Counterfactual Phenotyping with Censored Time-to-Events
arXiv:2202.11089 · doi:10.1145/3534678.3539110
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.
arXiv commentKDD 2022 Applied Data Science Paper. Note this version includes a correction of the published version in the definition of Restricted Mean Survival Time
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Random survival forests
- DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network
- Predictive learning via rule ensembles
- Deep Survival Analysis
- Enabling Counterfactual Survival Analysis with Balanced Representations
- Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines
- Survival Function Matching for Calibrated Time-to-Event Predictions
- X-CAL: Explicit Calibration for Survival Analysis