A machine-learning model for staging autoimmune gastritis based on endoscopic and serological features
Jingna Tao, Linghan Meng, Tong Li, Jiaqi Wang, Liju Zhang, Xiyan Zhang, Zhihong Li · 2026
Read A machine-learning model for staging autoimmune gastritis based on endoscopic and serological features by Jingna Tao, Linghan Meng, Tong Li, Jiaqi Wang, Liju Zhang, Xiyan Zhang, Zhihong Li (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/PMC13461725.txt.
Description
Jingna Tao and colleagues built machine learning models that stage autoimmune gastritis from scope images and blood tests. Autoimmune gastritis is a slow stomach disease where the immune system destroys acid-making cells, and staging today depends on observer judgement.
The study enrolled 203 patients classed into three stages by how much healthy stomach lining remained. Seven algorithms were trained on five feature sets, mixing standard scope views, magnified imaging, and a serum panel. A random forest using scope plus blood features staged best, with a macro-AUC of 0.878 across the three stages. Lost stomach folds and two blood markers ranked among the strongest staging signals, Tao reports. Barrett's oesophagus, a risky throat-lining change, appeared in 66.8 percent of patients, backing routine checks in this group.
Catalog record
| CREATOR | Jingna Tao, Linghan Meng, Tong Li, Jiaqi Wang, Liju Zhang, Xiyan Zhang, Zhihong Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 27 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |