Predicting the causes of unplanned reoperations using an AI-based multimodal system: a multicentre, multidepartmental study based on EMRs
Luyuan Xie, Congpu Zhao, Xutong Tan, Pengyu Zhao, Xuan Gong, Shengyang Li, Qingni Shen, Tianyu Luan, Guochen Yan, Dan Wang, Jiong Zhou, Xiaojun Ma, Zhonghai Wu · 2026
Read Predicting the causes of unplanned reoperations using an AI-based multimodal system: a multicentre, multidepartmental study based on EMRs by Luyuan Xie, Congpu Zhao, Xutong Tan, Pengyu Zhao, Xuan Gong, Shengyang Li, Qingni Shen, Tianyu Luan, Guochen Yan, Dan Wang, Jiong Zhou, Xiaojun Ma, Zhonghai Wu (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-13528333.txt.
Description
Xie and colleagues built an artificial intelligence system to predict why surgical patients end up back in theatre unexpectedly, information hospitals need to fix quality problems. Most earlier work mined records retrospectively for single diseases. Their 2026 system, called MPSUR, learned from 2,922 cases across 15 departments in eight hospitals between 2015 and 2024. It fused structured data like age and laboratory series with free clinical text through graph and recurrent neural networks.
In a reader study, the system beat surgeons at naming the true cause of reoperation, reaching mean accuracy around sixty percent while the human readers scored lower across every department tested. Removing the procedure performed and the department from its inputs hurt performance most, which tells developers where the predictive signal concentrates. The authors present the tool as decision support for quality review boards, triaging which reoperations deserve deep case review.
Catalog record
| CREATOR | Luyuan Xie, Congpu Zhao, Xutong Tan, Pengyu Zhao, Xuan Gong, Shengyang Li, Qingni Shen, Tianyu Luan, Guochen Yan, Dan Wang, Jiong Zhou, Xiaojun Ma, Zhonghai Wu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 39 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |