Key result
A deep learning model detected ischaemia caused by acute coronary artery occlusion with a better balance of sensitivity and specificity than STE criteria, computerised analysers, or cardiologists.
Why the study?
Current ST elevation criteria are insensitive, causing patients to miss primary PCI, while expert ECG interpretation increases sensitivity at the expense of specificity.
Does a deep learning model improve the detection of ischaemia caused by acute coronary artery occlusion on 12-lead ECGs compared to standard criteria and expert cardiologists?
Does a deep learning model improve the detection of ischaemia caused by acute coronary artery occlusion on 12-lead ECGs compared to standard criteria and expert cardiologists?
A deep learning model applied to 12-lead ECGs outperforms standard ST-elevation criteria, computerised analysers, and expert cardiologists in detecting acute coronary artery occlusion.
May support DL ECG models for acute coronary occlusion detection; leaves open prospective validation and outcome impact before practice change.
Early diagnosis of acute coronary artery occlusion based on electrocardiogram (ECG) findings is essential for prompt delivery of primary percutaneous coronary intervention. Current ST elevation (STE) criteria are specific but insensitive. Consequently, it is likely that many patients are missing out on potentially life-saving treatment. Experts combining non-specific ECG changes with STE detect ischaemia with higher sensitivity, but at the cost of specificity. We show that a deep learning model can detect ischaemia caused by acute coronary artery occlusion with a better balance of sensitivity and specificity than STE criteria, existing computerised analysers or expert cardiologists.
No takes yet. Share an insight, caveat, or question.
Brisk et al. (2019) studied Acute coronary artery occlusion. Deep learning model for ECG analysis vs. ST elevation (STE) criteria, existing computerised analysers, or expert cardiologists was evaluated on Detection of ischaemia caused by acute coronary artery occlusion. A deep learning model detected ischaemia caused by acute coronary artery occlusion with a better balance of sensitivity and specificity than STE criteria, computerised analysers, or cardiologists.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: