HazardFlow: Enhancing Health Status Representations via Score-based Energy Modeling

Qianyu Chen; Xin Li; Yonggang Zhang; Mingzhong Wang

doi:10.1145/3770855.3817616

Back

HazardFlow: Enhancing Health Status Representations via Score-based Energy Modeling

Conference paper

Open access

Peer reviewed

HazardFlow: Enhancing Health Status Representations via Score-based Energy Modeling

Qianyu Chen, Xin Li, Yonggang Zhang and Mingzhong Wang

Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, pp.425-436

ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 32nd (Jeju Island, Korea, 09-Aug-2026–13-Aug-2026)

ACM Conferences, Association for Computing Machinery

2026

DOI: https://doi.org/10.1145/3770855.3817616

Files and links (1)

pdf

3770855.38176161.54 MBDownload View

Published Version Open Access CC BY V4.0

Abstract

health risk prediction

health status representation

score-based generative modeling

Learning effective health status representations from Electronic Health Records (EHRs) is essential for accurate health risk prediction. While data-driven models have advanced this field, most existing approaches rely on heuristic patterns and often struggle to capture subtle risk dynamics, specifically under imbalanced label distributions. In this work, we propose a novel score-based energy modeling paradigm to enhance health status representation by incorporating a mathematically grounded formulation of health risk. We theoretically show that the hazard function, a canonical quantification of instantaneous risk, is mathematically proportional to the score function of the health status representation, providing a principled mechanism for modeling risk dynamics. Building on this insight, we develop HazardFlow, a pluggable module that explicitly estimates the hazard function and enhances health status representations with hazard escalation and reduction mechanisms. HazardFlow is designed for seamless integration into diverse health risk prediction models, including both uni-modal and multi-modal backbones. Extensive experiments on the MIMIC-III, MIMIC-IV, and MIMIC-CXR datasets demonstrate that HazardFlow consistently improves performance across diverse health risk prediction tasks, validating its generality, robustness, and theoretical soundness.

Details

Title: HazardFlow: Enhancing Health Status Representations via Score-based Energy Modeling
Authors: Qianyu Chen - Beijing Institute of Technology
Xin Li - Beijing Institute of Technology
Yonggang Zhang - Jilin University
Mingzhong Wang - University of the Sunshine Coast
Publication details: Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, pp.425-436
Conference details: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 32nd (Jeju Island, Korea, 09-Aug-2026–13-Aug-2026)
Series: ACM Conferences
Publisher: Association for Computing Machinery
Date published: 2026
DOI: 10.1145/3770855.3817616; 10.1145/3770855
Copyright note: This work is licensed under a Creative Commons Attribution- 4.0 International License.
Grant note: This work was partially supported by the National Key Research and Development Program of China (Grant No.2025YFC3309100), the National Natural Science Foundation of China (Grant No.62276024), the Beijing Natural Science Foundation (Grant No.4262066), the Fundamental Research Funds for the Central Universities, Jilin University (Grant No.93K172025K01), and the Fundamental Research Funds for the Central Universities (Grant No.2025CX01010).
Organisation Unit: Healthy Ageing Research Cluster; School of Science, Technology and Engineering
Language: English
Record Identifier: 991250589202621
Output Type: Conference paper

Metrics

1 Record Views