A bimodal CNN ensemble model co-training ECG grayscale images and scalograms achieved an AUC of 0.994 and 95.74% accuracy for cardiovascular disease classification, outperforming LSTM and single CNN models.
Does a bimodal CNN model co-training ECG grayscale images and scalograms improve diagnostic performance for cardiovascular disease classification compared to single-input models and traditional machine learning algorithms?
A bimodal CNN model utilizing both ECG grayscale images and scalograms demonstrates superior diagnostic performance for cardiovascular disease classification compared to single-input models and traditional machine learning algorithms.
Absolute Event Rate: 0.994% vs 0.991%
This study aimed to develop a bimodal convolutional neural network (CNN) by co-training grayscale images and scalograms of ECG for cardiovascular disease classification. The bimodal CNN model was developed using a 12-lead ECG database collected from Chapman University and Shaoxing People's Hospital. The preprocessed database contains 10,588 ECG data and 11 heart rhythms labeled by a specialist physician. The preprocessed one-dimensional ECG signals were converted into two-dimensional grayscale images and scalograms, which are fed simultaneously to the bimodal CNN model as dual input images. The proposed model aims to improve the performance of CVDs classification by making use of ECG grayscale images and scalograms. The bimodal CNN model consists of two identical Inception-v3 backbone models, which were pre-trained on the ImageNet database. The proposed model was fine-tuned with 6780 dual-input images, validated with 1694 dual-input images, and tested on 2114 dual-input images. The bimodal CNN model using two identical Inception-v3 backbones achieved best AUC (0.992), accuracy (95.08%), sensitivity (0.942), precision (0.946) and F1-score (0.944) in lead II. Ensemble model of all leads obtained AUC (0.994), accuracy (95.74%), sensitivity (0.950), precision (0.953), and F1-score (0.952). The bimodal CNN model showed better diagnostic performance than logistic regression, XGBoost, LSTM, single CNN model training with grayscale images alone or with scalograms alone. The proposed bimodal CNN model would be of great help in diagnosing cardiovascular diseases.
Yoon et al. (Mon,) conducted a other in Cardiovascular diseases (arrhythmias) (n=10,646). Bimodal CNN model (co-training ECG grayscale images and scalograms) vs. Logistic regression, XGBoost, LSTM, and single CNN models was evaluated on Area under the ROC curve (AUC) for cardiovascular disease classification. A bimodal CNN ensemble model co-training ECG grayscale images and scalograms achieved an AUC of 0.994 and 95.74% accuracy for cardiovascular disease classification, outperforming LSTM and single CNN models.