A single-centre diagnostic accuracy study by researchers at Hospital Professor Doutor Fernando Fonseca, Amadora, Portugal, evaluated ChatGPT-assisted ECG interpretation in the STEMI activation pathway. Timely identification of ST-segment elevation myocardial infarction (STEMI) and prompt catheterisation laboratory team activation are critical for patient outcomes, with guidelines recommending a first-medical-contact-to-balloon time of less than 90 minutes. However, real-world workflows are hampered by diagnostic uncertainty, as between 5–10% of emergent cath lab activations represent false positives. Prior studies of earlier ChatGPT versions for ECG interpretation showed moderate overall accuracy, with the model performing best for normal tracings and poorly for acute ischaemic changes. The emergence of multimodal large language models has enabled direct visual analysis of ECG images to support clinical triage. Dedicated AI ECG platforms have demonstrated high sensitivity and specificity on coronary occlusion detection but require institutional integration, whereas ChatGPT is accessible.