Researchecg aiomi detectionpowerful medicaldiagnostic accuracy
AI Outperforms Physicians in ECG OMI Detection
5.8
Shroyer et al. (Am J Emerg Med, Nov 2025) report a cross-sectional reader study comparing 95 physicians to the Queen of Hearts (QoH) deep-learning ECG algorithm on STEMI-equivalent and mimic ECGs. Physicians' cath-lab activation accuracy was 65.6% (EM) and 65.5% (cardiology) versus QoH's 88.9%. Authors note spectrum bias, differential verification, and conflicts of interest requiring prospective validation.
Key Points
- 1Reports QoH AI achieves 88.9% accuracy versus physicians' ~65.6% on ambiguous ECGs
- 2Highlights diagnostic gap for STEMI‑equivalents and mimics, increasing risk of missed or unnecessary cath activations
- 3Suggests QoH could reduce missed OMIs and false activations, but external validity concerns limit generalizability
Scoring Rationale
Moderate clinical relevance with clear accuracy advantage, but single biased reader-study and COIs limit generalizability.
Sources
Public references used for this report.
Practice with real Health & Insurance data
90 SQL & Python problems · 15 industry datasets
Used by DS/ML engineers at top companies
250 free problems · No credit card
See all Health & Insurance problems
