Key result
Machine learning models for acute chest pain show promise, but lack external validation and implementation studies in routine care.
Machine learning models for evaluating acute chest pain require external validation and implementation studies before routine clinical use.
Despite extensive research over the past decades, the rapid identification or exclusion of acute myocardial infarction in emergency department patients with chest pain remains a big challenge. Research on decision support models based on artificial intelligence and machine learning in the emergency department has increased in recent years,1–4 and much of the focus has been put on acute chest pain.5–7 Results with chest pain models are promising, but very few results have been externally validated, and implementation studies in routine care are almost non-existent.
No takes yet. Share an insight, caveat, or question.
Ekelund et al. (2022) conducted an editorial in Acute chest pain and acute myocardial infarction. Machine learning models was evaluated. Machine learning models for acute chest pain show promise, but lack external validation and implementation studies in routine care.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: