Researchers Use New Deep Learning Approach To Enable Analysis Of Electrocardiograms As Language

Mount Sinai researchers have developed an AI model for ECG analysis that interprets ECGs as language, allowing for more accurate and effective diagnoses. The model, known as HeartBEiT, outperformed established methods for ECG analysis in comparison tests. 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 more viable, especially for rare conditions. AI is revolutionizing the science of ECG analysis, with most of the work to date centered on convolutional neural networks.