Key result
The Multimodal Feature Fusion framework achieved classification accuracies of 99.7% for arrhythmia and 99.2% for myocardial infarction, outperforming single-modality approaches.
Why the study?
Existing ECG classification methods rely on manually extracted features or large, complex deep learning networks that only use 1D signals directly.
The proposed multimodal fusion frameworks achieved high classification accuracy for arrhythmia (99.7%) and MI (99.2%) using transformed ECG images.
May improve ECG-based diagnosis of arrhythmia and MI; extends single-modality approaches via multimodal fusion.
Electrocardiogram (ECG) is an authoritative source to diagnose and counter critical cardiovascular syndromes such as arrhythmia and myocardial infarction (MI). Current machine learning techniques either depend on manually extracted features or large and complex deep learning networks which merely utilize the 1D ECG signal directly. Since intelligent multimodal fusion can perform at the stateof-the-art level with an efficient deep network, therefore, in this paper, we propose two computationally efficient multimodal fusion frameworks for ECG heart beat classification called Multimodal Image Fusion (MIF) and Multimodal Feature Fusion (MFF). At the input of these frameworks, we convert the raw ECG data into three different images using Gramian Angular Field (GAF), Recurrence Plot (RP) and Markov Transition Field (MTF). In MIF, we first perform image fusion by combining three imaging modalities to create a single image modality which serves as input to the Convolutional Neural Network (CNN). In MFF, we extracted features from penultimate layer of CNNs and fused them to get unique and interdependent information necessary for better performance of classifier. These informational features are finally used to train a Support Vector Machine (SVM) classifier for ECG heart-beat classification. We demonstrate the superiority of the proposed fusion models by performing experiments on PhysioNets MIT-BIH dataset for five distinct conditions of arrhythmias which are consistent with the AAMI EC57 protocols and on PTB diagnostics dataset for Myocardial Infarction (MI) classification. We achieved classification accuracy of 99.7% and 99.2% on arrhythmia and MI classification, respectively.
No takes yet. Share an insight, caveat, or question.
Ahmad et al. (2021) studied Arrhythmia and Myocardial Infarction (n=337). Multimodal Feature Fusion (MFF) and Multimodal Image Fusion (MIF) vs. Single imaging modalities (GAF, RP, MTF) and conventional fusion methods was evaluated on Classification accuracy. The Multimodal Feature Fusion framework achieved classification accuracies of 99.7% for arrhythmia and 99.2% for myocardial infarction, outperforming single-modality approaches.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: