High quality ECG dataset based on MIT-BIH recordings for improved heartbeats classification

TL;DR

This paper introduces a high-quality ECG heartbeat dataset derived from MIT-BIH recordings, improving heartbeat classification accuracy and efficiency with a novel preprocessing approach and a ResNet model.

Contribution

The paper presents a new methodology for creating a high-quality ECG dataset with optimal heartbeat segmentation and demonstrates its effectiveness with a deep learning model.

Findings

Achieved 99.24% accuracy in heartbeat classification.

Improved model execution time by 33%.

Reduced memory usage threefold.

Abstract

Electrocardiogram (ECG) is a reliable tool for medical professionals to detect and diagnose abnormal heart waves that may cause cardiovascular diseases. This paper proposes a methodology to create a new high-quality heartbeat dataset from all 48 of the MIT-BIH recordings. The proposed approach computes an optimal heartbeat size, by eliminating outliers and calculating the mean value over 10-second windows. This results in independent QRS-centered heartbeats avoiding the mixing of successive heartbeats problem. The quality of the newly constructed dataset has been evaluated and compared with existing datasets. To this end, we built and trained a PyTorch 1-D Resnet architecture model that achieved 99.24\% accuracy with a 5.7\% improvement compared to other methods. Additionally, downsampling the dataset has improved the model's execution time by 33\% and reduced 3x memory usage.