Preoperative prediction of acute severe cholecystitis using an attentive interpretable tabular network (TabNet)-based radiomics model and a stacking ensemble: a two-center study
Hong-Yu Long, Wei Li, Xin Yan, Bai-Qing Chen, Feng Xie · 2026
Read Preoperative prediction of acute severe cholecystitis using an attentive interpretable tabular network (TabNet)-based radiomics model and a stacking ensemble: a two-center study by Hong-Yu Long, Wei Li, Xin Yan, Bai-Qing Chen, Feng Xie (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-13580380.txt.
Description
Hong-Yu Long and co-authors build a model to flag severe gallbladder attacks before surgery, in a 2026 study. Acute cholecystitis is a painful gallbladder inflammation that can turn severe. Spotting severe cases early guides safer care. The team used patient data from two large hospitals, with one site held back as an outside test.
Their model stacks two learners in layers. One reads image features from CT scans using an attention-based network. The other reads clinical and imaging traits with a boosting method. A simple final layer merges both forecasts. An explanation tool shows which inputs mattered most. The stacked model beat each single learner at both sites. Doctors get a tool that is both sharper and open to inspection.
Catalog record
| CREATOR | Hong-Yu Long, Wei Li, Xin Yan, Bai-Qing Chen, Feng Xie |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 27 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |