Key result
Custom neural network ArrhyNet achieves ~93% accuracy in five-class arrhythmia classification.
Why the study?
Arrhythmia detection and classification is critical in the treatment of irregular heartbeats, which are a major cause of cardiovascular disease.
Does ArrhyNet accurately detect and classify arrhythmias from ECG data?
Does ArrhyNet accurately detect and classify arrhythmias from ECG data?
ArrhyNet, a custom convolutional neural network utilizing specific filtering and SMOTE techniques, achieves 92.73% accuracy in classifying five classes of arrhythmias from the MIT-BIH database.
Cardiovascular diseases are one of the major causes of all human deaths. Irregular heartbeat or arrhythmia is one among many reasons for cardiovascular diseases. Arrhythmia detection and classification is critical in the treatment of irregular heartbeats. This paper presents a systematic method for high accuracy arrhythmia detection and classification using ArrhyNet, a custom convolutional neural network (CNN) for arrhythmia classification on MIT-BIH Arrhythmia Database. High and low frequency noise in the data is eliminated using low pass filter and baseline wander filter respectively, feature extraction is achieved using Daubechies Wavelet Transform and finally Synthetic Minority Over Sampling (SMOTE) technique is utilized to overcome the issue of imbalanced dataset. Using our technique, 16 different types of arrhythmias distributed in Association for Advancement of Medical Instrumentation (AAMI) standard were analyzed. The results indicate that the top-1 accuracy of our five-class classification system for the database used is 92.73%.
No takes yet. Share an insight, caveat, or question.
Aphale et al. (2021) studied Arrhythmia. ArrhyNet (custom convolutional neural network) was evaluated on Top-1 accuracy of five-class classification system. ArrhyNet, a custom convolutional neural network, achieved a top-1 accuracy of 92.73% for a five-class arrhythmia classification system using the MIT-BIH Arrhythmia Database.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: