Detection Of COVID-19 Cases Research Articles

Use of Antigen Rapid Diagnostic Test for Detection of COVID-19 Cases in University Settings in Cameroon.

Robust testing strategies are an essential aspect of COVID-19 pandemic preparedness and response. In 2022, most regions of Cameroon were still below the WHO's recommended level of 10 COVID-19 tests per 10,000 population. This study aimed to detect SARS-CoV-2 cases in university settings in Cameroon using antigen rapid diagnostic tests (Ag-RDTs) to increase national testing capacity and assess the knowledge, attitudes, and practices of this population regarding COVID-19 infection. Six universities in Buea, Douala, Dschang, Maroua, Ngaoundere, and Yaounde participated in this study from June to October 2022. Nasopharyngeal swabs were collected from participants and tested for COVID-19 using Ag-RDTs. For all positive cases, high-risk contacts were also tested by Ag-RDT. Participants were administered a structured questionnaire to assess their knowledge, attitudes, and practices regarding COVID-19. A total of 7,006 participants were recruited, and 54 (0.8%) were positive for SARS-CoV-2. Among close contacts, three of 62 (4.8%) tested positive. The University of Maroua was the only site to consistently report satisfactory testing capacity, achieving the study target of 30 tests/10,000 in 94.1% of cases. Participants' knowledge of COVID-19 was moderate to good (≥50%). However, 28% were unsure about the effectiveness of the COVID-19 vaccine. Two main factors were identified that could facilitate the spread of SARS-CoV-2 in university settings, namely the lack of restrictions on entering campus without a mask (36%) and the non-respect of social distancing on campus (42.7%). The results of this study will guide future policies to better control diseases with epidemic or pandemic potential by targeting educational institutions.

Neopterin production in relation to COVID-19 in the Haut-Ogooué Province, Gabon

BackgroundIn sub-Saharan Africa, understanding of the immune process associated with the COVID-19 pandemic remains scarce. This study aimed to investigate the relationship between plasma neopterin concentrations and COVID-19 infection, focusing on changes over time and age-related changes in immune response.MethodsA retrospective case study was conducted during the first wave of COVID-19 from March to August 2020. Whole blood and associated symptoms and comorbidities were collected from patients of all ages and sexes. Concentrations of plasma neopterin were measured using a commercial competitive neopterin ELISA (Neopterin ELISA, IBL International GmbH, Germany).ResultsWe analyzed data for 325 patients: 38% (n = 124) with COVID-19, and 62% (n = 201) without COVID-19, as a control group. We found that plasma neopterin concentrations were significantly higher in the COVID-19 group (mean value 45.1 nmol/L (SD 19)) than in the control group (mean value 33.8 nmol/L (SD 13)) (p = 0.004). In addition, neopterin levels decreased gradually over time in patients with COVID-19 (p < 0.001). Moreover, ROC analysis found that the best cut-off value for diagnosing COVID-19 patients based on plasma neopterin levels was 38.85 nmol/L with 70% sensitivity and 82% specificity (AUC, 0.74 [0.69–0.82], p < 0.05). We also found an increase in neopterin production with increasing age (p < 0.001).ConclusionOur findings contribute to our growing understanding of neopterin levels as a promising biomarker for the detection of COVID-19 cases in sub-Saharan Africa.

Detection of Covid-19 Cases from Chest X-Ray Images using CNN

The occurrence of COVID-19 has brought the worldwide threat to the living society. The severity of the unwellness is often understood by the huge variety of deaths and affected patients globally. If the identification is fast, the illnesses are often controlled in a very higher manner. The factitious intelligence researcher’s square measure focusing their experience data to develop mathematical models for analyzing this epidemic scenario mistreatment nationwide shared information. To contribute towards the well-being of living society, during this project, Deep learning algorithmic program are going to be wont to determine the COVID infected patients through chest X-Ray pictures. By using, Convolutional Neural Network and Deep Neural Network, the chest X-Ray pictures are going to be analyzed to observe, whether or not the actual patient has the signatures of COVID-19 viruses or not. The performance of each the model is going to be compared on the experimental basis and deliver the simplest model to the clinical and health care domain.

