ADHAM: Additive Deep Hazard Analysis Mixtures for Interpretable Survival Regression

Mert Ketenci, Vincent Jeanselme, Harry Reyes Nieva, Shalmali Joshi, Noémie Elhadad
Proceedings of the 10th Machine Learning for Healthcare Conference, PMLR 298, 2025.

Abstract

Survival analysis is a fundamental tool for modeling time-to-event outcomes in healthcare. Recent advances have introduced flexible neural network approaches for improved predictive performances. However, these models do not provide interpretable insights into the association between exposures and the modeled outcomes, a critical requirement for decision-making in clinical practice. To address this limitation, we propose Additive Deep Hazard Analysis Mixtures (ADHAM), an interpretable additive survival model. ADHAM assumes a conditional latent subpopulation structure that characterizes an individual, combined with covariate-specific hazard functions. To select the number of subpopulations, we introduce a post-training group refinement-based model-selection procedure; \ie an efficient approach to merge similar clusters to reduce the number of repetitive latent subpopulations identified by the model. We perform comprehensive studies to demonstrate ADHAM’s interpretability on population, subpopulation, and individual levels. Extensive experiments on real-world datasets show that ADHAM provides novel insights into the association between exposures and outcomes. Further, ADHAM remains on par with existing state-of-the-art survival baselines, offering a scalable and interpretable approach to time-to-event prediction in healthcare.

Cite this Paper

BibTeX
@InProceedings{pmlr-v298-ketenci25a, title = {{ADHAM}: Additive Deep Hazard Analysis Mixtures for Interpretable Survival Regression}, author = {Ketenci, Mert and Jeanselme, Vincent and Nieva, Harry Reyes and Joshi, Shalmali and Elhadad, No\'emie}, booktitle = {Proceedings of the 10th Machine Learning for Healthcare Conference}, year = {2025}, editor = {Agrawal, Monica and Deshpande, Kaivalya and Engelhard, Matthew and Joshi, Shalmali and Tang, Shengpu and Urteaga, Iñigo}, volume = {298}, series = {Proceedings of Machine Learning Research}, month = {15--16 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v298/main/assets/ketenci25a/ketenci25a.pdf}, url = {https://proceedings.mlr.press/v298/ketenci25a.html}, abstract = {Survival analysis is a fundamental tool for modeling time-to-event outcomes in healthcare. Recent advances have introduced flexible neural network approaches for improved predictive performances. However, these models do not provide interpretable insights into the association between exposures and the modeled outcomes, a critical requirement for decision-making in clinical practice. To address this limitation, we propose Additive Deep Hazard Analysis Mixtures (ADHAM), an interpretable additive survival model. ADHAM assumes a conditional latent subpopulation structure that characterizes an individual, combined with covariate-specific hazard functions. To select the number of subpopulations, we introduce a post-training group refinement-based model-selection procedure; \ie an efficient approach to merge similar clusters to reduce the number of repetitive latent subpopulations identified by the model. We perform comprehensive studies to demonstrate ADHAM’s interpretability on population, subpopulation, and individual levels. Extensive experiments on real-world datasets show that ADHAM provides novel insights into the association between exposures and outcomes. Further, ADHAM remains on par with existing state-of-the-art survival baselines, offering a scalable and interpretable approach to time-to-event prediction in healthcare.} }
Endnote
%0 Conference Paper %T ADHAM: Additive Deep Hazard Analysis Mixtures for Interpretable Survival Regression %A Mert Ketenci %A Vincent Jeanselme %A Harry Reyes Nieva %A Shalmali Joshi %A Noémie Elhadad %B Proceedings of the 10th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2025 %E Monica Agrawal %E Kaivalya Deshpande %E Matthew Engelhard %E Shalmali Joshi %E Shengpu Tang %E Iñigo Urteaga %F pmlr-v298-ketenci25a %I PMLR %U https://proceedings.mlr.press/v298/ketenci25a.html %V 298 %X Survival analysis is a fundamental tool for modeling time-to-event outcomes in healthcare. Recent advances have introduced flexible neural network approaches for improved predictive performances. However, these models do not provide interpretable insights into the association between exposures and the modeled outcomes, a critical requirement for decision-making in clinical practice. To address this limitation, we propose Additive Deep Hazard Analysis Mixtures (ADHAM), an interpretable additive survival model. ADHAM assumes a conditional latent subpopulation structure that characterizes an individual, combined with covariate-specific hazard functions. To select the number of subpopulations, we introduce a post-training group refinement-based model-selection procedure; \ie an efficient approach to merge similar clusters to reduce the number of repetitive latent subpopulations identified by the model. We perform comprehensive studies to demonstrate ADHAM’s interpretability on population, subpopulation, and individual levels. Extensive experiments on real-world datasets show that ADHAM provides novel insights into the association between exposures and outcomes. Further, ADHAM remains on par with existing state-of-the-art survival baselines, offering a scalable and interpretable approach to time-to-event prediction in healthcare.
APA
Ketenci, M., Jeanselme, V., Nieva, H.R., Joshi, S. & Elhadad, N.. (2025). ADHAM: Additive Deep Hazard Analysis Mixtures for Interpretable Survival Regression. Proceedings of the 10th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 298 Available from https://proceedings.mlr.press/v298/ketenci25a.html.

Related Material