Machine learning-based risk stratification for moderate-to-severe anxiety-depression in patients with hypertension and/or coronary heart disease: a multicenter cross-sectional study.
Source check: Source checked. Not independent scientific confirmation.
Finding: primary Methods/Results document the AI-enabled result, evaluation and bounded interpretation.
Technology: The named learned model operation is applied to the specific clinical/scientific endpoint and is linked to the result as described in the primary Methods/Results.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- to the specific clinical/scientific endpoint and is linked to the result as described in the primary Methods/Results
- Test and result
- Eight ML models risk-stratified PHQ-9/GAD-7 moderate/severe anxiety-depression among 4,006 hypertension/CHD survey respondents; RF test AUROC .838, Brier .134 and SHAP correlates. Full Methods/Results read. Cross-sectional self-report, internal-only validation; explicitly hypothesis-generating, not clinically ready
- Limitation / still unknown
- , endpoint/reference or comparator, and evaluation design/performance. Limitations are stated in the note; retrospective/internal/temporal validation is not represented as causal benefit or deployment
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/PMC13715117/ · https://pubmed.ncbi.nlm.nih.gov/42947157/
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 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.