Double Variable Importance Matching to Estimate Distinct Causal Effects on Event Probability and Timing

2026-02-04

AI Summary

This study addresses the challenge of disentangling the distinct causal effects of a treatment on both the probability of being cured and the timing of events in survival data with a cured fraction. The authors propose a novel matching-based framework that leverages a mixture cure model to inform a high-dimensional weighted distance metric, incorporating variable importance to construct separate, tailored matching strategies for estimating each causal effect. This approach is the first to enable decoupled estimation of these two types of causal effects, supported by theoretical guarantees regarding estimator consistency and optimality of the distance metric. Empirical evaluations on both simulated and real-world clinical datasets demonstrate that the framework yields robust and interpretable estimates of heterogeneous causal effects.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

In many clinical contexts, estimating effects of treatment in time-to-event data is complicated not only by confounding, censoring, and heterogeneity, but also by the presence of a cured subpopulation in which the event of interest never occurs. In such settings, treatment may have distinct effects on (1) the probability of being cured and (2) the event timing among non-cured individuals. Standard survival analysis and causal inference methods typically do not separate cured from non-cured individuals, obscuring distinct treatment mechanisms on cure probability and event timing. To address these challenges, we propose a matching-based framework that constructs distinct match groups to estimate heterogeneous treatment effects (HTE) on cure probability and event timing, respectively. We use mixture cure models to identify feature importance for both estimands, which in turn informs weighted distance metrics for matching in high-dimensional spaces. Within matched groups, Kaplan-Meier estimators provide estimates of cure probability and expected time to event, from which individual-level treatment effects are derived. We provide theoretical guarantees for estimator consistency and distance metric optimality under an equal-scale constraint. We further decompose estimation error into contributions from censoring, model fitting, and irreducible noise. Simulations and real-world data analyses demonstrate that our approach delivers interpretable and robust HTE estimates in time-to-event settings.

Problem

• cure model
• heterogeneous treatment effects
• time-to-event data
• causal inference
• survival analysis

Innovation

• mixture cure model
• heterogeneous treatment effects
• matching
• time-to-event analysis
• variable importance