A Machine Learning Model for Predicting In-Hospital Mortality in Chinese Patients With ST-Segment Elevation Myocardial Infarction: Findings From the China Myocardial Infarction Registry.
Source check: Source checked. Not independent scientific confirmation.
Finding: Machine-learning prediction on China Myocardial Infarction Registry data identified factors and estimated in-hospital mortality risk after ST-elevation myocardial infarction; conclusions are registry-specific.
Technology: XGBoost models use CAMI registry variables to estimate in-hospital mortality after ST-elevation myocardial infarction; SHAP interprets predictors.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- XGBoost models use CAMI registry variables to estimate in-hospital mortality after ST-elevation myocardial infarction; SHAP interprets predictors.
- Test and result
- Trained on 9,616 CAMI patients, the model achieved AUC 0.896 in a CAMI validation set and 0.840 in the independent China PEACE cohort, compared with lower GRACE/TIMI AUCs.
- Limitation / still unknown
- Registry-based evaluation is retrospective; cross-cohort prediction does not establish prospective impact on patient management.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://doi.org/10.2196/50067 · https://europepmc.org/article/MED/39079111 · https://europepmc.org/articles/PMC11322712 · https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_json/PMC11322712/unicode · https://pubmed.ncbi.nlm.nih.gov/39079111/
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.