Interpretable machine learning to predict postoperative adverse outcomes in cardiac surgery
Li lei, Dengkang Qin, Mengxue Liu, Die Ma, Xia Lei, Si Zeng, Zheng Chen, Qian Lei · 2026
Read Interpretable machine learning to predict postoperative adverse outcomes in cardiac surgery by Li lei, Dengkang Qin, Mengxue Liu, Die Ma, Xia Lei, Si Zeng, Zheng Chen, Qian Lei (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-13419318.txt.
Description
Li Lei and colleagues built an interpretable machine-learning model in 2026 to predict bad outcomes after heart surgery. Cardiac surgery carries heavy complication risks, and the team used data from 3270 bypass patients at one tertiary hospital, adding operating-room and early intensive-care data to a standard preoperative risk score.
The gradient-boosting model predicted adverse outcomes well on validation data, and counterfactual explanations showed which changes might have flipped individual predictions. Surgeons gain an updated risk estimate at intensive-care admission that they can actually interrogate, not just accept on trust in daily rounds.
Catalog record
| CREATOR | Li lei, Dengkang Qin, Mengxue Liu, Die Ma, Xia Lei, Si Zeng, Zheng Chen, Qian Lei |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |