AI Algorithm to Predict Acute Coronary Syndrome in Prehospital Cardiac Care: Retrospective Cohort Study.
Source check: Source checked. Not independent scientific confirmation.
Finding: A machine-learning algorithm using prehospital cardiac-care data predicted acute coronary syndrome and was evaluated against subsequent clinical diagnoses in a retrospective cohort.
Technology: A supervised text-classification model analyzes prehospital emergency-service records to predict acute coronary syndrome before emergency-department arrival.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- A supervised text-classification model analyzes prehospital emergency-service records to predict acute coronary syndrome before emergency-department arrival.
- Test and result
- In 7,458 retrospective EMS cases, the AI model had 99.5% sensitivity and 11% specificity, versus 99.5% sensitivity and 1% specificity under usual care.
- Limitation / still unknown
- The retrospective single-condition proof of concept does not evaluate other life-threatening diagnoses; prospective validation is required.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://doi.org/10.2196/51375 · https://europepmc.org/article/MED/37906226 · https://europepmc.org/articles/PMC10646678 · https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_json/PMC10646678/unicode · https://pubmed.ncbi.nlm.nih.gov/37906226/
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.