Classification of Heart Sounds with Deep Learning

Abstract: Health care is becoming more and more digitalized and examinations of patients from a distance are closer to reality than fiction. One of these examinations would be to automatically classify a patient-recorded audiosegment of its heartbeats as healthy or pathological. This thesis examines how it can be achieved by examining different kinds of neural networks; convolutional neural networks (CNN) and long short-term memory networks (LSTM). The theory of artificial neural networks is explained. With this foundation, the feed forward CNN and the recurrent LSTM-network have their methods described. Before these methods can be used, the required pre-processing has to be completed, which is different for the two types of networks. Using this theory, the process of how to implement the networks in Matlab is explained. Different CNN:s are compared to each other, then the best performing CNN is compared to the LSTM-network. When comparing the two different networks to each other, cross validation is used to achieve the most correct result possible. The networks are compared by accuracy, least amount of training time and least amount of training data. A final resulti s presented, to show which type of network has the best performance, together with a discussion to explain the results. The CNN performed better than the LSTM-network in all aspects. A reflection on what could have been done differently to achieve a better result is posted.