Electronic Nose Development and Preliminary Human Breath Testing for Rapid, Non-Invasive COVID-19 Detection.

We adapted an existing, spaceflight-proven, robust "electronic nose" (E-Nose) that uses an array of electrical resistivity-based nanosensors mimicking aspects of mammalian olfaction to conduct on-site, rapid screening for COVID-19 infection by measuring the pattern of sensor responses to volatile organic compounds (VOCs) in exhaled human breath. We built and tested multiple copies of a hand-held prototype E-Nose sensor system, composed of 64 chemically sensitive nanomaterial sensing elements tailored to COVID-19 VOC detection; data acquisition electronics; a smart tablet with software (App) for sensor control, data acquisition and display; and a sampling fixture to capture exhaled breath samples and deliver them to the sensor array inside the E-Nose. The sensing elements detect the combination of VOCs typical in breath at parts-per-billion (ppb) levels, with repeatability of 0.02% and reproducibility of 1.2%; the measurement electronics in the E-Nose provide measurement accuracy and signal-to-noise ratios comparable to benchtop instrumentation. Preliminary clinical testing at Stanford Medicine with 63 participants, their COVID-19-positive or COVID-19-negative status determined by concomitant RT-PCR, discriminated between these two categories of human breath with a 79% correct identification rate using "leave-one-out" training-and-analysis methods. Analyzing the E-Nose response in conjunction with body temperature and other non-invasive symptom screening using advanced machine learning methods, with a much larger database of responses from a wider swath of the population, is expected to provide more accurate on-the-spot answers. Additional clinical testing, design refinement, and a mass manufacturing approach are the main steps toward deploying this technology to rapidly screen for active infection in clinics and hospitals, public and commercial venues, or at home.

Dhanvantari: An intelligent diagnosis tool to classify malignant skin disease and Lung conditions using Deep Learning

The pandemic due to COVID-19 has created a huge gap in the medical field leading to a reduction in the efficacy of this field. To improve this situation, we propose a solution 'Dhanvantari'. A medical app that is powered by Artificial Intelligence performs a task where the diagnosis is done by computer vision observing CT scans, MRIs, and also some skin diseases. Dhanvantari focuses mainly on the combination of CT scans and skin disease classifications. In this paper, a novel approach has been proposed for developing a supervised model for the classification of skin disease and lung ailments (that is to identify a healthy lung with an infected lung due to pneumonia) through analog to digital image processing. This app helps the user in analyzing conditions and if any abnormalities are detected then alerts the user about it. This is a primary service care application developed to reduce the number of false cases hence only alerting the user if a complication is observed. The proposed approach utilizes a camera and computational device or mobile. Two datasets from Kaggle that had 9 classes of malignant skin disease and 2 lung conditions were used to train the model. Design, training, and the testing of the algorithm were performed with the help of colab. Generally, a standard test for malignant skin disease requires sample gathering and conduction of various tests. All these consume a lot of time. The other method is laser or radiation-induced procedures that might be harmful and lead to exposure of unwanted radiation to patients. The proposed 'Dhanvantari' requires the patient/user to use a camera to take a picture of the affected area (in case of skin condition) and it provides the primary diagnosis. This approach aids the doctors in quick decision-making during diagnosis and reduce the time per patient which in house helps them to prioritize patients. © 2022 IEEE.

Research on Mask Wearing Recognition Based on Deep Learning

Since the outbreak of COVID-19 epidemic, research results have shown that the COVID-19 transmitted by droplets, and the most effective means of epidemic prevention is to wear masks. In public places where crowds gather, it is particularly important to use technical means to detect the situation of wearing masks, and remind people to wear masks in time to prevent cross-infection. This paper mainly starts with the target detection and tracking technology in the field of computer vision, and takes the recognition of whether to wear a mask as the entry point. Using python as the development tool, based on the convolutional neural network, the YOLOv2 algorithm is used as the core algorithm, and the ResNet50 network structure is built. Compared with other existing system test experiments, we can see that the system we built has better detection performance. © 2022 Association for Computing Machinery.

