Machine-learning models estimate perioperative transfusion risk in lumbar fusion
Source check: Source checked. Not independent scientific confirmation.
Finding: Using retrospective records from 1,905 patients undergoing posterior lumbar interbody fusion at one hospital, the study compared five models after XGBoost feature selection. XGBoost had the highest validation-set AUC (0.958), with accuracy 0.903 and recall 0.897. This random split within a single-center cohort is internal validation; external performance and improved surgical decisions or patient outcomes are not established.
Technology: XGBoost, logistic regression, random forest, support vector machine, and other machine-learning classifiers
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- XGBoost selected features and the trained models estimated perioperative transfusion risk from clinical records.
- Test and result
- Five models were compared on a held-out validation subset of retrospective records from 1,905 lumbar-fusion patients at one hospital.
- Limitation / still unknown
- External validation and effects on care decisions or patient outcomes were not reported.
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/physiology/articles/10.3389/fphys.2023.1306453/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: Full primary publisher article, including Methods, Results, author affiliations and publication history.
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 3/5 · 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.