Artificial intelligence–enhanced detection of acute coronary occlusion in tachycardic patients using surface ECG

Background Accurate detection of acute coronary occlusion (ACO) in patients presenting with chest pain remains challenging, as conventional STEMI criteria frequently fail to identify ACO—occurring in up to one in four non-STEMI cases. AI-enhanced ECG analysis has the potential to improve diagnostic precision, particularly in tachycardic patients, where ST-segment deviations may reflect artefacts, supply–demand mismatch, or true coronary occlusion. Distinguishing among these mechanisms is essential to guide appropriate decisions between emergency coronary angiography and primary arrhythmia management. Purpose To assess the diagnostic performance of an AI-enhanced ECG model for detecting ACO in chest pain patients with tachycardia on admission ECG, compared with conventional STEMI criteria, in a metropolitan chest pain unit (CPU) cohort. Methods All consecutive tachycardic patients (>100 bpm) presenting with chest pain to the CPU (Nov 2018 to Jun 20221) were included. Clinical management followed current European Society of Cardiology guidelines. The endpoint was ACO, adjudicated by an independent physician blinded to the AI predictions, using coronary angiography, biomarker kinetics, and echocardiography. Diagnostic performance was assessed by ROC analysis and compared with STEMI criteria. A predefined subgroup analysis distinguished narrow (QRS <120 ms) and broad (QRS ≥120 ms) complex tachycardias. The AI model itself based on a deep convolutional neural network. Results A total of 639 patients presented with tachycardia and were included (mean age 56.3 ± 19.3 years; 60.6% male). Tachycardia and tachyarrhythmia are summarized in table 1. Overall, 590 (92.3%) patients had narrow complex tachycardia, while 49 (7.7%) had broad complex tachycardia. The prevalence of ACO was 3.9% (n = 25). STEMI criteria identified only 7 of these 25 cases (28%). In contrast, the AI-ECG model correctly classified 19 of 25 (76%) ACO. The area under the curve was 0.987 (95% CI 0.978 – 0.996) for the AI-ECG model and 0.607 (95% CI 0.480 – 0.735) for STEMI criteria. Across all diagnostic metrics the AI model outperformed STEMI criteria, consistently across both tachycardia subgroups (figure 1). In the low-risk rule-out population, the AI-ECG model yielded seven false positives, potentially avoiding fifteen unnecessary emergency angiographies compared with strict application of STEMI criteria. Conclusion In tachycardic chest pain patients, conventional STEMI criteria inadequately guide the need for emergency coronary angiography, resulting in both missed occlusions and potentially avoidable interventions. AI-enhanced ECG analysis markedly improved ACO detection and may enable more selective, clinically guided triage. Its strong negative predictive value further highlights its potential to distinguish patients requiring primary arrhythmia management from those needing urgent coronary intervention, supporting prospective validation in independent cohorts.TableFigure