Dynamic Survival Analysis for Early Event Prediction

Hugo Yèche, Manuel Burger, Dinara Veshchezerova, Gunnar Ratsch
Proceedings of the fifth Conference on Health, Inference, and Learning, PMLR 248:540-557, 2024.

Abstract

This study advances Early Event Prediction (EEP) in healthcare through Dynamic Survival Analysis (DSA), offering a novel approach by integrating risk localization into alarm policies to enhance clinical event metrics. By adapting and evaluating DSA models against traditional EEP benchmarks, our research demonstrates their ability to match EEP models on a time-step level and significantly improve event-level metrics through a new alarm prioritization scheme (up to 11% AuPRC difference). This approach represents a significant step forward in predictive healthcare, providing a more nuanced and actionable framework for early event prediction and management.

Cite this Paper

BibTeX
@InProceedings{pmlr-v248-yeche24a, title = {Dynamic Survival Analysis for Early Event Prediction}, author = {Y\`eche, Hugo and Burger, Manuel and Veshchezerova, Dinara and Ratsch, Gunnar}, booktitle = {Proceedings of the fifth Conference on Health, Inference, and Learning}, pages = {540--557}, year = {2024}, editor = {Pollard, Tom and Choi, Edward and Singhal, Pankhuri and Hughes, Michael and Sizikova, Elena and Mortazavi, Bobak and Chen, Irene and Wang, Fei and Sarker, Tasmie and McDermott, Matthew and Ghassemi, Marzyeh}, volume = {248}, series = {Proceedings of Machine Learning Research}, month = {27--28 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v248/main/assets/yeche24a/yeche24a.pdf}, url = {https://proceedings.mlr.press/v248/yeche24a.html}, abstract = {This study advances Early Event Prediction (EEP) in healthcare through Dynamic Survival Analysis (DSA), offering a novel approach by integrating risk localization into alarm policies to enhance clinical event metrics. By adapting and evaluating DSA models against traditional EEP benchmarks, our research demonstrates their ability to match EEP models on a time-step level and significantly improve event-level metrics through a new alarm prioritization scheme (up to 11% AuPRC difference). This approach represents a significant step forward in predictive healthcare, providing a more nuanced and actionable framework for early event prediction and management.} }
Endnote
%0 Conference Paper %T Dynamic Survival Analysis for Early Event Prediction %A Hugo Yèche %A Manuel Burger %A Dinara Veshchezerova %A Gunnar Ratsch %B Proceedings of the fifth Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2024 %E Tom Pollard %E Edward Choi %E Pankhuri Singhal %E Michael Hughes %E Elena Sizikova %E Bobak Mortazavi %E Irene Chen %E Fei Wang %E Tasmie Sarker %E Matthew McDermott %E Marzyeh Ghassemi %F pmlr-v248-yeche24a %I PMLR %P 540--557 %U https://proceedings.mlr.press/v248/yeche24a.html %V 248 %X This study advances Early Event Prediction (EEP) in healthcare through Dynamic Survival Analysis (DSA), offering a novel approach by integrating risk localization into alarm policies to enhance clinical event metrics. By adapting and evaluating DSA models against traditional EEP benchmarks, our research demonstrates their ability to match EEP models on a time-step level and significantly improve event-level metrics through a new alarm prioritization scheme (up to 11% AuPRC difference). This approach represents a significant step forward in predictive healthcare, providing a more nuanced and actionable framework for early event prediction and management.
APA
Yèche, H., Burger, M., Veshchezerova, D. & Ratsch, G.. (2024). Dynamic Survival Analysis for Early Event Prediction. Proceedings of the fifth Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 248:540-557 Available from https://proceedings.mlr.press/v248/yeche24a.html.

Related Material