What is the clinical evidence from this study?

Study design: Other. Population: Arrhythmia (n=193690). Intervention: Convolutional Neural Network with Lead Encoder Attention (LEA) mechanism vs. Other deep learning and machine learning models. Primary outcome: Accuracy and TPR95 for classification of normal and abnormal ECG records.

May 12, 2025Scientific Reports11 citationsOpen Access

Classification of multi-lead ECG based on multiple scales and hierarchical feature convolutional neural networks

FZFeiyan ZhouXidian University DFDuanshu FangGuangxi Normal University

Key Result

The proposed Convolutional Neural Network with Lead Encoder Attention mechanism achieved an accuracy of 99.5% on the MIT-BIH-AR database and a TPR95 of 78.5% on the CCDD for ECG classification.

Structured PICO

Population

ECG records from the MIT-BIH Arrhythmia (MIT-BIH-AR) Database and over 150,000 ECG records from the Chinese Cardiovascular Disease Database (CCDD)

Intervention

Convolutional Neural Network (CNN) incorporating mixed scales and hierarchical features combined with the Lead Encoder Attention (LEA) mechanism

Outcome

Accuracy (Acc) and TPR95 for the classification of normal and abnormal heartbeats/ECG records

A novel CNN with Lead Encoder Attention mechanism demonstrates high accuracy in classifying normal and abnormal multi-lead ECGs across different databases.

Limitations

The model's structure is more suited to processing complete ECG recordings as long sequences, resulting in lower sensitivity on segmented heartbeat data like the MIT-BIH-AR database.
Suboptimal signal quality in the CCDD due to noise, electrode detachment, and difficulties in detecting R-peak markers poses challenges for recognizing abnormal categories.

Abstract

Detecting and classifying arrhythmias is essential in diagnosing cardiovascular diseases. However, current deep learning-based classification methods often encounter difficulties in effectively integrating both the morphological and temporal features of Electrocardiograms (ECGs). To address this challenge, we propose a Convolutional Neural Network (CNN) that incorporates mixed scales and hierarchical features combined with the Lead Encoder Attention (LEA) mechanism for multi-lead ECG classification. We validated the performance of our proposed method using the intrapatient approach of the MIT-BIH Arrhythmia (MIT-BIH-AR) Database and the interpatient approach of the Chinese Cardiovascular Disease Database (CCDD). Our model achieves an Accuracy (Acc) of 99.5% for the classification of normal and abnormal heartbeats in the MIT-BIH-AR database. Our method achieves a TPR95 (NPV under the condition of True Positive Rate being equal to 95 percent) of 78.5% and an Acc of 88.5% when classifying normal and abnormal ECG records from over 150,000 ECG records in the CCDD. The cross-dataset experimental results also confirm the model's strong generalization capability.

Ask AI

Helpful

Bookmark

View Full Paper