Key result
AI detects myocardial ischaemia on clean intermittent ECGs with ~99% specificity.
Why the study?
Perioperative ECG monitoring can detect myocardial ischaemia immediately, but its use is hampered by frequent false alarms and signal contamination, prompting a review of AI in perioperative ECG interpretation.
Does artificial intelligence improve the electrocardiographic diagnosis of perioperative myocardial ischaemia and infarction compared to physician interpretation?
Systematic Review (n=182)
Does artificial intelligence improve the electrocardiographic diagnosis of perioperative myocardial ischaemia and infarction compared to physician interpretation?
While AI algorithms show high accuracy for detecting myocardial infarction on clean ECG data, their clinical applicability in noisy, real-time perioperative settings remains unproven and requires prospective validation.
High accuracy on clean ECGs does not support perioperative use; leaves open prospective validation in noisy real-time settings.
BACKGROUND: Perioperative electrocardiographic monitoring can offer immediate detection of myocardial ischaemia, yet its application in perioperative and remote monitoring settings is hampered by frequent false alarms and signal contamination. We performed a scoping review for the current state of artificial intelligence (AI) in perioperative ECG interpretation. METHODS: A literature search in Ovid MEDLINE, EMBASE, Compendex, and CINAHL databases was performed from inception to May 10, 2023. All original research of ECG monitoring for myocardial ischaemia, myocardial infarction, or both was included. RESULTS: A total of 182 original research articles published between 1991 and 2023 were included. Most studies (n=132) used a pre-existing ECG database to develop AI algorithms retrospectively, and the rest did not specify their sources. Processing filters were used in 58% of the studies to remove ECG noises/artifacts before AI algorithm development. Amongst the AI technologies used, ResNet demonstrated the highest median sensitivity, precision, and specificity at 98.4%, 99.8%, and 99.1%, respectively. There are only five studies with intermittent prospective ECG collection on ST-segment elevation myocardial infarction. No studies prospectively collected continuous ECG perioperatively, with frequent false alarms and signal contamination. CONCLUSIONS: AI technology can achieve high diagnostic accuracy for myocardial ischaemia detection in clean intermittent electrocardiograms. However, almost all these algorithms were developed from a few open-source clean ECG databases without testing on 'noisy data', which limited their clinical applicability in the perioperative setting where signal contamination is frequent. AI algorithms on perioperative electrocardiography, tested in a noisy perioperative and remote monitoring environment, including wearable devices, are needed.
No takes yet. Share an insight, caveat, or question.
Kim et al. (2025) conducted a systematic review in Perioperative myocardial ischaemia and infarction (n=182). Artificial intelligence algorithms for ECG interpretation vs. Physician interpretation (reference standard) was evaluated on Diagnostic accuracy (sensitivity, specificity, precision) for myocardial ischaemia or infarction. Artificial intelligence algorithms achieved high diagnostic accuracy for myocardial ischaemia detection in clean intermittent electrocardiograms, with ResNet demonstrating a median sensitivity of 98.4% and specificity of 99.1%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: