A Hybrid GCN-LSTM Model for Ventricular Arrhythmia Classification Based on ECG Pattern Similarity

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

192 Downloads (Pure)

Abstract

Accurate differentiation between Ventricular Tachycardia (VT) and Ventricular Fibrillation (VF) is essential in the field of cardiology. Recent advancements in deep learning have facilitated automated arrhythmia recognition, surpassing traditional electrocardiogram (ECG) methods that depend on manual feature extraction. Building on our previous work, which emphasized the importance of identifying patterns of regularity, we have developed a model that merges Graph Convolutional Networks (GCN) with Long Short-Term Memory (LSTM) networks. This GCN-LSTM model employs a trainable weighted ε-neighborhood graph to capture the similarity among time series within ECG segments. This approach has demon- strated substantial improvement in the classification of VT, VF, and non-ventricular rhythms.
Original languageEnglish
Title of host publication46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024
Subtitle of host publicationIEEE
Number of pages4
Publication statusAccepted/In press - 15 Apr 2024

Cite this