerful moments in everyday working life. For proofreading this thesis and providing helpful comments, I thank Tobias, Katharina and Steffen. Last but not least, I want to thank everybody who supported me in my private life. In particular, I would like to thank my parents for their continuous support and unconditional love. Special thanks also go to my siblings and Markus for their support and understanding, and for the often-needed distraction.

show abstract

Comparing algorithms for characterizing treatment effect heterogeneity in randomized trials

Cited by 5 publications

References 69 publications

Predicting subgroup treatment effects for a new study: Motivations, results and learnings from running a data challenge in a pharmaceutical corporation

Predicting subgroup treatment effects for a new study: Motivations, results and learnings from running a data challenge in a pharmaceutical corporation

Heterogeneous treatment effect estimation for observational data using model-based forests

Identification of biomarker-defined populations in precision medicine

Contact Info

Product

Resources

About