Beyond NIHSS and neuroimaging: an interpretable gradient boosting model for predicting in-hospital mortality in ICU patients with acute ischemic stroke
Limin Yang, Yue Song, Guangxin Gu, Ruiwen Wang, Peng Chen, Lianhui Fan · 2026
Read Beyond NIHSS and neuroimaging: an interpretable gradient boosting model for predicting in-hospital mortality in ICU patients with acute ischemic stroke by Limin Yang, Yue Song, Guangxin Gu, Ruiwen Wang, Peng Chen, Lianhui Fan (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-13338277.txt.
Description
Predicting which intensive care stroke patients will die in hospital usually leans on a standard stroke score and brain scans. A model built only from routine bedside data may do as well, Limin Yang and co-authors show in this 2026 study. Records covered more than three thousand stroke patients in intensive care at a large Chinese hospital.
Sixteen predictors available within forty-eight hours of admission fed six competing models. The best used a gradient boosting method and stayed interpretable, so doctors can see which factors drive each prediction. Dropping the specialist score and scans makes the tool usable in smaller hospitals and earlier in the stay. The authors compared accuracy and calibration across the models before naming a winner.
Catalog record
| CREATOR | Limin Yang, Yue Song, Guangxin Gu, Ruiwen Wang, Peng Chen, Lianhui Fan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |