Early identification of acute kidney injury progression in critically ill patients with sepsis: interpretable machine learning approach
Xiaodong You, Yanlong Chen, Jiahui Chen, Xinyi Mao, Yifei Wang, Zhongman Zhang, Zheng Zhou, Wei Li, Yong Mei, Yi Zhu, Peipei Huang, Xufeng Chen · 2026
Read Early identification of acute kidney injury progression in critically ill patients with sepsis: interpretable machine learning approach by Xiaodong You, Yanlong Chen, Jiahui Chen, Xinyi Mao, Yifei Wang, Zhongman Zhang, Zheng Zhou, Wei Li, Yong Mei, Yi Zhu, Peipei Huang, Xufeng Chen (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/PMC13452581.txt.
Description
Xiaodong You and eleven co-authors train a computer model to warn early when kidney injury in sepsis patients is about to get worse. Sepsis is a body wide response to infection, and kidney injury is one of its deadliest turns. Their 2026 study defines worsening as a jump to the most severe kidney stage within seven days of the first injury.
Records came from four intensive care databases, with over 9,000 patients in the main training set alone. Twelve measures fed the final model, among them weight, blood pressure, urine output, and blood urea nitrogen. A random forest model, which averages many decision trees, beat five rival methods in checks inside and outside its home data. The team also built a simple web tool so doctors can enter the measures and get a risk score at the bedside.
Catalog record
| CREATOR | Xiaodong You, Yanlong Chen, Jiahui Chen, Xinyi Mao, Yifei Wang, Zhongman Zhang, Zheng Zhou, Wei Li, Yong Mei, Yi Zhu, Peipei Huang, Xufeng Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34034 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |