Machine learning prediction of deep vein thrombosis before staged surgery in lower-leg and ankle fractures treated with temporary external fixation
Source check: Source checked. Not independent scientific confirmation.
Finding: Naive Bayes predicted DVT before staged lower-limb/ankle surgery in 356 patients; held-out validation AUC was 0.807 (95% CI 0.705–0.909), with low precision-recall AUC 0.343 and optimism-corrected AUC 0.773. This is a small retrospective risk-stratification result, not a validated clinical tool.
Technology: Boruta feature selection plus 12 classifiers; Naive Bayes selected on clinical predictors and interpreted with SHAP.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Boruta feature selection plus 12 classifiers; Naive Bayes selected on clinical predictors and interpreted with SHAP.
- Test and result
- Naive Bayes predicted DVT before staged lower-limb/ankle surgery in 356 patients; held-out validation AUC was 0.807 (95% CI 0.705–0.909), with low precision-recall AUC 0.343 and optimism-corrected AUC 0.773. This is a small retrospective risk-stratification result, not a validated clinical tool. Stratified 70/30 split (106 validation patients), five-fold development CV, 500 bootstrap optimism correction, calibration and decision curves.
- Limitation / still unknown
- not a validated clinical tool.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2026.1963261/full
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: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
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.