Detection Of COVID-19 Infection Research Articles

Covi-Assist: Automatic COVID-19 Detection from Chest X-Rays

Abstract: The spike in the number of patients with COVID-19, a respiratory virus, has put an unprecedented load over healthcare systems across the world. The early and automatic diagnosis of COVID-19 may be beneficial for countries for timely referral of patients to quarantine, rapid intubation of serious cases in specialized hospitals, and monitoring of the spread of the disease. In this work, we propose the use of chest X-Ray to detect COVID-19 infection in patients by studying the medical images and identifying possible patterns that may lead to the automatic diagnosis of the disease. This work's main contribution is proposing a deep neural network-based model for highly accurate detection of COVID-19 infection from chest X-ray images.

D-Cov19Net: A DNN based COVID-19 detection system using lung sound

The limitations of proper detectors for COVID-19 for the proliferating number of patients provoked us to build an auto-diagnosis system to detect COVID-19 infection using only one parameter. Our designed model is based on Deep Convolution Neural Network and considers lung/respiratory sound as the deterministic input for our approach. 'D-Cov19Net' has been trained with 23,592 recordings, begetting an AUC of 0.972 and sensitivity of 0.983 after 100 epochs. The model can be of immense utility in biomedical technology due to its significant accuracy, simplicity, user convenience, feasibility, and faster detection while maintaining social distancing.

Detection of COVID-19 Infection in CT and X-ray images using transfer learning approach.

The infection caused by the SARS-CoV-2 (COVID-19) pandemic is a threat to human lives. An early and accurate diagnosis is necessary for treatment. The study presents an efficient classification methodology for precise identification of infection caused by COVID-19 using CT and X-ray images. The depthwise separable convolution-based model of MobileNet V2 was exploited for feature extraction. The features of infection were supplied to the SVM classifier for training which produced accurate classification results. The accuracies for CT and X-ray images are 99.42% and 98.54% respectively. The MCC score was used to avoid any mislead caused by accuracy and F1 score as it is more mathematically balanced metric. The MCC scores obtained for CT and X-ray were 0.9852 and 0.9657, respectively. The Youden's index showed a significant improvement of more than 2% for both imaging techniques. The proposed transfer learning-based approach obtained the best results for all evaluation metrics and produced reliable results for the accurate identification of COVID-19 symptoms. This study can help in reducing the time in diagnosis of the infection.

A Cost Comparison Modeling Analysis for Healthcare Access and Equity: Cost of COVID-19 Test Screening by Point of Care (POC) Versus Rapid Reverse Transcriptase Polymerase Chain Reaction (RT-PCR)

Abstract Introduction/Objective Testing platforms to detect COVID-19 infection include antigen-based point of care (POC) testing and reverse transcriptase polymerase chain reaction (RT-PCR) to detect viral ribonucleic acid (RNA). RT-PCR, generally considered the gold standard for diagnosis of COVID-19 infection, is capable of being used for mass population screening but may be more expensive. Alternatively, antigen based POC testing can not only produce results rapidly (15 minutes on some assays) but also may be less expensive. This reduced cost provides an argument that it may be economical to use POC testing for mass surveillance in asymptomatic or mildly symptomatic patients while reserving the more expensive gold standard RT-PCR testing for sensitivity for hospitalized and more significantly at risk or ill patients. However, cost modeling between the two modalities for mass screening is sparse, particularly for studies including the Veteran Affairs system that may have different costs from the general community retail pricing. Methods/Case Report Cost information reviewed at the regional VAMC included costs for the Alinity-m SARS-CoV-2 RT-PCR assay (Abbott, Chicago IL), the Cepheid Xpert-Xpress-CoV-2-Flu-RSV-Plus RT-PCR assay (Cepheid, Sunnyvale CA), and the BinaxNOW POC antigen-based assay (Abbott, Chicago IL). The median cost of RT-PCR testing in the community was obtained from the Peterson-KFF Health System Tracker. Publicly available quoted prices for selected POC assays in the community were reviewed for comparison. Results (if a Case Study enter NA) Test costs at the regional VAMC was $28.34 (Alinity-m), $68 (Cepheid), and $5 (BinaxNOW). These costs did not include technologist time or standard laboratory consumables that would be part of the standard overhead costs of running the laboratory. The median community RT-PCR assay price per the Peterson- KFF Health System Tracker was $148, and the Abbott’s quoted BinaxNOW price was $25. POC testing cost was 82% less than the cheapest RT-PCR assay available at the regional VAMC. This trend in being significantly cheaper holds true in the community whereby BinaxNOW testing was 83% cheaper. Publicly available quoted prices from other selected POC assays confirm this trend. Conclusion For a mass surveillance screening program, the use of POC assays would result in significant cost savings.

Reduction of Feature Extraction for COVID-19 CXR using Depthwise Separable Convolution Network

A Convolutional Neural Network (CNN) classifier is generally utilized to classify an image tensor according to the mapped labels. The simplification of the classifier causes CNN to be often used to classify images, especially in the biomedical field. Thus, CNN is widely used to classify computer tomography (CT) and chest X-ray (CXR) images against the mapped labels. Several transfer learning models were implemented to classify CXR images for preliminary detection of COVID-19 infection, e.g., ResNet, Inception, Xception, etc. However, a transfer learning model has a maximum and minimum input resolution. Thus, the computational cost tends to be huge and unable to be optimized. Therefore, A custom CNN model can be a solution to reduce computational costs by configuring the feature extraction layers. This study proposed an efficient reduction of feature extraction for COVID-19 CXR namely Depthwise Separable Convolution Network. Furthermore, numerous strategies were adopted to lower the computational cost while retaining accuracy, including customizing the Batch Normalization (BN) layer and replacing the convolution layer with a separable convolution layer. The proposed model successfully reduced the feature extraction represented by the decreases in trainable parameters from 28.640 trainable parameters to 4.640 trainable parameters. The depthwise separable convolution effectively retains the performance accuracy 72.96%, loss 12.43%, recall 74.67%, precision 77.67%, and F1-score 75.33%. The CXR augmentation is also successfully increase the performance accuracy 74.55%, loss 11.37%, recall 77.67%, precision 79.56%, and F1-score 78.33%.

A machine learning study of COVID-19 serology and molecular tests and predictions.

Serology and molecular tests are the two most commonly used methods for rapid COVID-19 infection testing. The two types of tests have different mechanisms to detect infection, by measuring the presence of viral SARS-CoV-2 RNA (molecular test) or detecting the presence of antibodies triggered by the SARS-CoV-2 virus (serology test). A handful of studies have shown that symptoms, combined with demographic and/or diagnosis features, can be helpful for the prediction of COVID-19 test outcomes. However, due to nature of the test, serology and molecular tests vary significantly. There is no existing study on the correlation between serology and molecular tests, and what type of symptoms are the key factors indicating the COVID-19 positive tests.In this study, we propose a machine learning based approach to study serology and molecular tests, and use features to predict test outcomes. A total of 2,467 donors, each tested using one or multiple types of COVID-19 tests, are collected as our testbed. By cross checking test types and results, we study correlation between serology and molecular tests. For test outcome prediction, we label 2,467 donors as positive or negative, by using their serology or molecular test results, and create symptom features to represent each donor for learning. Because COVID-19 produces a wide range of symptoms and the data collection process is essentially error prone, we group similar symptoms into bins. This decreases the feature space and sparsity. Using binned symptoms, combined with demographic features, we train five classification algorithms to predict COVID-19 test results. Experiments show that XGBoost achieves the best performance with 76.85% accuracy and 81.4% AUC scores, demonstrating that symptoms are indeed helpful for predicting COVID-19 test outcomes. Our study investigates the relationship between serology and molecular tests, identifies meaningful symptom features associated with COVID-19 infection, and also provides a way for rapid screening and cost effective detection of COVID-19 infection.

COVID-19 detection prior to motility examinations: Prospective evaluation of pre-test questionnaires and PCR-testing

Background/AimsCOVID-19 pandemic has produced an increased burden for motility laboratories due to the need to implement measures to minimize infection risk during examinations. International Societies have proposed algorithms for evaluation of active infection risk using symptom questionnaires or performing COVID-19 specific detection tests. The aim of the present study is to evaluate prospectively the independent value of a symptom-based questionnaire and RT-PCR test to detect COVID-19 infection before a digestive motility examination. Patients/MethodsAll patients referred for a motility study during a 4 month period with high incidence of COVID-19 in the community were prospectively evaluated with a symptom-questionnaire administered by phone one week before the examination, and a PCR test performed 48h before the examination, following international guidelines recommendations. ResultsThe symptom questionnaire could be obtained from 435 patients, 7 patients referred COVID-19 symptoms, but only 1 of them had a positive PCR. From 481 PCR tests performed, 8 were positive. Only 1 patient had reported symptoms in the previous questionnaire, and 2 additional patients developed COVID-19 symptoms later. Hence, 435 telephonic questionnaires should be done for one COVID-19 case detection (detection tax 0.22%); and 60 PCR should be performed for one COVID-19 case detection (detection tax 1.66%). ConclusionsThe use of screening strategies prior to a motility exploration results in a low rate of infection detection, especially the use of subjective symptom questionnaires, and the correct protection measures during motility explorations with aerosol generation remain the cornerstone to prevent COVID-19 infections.

The impact of COVID-19 pandemic on IBD surgery: a single center experience.

The spread of COVID-19 pandemic forced the national healthcare system to reorganize almost all surgical services, in order to maintain an adequate therapeutic offer. At General Surgery department of Fondazione Policlinico Gemelli in Rome, surgical procedures were progressively reduced to provide beds and personnel for COVID-19. The aim of our study was to analyze the effect of one year of COVID-19 pandemic on Inflammatory Bowel Disease (IBD) surgery in a cohort of patients and evaluate post-operative short-term complications. Our team retrospectively analyzed the records of IBD patients who were referred to an IBD-related resective surgery from January 2020 to December 2020. These patients were compared to a comparable group of IBD patients who were operated from January 2019 to December 2019. A total of 160 patients were included in the study. Median age was 44 (range 15-77). Patients were referred for Ulcerative colitis (23.1%) and Crohn's disease (76.9%). Eighty-three patients underwent surgery from January 2020 to December 2020, which constitutes a 4.6% increase in the number of patients compared to the same period in 2019. Median post-operative hospital stay increased (7 days in 2019 vs. 6 days in 2020). Laparoscopic was the most frequently performed procedure during both periods (49% in 2019 and 59% in 2020). Complication rates, reported as Clavien-Dindo score 3 or 4, slightly decreased in 2020 (6.5 in 2019 vs. 4.8 in 2020). PCR test for detection of COVID-19 infection was conducted in all the patients before the hospitalization. Two patients out of 70 were tested positive for COVID-19 and their surgeries were rescheduled. There was no significant reduction in IBD resective surgeries at our center in 2020, nor a deterioration of the outcomes. A reduction of other elective surgical procedures had to be carried out and adequate protective measures for both patients and healthcare workers were established.

Blocked by Gender: Disparities in COVID19 infection detection in Tamil Nadu, India.

Globally, a gender gap in COVID-19 has been noted with men reporting higher share of both morbidity and deaths compared to women. While the gender gap in fatalities has been similar across the globe, there have been interesting disparities in the detection of COVID-19 cases in men and women. While wealthier, more developed nations have generally seen similar case detection in men and women, LMICs especially in Asia have seen far greater proportion of COVID-19 cases among men than women. We utilize age and sex-disaggregated data from the southern Indian state of Tamil Nadu across two waves of the pandemic (May 2020 – Nov 2020, and March 2021, to June 2021) and find that there were only ~70% as many detected COVID-19 cases among women as there were among men. Our initial reading suggested that this might be a protective effect of lower labor force participation rates among women across much of South Asia. However, subsequent sero-prevalence results from Tamil Nadu conducted on October-November 2020, and June-July, 2021 suggest that infection incidence has been similar among men and women; as is the case in countries with better health infrastructure. This empirical puzzle suggests that reduced case detection among women cannot be immediately associated with limited public exposure, but rather evidence of a chronic neglect of women in healthcare access. Overall, we contend that an attention to the gender context holds promise to effective interventions in detection and prevention that goes beyond the traditional epidemiological logic of diseases.

A systematic comparison of transfer learning models for COVID-19 prediction

The pandemic COVID-19 is already in its third year and there is no sign of ebbing. The world continues to be in a never-ending cycle of disease outbreaks. Since the introduction of Omicron-the most mutated and transmissible of the five variants of COVID-19 – fear and instability have grown. Many papers have been written on this topic, as early detection of COVID-19 infection is crucial. Most studies have used X-rays and CT images as these are highly sensitive to detect early lung changes. However, for privacy reasons, large databases of these images are not publicly available, making it difficult to obtain very accurate AI Deep Learning models. To address this shortcoming, transfer learning (pre-trained) models are used. The current study aims to provide a thorough comparison of known AI Deep Transfer Learning models for classifying lung radiographs into COVID-19, non COVID pneumonia and normal (healthy). The VGG-19, Inception-ResNet, EfficientNet-B0, ResNet-50, Xception and Inception models were trained and tested on 3568 radiographs. The performance of the models was evaluated using accuracy, sensitivity, precision and F1 score. High detection accuracy scores of 98% and 97% were found for the VGG-19 and Inception-ResNet models, respectively.

CodnNet: A lightweight CNN architecture for detection of COVID-19 infection

The application of Convolutional Neural Network (CNN) on the detection of COVID-19 infection has yielded favorable results. However, with excessive model parameters, the CNN detection of COVID-19 is low in recall, highly complex in computation. In this paper, a novel lightweight CNN model, CodnNet is proposed for quick detection of COVID-19 infection. CodnNet builds a more effective dense connections based on DenseNet network to make features highly reusable and enhances interactivity of local and global features. It also uses depthwise separable convolution with large convolution kernels instead of traditional convolution to improve the range of receptive field and enhances classification performance while reducing model complexity. The 5-Fold cross validation results on Kaggle’s COVID-19 Dataset showed that CodnNet has an average precision of 97.9%, recall of 97.4%, F1score of 97.7%, accuracy of 98.5%, mAP of 99.3%, and mAUC of 99.7%. Compared to the typical CNNs, CodnNet with fewer parameters and lower computational complexity has achieved better classification accuracy and generalization performance. Therefore, the CodnNet model provides a good reference for quick detection of COVID-19 infection.

Detecting COVID-19 infection status from chest X-ray and CT scan via single transfer learning-driven approach.

COVID-19 has caused over 528 million infected cases and over 6.25 million deaths since its outbreak in 2019. The uncontrolled transmission of the SARS-CoV-2 virus has caused human suffering and the death of uncountable people. Despite the continuous effort by the researchers and laboratories, it has been difficult to develop reliable efficient and stable vaccines to fight against the rapidly evolving virus strains. Therefore, effectively preventing the transmission in the community and globally has remained an urgent task since its outbreak. To avoid the rapid spread of infection, we first need to identify the infected individuals and isolate them. Therefore, screening computed tomography (CT scan) and X-ray can better separate the COVID-19 infected patients from others. However, one of the main challenges is to accurately identify infection from a medical image. Even experienced radiologists often have failed to do it accurately. On the other hand, deep learning algorithms can tackle this task much easier, faster, and more accurately. In this research, we adopt the transfer learning method to identify the COVID-19 patients from normal individuals when there is an inadequacy of medical image data to save time by generating reliable results promptly. Furthermore, our model can perform both X-rays and CT scan. The experimental results found that the introduced model can achieve 99.59% accuracy for X-rays and 99.95% for CT scan images. In summary, the proposed method can effectively identify COVID-19 infected patients, could be a great way which will help to classify COVID-19 patients quickly and prevent the viral transmission in the community.

Detection of COVID-19 using deep learning on x-ray lung images.

COVID-19 is a widespread deadly virus that directly affects the human lungs. The spread of COVID-19 did not stop at humans but also reached animals, so it was necessary to limit it is spread and diagnose cases quickly by applying a quarantine to the infected people. Recently x-ray lung images are used to determine the infection and from here the idea of this research came to use deep learning techniques to analyze x-ray lung images publicly available on Kaggle to possibly detect COVID-19 infection. In this article, we have proposed a method to possibly detect the COVID-19 by analyzing the X-ray images and applying a number of deep learning pre-trained models such as InceptionV3, DenseNet121, ResNet50, and VGG16, and the results are compared to determine the best performance model and accuracy with the least loss for our dataset. Our evaluation results showed that the best performing model for our dataset is ResNet50 with accuracies of 99.99%, 99.50%, and 99.44% for training, validation, and testing respectively followed by DenseNet121, InceptionV3, and finally VGG16.

Changing Trend of Risk Factors of Mucormycosis Including Diabetes, Acidosis, and Serum Iron in the Second Wave of COVID-19.

To analyze the clinic-pathological profile of patients presenting with mucormycosis infection to a tertiary care center during the second wave of the COVID-19 pandemic in India. This descriptive cross-sectional study was conducted in a hospital setting from April 2021 to July 2021 and analysis was carried out to find associations between the stratified data and the extent of the disease involvement based on radiological findings. Statistical tests like percentage, average, chi-square test, etc. were used wherever relevant using software called Minitab13. All the 51 patients had involvement of at least one paranasal sinus. The incidence of previously established risk factors was diabetes (66.67%), history of severe COVID-19 disease (5.88%), raised serum iron levels (1.96%), Acidosis (3.92%), steroid administration (62.75%), oxygen administration (25.49%). Elevated serum urea levels (76.47%), alkalosis in 50.98% and hyperglycemia on multiple occasions (41.17%) were observed. The mean days between start of treatment for COVID-19 and appearance of first symptom suggesting mucormycosis were found to be 27.59 days. Only in 5.88% participants mucormycosis preceded COVID-19 infection detection. The current work finds presence of traditional risk factors and associations in significantly lower frequencies than the reviewed literature. However, blood urea was elevated in three fourths of the participants. Larger scale studies in mucormycosis patients are warranted for finding the role of other risk factors including possible role of elevated blood urea and hyperglycemia in the present era.

