An explainable machine learning model for predicting osteoporotic fragility fractures: a retrospective study in South China
Zebing Si, Konghe Hu, Huajun Wang, Xiaofei Zheng · 2026
Read An explainable machine learning model for predicting osteoporotic fragility fractures: a retrospective study in South China by Zebing Si, Konghe Hu, Huajun Wang, Xiaofei Zheng (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/PMC13327856.txt.
Description
Zebing Si and co-authors build an explainable fracture forecast for weak bones in a 2026 study from South China. They gathered 1,125 hospitalized patients with osteoporotic fractures who had bone density scans at one hospital between 2019 and 2025. From each record they drew 73 clinical, lab, and imaging features.
Six learning methods competed after a filter step cut weak features, and LightGBM won, reaching an AUC of 0.903 in training and 0.840 on the held-back test set in their checks. Explanation analysis named age, a hepatitis C antibody marker, and blood sodium as the top factors pushing risk upward. Such a tool could flag fragile patients early enough for preventive treatment.
Catalog record
| CREATOR | Zebing Si, Konghe Hu, Huajun Wang, Xiaofei Zheng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36135 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |