Integrative and interpretable machine learning framework for early non-invasive detection of clinically significant liver fibrosis
Dong Cao, Junjie Wang, Chenxi Hou, Jingyu Zeng, Baiyue Tian, Yuan Liu, Xing Luo, Jiaxin Tian, Mingbo Zhou, Pan Li, Huilong Fang, Ze Liu, Zheng Gong · 2026
Read Integrative and interpretable machine learning framework for early non-invasive detection of clinically significant liver fibrosis by Dong Cao, Junjie Wang, Chenxi Hou, Jingyu Zeng, Baiyue Tian, Yuan Liu, Xing Luo, Jiaxin Tian, Mingbo Zhou, Pan Li, Huilong Fang, Ze Liu, Zheng Gong (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/PMC13337473.txt.
Description
Dong Cao leads a large 2026 team building an explainable machine learning tool for early liver fibrosis detection. Scarring predicts poor liver outcomes, yet early stages hide well. Using NHANES 2017–2020 data, the team classified 6,164 participants by liver stiffness scans and benchmarked 29 learning models after automated feature selection.
A Gamboost model won, reaching an AUC of 0.824 in training and 0.872 in testing cohorts in the reported evaluation, and it held 0.848 on an external set of 684 samples during validation. Body mass index, the liver enzyme AST, and waist size led the predictors, with high AST plus large waist jointly raising risk in the explanation analyses. Routine clinic data could thus flag fibrosis early without a biopsy.
Catalog record
| CREATOR | Dong Cao, Junjie Wang, Chenxi Hou, Jingyu Zeng, Baiyue Tian, Yuan Liu, Xing Luo, Jiaxin Tian, Mingbo Zhou, Pan Li, Huilong Fang, Ze Liu, Zheng Gong |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 65404 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |