A small clinical dataset tests machine-learning infection classification
Source check: Source checked. Not independent scientific confirmation.
Finding: In 25 emergency patients selected for suspected severe limb infection and ultrasound-detected fascial fluid, a six-feature random forest reported apparent sensitivity of 90.4% and specificity of 92.2% for necrotizing infection versus cellulitis. These small-cohort estimates do not establish performance for general soft-tissue infections.
Technology: Random forest
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Random forest fitted the represented classification or candidate-selection model; preprocessing and expert reference labels are distinguished from the learned contribution.
- Test and result
- Thirteen infection cases and twelve cellulitis controls contributed the dataset. Four algorithms were evaluated over ten random 80/20 splits; six features were selected using random-forest Gini importance.
- Limitation / still unknown
- Initial significance screening and later feature selection are not shown to be nested inside held-out evaluation. Each nominal test split contains about five patients; repeated splits are not independent cohorts. No prospective utility, separate-team replication or causal mechanism is established. This was a selected fluid-positive cohort with different diagnostic ascertainment for infection cases and cellulitis controls, including pathology for the former. The six-feature table does not independently establish a new held-out evaluation after feature selection.
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/PMC11066613/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 21 Nov 2026. Review scope: Primary article full-text bibliographic metadata and relevant computational evaluation Methods/Results: sec2.3, sec3.4. Primary-source caveat and denominator review; candidate-panel identity corrected where relevant..
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 1/5 · 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.