The determinants of COVID-19 case reporting across Africa.

According to study on the under-estimation of COVID-19 cases in African countries, the average daily case reporting rate was only 5.37% in the initial phase of the outbreak when there was little or no control measures. In this work, we aimed to identify the determinants of the case reporting and classify the African countries using the case reporting rates and the significant determinants. We used the COVID-19 daily case reporting rate estimated in the previous paper for 54 African countries as the response variable and 34 variables from demographics, socioeconomic, religion, education, and public health categories as the predictors. We adopted a generalized additive model with cubic spline for continuous predictors and linear relationship for categorical predictors to identify the significant covariates. In addition, we performed Hierarchical Clustering on Principal Components (HCPC) analysis on the reporting rates and significant continuous covariates of all countries. 21 covariates were identified as significantly associated with COVID-19 case detection: total population, urban population, median age, life expectancy, GDP, democracy index, corruption, voice accountability, social media, internet filtering, air transport, human development index, literacy, Islam population, number of physicians, number of nurses, global health security, malaria incidence, diabetes incidence, lower respiratory and cardiovascular diseases prevalence. HCPC resulted in three major clusters for the 54 African countries: northern, southern and central essentially, with the northern having the best early case detection, followed by the southern and the central. Overall, northern and southern Africa had better early COVID-19 case identification compared to the central. There are a number of demographics, socioeconomic, public health factors that exhibited significant association with the early case detection.

EfficientCovNet: A CNN-based approach to detect various pulmonary diseases including COVID-19 using modified EfficientNet

The ongoing COVID-19 pandemic has brought about severe consequences, including numerous tragic losses of loved ones and significant disruptions to the global economy and daily routines. To curb the spread of the virus, timely and precise detection of COVID-19 cases is crucial. However, the traditional RT-PCR testing system is time-consuming, and its sensitivity can vary depending on the testing environment. In this context, X-ray images of the lungs have emerged as a potential tool for COVID-19 detection, as the virus predominantly affects the lungs. However, distinguishing COVID-19 from other significant pulmonary diseases such as Viral Pneumonia and Lung Opacity is essential to avoid misdiagnosis and ensure appropriate treatment.In this study, we propose a modified efficient Convolutional Neural Network (CNN)-based architecture named EfficientCovNet for accurate classification of different lung diseases, including COVID-19, Viral Pneumonia, and Lung Opacity, as they all share common symptoms of shortness of breath. Our proposed model achieved a remarkable test accuracy of +2% (96.12%) compared to existing CNN models, as demonstrated pictorially in the later sections. Furthermore, we utilized a comparatively large dataset of 20,000 radiograph images encompassing various disease categories, enhancing the robustness and reliability of our model. Our findings highlight the potential of CNN-based models in accurately classifying lung diseases, including COVID-19, and can aid in effective disease management and containment strategies.

The Use of Infectious Diseases Hospital Resources During the COVID-19 Epidemic Depending on Patient Characteristics

Background. The research of infectious hospital bed use and infectious patients’ characteristics during the COVID-19 pandemic allows proposing effective management strategies for possible future epidemics.Aim of study. The analysis of infectious bed fund use at the N.V. Sklifosovsky Research Institute for Emergency Medicine (the Institute) and the characteristics of admitted patients with COVID-19 in order to determine the factors that are important for improving the medical care provision.Material and methods. The data of 3365 patients treated at the Institute from March 2020 to June 2021 was used. Among them 1778 males, median age 62, average length of stay 11.2, mortality rates 17.8%, non-invasive mechanical ventilation was used for 21.5% of patients, invasive one — for 16%. For comparing the patients according to various characteristics, Fisher’s exact test and Pearson’s correlation coefficient were used. Length of stay was compared to exponential distribution using Pearson’s chi-squared test. Comorbidity was measured using the Charlson Comorbidity Index. For all calculations R software environment was used. Survival curves were obtained via the Kaplan-Meier method. Statistical significance was less than 0.05.Results. Periods of increase and decrease in hospitalization number correspond to an increase and decrease in the detection of COVID-19 cases in Moscow without lag. Intensive care for COVID-19 patients was needed in 96% of cases, readmissions to intensive care – 37%. The effective ratio of intensive care to hospital beds was determined to be higher than 2/1. The improvement in resuscitation capacity helps to avoid overload with an increase in the number of patients treated. When a patient is admitted in satisfactory condition, mortality is practically zero, while with increasing severity, mortality reaches 30–100%. The mortality rates of patients treated with the help of respiratory support is 7–40 times higher than in patients with spontaneous breathing. Higher values of the Charlson Comorbidity Index correspond to increased risks of severe course and death for patients.Conclusion. When providing medical care during the increase in number of infectious disease daily cases, the amount of deployed intensive care units becomes of a paramount importance. To determine the size of the bed fund, it is possible to use readily available estimates of the proportion of the population at risk of an adverse outcome from an infectious disease, based on the value of the Comorbidity Index.

