Identification and validation of a chronic kidney disease prediction model after radical nephrectomy: a multicenter cohort retrospective study
Xinning Wang, Tianwei Zhang, Jingxian Wang, Yongchao Yan, Haoyuan Wang, Kefan Song, Yongbo Yu, Zhilei Zhang, Benkui Zou, Changlei Yao, Jianbo Zheng, Jie Liu · 2026
Read Identification and validation of a chronic kidney disease prediction model after radical nephrectomy: a multicenter cohort retrospective study by Xinning Wang, Tianwei Zhang, Jingxian Wang, Yongchao Yan, Haoyuan Wang, Kefan Song, Yongbo Yu, Zhilei Zhang, Benkui Zou, Changlei Yao, Jianbo Zheng, Jie Liu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13629762.txt.
Description
Xinning Wang and seventeen colleagues built machine learning models for kidney cancer care. The models predict which patients will lose kidney function after the tumour-bearing kidney is removed. Their study gathered 649 patients from eight hospitals. Five algorithms were trained at one centre. Results were tested at home and on patients from seven other centres.
About a third of patients advanced a chronic kidney disease stage within three years. A gradient boosting model performed best in both test sets. Ranking of the drivers put prior kidney function first. Tumour size came next. The creatinine change after surgery also ranked high, and age mattered too. The authors offer the model as a screening aid. High-risk patients can then get stricter preventive follow-up from the first treatment visit.
Catalog record
| CREATOR | Xinning Wang, Tianwei Zhang, Jingxian Wang, Yongchao Yan, Haoyuan Wang, Kefan Song, Yongbo Yu, Zhilei Zhang, Benkui Zou, Changlei Yao, Jianbo Zheng, Jie Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |