What question did this study set out to answer?

To develop efficient deep learning models for classifying heart diseases based on ECG signals.

March 18, 2026Open Access

Efficient Deep Learning Models Integrated with a Smart Web Application for Classifying Heart Diseases Based on ECG Signals

Key Result

The Vision Transformer (ViT) deep learning model achieved a 100% F1-score, true positive rate, and AUPR for classifying arrhythmia, myocardic, and normal patients from ECG signals.

Key Points

To develop efficient deep learning models for classifying heart diseases based on ECG signals.
Implemented three deep learning models: Swin Transformer, VGG-19, and Vision Transformer.
Used a balanced dataset comprising 600 ECG samples across three classes: Arrhythmia Patient, Myocardic Patient, and Normal Patient.
Applied data augmentation techniques and fine-tuned hyperparameters using PyTorch framework v2.10.0.
Evaluated model performance using metrics like area under precision-recall curves and normalized confusion matrices.
Achieved high classification accuracy for heart patients with varied testing loss rates.
Swin-T, VGG-19, and ViT had testing loss rates of 0.0707, 0.4138, and 0.0015, respectively.
ViT attained an F1-score of 100%, along with high true positive rates and area under precision-recall curves.

Structured PICO

Can deep learning models accurately classify heart diseases based on ECG signals?

Population

600 electrocardiogram (ECG) samples comprising Arrhythmia Patient, Myocardic Patient, and Normal Patient classes

Intervention

Deep learning models (Swin Transformer, VGG-19, and Vision Transformer) integrated with a smart web application

Outcome

Classification accuracy and performance metrics (AUPR, NCMs, F1-score, TPR, testing loss)surrogate

Deep learning models, particularly the Vision Transformer, demonstrate exceptional accuracy in classifying ECG signals into arrhythmia, myocardic, and normal categories.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Recent advancements in the accuracy of deep learning (DL) hold significant promise for improving the classification of heart patients. Nevertheless, continued refinement is essential to achieve even greater levels of precision in DL techniques. This paper proposes three efficient DL models: Swin Transformer (Swin-T), Visual Geometry Group (VGG)-19, and Vision Transformer (ViT), which are implemented to classify different types of heart patients. The three DL models are learned on a balanced dataset comprising 600 electrocardiogram (ECG) samples. This dataset contains three classes: Arrhythmia Patient, Myocardic Patient, and Normal Patient. The DL models are applied using a PyTorch framework v2.10.0, with fine-tuning for the models’ hyperparameters to maximize the classification accuracy, and data augmentation techniques are implemented for the ECG samples. Additionally, a smart web application is designed for classifying heart patients into three different diagnostic categories. The performance of the three models is assessed by several metrics such as area under precision-recall (AUPR) curves and normalized confusion matrices (NCMs). The proposed three models achieve high testing accuracy for the classification of heart patients. Regarding testing loss (TL) rates for the Swin-T, VGG-19, and ViT achieve rates of 0.0707, 0.4138, and 0.0015, respectively. Also, the ViT achieves an F1-score, true positive rate (TPR), and AUPR curves of 100%.