Bayesian Approaches to Subgroup Analysis and Related Adaptive Clinical Trial Designs

An interpretable framework to identify responsive subgroups from clinical trials regarding treatment effects: Application to treatment of intracerebral hemorrhage

Randomized Clinical trials (RCT) suffer from a high failure rate which could be caused by heterogeneous responses to treatment. Despite many models being developed to estimate heterogeneous treatment effects (HTE), there remains a lack of interpretable methods to identify responsive subgroups. This work aims to develop a framework to identify subgroups based on treatment effects that prioritize model interpretability. The proposed framework leverages an ensemble uplift tree method to generate descriptive decision rules that separate samples given estimated responses to the treatment. Subsequently, we select a complementary set of these decision rules and rank them using a sparse linear model. To address the trial's limited sample size problem, we proposed a data augmentation strategy by borrowing control patients from external studies and generating synthetic data. We apply the proposed framework to a failed randomized clinical trial for investigating an intracerebral hemorrhage therapy plan. The Qini-scores show that the proposed data augmentation strategy plan can boost the model's performance and the framework achieves greater interpretability by selecting complementary descriptive rules without compromising estimation quality. Our model derives clinically meaningful subgroups. Specifically, we find those patients with Diastolic Blood Pressure≥70 mm hg and Systolic Blood Pressure<215 mm hg benefit more from intensive blood pressure reduction therapy. The proposed interpretable HTE analysis framework offers a promising potential for extracting meaningful insight from RCTs with neutral treatment effects. By identifying responsive subgroups, our framework can contribute to developing personalized treatment strategies for patients more efficiently.

Exploration of predictors of benefit from nivolumab monotherapy for patients with pretreated advanced gastric and gastroesophageal junction cancer: post hoc subanalysis from the ATTRACTION-2 study

BACKGROUND

The phase 3 ATTRACTION-2 study demonstrated that nivolumab monotherapy was superior to placebo for patients with pretreated advanced gastric or gastroesophageal junction cancer, but early progression of tumors in some patients was of concern.

METHODS

This post hoc analysis statistically explored the baseline characteristics of the ATTRACTION-2 patients and extracted a single-factor and double-factor combinations associated with early disease progression or early death. In the extracted patient subgroups, the 3-year restricted mean survival times of progression-free survival and overall survival were compared between the nivolumab and placebo arms.

RESULTS

Two single factors (age and peritoneal metastasis) were extracted as independent predictors of early progression, but none of them, as a single factor, stratified patients into two subgroups with significant differences in restricted mean survival time. In contrast, two double-factor combinations (serum sodium level and white blood cell count; serum sodium level and neutrophil-lymphocyte ratio) stratifying patients into two subgroups with significant differences in the restricted mean survival time were extracted. Additional exploratory analysis of a triple-factor combination showed that patients aged < 60 years with peritoneal metastasis and low serum sodium levels (approximately 7% of all patients) might receive less benefit from nivolumab, and patients aged ≥ 60 years with no peritoneal metastasis and normal serum sodium levels might receive higher benefit.

CONCLUSIONS

A combination of age, peritoneal metastasis, and serum sodium level might predict benefit from nivolumab as salvage therapy in advanced gastric or gastroesophageal junction cancer patients, especially less benefit for patients having all three risk factors.

A Bayesian Decision-Theoretic Design for Simultaneous Biomarker-Based Subgroup Selection and Efficacy Evaluation

The success of drug development of targeted therapy often hinges on an appropriate selection of the sensitive patient population, mostly based on patients' biomarker levels. At the planning stage of a phase II study, although a potential biomarker may have been identified, a threshold value for defining sensitive patient population is often unavailable for adopting many existing biomarker-guided designs. To address this issue, we propose a two-stage design that allows for simultaneous biomarker threshold selection and efficacy evaluation while accommodating situations where the drug is efficacious in the entire patient population. The design uses a Bayesian decision-theoretic approach and incorporates the benefit and cost considerations of the study into a utility function. The operating characteristics of the proposed design under different scenarios are investigated via simulations. We also provide a discussion on the choice of the benefit and cost parameters in practice.