A Machine Learning Framework for Detecting COVID-19 Infection Using Surface-Enhanced Raman Scattering.

In this study, we explored machine learning approaches for predictive diagnosis using surface-enhanced Raman scattering (SERS), applied to the detection of COVID-19 infection in biological samples. To do this, we utilized SERS data collected from 20 patients at the University of Maryland Baltimore School of Medicine. As a preprocessing step, the positive-negative labels are obtained using Polymerase Chain Reaction (PCR) testing. First, we compared the performance of linear and nonlinear dimensionality techniques for projecting the high-dimensional Raman spectra to a low-dimensional space where a smaller number of variables defines each sample. The appropriate number of reduced features used was obtained by comparing the mean accuracy from a 10-fold cross-validation. Finally, we employed Gaussian process (GP) classification, a probabilistic machine learning approach, to correctly predict the occurrence of a negative or positive sample as a function of the low-dimensional space variables. As opposed to providing rigid class labels, the GP classifier provides a probability (ranging from zero to one) that a given sample is positive or negative. In practice, the proposed framework can be used to provide high-throughput rapid testing, and a follow-up PCR can be used for confirmation in cases where the model’s uncertainty is unacceptably high.

A review of thermal impact of surface acoustic waves on microlitre droplets in medical applications

The surface acoustic waves (SAW) propagate inside the microdroplets resulting in kinetic and thermal impacts. The kinetic drives fluid particles inside the droplet while thermal impact increases the liquid’s temperature. This paper provides a comprehensive review of the research investigations related to internal kinetics and heating inside the microdroplet caused by the acoustic waves. The main factors that affect the kinetics and convection heat transfer are the piezoelectric materials, shape of the interdigital transducer (IDT) and mode of acoustic waves. Internal streaming (kinetic) leads to particle mixing, particle manipulation, cell sorting, cell patterning, cell separation, measuring the concentration of immunoglobulin and so forth. The effect of changing the mode of waves and the shape of IDT on the relevant applications are presented. Internal convection heat transfer is important where heating of the liquid is essential for many applications such as monitoring blood coagulation in the human plasma and an acoustic tweezer for particle trapping. Experimental methods developed by researchers to realise uniform temperature with constant heating and cooling cycles are also discussed. Such methods are widely used in the polymerase chain reaction (PCR) to detect COVID-19 infection. The heating of the droplet can be efficiently controlled by changing the input power and by varying the duty factor.

Comparative analysis of specificity and sensitivity between Cobas 6800 system and SARS-CoV-2 rRT-PCR to detect COVID-19 infection in clinical samples.

Fast and reliable testing for the COVID 19 infection is the need of the hour for the development of effective and reliable tools and assays. However, it is difficult to find the performance relativity among all these tests which are poorly understood. In this study, we aimed to evaluate the two different platforms where we determine the difference of sensitivity and specificity between the fully automated analyzer (Roche Diagnostics Cobas 6800 SARS-CoV-2 test) under FDA Emergency Use Authorization (EUA) and the laboratory designed test (SARS-CoV-2 rRT-PCR) based on the protocol developed by ICMR (Indian Council for Medical Research). The study was conducted for individual samples. We performed our study with two different approaches, first with validation method consisting of 188 samples (2 batches) on cobas 6800 instrument (Roche Molecular Systems, Branchburg, NJ) soon after we received US FDA EUA on 1 June 2021, all these samples were tested earlier with laboratory designed tests on 25th and 26th May 2021. Over all agreement between the two tests is of 88% and the coefficient of agreement between the two testing platform Cohen’sκ coefficient was found to be 0.76 (95% CI, 2.5897–13.4103) suggesting the substantial agreement between the two platforms. However, in some of the cases, both tests have shown a little disagreement. An overall discordance rate between two systems was found 11.1%. The difference may be due to the limit of detection, variation in the sequences of the primer design or may be due to other factors depicting the importance of comparing the two platforms used in the testing for SARS-CoV-2. Second approach includes head to head evaluation which comprises 1631 samples showed overall agreement of 99% and kappa value of 0.98. These results showed that cobas is effective and reliable assay for the detection of SARS-CoV-2 infection.

