Investigators from University of Tokyo Hospital Have Reported New Data on Obesity, Fitness and Wellness (Deep Learning Models for Predicting Left Heart Abnormalities From Single-lead Electrocardiogram for the Development of Wearable Devices).

Researchers from the University of Tokyo Hospital have conducted a study on the use of deep learning models to predict left heart abnormalities using single-lead electrocardiogram (ECG) data. Left heart abnormalities are risk factors for heart failure, and echocardiography is not always readily available. The researchers developed ECG models to detect low ejection fraction, wall motion abnormality, left ventricular hypertrophy, left ventricular dilatation, and left atrial dilatation. The models showed superior or equivalent performance to cardiologists using 12-lead ECGs. This research has been peer-reviewed and may have implications for the development of wearable devices. [Extracted from the article]