Mobile Health-Supported Active Syndrome Surveillance for COVID-19 Early Case Finding in Addis Ababa, Ethiopia: Comparative Study.

Since most people in low-income countries do not have access to reliable laboratory services, early diagnosis of life-threatening diseases like COVID-19 remains challenging. Facilitating real-time assessment of the health status in a given population, mobile health (mHealth)-supported syndrome surveillance might help identify disease conditions earlier and save lives cost-effectively. This study aimed to evaluate the potential use of mHealth-supported active syndrome surveillance for COVID-19 early case finding in Addis Ababa, Ethiopia. A comparative cross-sectional study was conducted among adults randomly selected from the Ethio telecom list of mobile phone numbers. Participants underwent a comprehensive phone interview for COVID-19 syndromic assessments, and their symptoms were scored and interpreted based on national guidelines. Participants who exhibited COVID-19 syndromes were advised to have COVID-19 diagnostic testing at nearby health care facilities and seek treatment accordingly. Participants were asked about their test results, and these were cross-checked against the actual facility-based data. Estimates of COVID-19 detection by mHealth-supported syndromic assessments and facility-based tests were compared using Cohen Kappa (κ), the receiver operating characteristic curve, sensitivity, and specificity analysis. A total of 2741 adults (n=1476, 53.8% men and n=1265, 46.2% women) were interviewed through the mHealth platform during the period from December 2021 to February 2022. Among them, 1371 (50%) had COVID-19 symptoms at least once and underwent facility-based COVID-19 diagnostic testing as self-reported, with 884 (64.5%) confirmed cases recorded in facility-based registries. The syndrome assessment model had an optimal likelihood cut-off point sensitivity of 46% (95% CI 38.4-54.6) and specificity of 98% (95% CI 96.7-98.9). The area under the receiver operating characteristic curve was 0.87 (95% CI 0.83-0.91). The level of agreement between the mHealth-supported syndrome assessment and the COVID-19 test results was moderate (κ=0.54, 95% CI 0.46-0.60). In this study, the level of agreement between the mHealth-supported syndromic assessment and the actual laboratory-confirmed results for COVID-19 was found to be reasonable, at 89%. The mHealth-supported syndromic assessment of COVID-19 represents a potential alternative method to the standard laboratory-based confirmatory diagnosis, enabling the early detection of COVID-19 cases in hard-to-reach communities, and informing patients about self-care and disease management in a cost-effective manner. These findings can guide future research efforts in developing and integrating digital health into continuous active surveillance of emerging infectious diseases.

The importance of community health workers as frontline responders during the COVID-19 pandemic, Somalia, 2020-2021.

We examined the contribution of community health workers as frontline responders for the community-based surveillance in Somalia during the first year of the COVID-19 pandemic for detection of COVID-19 cases and identification of contacts. We retrieved COVID-19 surveillance data from 16 March 2020 to 31 March 2021 from the health ministry's central database. These data were collected through community health workers, health facilities or at the points of entry. We compared the number of suspected COVID-19 cases detected by the three surveillance systems and the proportion that tested positive using the chi-squared test. We used logistic regression analysis to assess association between COVID-19 infection and selected variables. During the study period, 154,004 suspected cases of COVID-19 were detected and tested, of which 10,182 (6.6%) were positive. Of the notified cases, 32.7% were identified through the community-based surveillance system, 54.0% through the facility-based surveillance system, and 13.2% at points of entry. The positivity rate of cases detected by the community health workers was higher than that among those detected at health facilities (8.6% versus 6.4%; p < 0.001). The community health workers also identified more contacts than those identified through the facility-based surveillance (13,279 versus 1,937; p < 0.001). The odds of COVID-19 detection generally increased by age. Community-based surveillance and health facility-based surveillance had similar odds of detecting COVID-19 cases compared with the points-of-entry surveillance (aOR: 7.0 (95% CI: 6.4, 7.8) and aOR: 7.5 (95% CI: 6.8, 8.3), respectively). The community health workers proved their value as first responders to COVID-19. They can be effective in countries with weak health systems for targeted community surveillance in rural and remote areas which are not covered by the facility-based surveillance system.

Efficient machine learning classifier to detect and monitor COVID-19 cases based on internet of things framework

&lt;p&gt;In this research work, coronavirus disease (COVID-19) has been considered to help mankind survive the present-day pandemic. This research is helpful to monitor the patients newly infected by the virus, and patients who have already recovered from the disease, and also to study the flow of virus from similar health issues. In this paper, an Internet of things (IoT) framework has been developed for the early detection of suspected cases. This framework is used for collecting and uploading symptoms (data) through sensor devices to the physician, data analytics center, cloud, and isolation/health centers. The symptoms of the first wave, second wave, and omicron are used to identify the suspects. Five machine learning algorithms which are considered to be the best in the existing literature have been used to find the best machine learning classifier in this research work. The proposed framework is used for the rapid detection of COVID-19 cases from real-world COVID-19 symptoms to mitigate the spread in society. This model also monitors the affected patient who has undergone treatment and recovered. It also collects data for analysis to perform further improvements in algorithms based on daily updated information from patients to provide better solutions to mankind.&lt;/p&gt;

Knowledge, Attitude, and Practices Regarding COVID-19 among Patients Attending the Dermatology Outpatient Department: A Cross-Sectional Study

Background: The current trend in the declining rates of new COVID-19 case detection may be attributed to better awareness and more robust screening and testing programs all across the country. Although there have been many studies on the impact of COVID-19 in India and its management, there are no studies currently regarding the knowledge, attitudes, and practices (KAP) among the community. Objective: This study aims to study the KAP regarding COVID-19 attending the dermatology outpatient department in a tertiary care center. Materials and Methods: A cross-sectional, descriptive study was conducted on 202 patients attending the dermatology outpatient department. After taking consent, the enrolled patients were directed to complete the COVID-19 KAP questionnaire, which was adapted from a previous study, and was translated into Hindi. Results: Our study showed a good knowledge score of 8.01 ± 1.94 for males and 7.71 ± 2.4 for females. The knowledge scores were similar in both genders and across all age groups and employment groups. The knowledge scores were significantly higher in those with higher education levels. Conclusion: Male gender, with higher education and a higher COVID-19 knowledge score, was also associated with a significantly more positive attitude. Females, with higher education and a higher COVID-19 knowledge score, were also found to have better protective measures against COVID-19.

A Novel Approach to detect COVID-19 from chest X-ray images using CNN

In light of the present COVID-19 pandemic, it is important to consider the worth of human life, prosperity, and quality of life while also realizing that it is difficult to restrict case spread and mortality. One of the most difficult challenges for practitioners is identifying individuals who are COVID19-infected and isolating patients to stop COVID transmission. Therefore, identifying the covid19 infection is important. For the detection of COVID-19, a 4-6-hour reverse transcriptase chain reaction is used. Chest X-rays provide us with a different method for detecting Coronavirus early in the disease phase. We detected properties from chest X-ray scans and divided them into three categories with VGG16 as well as ResNet50 deep learning algorithms: COVID-19, normal, and viral pneumonia. To test the model's accuracy in specialized cases, we injected them with 15153 scans. The average COVID-19 case detection accuracy for the ResNet50 model is 91.39%, compared to 89.34% for the VGG16 model. However, a larger dataset is required when using deep learning to identify COVID-19. It accurately detects situations, which is the desired outcome.

