Related Experiment Video
Updated: Sep 22, 2025
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
Published on: May 10, 2024
Automated Detection of COVID-19 Using Deep Learning Approaches with Paper-Based ECG Reports
Mahmoud M Bassiouni1, Islam Hegazy2, Nouhad Rizk3
1Egyptian E-Learning University (EELU), 33 El-messah Street, Eldokki, El-Giza, 11261 Egypt.
Insights
This study developed ECGConvnet, a deep learning model using convolutional neural networks (CNNs), for accurate COVID-19 diagnosis from ECG images. The model achieved over 99% accuracy, showing potential for an automated diagnostic system.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Medicine
- Cardiology
Background:
- The COVID-19 pandemic necessitates rapid and accurate diagnostic tools.
- Existing COVID-19 diagnostic methods have limitations, driving the need for novel approaches.
- Electrocardiogram (ECG) signals offer a potential, non-invasive biomarker for COVID-19 detection.
Purpose of the Study:
- To develop and evaluate a deep learning-based system for the early diagnosis of COVID-19 using ECG images.
- To enhance diagnostic performance by employing advanced feature extraction and classification techniques.
- To investigate the efficacy of a novel ensemble model, ECGConvnet, for COVID-19 detection.
Main Methods:
- Utilized publicly available ECG image datasets, including those with COVID-19 reports.
- Applied image preprocessing and data augmentation techniques to enhance data quality and balance classes.
- Employed deep learning, specifically Convolutional Neural Networks (CNNs), for feature extraction using pre-trained models (Vgg16, Vgg19, ResNet-101, Xception).
- Proposed an ensemble model, ECGConvnet (Xception + TCN), and evaluated its performance with classifiers like SVM, RF, MLP, and Softmax via fivefold cross-validation.
Main Results:
- The proposed ECGConvnet model demonstrated superior performance compared to individual pre-trained models.
- The Support Vector Machine (SVM) classifier achieved the highest accuracy when combined with ECGConvnet.
- Achieved high accuracies, including 99.74%, 98.6%, and 99.1% for multi-class diagnosis, and up to 100% for binary-class diagnosis of COVID-19.
Conclusions:
- ECGConvnet, an ensemble deep learning model, shows significant potential for accurate COVID-19 diagnosis.
- ECG data, analyzed via deep learning, can form the basis of an effective automated COVID-19 diagnostic system.
- The study highlights the clinical utility of ECG in the pandemic response, offering a promising non-invasive diagnostic avenue.
Abstract:
One of the pandemics that have caused many deaths is the Coronavirus disease 2019 (COVID-19). It first appeared in late 2019, and many deaths are increasing day by day until now. Therefore, the early diagnosis of COVID-19 has become a salient issue. Additionally, the current diagnosis methods have several demerits, and a new investigation is required to enhance the diagnosis performance. In this paper, a set of phases are performed, such as collecting data, filtering and augmenting images, extracting features, and classifying ECG images. The data were obtained from two publicly available ECG image datasets, and one of them contained COVID ECG reports. A set of preprocessing methods are applied to the ECG images, and data augmentation is performed to balance the ECG images based on the classes. A deep learning approach based on a convolutional neural network (CNN) is performed for feature extraction. Four different pre-trained models are applied, such as Vgg16, Vgg19, ResNet-101, and Xception. Moreover, an ensemble of Xception and the temporary convolutional network (TCN), which is named ECGConvnet, is proposed. Finally, the results obtained from the former models are fed to four main classifiers. These classifiers are softmax, random forest (RF), multilayer perception (MLP), and support vector machine (SVM). The former classifiers are used to evaluate the diagnosis ability of the proposed methods. The classification scenario is based on fivefold cross-validation. Seven experiments are presented to evaluate the performance of the ECGConvnet. Three of them are multi-class, and the remaining are binary class diagnosing. Six out of seven experiments diagnose COVID-19 patients. The aforementioned experimental results indicated that ECGConvnet has the highest performance over other pre-trained models, and the SVM classifier showed higher accuracy in comparison with the other classifiers. The resulting accuracies from ECGConvnet based on SVM are (99.74%, 98.6%, 99.1% on the multi-class diagnosis tasks) and (99.8% on one of the binary-class diagnoses, while the remaining achieved 100%). It is possible to develop an automatic diagnosis system for COVID based on deep learning using ECG data.
