Machine learning identified predictors of patient-reported stroke rehabilitation outcomes
Source check: Source checked. Not independent scientific confirmation.
Finding: In retrospective data from 124 people with chronic stroke, machine-learning models predicted post-intervention change in four patient-reported activity and participation outcomes. Baseline outcome scores were among the strongest predictors; best model accuracies ranged from 0.72 to 0.96 with 18 features and 0.72 to 0.84 with reduced feature sets. This small-sample prediction study does not show which individuals causally benefit from rehabilitation or generalize beyond its setting.
Technology: Logistic regression, k-nearest neighbors, SVM and random forest
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Classification models predicted changes in four patient-reported rehabilitation outcomes and identified outcome-specific predictors.
- Test and result
- The study used an 80/20 split, stratified ten-fold tuning and a held-out test set. It reused retrospective data from earlier studies and has limited single-context generalizability.
- Limitation / still unknown
- No independent, prospective or clinical-impact evaluation is reported unless specified in the tested field.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://link.springer.com/article/10.1186/s12984-023-01151-6
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: Read the original full text, including author affiliations, Methods and Results; checked the first result-bearing version and active/archive catalog for same-result records..
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 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.