SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

Abstract

We study the problem of inferring heterogeneous treatment effects from time-to-event data. While both the related problems of (i) estimating treatment effects for binary or continuous outcomes and (ii) predicting survival outcomes have been well studied in the recent machine learning literature, their combination -- albeit of high practical relevance -- has received considerably less attention. With the ultimate goal of reliably estimating the effects of treatments on instantaneous risk and survival probabilities, we focus on the problem of learning (discrete-time) treatment-specific conditional hazard functions. We find that unique challenges arise in this context due to a variety of covariate shift issues that go beyond a mere combination of well-studied confounding and censoring biases. We theoretically analyse their effects by adapting recent generalization bounds from domain adaptation and treatment effect estimation to our setting and discuss implications for model design. We use the resulting insights to propose a novel deep learning method for treatment-specific hazard estimation based on balancing representations. We investigate performance across a range of experimental settings and empirically confirm that our method outperforms baselines by addressing covariate shifts from various sources.

arXiv commentProceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS 2021)

References in corpus (16)

• Recursive Partitioning for Heterogeneous Causal Effects
• Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning
• Fast Computation of Wasserstein Barycenters
• Discussion on "Bayesian Regression Tree Models for Causal Inference: Regularization, Confounding, and Heterogeneous Effects" by Hahn, Murray and Carvalho
• Causal Effect Inference with Deep Latent-Variable Models
• An introduction to domain adaptation and transfer learning
• Estimating heterogeneous survival treatment effect in observational data using machine learning
• Deep Learning for Patient-Specific Kidney Graft Survival Analysis
• Support and Invertibility in Domain-Invariant Representations
• Learning Weighted Representations for Generalization Across Designs
• Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects
• Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithms
• Enabling Counterfactual Survival Analysis with Balanced Representations
• Countdown Regression: Sharp and Calibrated Survival Predictions
• Estimating heterogeneous treatment effects with right-censored data via causal survival forests
• Understanding the role of importance weighting for deep learning