Community-based COVID-19 active case finding and rapid response in the Democratic Republic of the Congo: Improving case detection and response.

A community-based coronavirus disease (COVID-19) active case-finding strategy using an antigen-detecting rapid diagnostic test (Ag-RDT) was implemented in the Democratic Republic of Congo (DRC) to enhance COVID-19 case detection. With this pilot community-based active case finding and response program that was designed as a clinical, prospective testing performance, and implementation study, we aimed to identify insights to improve community diagnosis and rapid response to COVID-19. This pilot study was modeled on the DRC's National COVID-19 Response Plan and the COVID-19 Ag-RDT screening algorithm defined by the World Health Organization (WHO), with case findings implemented in 259 health areas, 39 health zones, and 9 provinces. In each health area, a 7-member interdisciplinary field team tested the close contacts (ring strategy) and applied preventive and control measures to each confirmed case. The COVID-19 testing capacity increased from 0.3 tests per 10,000 inhabitants per week in the first wave to 0.4, 1.6, and 2.2 in the second, third, and fourth waves, respectively. From January to November 2021, this capacity increase contributed to an average of 10.5% of COVID-19 tests in the DRC, with 7,110 positive Ag-RDT results for 40,226 suspected cases and close contacts who were tested (53.6% female, median age: 37 years [interquartile range: 26.0-50.0)]. Overall, 79.7% (n = 32,071) of the participants were symptomatic and 7.6% (n = 3,073) had comorbidities. The Ag-RDT sensitivity and specificity were 55.5% and 99.0%, respectively, based on reverse transcription polymerase chain reaction analysis, and there was substantial agreement between the tests (k = 0.63). Despite its limited sensitivity, the Ag-RDT has improved COVID-19 testing capacity, enabling earlier detection, isolation, and treatment of COVID-19 cases. Our findings support the community testing of suspected cases and asymptomatic close contacts of confirmed cases to reduce disease spread and virus transmission.

Rapid SARS-CoV-2 Antigen Detection Self-Tests to Increase COVID-19 Case Detection in Peru: Qualitative Study.

The COVID-19 pandemic heavily impacted many low- and middle-income countries (LMICs), such as Peru, overwhelming their health systems. Rapid antigen detection self-tests for SARS-CoV-2, the virus that causes COVID-19, have been proposed as a portable, safe, affordable, and easy-to-perform approach to improve early detection and surveillance of SARS-CoV-2 in resource-constrained populations where there are gaps in access to health care. This study aims to explore decision makers' values and attitudes around SARS-CoV-2 self-testing. In 2021, we conducted a qualitative study in 2 areas of Peru (urban Lima and rural Valle del Mantaro). Purposive sampling was used to identify representatives of civil society groups (RSCs), health care workers (HCWs), and potential implementers (PIs) to act as informants whose voices would provide a proxy for the public's attitudes around self-testing. In total, 30 informants participated in individual, semistructured interviews (SSIs) and 29 informants participated in 5 focus group discussions (FGDs). Self-tests were considered to represent an approach to increase access to testing that both the rural and urban public in Peru would accept. Results showed that the public would prefer saliva-based self-tests and would prefer to access them in their community pharmacies. In addition, information about how to perform a self-test should be clear for each population subgroup in Peru. The tests should be of high quality and low cost. Health-informed communication strategies must also accompany any introduction of self-testing. In Peru, decision makers consider that the public would be willing to accept SARS-CoV-2 self-tests if they are accurate, safe to use, easily available, and affordable. Adequate information about the self-tests' features and instructions, as well as about postuse access to counseling and care, must be made available through the Ministry of Health in Peru.

Detection of COVID-19 Case from Chest CT Images Using Deformable Deep Convolutional Neural Network.

