Counterfactual Phenotyping with Censored Time-to-Events

TL;DR

This paper introduces a latent variable model for counterfactual phenotyping in censored time-to-event data, enabling the discovery of distinct patient response groups in clinical trials.

Contribution

It proposes a novel latent clustering approach to disentangle baseline survival effects from treatment effects in censored time-to-event data.

Findings

Successfully identified actionable patient phenotypes.

Improved understanding of heterogeneous treatment responses.

Validated on large cardiovascular clinical trials.

Abstract

Estimation of treatment efficacy of real-world clinical interventions involves working with continuous outcomes such as time-to-death, re-hospitalization, or a composite event that may be subject to censoring. Counterfactual reasoning in such scenarios requires decoupling the effects of confounding physiological characteristics that affect baseline survival rates from the effects of the interventions being assessed. In this paper, we present a latent variable approach to model heterogeneous treatment effects by proposing that an individual can belong to one of latent clusters with distinct response characteristics. We show that this latent structure can mediate the base survival rates and helps determine the effects of an intervention. We demonstrate the ability of our approach to discover actionable phenotypes of individuals based on their treatment response on multiple large randomized clinical trials originally conducted to assess appropriate treatments to reduce cardiovascular risk.