Predicting 28-Day Mortality in Critically Ill Patients Receiving Continuous Renal Replacement Therapy: A Novel Interpretable Machine Learning Approach
The GP-based model accurately predicts 28-day mortality in CRRT patients and demonstrates strong generalizability. By integrating SHAP explanations, it offers clinicians an interpretable tool to identify high-risk patients early, potentially improving outcomes.
Authors
- Shaohan Guo
- Xiaoxuan Fan (ORCID: https://orcid.org/0000-0002-0876-3091)
- Tao Zhang (ORCID: https://orcid.org/0000-0002-6681-7983)
- Congcong Zhao (ORCID: https://orcid.org/0000-0003-4474-0687)
- Nan Zhang (ORCID: https://orcid.org/0000-0001-9620-5665)
- Zhenjie Hu (ORCID: https://orcid.org/0000-0003-1404-5691)
- Xin Yan
- Jing-Xiao Pang (ORCID: https://orcid.org/0009-0002-2597-2394)
Institutions
- Hebei Medical University (CN)
- Fourth Hospital of Hebei Medical University (CN)
- First Hospital of Shijiazhuang (CN)
Publication Details
- Journal
- Journal of Multidisciplinary Healthcare
- Published
- 2025-09-01
- DOI
- https://doi.org/10.2147/jmdh.s533031
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Massachusetts Institute of Technology
- Health Commission of Hebei Province