Sebastiano Massaro at the University of Surrey, Mihaela Porumb and Leandro Pecchia at the University of Warwick, and Ernesto Iadanza at the University of Florence have developed an advanced signal processing and machine learning method to identify congestive heart failure with 100% accuracy through analysis of one raw ECG heartbeat.
The CNN model was trained and tested on large ECG datasets, including CHF and healthy, non-arrhythmic subjects. The team said that it was 100% accurate, and that the model is one of the first to identify ECG morphological features associated with the CHF severity.