Description of complaints/clinical symptoms and examination results of the SARS-CoV-2 rapid test in Brata Medika Laboratory Clinic Pare - Kediri in February 2021

SARS-CoV-2 antigen rapid test is one of the examinations widely used for early detection of Covid-19 infection. Rapid test is considered to have more advantages, is faster, and is cheaper than molecular PCR testing, and more accurate than rapid antibody tests. Its weakness is especially in detecting samples with small quantities of the virus. The study was conducted using a retrospective method. The data was taken from the patient's medical record of the SARS -CoV-2 antigen rapid swab test at Brata Medika Pare Clinical Laboratory for the period of February 2021. Data inclusion criteria including the examination, complete identity, results of anamnesis examination and rapid test examinations. Data were analyzed in a tabular form containing frequency and percentage. There were 18 (22.5%) patients with positive SARS-CoV-2antigen rapid swab test results, 16 (89%) with complaints/symptoms, and 2 (11%) without complaints/symptoms. Meanwhile, 62 (77.5%) were found with negative SARS-CoV-2 antigen rapid swab test results where 18 (29.0%) were patients with complaints/symptoms and 44 (71.0%) were patients without complaints/symptoms. The high percentage of negative SARS-CoV-2 antigen rapid swab test results in patients with complaints/symptoms (29.0%), it is recommended that a confirmatory examination with the molecular PCR test be carried out.

The Use of an Incremental Learning Algorithm for Diagnosing COVID-19 from Chest X-ray Images

The new Coronavirus or simply Covid-19 causes an acute deadly disease. It has spread rapidly across the world, which has caused serious consequences for health professionals and researchers. This is due to many reasons including the lack of vaccine, shortage of testing kits and resources. Therefore, the main purpose of this study is to present an inexpensive alternative diagnostic tool for the detection of Covid-19 infection by using chest radiographs and Deep Convolutional Neural Network (DCNN) technique. In this paper, we have proposed a reliable and economical solution to detect COVID-19. This will be achieved by using X-rays of patients and an Incremental-DCNN (I-DCNN) based on ResNet-101 architecture. The datasets used in this study were collected from publicly available chest radiographs on medical repositories. The proposed I-DCNN method will help in diagnosing the positive Covid-19 patient by utilising three chest X-ray imagery groups, these will be: Covid-19, viral pneumonia, and healthy cases. Furthermore, the main contribution of this paper resides on the use of incremental learning in order to accommodate the detection system. This has high computational energy requirements, time consuming challenges, while working with large-scale and regularly evolving images. The incremental learning process will allow the recognition system to learn new datasets, while keeping the convolutional layers learned previously. The overall Covid-19 detection rate obtained using the proposed I-DCNN was of 98.70\% which undeniably can contribute effectively to the detection of COVID-19 infection.

PCovNet: A presymptomatic COVID-19 detection framework using deep learning model using wearables data

While the advanced diagnostic tools and healthcare management protocols have been struggling to contain the COVID-19 pandemic, the spread of the contagious viral pathogen before the symptom onset acted as the Achilles’ heel. Although reverse transcription-polymerase chain reaction (RT-PCR) has been widely used for COVID-19 diagnosis, they are hardly administered before any visible symptom, which provokes rapid transmission. This study proposes PCovNet, a Long Short-term Memory Variational Autoencoder (LSTM-VAE)-based anomaly detection framework, to detect COVID-19 infection in the presymptomatic stage from the Resting Heart Rate (RHR) derived from the wearable devices, i.e., smartwatch or fitness tracker. The framework was trained and evaluated in two configurations on a publicly available wearable device dataset consisting of 25 COVID-positive individuals in the span of four months including their COVID-19 infection phase. The first configuration of the framework detected RHR abnormality with average Precision, Recall, and F-beta scores of 0.946, 0.234, and 0.918, respectively. However, the second configuration detected aberrant RHR in 100% of the subjects (25 out of 25) during the infectious period. Moreover, 80% of the subjects (20 out of 25) were detected during the presymptomatic stage. These findings prove the feasibility of using wearable devices with such a deep learning framework as a secondary diagnosis tool to circumvent the presymptomatic COVID-19 detection problem.