Development and validation of an explainable XGBoost model for early mortality prediction in pediatric sepsis
Hong-mei Chen, Li-nong Wang, Yan-bing Fu, Jun Hua · 2026
Read Development and validation of an explainable XGBoost model for early mortality prediction in pediatric sepsis by Hong-mei Chen, Li-nong Wang, Yan-bing Fu, Jun Hua (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-13572637.txt.
Description
Chen and co-authors present a 2026 study building an explainable model to predict death risk in children with sepsis. Early warning can steer intensive care choices for these fragile patients. Records covered 752 children admitted to a Suzhou children's ICU from 2019 to mid-2023. Twenty-six routine measures from the first day fed the model search.
Twelve learning methods were trained and compared on standard accuracy tests. A boosted-tree model, XGBoost, came out on top among them. A tool called SHAP then showed which measures pushed each prediction up or down. The authors stress that doctors can see the reasons, not just a score. The model was checked inside the same hospital data.
Catalog record
| CREATOR | Hong-mei Chen, Li-nong Wang, Yan-bing Fu, Jun Hua |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |