Explainable Machine Learning Model for Predicting Persistent Sepsis-Associated Acute Kidney Injury: Development and Validation Study
The interpretable GBM model was shown to successfully and accurately predict the occurrence of persistent SA-AKI, demonstrating good predictive ability in both internal and external validation cohorts. Furthermore, the model was demonstrated to outperform the biomarker CCL14 in prospective cohort validation.
Authors
- Yaosheng Zhang (ORCID: https://orcid.org/0000-0002-9340-3479)
- Quan Yuan (ORCID: https://orcid.org/0000-0002-2552-333X)
- Shiqi Xu
- Jun Shao (ORCID: https://orcid.org/0000-0002-9520-9653)
- Chuanqing Zhang (ORCID: https://orcid.org/0000-0002-0493-1959)
- Luanluan Li (ORCID: https://orcid.org/0009-0008-1371-6370)
- Jiangquan Yu (ORCID: https://orcid.org/0000-0001-9338-4311)
- Jing Wang (ORCID: https://orcid.org/0009-0008-7175-9870)
- Siqi Liu (ORCID: https://orcid.org/0000-0001-5278-3156)
- Yongwei Zhang (ORCID: https://orcid.org/0000-0001-9958-3098)
- Xianghui Li (ORCID: https://orcid.org/0000-0001-8352-0017)
- Song Lin (ORCID: https://orcid.org/0000-0002-8922-4777)
- Wei Jiang (ORCID: https://orcid.org/0000-0002-5278-3057)
- Ruiqiang Zheng (ORCID: https://orcid.org/0009-0001-3774-9918)
- Jiayi Weng
- Keran Shi
Institutions
- Beijing Jiaotong University (CN)
- Northern Jiangsu People's Hospital (CN)
- Shandong First Medical University (CN)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-04-09
- DOI
- https://doi.org/10.2196/62932
- Citations
- 13
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 17.60