Interpretable Survival Analysis for Heart Failure Risk Prediction

Mike Van Ness, Tomas Bosschieter, Natasha Din, Andrew Ambrosy, Alexander Sandhu, Madeleine Udell
Proceedings of the 3rd Machine Learning for Health Symposium, PMLR 225:574-593, 2023.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v225-van-ness23a, title = {Interpretable Survival Analysis for Heart Failure Risk Prediction}, author = {Van Ness, Mike and Bosschieter, Tomas and Din, Natasha and Ambrosy, Andrew and Sandhu, Alexander and Udell, Madeleine}, booktitle = {Proceedings of the 3rd Machine Learning for Health Symposium}, pages = {574--593}, year = {2023}, editor = {Hegselmann, Stefan and Parziale, Antonio and Shanmugam, Divya and Tang, Shengpu and Asiedu, Mercy Nyamewaa and Chang, Serina and Hartvigsen, Tom and Singh, Harvineet}, volume = {225}, series = {Proceedings of Machine Learning Research}, month = {10 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v225/van-ness23a/van-ness23a.pdf}, url = {https://proceedings.mlr.press/v225/van-ness23a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Interpretable Survival Analysis for Heart Failure Risk Prediction %A Mike Van Ness %A Tomas Bosschieter %A Natasha Din %A Andrew Ambrosy %A Alexander Sandhu %A Madeleine Udell %B Proceedings of the 3rd Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2023 %E Stefan Hegselmann %E Antonio Parziale %E Divya Shanmugam %E Shengpu Tang %E Mercy Nyamewaa Asiedu %E Serina Chang %E Tom Hartvigsen %E Harvineet Singh %F pmlr-v225-van-ness23a %I PMLR %P 574--593 %U https://proceedings.mlr.press/v225/van-ness23a.html %V 225 %X 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.
APA
Van Ness, M., Bosschieter, T., Din, N., Ambrosy, A., Sandhu, A. & Udell, M.. (2023). Interpretable Survival Analysis for Heart Failure Risk Prediction. Proceedings of the 3rd Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 225:574-593 Available from https://proceedings.mlr.press/v225/van-ness23a.html.

Related Material