Key result
Novel neural network pre-processing method achieves ~99% accuracy in 16-class arrhythmia classification.
Why the study?
Existing ECG databases have limited numbers of samples and imbalanced distributions, making it difficult to train practical and efficient neural networks.
Does a heartbeat self-processing method improve arrhythmia classification accuracy in a unified ECG database?
Does a heartbeat self-processing method improve arrhythmia classification accuracy in a unified ECG database?
A novel heartbeat self-processing method and unified database approach enables highly accurate 16-class arrhythmia detection using a relatively simple neural network.
May support unified ECG preprocessing for accurate multi-class arrhythmia detection; leaves open prospective clinical validation.
According to the World Health Organization, cardiovascular diseases are the leading cause of deaths globally. Electrocardiogram (ECG) is a non-invasive approach for detecting heart diseases and reducing the risk of heart disease-related death. However, there are limited numbers of ECG samples and imbalance distribution for existing ECG databases. It is difficult to train practical and efficient neural networks. Based on the analysis and research of many existing ECG databases, this paper conduct an in-depth study on three fine-labeled ECG databases, to extract heartbeats, unify the sampling frequency, and propose a self-processing method of heartbeats, and finally form a unified ECG arrhythmia classification database, noted as Hercules-3. It is separated into training sets (80%) and testing sets (the remaining 20%). In order to verify its capabilities, we have trained a 16-classification fully connected neural network based on Hercules-3 and it achieves an accuracy rate of up to 98.67%. Compared with other data processing, our proposed method improves classification recall by at least 6%, classification accuracy by at least 4%, and F1-score by at least 7%.
No takes yet. Share an insight, caveat, or question.
Meng et al. (2023) studied Arrhythmia (n=2,186,555). Heartbeat self-processing method and neural network vs. Traditional data pre-processing methods was evaluated on Classification accuracy. The proposed heartbeat self-processing method and 5-layer fully connected neural network achieved a 16-class arrhythmia classification accuracy of 98.67%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: