The machine learning model achieved an AUROC of 0.91 for diagnosing occlusion myocardial infarction, significantly outperforming clinicians (AUROC 0.79) and commercial systems (AUROC 0.78).
Observational (n=7,313)
Yes
Does a machine learning model using pre-hospital 12-lead ECGs improve the diagnostic accuracy of occlusion myocardial infarction in patients with chest pain compared to practicing clinicians and commercial systems?
A machine learning model using 12-lead ECGs significantly improved the detection and risk stratification of occlusion myocardial infarction in patients without STEMI compared to clinicians and commercial software.
Effect estimate: AUROC 0.91 (95% CI 0.87-0.96)
p-value: p=<0.001
Abstract Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting electrocardiogram (ECG) are increasing in numbers. These patients have a poor prognosis and would benefit from immediate reperfusion therapy, but, currently, there are no accurate tools to identify them during initial triage. Here we report, to our knowledge, the first observational cohort study to develop machine learning models for the ECG diagnosis of OMI. Using 7,313 consecutive patients from multiple clinical sites, we derived and externally validated an intelligent model that outperformed practicing clinicians and other widely used commercial interpretation systems, substantially boosting both precision and sensitivity. Our derived OMI risk score provided enhanced rule-in and rule-out accuracy relevant to routine care, and, when combined with the clinical judgment of trained emergency personnel, it helped correctly reclassify one in three patients with chest pain. ECG features driving our models were validated by clinical experts, providing plausible mechanistic links to myocardial injury.
Al‐Zaiti et al. (Thu,) conducted a observational in Occlusion myocardial infarction (OMI) (n=7,313). Machine learning model for ECG diagnosis of OMI vs. Practicing clinicians and commercial ECG interpretation systems was evaluated on ECG diagnosis accuracy for occlusion myocardial infarction (AUROC 0.91, 95% CI 0.87-0.96, p=<0.001). The machine learning model achieved an AUROC of 0.91 for diagnosing occlusion myocardial infarction, significantly outperforming clinicians (AUROC 0.79) and commercial systems (AUROC 0.78).