The infectious coronavirus disease (COVID-19) has become a great threat to global human health. Timely and rapid detection of COVID-19 cases is very crucial to control its spreading through isolation measures as well as for proper treatment. Though the real-time reverse transcription-polymerase chain reaction (RT-PCR) test is a widely used technique for COVID-19 infection, recent researches suggest chest computed tomography (CT)-based screening as an effective substitute in cases of time and availability limitations of RT-PCR. In consequence, deep learning-based COVID-19 detection from chest CT images is gaining momentum. Furthermore, visual analysis of data has enhanced the opportunities of maximizing the prediction performance in this big data and deep learning realm. In this article, we have proposed two separate deformable deep networks converting from the conventional convolutional neural network (CNN) and the state-of-the-art ResNet-50, to detect COVID-19 cases from chest CT images. The impact of the deformable concept has been observed through performance comparative analysis among the designed deformable and normal models, and it is found that the deformable models show better prediction results than their normal form. Furthermore, the proposed deformable ResNet-50 model shows better performance than the proposed deformable CNN model. The gradient class activation mapping (Grad-CAM) technique has been used to visualize and check the targeted regions' localization effort at the final convolutional layer and has been found excellent. Total 2481 chest CT images have been used to evaluate the performance of the proposed models with a train-valid-test data splitting ratio of 80 : 10 : 10 in random fashion. The proposed deformable ResNet-50 model achieved training accuracy of 99.5% and test accuracy of 97.6% with specificity of 98.5% and sensitivity of 96.5% which are satisfactory compared with related works. The comprehensive discussion demonstrates that the proposed deformable ResNet-50 model-based COVID-19 detection technique can be useful for clinical applications.

LiMS-Net: A Lightweight Multi-Scale CNN for COVID-19 Detection from Chest CT Scans

Recent years have witnessed a rise in employing deep learning methods, especially convolutional neural networks (CNNs) for detection of COVID-19 cases using chest CT scans. Most of the state-of-the-art models demand a huge amount of parameters which often suffer from overfitting in the presence of limited training samples such as chest CT data and thereby, reducing the detection performance. To handle these issues, in this paper, a lightweight multi-scale CNN called LiMS-Net is proposed. The LiMS-Net contains two feature learning blocks where, in each block, filters of different sizes are applied in parallel to derive multi-scale features from the suspicious regions and an additional filter is subsequently employed to capture discriminant features. The model has only 2.53M parameters and therefore, requires low computational cost and memory space when compared to pretrained CNN architectures. Comprehensive experiments are carried out using a publicly available COVID-19 CT dataset and the results demonstrate that the proposed model achieves higher performance than many pretrained CNN models and state-of-the-art methods even in the presence of limited CT data. Our model achieves an accuracy of 92.11% and an F1-score of 92.59% for detection of COVID-19 from CT scans. Further, the results on a relatively larger CT dataset indicate the effectiveness of the proposed model.

Self-testing for COVID-19 in Durban and Eastern Cape, South Africa: a qualitative inquiry targeting decision-takers

ABSTRACT Innovative diagnostic solutions are essential to improve COVID-19 case detection and slow its spread in resource-constrained settings. To understand how South African communities may utilise rapid SARS-CoV-2 antigen self-testing and react to self-test results, we conducted a qualitative study, involving semi-structured interviews and focus group discussions, of healthcare workers, representatives of civil society groups, and potential self-testing implementors. A sex- and location-sensitive thematic analysis approach was used to assess how 52 decision-takers on self-testing roll-out in South Africa perceive the value and utility of this innovative diagnostic approach. Informants suggested South Africans might value a device that allows them to self-test in private, at their own convenience, while avoiding the risk of social stigma and having to wait for COVID-19 test results in a facility. They also emphasised the need for awareness and sensitisation campaigns and to ensure pre-/post-self-test counselling services are easily accessible. Collaboration with traditional leaders and community-based organisations would improve results communication and linkage to counselling and confirmatory testing. SARS-CoV-2 self-testing was perceived to be acceptable to a population already sensitised to the use of HIV self-testing, being a decentralised solution that would help reduce the incidence of COVID-19 and prevent any further deterioration of socio-economic indicators.

