RESUMO
The reliable and rapid identification of the COVID-19 has become crucial to prevent the rapid spread of the disease, ease lockdown restrictions and reduce pressure on public health infrastructures. Recently, several methods and techniques have been proposed to detect the SARS-CoV-2 virus using different images and data. However, this is the first study that will explore the possibility of using deep convolutional neural network (CNN) models to detect COVID-19 from electrocardiogram (ECG) trace images. In this work, COVID-19 and other cardiovascular diseases (CVDs) were detected using deep-learning techniques. A public dataset of ECG images consisting of 1937 images from five distinct categories, such as normal, COVID-19, myocardial infarction (MI), abnormal heartbeat (AHB), and recovered myocardial infarction (RMI) were used in this study. Six different deep CNN models (ResNet18, ResNet50, ResNet101, InceptionV3, DenseNet201, and MobileNetv2) were used to investigate three different classification schemes: (i) two-class classification (normal vs COVID-19); (ii) three-class classification (normal, COVID-19, and other CVDs), and finally, (iii) five-class classification (normal, COVID-19, MI, AHB, and RMI). For two-class and three-class classification, Densenet201 outperforms other networks with an accuracy of 99.1%, and 97.36%, respectively; while for the five-class classification, InceptionV3 outperforms others with an accuracy of 97.83%. ScoreCAM visualization confirms that the networks are learning from the relevant area of the trace images. Since the proposed method uses ECG trace images which can be captured by smartphones and are readily available facilities in low-resources countries, this study will help in faster computer-aided diagnosis of COVID-19 and other cardiac abnormalities.
RESUMO
PURPOSE: The COVID-19 pandemic has spread with increased fatalities around the world and has become an international public health crisis. Public health authorities in many countries have introduced contact tracing apps to track and trace infected persons as part of measures to contain the spread of the Severe Acute Respiratory Syndrome-Coronavirus 2. However, there are major concerns about its efficacy and privacy which affects mass acceptance amongst a population. This systematic literature review encompasses the current challenges facing this technology and recommendations to address such challenges in the fight against the COVID-19 pandemic in neo-liberal societies. METHODS: The systematic literature review was conducted by searching databases of Google Scholar, Web of Science, PubMed, IEEE Xplore Digital Library, PsycInfo and ScienceDirect using the search terms ("Contact Tracing" OR "Contact Tracing apps") AND ("COVID-19" OR "Coronavirus") to identify relevant literature. The searches were run against the title, keywords, or abstract, depending on the search platforms. The searches were conducted between January 1, 2020, through 31st January 2021. Further inputs were also taken from preprints, published government and technical reports. We explore and discuss from the selected literature, the key challenges and issues that influence unwillingness to use these contact tracing apps in neo-liberal societies which include the plausibility of abuse of user privacy rights and lack of trust in the government and public health authorities by their citizens. Other challenges identified and discussed include ethical issues, security vulnerabilities, user behaviour and participation, and technical constraints. RESULTS AND CONCLUSION: Finally, in the analysis of this systematic literature review, recommendations to address these challenges, future directions, and considerations in the use of digital contact tracing apps and related technologies to contain the spread of future pandemic outbreaks are presented. For policy makers in neo-liberal societies, this study provides an in-depth review of issues that must be addressed. We highlight recommendations to improve the willingness to use such digital technologies and could facilitate mass acceptance amongst users.
