Coronary disease & ACSCohort study
Specificity of the Occlusion Myocardial Infarction-Trained PMcardio “Queen of Hearts” AI-ECG in Inflammatory Myopericardial Syndromes
- single-centre retrospective study
- consecutive emergency department patients
Authors' conclusion
In IMPS, the OMI-trained QoH model demonstrated high specificity and fewer false-positive OMI classifications than guideline ECG-STEMI criteria, ECG-based scores, and general-purpose LLMs.
Study context
- Population
- Emergency department patients with adjudicated inflammatory myopericardial syndromes (IMPS), obstructive coronary artery disease excluded, University & Hospital of Fribourg (2010–2025)
- Participants
- 242 IMPS patients
- Exposure
- Specificity was compared with European Society of Cardiology (ESC) STEMI ECG criteria, the 4-variable formula (when applicable), and 3 large language models
- 4-variable formulan = 30
- Outcome
- ECG-level specificity
Main finding
As reported in the abstract
Queen of Hearts (QoH)
95.0%
230 events
ESC STEMI ECG criteria
78.1%
specificity
Large language models (LLMs)
26.9% to 70.2%
specificity
Observational data: associations, not effects.
Further findings
Specificity
| Outcome | (myo)pericarditis | (peri)myocarditis |
|---|---|---|
| QoH specificity by phenotype | 97.7% | 87.7% |
- QoH specificity by phenotype: P = 0.004
Discordant ESC-positive/QoH-negative cases
- Discordant ESC-positive/QoH-negative cases (n = 43) predominantly showed diffuse, nonterritorial inflammatory ECG patterns
- 43
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Specificity of the Occlusion Myocardial Infarction-Trained PMcardio “Queen of Hearts” AI-ECG in Inflammatory Myopericardial Syndromes. JACC Adv. Published 23 July 2026. doi:10.1016/j.jacadv.2026.103046
Summarised from the published abstract; every number is checked against it