Tutorial in biostatistics: data‐driven subgroup identification and analysis in clinical trials

Abstract

It is well known that both the direction and magnitude of the treatment effect in clinical trials are often affected by baseline patient characteristics (generally referred to as biomarkers). Characterization of treatment effect heterogeneity plays a central role in the field of personalized medicine and facilitates the development of tailored therapies. This tutorial focuses on a general class of problems arising in data-driven subgroup analysis, namely, identification of biomarkers with strong predictive properties and patient subgroups with desirable characteristics such as improved benefit and/or safety. Limitations of ad-hoc approaches to biomarker exploration and subgroup identification in clinical trials are discussed, and the ad-hoc approaches are contrasted with principled approaches to exploratory subgroup analysis based on recent advances in machine learning and data mining. A general framework for evaluating predictive biomarkers and identification of associated subgroups is introduced. The tutorial provides a review of a broad class of statistical methods used in subgroup discovery, including global outcome modeling methods, global treatment effect modeling methods, optimal treatment regimes, and local modeling methods. Commonly used subgroup identification methods are illustrated using two case studies based on clinical trials with binary and survival endpoints. Copyright © 2016 John Wiley & Sons, Ltd.

Use of large-scale HRQoL datasets to generate individualised predictions and inform patients about the likely benefit of surgery

“…We employed non-parametric data mining techniques to populate separate regression trees for each of the treatments [17, 30]. The trees were generated through a recursive Classification and Regression Tree (CART) algorithm that split the dataset along risk variables to generate nodes and then repeated this process for each resulting tree branch until the dataset could not be split further or the overall fit of the model could no longer be improved.…”

“…To be able to participate in shared decision-making (SDM) patients require information on the relative effectiveness of alternative treatment options. But the effectiveness of medical treatments is often moderated by patient characteristics, such as age, gender, co-morbidity burden or genetic factors [17]. Hence, for information to be most relevant for the specific SDM context, it needs to reflect patients’ personal circumstances closely [1].…”

Treatment evaluation for a data‐driven subgroup in adaptive enrichment designs of clinical trials

“…There is a great variety of choices for in the literature on adaptive signature designs, 9,10 subgroup selection, [25][26][27] and optimal treatment regimes. [28][29][30][31][32][33] As a simple example, can be based on a working regression model such as…”

Can We Identify Patients at High Risk of Harm under a Generally Safe Intervention?

“…If they are continuous (like age), subsets can be obtained by defining a threshold and assigning all subjects with values above the threshold to one subset and the rest to the other subset. Subgroups can then be formed by intersections of the subsets generated by covariates as shown for two covariates X 1 and X 2 in Figure 1 (see [10] for an overview). There are basically two ways to identify subgroups: First, to consider the treatment effect within each subgroup or to consider the excess effect in one subgroup relative to the effect in a reference subgroup, i.e., treatment by subgroup interactions.…”