Beyond static risk scores: dynamic world models simulating patient-specific trajectories to inform preoperative risk mitigation strategies
Jiawen Li, Xuchao Fang, Ping Yu, Lanfang Jiang · 2026
Read Beyond static risk scores: dynamic world models simulating patient-specific trajectories to inform preoperative risk mitigation strategies by Jiawen Li, Xuchao Fang, Ping Yu, Lanfang Jiang (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-13627387.txt.
Description
Jiawen Li, Xuchao Fang, Ping Yu, and Lanfang Jiang propose a world model that simulates how a surgery patient's health evolves, replacing fixed risk scores, in a study from 2026. Standard scores freeze risk at one moment. They miss the rapid swings in physiology and care that unfold around an operation.
Their Dynamic Patient World Model has three parts. An encoder handles messy, irregular clinical data. A dynamics module predicts state changes under each intervention. A counterfactual evaluator scores the other choices. Tested on three public surgical databases against fourteen rivals, it raised complication prediction accuracy by 1.4 to 2.2 points. One of those gains, though, was not significant. Most of its suggested interventions matched decisions linked to good outcomes.
Catalog record
| CREATOR | Jiawen Li, Xuchao Fang, Ping Yu, Lanfang Jiang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 79 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |