Personalised thrombo-embolic risk prediction after endometrial cancer surgery: an explainable AI approach using SHAP
Qing Zhou, Fudan Liu, Jiaxiu Li, Qiyin Zhou, Xiaorong Xiang, Cheng Dai, Lianli Hen, ShouLi Dao, Mingjie Zhang, Bowen Gao, Yuxi Li, Lin Xu, Yonghu Chang, Donghong Wang · 2026
Read Personalised thrombo-embolic risk prediction after endometrial cancer surgery: an explainable AI approach using SHAP by Qing Zhou, Fudan Liu, Jiaxiu Li, Qiyin Zhou, Xiaorong Xiang, Cheng Dai, Lianli Hen, ShouLi Dao, Mingjie Zhang, Bowen Gao, Yuxi Li, Lin Xu, Yonghu Chang, Donghong Wang (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-13490570.txt.
Description
Qing Zhou and others build an explainable machine-learning tool to predict leg vein clots after womb lining cancer surgery. In 2026, the study uses around surgery data from 841 patients across multiple centers, testing twenty-six algorithms with data augmentation methods. Standard clot scores perform poorly in gynecologic oncology and cannot use changing after surgery lab values.
A support vector machine model won, refined to four variables: after surgery D-dimer, age, fibrinogen, and medical stage. It scored 0.828 internally and 0.819 in an external cohort, while SHAP explanations revealed non-linear effects such as a key D-dimer threshold. A web interface delivers real-time, interpretable risk estimates to guide preventive care.
Catalog record
| CREATOR | Qing Zhou, Fudan Liu, Jiaxiu Li, Qiyin Zhou, Xiaorong Xiang, Cheng Dai, Lianli Hen, ShouLi Dao, Mingjie Zhang, Bowen Gao, Yuxi Li, Lin Xu, Yonghu Chang, Donghong Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |