# Counterfactual Phenotyping with Censored Time-to-Events

arXiv: https://arxiv.org/abs/2202.11089 · HTML: https://mlsanity.com/paper/2202.11089/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 48 references that are in the map.
- First posted on arXiv 22 Feb 2022.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network](https://mlsanity.com/paper/1606.00931/) (2016)
- [Deep Survival Machines: Fully Parametric Survival Regression and Representation Learning for Censored Data with Competing Risks](https://mlsanity.com/paper/2003.01176/) (2020)
- [Deep Survival Analysis](https://mlsanity.com/paper/1608.02158/) (2016)
- [Deep Cox Mixtures for Survival Regression](https://mlsanity.com/paper/2101.06536/) (2021)
- [Adversarial Time-to-Event Modeling](https://mlsanity.com/paper/1804.03184/) (2018)
- [X-CAL: Explicit Calibration for Survival Analysis](https://mlsanity.com/paper/2101.05346/) (2021)
- [A Deep Variational Approach to Clustering Survival Data](https://mlsanity.com/paper/2106.05763/) (2021)
- [SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data](https://mlsanity.com/paper/2110.14001/) (2021)
- [Survival Cluster Analysis](https://mlsanity.com/paper/2003.00355/) (2020)
- [Causal Rule Sets for Identifying Subgroups with Enhanced Treatment Effect](https://mlsanity.com/paper/1710.05426/) (2017)
- [Gaussian Processes for Survival Analysis](https://mlsanity.com/paper/1611.00817/) (2016)
- [Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines](https://mlsanity.com/paper/1905.03297/) (2019)

## Built on by (most cited first, 13 of 13)

- [Deep Learning for Survival Analysis: A Review](https://mlsanity.com/paper/2305.14961/) (2023)
- [Neural Fine-Gray: Monotonic neural networks for competing risks](https://mlsanity.com/paper/2305.06703/) (2023)
- [auton-survival: an Open-Source Package for Regression, Counterfactual Estimation, Evaluation and Phenotyping with Censored Time-to-Event Data](https://mlsanity.com/paper/2204.07276/) (2022)
- [Modeling Events and Interactions through Temporal Processes -- A Survey](https://mlsanity.com/paper/2303.06067/) (2023)
- [Competing Risks: Impact on Risk Estimation and Algorithmic Fairness](https://mlsanity.com/paper/2508.05435/) (2025)
- [BENK: The Beran Estimator with Neural Kernels for Estimating the Heterogeneous Treatment Effect](https://mlsanity.com/paper/2211.10793/) (2022)
- [Recovering Sparse and Interpretable Subgroups with Heterogeneous Treatment Effects with Censored Time-to-Event Outcomes](https://mlsanity.com/paper/2302.12504/) (2023)
- [Maximum Likelihood Estimation of Flexible Survival Densities with Importance Sampling](https://mlsanity.com/paper/2311.01660/) (2023)
- [Variational Deep Survival Machines: Survival Regression with Censored Outcomes](https://mlsanity.com/paper/2404.15595/) (2024)
- [Identifying treatment response subgroups in observational time-to-event data](https://mlsanity.com/paper/2408.03463/) (2024)
- [ADHAM: Additive Deep Hazard Analysis Mixtures for Interpretable Survival Regression](https://mlsanity.com/paper/2509.07108/) (2025)
- [Counterfactual Understanding via Retrieval-aware Multimodal Modeling for Time-to-Event Survival Prediction](https://mlsanity.com/paper/2602.19987/) (2026)
- [SurvCF(t): Counterfactual Explanations for Survival Analysis in Predictive Maintenance Multivariate Time Series Data](https://mlsanity.com/paper/2607.16969/) (2026)

## Abstract (arXiv)

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.