# Interpretable Survival Analysis for Heart Failure Risk Prediction

arXiv: https://arxiv.org/abs/2310.15472 · HTML: https://mlsanity.com/paper/2310.15472/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## Builds on (most cited first, 19 of 19)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network](https://mlsanity.com/paper/1606.00931/) (2016)
- [Neural Additive Models: Interpretable Machine Learning with Neural Nets](https://mlsanity.com/paper/2004.13912/) (2020)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [InterpretML: A Unified Framework for Machine Learning Interpretability](https://mlsanity.com/paper/1909.09223/) (2019)
- [Model-Agnostic Interpretability of Machine Learning](https://mlsanity.com/paper/1606.05386/) (2016)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [On the Tractability of SHAP Explanations](https://mlsanity.com/paper/2009.08634/) (2020)
- [Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models](https://mlsanity.com/paper/1911.04974/) (2019)
- [Accuracy, Interpretability, and Differential Privacy via Explainable Boosting](https://mlsanity.com/paper/2106.09680/) (2021)
- [A study of data and label shift in the LIME framework](https://mlsanity.com/paper/1910.14421/) (2019)
- [SurvNAM: The machine learning survival model explanation](https://mlsanity.com/paper/2104.08903/) (2021)
- [Survival stacking: casting survival analysis as a classification problem](https://mlsanity.com/paper/2107.13480/) (2021)
- [ControlBurn: Feature Selection by Sparse Forests](https://mlsanity.com/paper/2107.00219/) (2021)
- [BDNNSurv: Bayesian deep neural networks for survival analysis using pseudo values](https://mlsanity.com/paper/2101.03170/) (2021)
- [ControlBurn: Nonlinear Feature Selection with Sparse Tree Ensembles](https://mlsanity.com/paper/2207.03935/) (2022)
- [Pseudo value-based Deep Neural Networks for Multi-state Survival Analysis](https://mlsanity.com/paper/2207.05291/) (2022)
- [Using Interpretable Machine Learning to Predict Maternal and Fetal Outcomes](https://mlsanity.com/paper/2207.05322/) (2022)

## Built on by (most cited first, 6 of 6)

- [Position: Stop Chasing the C-index when Evaluating Survival Analysis Models](https://mlsanity.com/paper/2506.02075/) (2025)
- [MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets](https://mlsanity.com/paper/2411.00200/) (2024)
- [Interpretable Prediction and Feature Selection for Survival Analysis](https://mlsanity.com/paper/2404.14689/) (2024)
- [FAST: An Optimization Framework for Fast Additive Segmentation in Transparent ML](https://mlsanity.com/paper/2402.12630/) (2024)
- [dnamite: A Python Package for Neural Additive Models](https://mlsanity.com/paper/2503.07642/) (2025)
- [Isotonic Survival Regression: Calibrated Survival Distributions from Deep Cox Models](https://mlsanity.com/paper/2605.16571/) (2026)

## Abstract (arXiv)

Survival analysis, or time-to-event analysis, is an important and widespread problem in healthcare research. Medical research has traditionally relied on Cox models for survival analysis, due to their simplicity and interpretability. Cox models assume a log-linear hazard function as well as proportional hazards over time, and can perform poorly when these assumptions fail. Newer survival models based on machine learning avoid these assumptions and offer improved accuracy, yet sometimes at the expense of model interpretability, which is vital for clinical use. We propose a novel survival analysis pipeline that is both interpretable and competitive with state-of-the-art survival models. Specifically, we use an improved version of survival stacking to transform a survival analysis problem to a classification problem, ControlBurn to perform feature selection, and Explainable Boosting Machines to generate interpretable predictions. To evaluate our pipeline, we predict risk of heart failure using a large-scale EHR database. Our pipeline achieves state-of-the-art performance and provides interesting and novel insights about risk factors for heart failure.