Heartbeat Anomaly Detection using Adversarial Oversampling
This work addresses early detection of cardiovascular diseases, a major global health issue, but is incremental as it adapts existing methods to a specific domain problem.
The paper tackles heartbeat anomaly detection by addressing class imbalance in cardiovascular disease classification using a two-dimensional Convolutional Neural Network combined with an InfoGAN for synthetic image generation, called Adversarial Oversampling, which improves minority class performance without harming balanced classes.
Cardiovascular diseases are one of the most common causes of death in the world. Prevention, knowledge of previous cases in the family, and early detection is the best strategy to reduce this fact. Different machine learning approaches to automatic diagnostic are being proposed to this task. As in most health problems, the imbalance between examples and classes is predominant in this problem and affects the performance of the automated solution. In this paper, we address the classification of heartbeats images in different cardiovascular diseases. We propose a two-dimensional Convolutional Neural Network for classification after using a InfoGAN architecture for generating synthetic images to unbalanced classes. We call this proposal Adversarial Oversampling and compare it with the classical oversampling methods as SMOTE, ADASYN, and RandomOversampling. The results show that the proposed approach improves the classifier performance for the minority classes without harming the performance in the balanced classes.