Artificial Intelligence (AI) guided algorithms can provide point-of-care and
accurate ECG interpretation that has the potential of improving patient management. The cumbersome and costly traditional electrocardiogram (ECG) relies completely on the interpretation of a cardiologist and may present accuracy variations that depend on the physician’s expertise. We demonstrate the feasibility of an automated AI-guided Single-lead ECG analysis for STEMI diagnosis. Methods : Sample: 8,511 ECG anonymized records, previously diagnosed by cardiologists as “normal”, “abnormal” (over 200 conditions excluding STEMI) or “STEMI” (4,255 cases).
The sample was derived from the private International Telemedical Systems (ITMS) database. Preprocessing: detection of QRS complexes by wavelet system, segmentation of each ECG into individual heartbeats (total 90,592) with fixed window of 0.4s to the left and 0.9s to the right of main QRS; Classification: A 1-D convolutional neural network was implemented, "STEMI" and "Not-STEMI" classes were considered for each heartbeat, individual probabilities were aggregated to generate the final label for each record. Training & Testing: 90% and 10% of the sample were used, respectively. Results: The AI model achieved a high level of accuracy, sensitivity, and specificity in comparison to the cardiologists' annotations.
Conclusion(s): 1) AI-guided interpretation of the ECG is able to reliably detect STEMI; 2) AI algorithms can be incorporated into wearable devices for prehospital diagnosis, single page activation and, emergency department bypass, facilitating more efficient STEMI pathways and avoiding delays.

06 - Detection of ST-Elevation Myocardial Infarction Using An Artificial Intelligence-Guided Single Lead ECG