From Electrocardiography to the Catheterization Laboratory: A Multimodal Artificial Intelligence Framework for Acute Coronary Syndrome Detection and Risk Stratification

Current acute coronary syndrome (ACS) care relies on sequential, single-modality diagnostics, in which the electrocardiogram, the troponin trajectory, and the coronary angiogram are interpreted independently rather than as a joint signal. This narrative review maps rather than pools the evidence. We selectively searched PubMed, EMBASE, Cochrane CENTRAL, and Web of Science (January 2015–February 2026); study selection was performed by a single reviewer, without duplicate screening, a PRISMA flow diagram, or a formal risk-of-bias assessment. The three key findings are as follows: A machine learning-enabled electrocardiogram (ECG) for diagnosing occlusion due to myocardial infarction achieved an AUC of 0.938 (95% CI = 0.924–0.951) on data not seen during training and correctly diagnosed 42% of patients that expert interpreters missed. A machine learning-enabled high-sensitivity troponin interpretation method, CoDE-ACS, reported an AUC of 0.953 and increased the number of patients ruled out at initial evaluation from 27% to 61%. Angiographically derived physiological methods produced conflicting results—quantitative flow ratios reduced major adverse cardiovascular events (MACE) in the FAVOR III China trial (HR 0.65), but in FAVOR III Europe the angiography-derived approach did not prove non-inferior to FFR; if anything, QFR guidance led to more events (6.7% vs. 4.2%, an event rate about 60% higher in the QFR arm; HR 1.63; 95% CI 1.11–2.41). There was no difference between FFR-angio and FFR in the ALL-RISE trial. These are diagnostic-accuracy and prognostic-association findings; no trial has yet shown that AI-guided ACS care reduces death, reinfarction, or ischemia-driven revascularization.