Development of an interpretable machine learning model for predicting in-hospital mortality in ICU patients with sepsis: a retrospective cohort study
Tianyu Zhao, Kexin Wen, Xumin Han, Ruimin Tan, Yongtao Wang, Quansheng Du · 2026
Read Development of an interpretable machine learning model for predicting in-hospital mortality in ICU patients with sepsis: a retrospective cohort study by Tianyu Zhao, Kexin Wen, Xumin Han, Ruimin Tan, Yongtao Wang, Quansheng Du (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/pmc-13619919.txt.
Description
Tianyu Zhao and five colleagues build a machine learning model to predict which intensive care patients with sepsis will die in hospital. Sepsis drives many ICU deaths, and standard scores spot high-risk patients only weakly. A model doctors can read matters as much as raw accuracy.
The study screened 503 sepsis patients at a Hebei hospital and kept 431 with full data. Nearly half died during the stay. Eight algorithms trained on two thirds of the cases, with twelve key predictors picked by a feature filter. A random forest gave the most balanced results. Importance scores then explained which factors drove each prediction. The authors offer the tool for earlier, clearer warnings at the bedside.
Catalog record
| CREATOR | Tianyu Zhao, Kexin Wen, Xumin Han, Ruimin Tan, Yongtao Wang, Quansheng Du |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |