Development of a Multimodal Machine Learning Model for Predicting Second Osteoporotic Vertebral Compression Fractures
Hoyeon Cho, Min Kyoon Joo, Pyung Goo Cho, Sang Hyun Kim, Sung Hyeon Noh · 2026
Read Development of a Multimodal Machine Learning Model for Predicting Second Osteoporotic Vertebral Compression Fractures by Hoyeon Cho, Min Kyoon Joo, Pyung Goo Cho, Sang Hyun Kim, Sung Hyeon Noh (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-13526500.txt.
Description
Hoyeon Cho and co-authors build a machine learning model to predict a second osteoporotic vertebral compression fracture after a first one. Published in 2026, the study reviews 178 patients treated at one institution over twenty years. The model joins eighteen clinical variables, bone density and body composition from DEXA scans, and imaging data, fusing them at an intermediate stage.
A model that paired the fused features with a random forest scored near perfect marks in internal cross validation. On an outside cohort its scores fell but stayed strong, a sign of dataset shift and possible overfitting, the authors note. Body composition measures and image derived features carried the most weight. The tool aims to flag high risk patients early.
Catalog record
| CREATOR | Hoyeon Cho, Min Kyoon Joo, Pyung Goo Cho, Sang Hyun Kim, Sung Hyeon Noh |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |