Clustering and Meta-Analysis Using a Mixture of Dependent Linear Tail-Free Priors

TL;DR

This paper introduces a new Bayesian nonparametric method for meta-analysis of event time data, incorporating dependent tail-free processes and hierarchical clustering to handle diverse and heterogeneous studies.

Contribution

It extends linear dependent tail-free processes with conjugate updating and hierarchical clustering via Dirichlet process mixtures for meta-analysis.

Findings

Validated on cancer immunotherapy studies

Effectively handles heterogeneity across studies

Supports biomarker validation in immunotherapy design

Abstract

We propose a novel nonparametric Bayesian approach for meta-analysis with event time outcomes. The model is an extension of linear dependent tail-free processes. The extension includes a modification to facilitate (conditionally) conjugate posterior updating and a hierarchical extension with a random partition of studies. The partition is formalized as a Dirichlet process mixture. The model development is motivated by a meta-analysis of cancer immunotherapy studies. The aim is to validate the use of relevant biomarkers in the design of immunotherapy studies. The hypothesis is about immunotherapy in general, rather than about a specific tumor type, therapy and marker. This broad hypothesis leads to a very diverse set of studies being included in the analysis and gives rise to substantial heterogeneity across studies