Evolution of single-lead ECG for STEMI detection using a deep learning approach.

BACKGROUND: While ST-Elevation Myocardial Infarction (STEMI) door-to-balloon times are often below 90 min, symptom to door times remain long at 2.5-h, due at least in part to a delay in diagnosis. OBJECTIVES: To develop and validate a machine learning-guided algorithm which uses a single­lead electrocardiogram (ECG) for STEMI detection to speed diagnosis. METHODS: Data was extracted from the Latin America Telemedicine Infarct Network (LATIN), a population-based Acute Myocardial Infarction (AMI) program that provides care to patients in Brazil, Colombia, Mexico, and Argentina through telemedicine. SAMPLE: the first dataset was comprised of 8511 ECGs that were used for various machine learning experiments to test our Deep Learning approach for STEMI diagnosis. The second dataset of 2542 confirmed STEMI diagnosis EKG records, including specific ischemic heart wall information (anterior, inferior, and lateral), was derived from the previous dataset to test the STEMI localization model. Preprocessing: Detection of QRS complexes by wavelet system, segmentation of each EKG record into individual heartbeats with fixed window of 0.4 s to the left and 0.9 s to the right of main. Training & Testing: 90% and 10% of the total dataset, respectively, were used for both models. CLASSIFICATION: two 1-D convolutional neural networks were implemented, two classes were considered for first models (STEMI/Not-STEMI) and three classes for the second model (Anterior/Inferior/Lateral) each corresponding to the heart wall affected. These individual probabilities were aggregated to generate the final label for each model. RESULTS: The single­lead ECG strategy was able to provide an accuracy of 90.5% for STEMI detection with Lead V2, which also yielded the best results overall among individual leads. STEMI Localization model provided promising results for anterior and inferior wall STEMIs but remained suboptimal for Lateral STEMI. CONCLUSIONS: An Artificial Intelligence-enhanced single­lead ECG is a promising screening tool. This technology provides an autonomous and accurate STEMI diagnostic alternative that can be incorporated into wearable devices, potentially providing patients reliable means to seek treatment early and offers the potential to thereby improve STEMI outcomes in the long run.

Impact of a telemedicine-guided, population-based, STEMI network on reperfusion strategy, efficiency, and outcomes: Impact of telemedicine on STEMI management.

AIMS: A telemedicine-guided strategy increases the access to and efficiency of ST-elevation myocardial infarction (STEMI) networks resulting in increased access to, and reduced disparities in, acute myocardial infarction (AMI) care between rural and urban areas. METHODS AND RESULTS: The Latin America Telemedicine Infarct Network (LATIN) was developed for poor and remote regions in Brazil and Colombia that lacked coordinated AMI systems of care. It strategically connects small clinics and primary care health centres (spokes) to hubs with 24/7 percutaneous coronary intervention (PCI) capability. Experts at three remote sites provide urgent electrocardiogram (ECG) diagnosis and tele-consultation for the entire network. Data from the busiest LATIN site, the Santa Marcelina Hospital in Sao Paolo, Brazil, were compared with health statistics from Sistema Unico de Saude (Brazilian Public Health System - SUS). A total of 192 centres were networked using standardised and guideline-based protocols for AMI care. Overall, 313,897 patients were remotely screened, 3,572 AMI diagnosed (1.1%), and 1,636 AMI urgently reperfused (45.8%), mainly by primary PCI (n=1,351; 83%). CONCLUSIONS: In conclusion, a comparison between a pre-LATIN cohort from SUS (1,015) and a LATIN cohort from Santa Marcelina Hospital (1,247) revealed increased reperfusion with PCI (65.52% vs 75.2%), increased cost ($2,037.12 vs $2,246.40, p<0.005), a statistically significant reduction in PCI mortality (8.5% vs 4.3% p<0.01) and a non-significant reduction in mortality overall amongst all treatment pathways (9.69% vs 9.43%, p=0.931).