Development and evaluation of low-volume tests to detect and characterize antibodies to SARS-CoV-2.

Low-volume antibody assays can be used to track SARS-CoV-2 infection rates in settings where active testing for virus is limited and remote sampling is optimal. We developed 12 ELISAs detecting total or antibody isotypes to SARS-CoV-2 nucleocapsid, spike protein or its receptor binding domain (RBD), 3 anti-RBD isotype specific luciferase immunoprecipitation system (LIPS) assays and a novel Spike-RBD bridging LIPS total-antibody assay. We utilized pre-pandemic (n=984) and confirmed/suspected recent COVID-19 sera taken pre-vaccination rollout in 2020 (n=269). Assays measuring total antibody discriminated best between pre-pandemic and COVID-19 sera and were selected for diagnostic evaluation. In the blind evaluation, two of these assays (Spike Pan ELISA and Spike-RBD Bridging LIPS assay) demonstrated >97% specificity and >92% sensitivity for samples from COVID-19 patients taken >21 days post symptom onset or PCR test. These assays offered better sensitivity for the detection of COVID-19 cases than a commercial assay which requires 100-fold larger serum volumes. This study demonstrates that low-volume in-house antibody assays can provide good diagnostic performance, and highlights the importance of using well-characterized samples and controls for all stages of assay development and evaluation. These cost-effective assays may be particularly useful for seroprevalence studies in low and middle-income countries.

Detection of COVID-19 Cases Based on Deep Learning with X-ray Images

Since the outbreak of COVID-19, the coronavirus has caused a massive threat to people’s lives. With the development of artificial intelligence technology, identifying key features in medical images through deep learning, infection cases can be screened quickly and accurately. This paper uses deep-learning-based approaches to classify COVID-19 and normal (healthy) chest X-ray images. To effectively extract medical X-ray image features and improve the detection accuracy of COVID-19 images, this paper extracts the texture features of X-ray images based on the gray level co-occurrence matrix and then realizes feature selection by principal components analysis (PCA) and t-distributed stochastic neighbor embedding (T-SNE) algorithms. To improve the accuracy of X-ray image detection, this paper designs a COVID-19 X-ray image detection model based on the multi-head self-attention mechanism and residual neural network. It applies the multi-head self-attention mechanism to the residual network bottleneck layer. The experimental results show that the multi-head self-attention residual network (MHSA-ResNet) detection model has an accuracy of 95.52% and a precision of 96.02%. It has a good detection effect and can realize the three classifications of COVID-19 pneumonia, common pneumonia, and normal lungs, proving the method’s effectiveness and practicability in this paper.

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.

Detection of COVID-19 Cases from Chest X-Rays using Deep Learning Feature Extractor and Multilevel Voting Classifier

Purpose: During the current pandemic scientists, researchers, and health professionals across the globe are in search of new technological methods for tackling COVID-19. The magnificent performance reported by machine learning and deep learning methods in the previous epidemic has encouraged researchers to develop systems with these methods to diagnose COVID-19. Methods: In this paper, an ensemble-based multi-level voting model is proposed to diagnose COVID-19 from chest x-rays. The multi-level voting model proposed in this paper is built using four machine learning algorithms namely Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM) with a linear kernel, and K-Nearest Neighbor (KNN). These algorithms are trained with features extracted using the ResNet50 deep learning model before merging them to form the voting model. In this work, voting is performed at two levels, at level 1 these four algorithms are grouped into 2 sets consisting of two algorithms each (set 1 — SVM with linear kernel and LR and set 2 — RF and KNN) and intra set hard voting is performed. At level 2 these two sets are merged using hard voting to form the proposed model. Results: The proposed multilevel voting model outperformed all the machine learning algorithms, pre-trained models, and other proposed works with an accuracy of 100% and specificity of 100%. Conclusion: The proposed model helps for the faster diagnosis of COVID-19 across the globe.