Dynamic Survival Analysis for Early Event Prediction
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
Text
Yèche et al. "Dynamic Survival Analysis for Early Event Prediction." Proceedings of the fifth Conference on Health, Inference, and Learning, 2024.Markdown
[Yèche et al. "Dynamic Survival Analysis for Early Event Prediction." Proceedings of the fifth Conference on Health, Inference, and Learning, 2024.](https://mlanthology.org/chil/2024/yeche2024chil-dynamic/)BibTeX
@inproceedings{yeche2024chil-dynamic,
title = {{Dynamic Survival Analysis for Early Event Prediction}},
author = {Yèche, Hugo and Burger, Manuel and Veshchezerova, Dinara and Ratsch, Gunnar},
booktitle = {Proceedings of the fifth Conference on Health, Inference, and Learning},
year = {2024},
pages = {540-557},
volume = {248},
url = {https://mlanthology.org/chil/2024/yeche2024chil-dynamic/}
}