Dynamic Survival Analysis for Early Event Prediction
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 13 of its 41 references that are in the map. First posted on arXiv 19 Mar 2024.
Builds on
13 of 41 references.
References · 13
- 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
- 2016DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Networkcited by 354
- 2019Time-to-Event Prediction with Neural Networks and Cox Regressioncited by 173
- 2019Set Functions for Time Seriescited by 137
- 2019MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-IIIcited by 121
- 2018A Scalable Discrete-Time Survival Model for Neural Networkscited by 70
- 2018Deep Recurrent Survival Analysiscited by 61
- 2017Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifiercited by 47
- 2021HiRID-ICU-Benchmark -- A Comprehensive Machine Learning Benchmark on High-resolution ICU Datacited by 38
- 2023Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical MLcited by 28
- 2022Temporal Label Smoothing for Early Event Predictioncited by 12
- 2018SAFE: A Neural Survival Analysis Model for Fraud Early Detectioncited by 7
Built on by
Citing papers per year: 2024: 2; 2025: 1; 2026: 2.
5 papers.
- 2024MEDS-Tab: Automated tabularization and baseline methods for MEDS datasetscited by 4
- 2024Towards Foundation Models for Critical Care Time Seriescited by 3
- 2025Data-Driven Discovery of Feature Groups in Clinical Time Seriescited by 1
- 2026Weighted Score-Oriented Losses for Temporally Localized Event Predictioncited by 0
- 2026Horizon-Aware Early Event Prediction for Tokamak Disruption Alarmscited by 0
- 2026Horizon-Aware Early Event Prediction for Tokamak Disruption Alarms21 Sep 2026
- 2026Weighted Score-Oriented Losses for Temporally Localized Event Prediction22 Jun 2026
- 2025Data-Driven Discovery of Feature Groups in Clinical Time Series11 Nov 2025
- 2024Towards Foundation Models for Critical Care Time Series25 Nov 2024
- 2024MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets31 Oct 2024