Development and validation of an explainable machine learning model for predicting acute kidney injury after robot-assisted partial nephrectomy: a retrospective multicenter study
The GBM model exhibited strong predictive performance in both internal training dataset and external validation dataset and has the potential to assist clinicians to identify the high-risk patients early, enabling timely interventions that may reduce the incidence of RAPN-AKI and improving clinical outcomes. While, the interpretable machine learning model is currently applicable only to patients with low-risk or normal preoperative renal function.
Authors
- Han Gao (ORCID: https://orcid.org/0000-0002-7900-9483)
- Yan Jin (ORCID: https://orcid.org/0000-0002-0378-1362)
- Yi Liu (ORCID: https://orcid.org/0000-0002-0973-4241)
- Yongzhe Liu
- Jiang Huo
- Huixian Chen (ORCID: https://orcid.org/0000-0003-2808-5360)
- Changhong Sun
- Weiwei Liu (ORCID: https://orcid.org/0000-0003-4708-8057)
- Xiufeng Li (ORCID: https://orcid.org/0000-0002-0764-4613)
- Longhe Xu (ORCID: https://orcid.org/0000-0002-5699-8231)
- Yingqun Yu
- Yunfei Lv
- Fei Liu (ORCID: https://orcid.org/0000-0002-7848-5226)
- Jiaxin Li (ORCID: https://orcid.org/0000-0002-8594-0506)
Institutions
- Chinese PLA General Hospital (CN)
- Chinese People's Armed Police Force Medical College Affiliated Hospital (CN)
Publication Details
- Journal
- BMC Nephrology
- Published
- 2025-12-05
- DOI
- https://doi.org/10.1186/s12882-025-04676-1
- Primary Topic
- Renal cell carcinoma treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00