CatBoost evaluates fragility-fracture risk in a community cohort
Source check: Source checked. Not independent scientific confirmation.
Finding: CatBoost evaluated fragility-fracture risk in 2,227 participants from the Korean Ansung cohort followed for a mean 7.5 years. Reported total-fracture AUC was 0.688, compared with 0.663 for FRAX, using repeated internal cross-validation. The study also ranked candidate predictors, but did not estimate time to fracture or demonstrate benefit from model-guided prevention. External populations remain to be tested.
Technology: CatBoost
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Categorical gradient boosting learns fracture-risk relationships from clinical variables and is compared with FRAX, SVM and logistic regression.
- Test and result
- Retrospective outcome modeling within a longitudinal cohort, with three-fold cross-validation repeated 1,000 times.
- Limitation / still unknown
- External ethnic/population validation, time-to-event prediction and clinical benefit remain unestablished.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC7059838/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 21 Nov 2026. Review scope: Primary full paper relevant model Methods, study Results and limitations; exact primary front-matter identity and Europe PMC metadata checked..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.