ECG beat classification using machine learning and pre-trained convolutional neural networks

Abstract: The electrocardiogram (ECG) is routinely used in hospitals to analyze cardiovascular status and health of an individual. Abnormal heart rhythms can be a precursor to more serious conditions including sudden cardiac death. Classifying abnormal rhythms is a laborious process prone to error. Therefore, tools that perform automated classification with high accuracy are highly desirable. The work presented classifies five different types of ECG arrhythmia based on AAMI EC57 standard and using the MIT-BIH data set. These include non-ectopic (normal), supraventricular, ventricular, fusion, and unknown beat. By appropriately transforming pre-processed ECG waveforms into a rich feature space along with appropriate post-processing and utilizing deep convolutional neural networks post fine-tuning and hyperparameter selection, it is shown that highly accurate classification for the five waveform types can be obtained. Performance on the test set indicated higher overall accuracy (98.62%), as well as better performance in classifying each of the five waveforms than hitherto reported in literature.