Perioperative medicine & outcomes
Artificial intelligence for electrocardiographic diagnosis of perioperative myocardial ischaemia: a scoping review
Authors' conclusion
AI technology can achieve high diagnostic accuracy for myocardial ischaemia detection in clean intermittent electrocardiograms.
Study context
- Population
- Original research of artificial intelligence (AI) for ECG monitoring for myocardial ischaemia and/or MI (Ovid MEDLINE, EMBASE, Compendex, CINAHL, inception to May 10, 2023)original research articles, 1991–2023
- Participants
- 182 participants
- Outcome
- State of AI in perioperative ECG interpretation for myocardial ischaemia
Main finding
As reported in the abstract
| Group | Median sensitivity | Median precision | Median specificity |
|---|---|---|---|
| ResNet | 98.4% | 99.8% | 99.1% |
ResNet
Median sensitivity98.4%
Median precision99.8%
Median specificity99.1%
- Studies using a pre-existing ECG database to develop AI algorithms retrospectively
- 132
- Studies using processing filters to remove ECG noise/artifacts
- 58%
- Studies with intermittent prospective ECG collection on ST-segment elevation MI
- 5
Original publication
Artificial intelligence for electrocardiographic diagnosis of perioperative myocardial ischaemia: a scoping review. Br J Anaesth. Published 4 July 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →