High quality ECG dataset based on MIT-BIH recordings for improved heartbeats classification
This work addresses the need for better ECG datasets for medical professionals to diagnose cardiovascular diseases, but it is incremental as it builds on existing MIT-BIH recordings.
The paper tackled the problem of creating a high-quality ECG dataset from MIT-BIH recordings to improve heartbeat classification, resulting in a model achieving 99.24% accuracy with a 5.7% improvement over other methods and reducing execution time by 33% and memory usage by 3x.
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.