Mount Sinai Researchers Use New Deep Learning Approach To Enable Analysis

Mount Sinai researchers have developed an innovative artificial intelligence (AI) model for electrocardiogram (ECG) analysis that uses language to interpret ECGs. This model, known as HeartBEiT, was tested against established methods and was found to outperform them. HeartBEiT is specialized to ECGs and can perform as well as, if not better than, other methods using a tenth of the data, making ECG-based diagnosis considerably more viable. AI is revolutionizing the science of ECG analysis, with most of the work to date centered on convolutional neural networks (CNNs).