The traditional ST-segment elevation myocardial infarction (STEMI) paradigm has directed the identification and treatment of acute coronary occlusion (ACO) in the in-hospital and out-of-hospital (OOH) environment. Growing evidence suggests that it fails to identify a substantial proportion of ACO cases, leading to delays in intervention and missed treatment opportunities. The occlusion myocardial infarction (OMI) paradigm has emerged as a more inclusive diagnostic framework, emphasising the recognition of ACO regardless of ST-segment elevation. While OMI offers a more accurate classification, its adoption in OOH settings presents challenges, particularly due to the complexity of ECG interpretation and variability in clinician expertise. Artificial intelligence (AI) has the potential to address these limitations by providing real-time ECG analysis, improving diagnostic accuracy, and reducing inter-rater variability. AI-driven models, particularly artificial neural networks, have demonstrated superior sensitivity in detecting ACO compared to clinician interpretation using the traditional STEMI criteria, with the ability to identify occlusion earlier and more consistently. Additionally, AI integration with telemedicine could facilitate remote expert consultation, ensuring timely decision-making, particularly in resource-limited settings. By enhancing diagnostic accuracy and enabling earlier intervention, AI has the potential to improve prehospital cardiac care, and ultimately, patient outcomes. Future research should focus on optimising AI models, integrating them into OOH workflows, and validating their real-world effectiveness in acute coronary syndrome management.
Bishop et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: