Classification of Cardiac Arrhythmias Based on Electrocardiogram Data Using a Convolutional Neural Network Model

Cardiac arrhythmias are a disease with considerable incidence and prevalence worldwide, and their diagnosis can be complex due to the existence of different types of arrhythmias that share similar characteristics and make an accurate diagnosis difficult. Making a correct diagnosis of the kind of arrhythmia that affects an individual is important to define the most appropriate type of treatment for the case. Machine Learning and Deep Learning techniques have been proposed to automate the diagnosis of arrhythmias to assist healthcare professionals in decision-making. This study proposes a Convolutional Neural Network model for classifying cardiac arrhythmias using electrocardiogram data. The objective is to present a model that achieves high accuracy rates in identifying types of arrhythmias and presents an adequate balance between performance and computational costs. The model was trained with a dataset composed of electrocardiogram exams with 32 types of arrhythmias. In the pre-processing phase, the dataset was restructured to allow the data to be treated as a time series to explore the potential of Convolutional Neural Networks in dealing with data organized in this way. Training was carried out using a state-of-the-art Deep Learning model and the model achieved an accuracy rate of 98.37% in its predictions. This excellent performance confirms the ability of Convolutional Neural Networks to efficiently deal with pattern learning in time series. The results obtained demonstrate the potential of Deep Learning techniques as aiding tools to provide improvements in medical processes.