Development of machine learning models with explainable AI for frailty risk prediction and their web-based application in community public health
An explainable machine learning model with strong discrimination performance and adequate calibration was developed, accompanied by a lightweight web application for potential use in community and clinical settings. However, external validation, recalibration, and subgroup fairness assessments are needed to ensure generalizability and clinical adoption.
Authors
- Myung‐Jun Shin (ORCID: https://orcid.org/0000-0003-4010-0383)
- Up Huh (ORCID: https://orcid.org/0000-0002-7739-3979)
- Zoran Obradović (ORCID: https://orcid.org/0000-0002-2051-0142)
- J. Cho (ORCID: https://orcid.org/0000-0002-9185-0283)
- Jong‐Hwan Park (ORCID: https://orcid.org/0000-0003-2815-7248)
- Daniel J. Rubin (ORCID: https://orcid.org/0000-0002-6871-6246)
- Byung Kwan Choi (ORCID: https://orcid.org/0000-0001-5244-4592)
- Seulgi Kim (ORCID: https://orcid.org/0000-0002-8015-7379)
- Jae Il Lee
Institutions
- Pusan National University Hospital (KR)
- Pusan National University Yangsan Hospital (KR)
- Pusan National University (KR)
- Temple University (US)
Publication Details
- Journal
- Frontiers in Public Health
- Published
- 2025-11-06
- DOI
- https://doi.org/10.3389/fpubh.2025.1698062
- Citations
- 1
- Primary Topic
- Frailty in Older Adults
- Type
- article
- Field-Weighted Citation Impact
- 1.22
Funders
- Pusan National University
- Pusan National University Hospital