Graphical analysis of the progression of atrial arrhythmia through an ensemble of Generative Adversarial Network Discriminators

摘要

Logs of arrhythmia episodes in patients with pacemakers are used to estimate the temporal progression of atrial arrhythmia. In order to attain an early detection, a stream of dates and episode lengths are fed to an array of detectors, each of which is responsive to a narrow range of arrhythmias. The outputs of these detectors are organized on a projection map, used by the specialist to assess the risk in the evolution of the patient. Each of the mentioned detectors is a Recurrent Neural Network (RNN), that is in turn the discriminating element of a Generative Adversarial Network (GAN) that has been trained to generate temporal sequences of values of the degrees of truth that the arrhythmia episodes are not isolated.