Development and external validation of an interpretable machine learning model for predicting prolonged postoperative ICU length of stay in coronary artery bypass grafting patients using MIMIC-IV 3.1 and eICU-CRD 2.0
Dayan Liu, Pengyu Lu, Yulan Meng, Xianglong Liu, Wei Huang · 2026
Read Development and external validation of an interpretable machine learning model for predicting prolonged postoperative ICU length of stay in coronary artery bypass grafting patients using MIMIC-IV 3.1 and eICU-CRD 2.0 by Dayan Liu, Pengyu Lu, Yulan Meng, Xianglong Liu, Wei Huang (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/PMC13579721.txt.
Description
Dayan Liu and colleagues build a calculator that flags heart bypass patients likely to linger in intensive care, in a 2026 study. Long ICU stays after bypass surgery strain beds and budgets, and the call must be made at the one day check. Records came from two large critical care databases, one used to build the model and one held back for a cold test.
Eight bedside facts from the first day fed the model, led by fluid intake, overall illness load, and a rhythm fault. A boosting model won a nine way race. It sorted risk fairly at home, with well matched odds, and kept its calibration abroad though its sorting dipped. A web calculator shows each patient's drivers one by one. The authors pitch it as honest decision support, not a verdict.
Catalog record
| CREATOR | Dayan Liu, Pengyu Lu, Yulan Meng, Xianglong Liu, Wei Huang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42866 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |