Abstract

Info

Title:: Automatic ECG diagnosis model based on bidirectional selective state space model

Author(s):: LIN Mingjun1; WEN Yaoqi1; ZHANG Xin1; HONG Yong1; CHEN Chaomin1; WU Yuliang2; 1. School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; 2. Radiation Oncology Center,Dongguan People’s Hospital/the Tenth Affiliated Hospital of Southern Medical University, Dongguan 523059, China

Keywords:: electrocardiogram; automatic electrocardiogram diagnosis model; elective state space model; deep learning

Abstract:: To address the limitations of the existing automatic electrocardiogram (ECG) diagnosis models in learninglong-term dependencies, an automatic 12-lead long-term ECG signal diagnosis model which combines bidirectional selectivestate space model (bidirectional mamba, BiMamba) with residual multi-scale receptive field block (RMSF) is proposed:(1) designing a multi-scale receptive field module with residual connections to realize more extensive feature extraction andfusion; (2) introducing BiMamba block to enhance the model’s temporal modeling capability by employing both forward andbackward temporal processing; (3) using the classifier to process features from BiMamba for accomplishing multi-label ECGclassification. Five major diagnostic categories from the PTB-XL dataset are extracted and subjected to 5-fold crossvalidation experiments. The experimental results from the comparative study show that BiMamba-RMSF achieves anaverage accuracy of 89.42%, an average AUC of 0.9356, and an average F1 score of 72.85%, outperforming the other 4automatic ECG diagnosis models. Additionally, ablation study further validates the effectiveness of BiMamba block. It isdemonstrated that the proposed model has a high precision in the multi-label classification for 12-lead long-term ECG signals.