A COVID-19 Infection Rate Detection Technique Using Bayes Probability

The main objective of this paper is to detect the infection rate of the SARS-Cov-2 virus among patients who are suffering from COVID with different symptoms. In this work, some data inputs from the intended patients (like contact with any COVID infected person and any COVID patient within 1 km.) are collected in the form of a questionnaire and then applied Naïve Bayes probabilistic technique to evaluate the probability of how much that patient is affected in this deadly virus. Following this process, we collect sample data of 80 patients and apply the proposed analysis process using the C programming language. This approach also shows the comparison for different test cases with respect to the feedbacks of actual patient data analysis. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Mobile Application for the Timely Detection of Potential COVID-19 Infections

The objective of this study is to determine user acceptance of a mobile application for the timely detection of possible COVID-19 infections in the city of Cajamarca. For this purpose, the mobile application Covid Alerta (Covid Alert) was developed for devices with the Android operating system. The OpenUp software development methodology was used for the development of this application. The applied, quantitative, exploratory research used 2 survey forms: one to measure how the detection of COVID-19 was carried out in the city of Cajamarca, and another to measure the impact of using a mobile application to detect infected contacts. The results indicated that the most reliable screening tests are molecular tests;in addition, 85% of respondents felt much safer receiving alerts of infected contacts on their mobile devices. Likewise, 88.5% indicated confidently that the application complies with registering and reporting infected contacts. This shows that 88.8% of users accepted the use of mobile applications for the timely detection of possible COVID-19 infections. © 2022 IEEE.

A COVID-19 Infection Rate Detection Technique Using Bayes Probability

The main objective of this paper is to detect the infection rate of the SARS-Cov-2 virus among patients who are suffering from COVID with different symptoms. In this work, some data inputs from the intended patients (like contact with any COVID infected person and any COVID patient within 1 km.) are collected in the form of a questionnaire and then applied Naïve Bayes probabilistic technique to evaluate the probability of how much that patient is affected in this deadly virus. Following this process, we collect sample data of 80 patients and apply the proposed analysis process using the C programming language. This approach also shows the comparison for different test cases with respect to the feedbacks of actual patient data analysis. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Bayesian Learning of Shifted-Scaled Dirichlet Mixture Models and Its Application to Early COVID-19 Detection in Chest X-ray Images.

Early diagnosis and assessment of fatal diseases and acute infections on chest X-ray (CXR) imaging may have important therapeutic implications and reduce mortality. In fact, many respiratory diseases have a serious impact on the health and lives of people. However, certain types of infections may include high variations in terms of contrast, size and shape which impose a real challenge on classification process. This paper introduces a new statistical framework to discriminate patients who are either negative or positive for certain kinds of virus and pneumonia. We tackle the current problem via a fully Bayesian approach based on a flexible statistical model named shifted-scaled Dirichlet mixture models (SSDMM). This mixture model is encouraged by its effectiveness and robustness recently obtained in various image processing applications. Unlike frequentist learning methods, our developed Bayesian framework has the advantage of taking into account the uncertainty to accurately estimate the model parameters as well as the ability to solve the problem of overfitting. We investigate here a Markov Chain Monte Carlo (MCMC) estimator, which is a computer-driven sampling method, for learning the developed model. The current work shows excellent results when dealing with the challenging problem of biomedical image classification. Indeed, extensive experiments have been carried out on real datasets and the results prove the merits of our Bayesian framework.

SARS-CoV-2 Infections in the World: An Estimation of the Infected Population and a Measure of How Higher Detection Rates Save Lives.

This paper provides an estimation of the accumulated detection rates and the accumulated number of infected individuals by the novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Worldwide, on July 20, it has been estimated above 160 million individuals infected by SARS-CoV-2. Moreover, it is found that only about 1 out of 11 infected individuals are detected. In an information context in which population-based seroepidemiological studies are not frequently available, this study shows a parsimonious alternative to provide estimates of the number of SARS-CoV-2 infected individuals. By comparing our estimates with those provided by the population-based seroepidemiological ENE-COVID study in Spain, we confirm the utility of our approach. Then, using a cross-country regression, we investigated if differences in detection rates are associated with differences in the cumulative number of deaths. The hypothesis investigated in this study is that higher levels of detection of SARS-CoV-2 infections can reduce the risk exposure of the susceptible population with a relatively higher risk of death. Our results show that, on average, detecting 5 instead of 35 percent of the infections is associated with multiplying the number of deaths by a factor of about 6. Using this result, we estimated that 120 days after the pandemic outbreak, if the US would have tested with the same intensity as South Korea, about 85,000 out of their 126,000 reported deaths could have been avoided.

Serologic Detection of SARS-CoV-2 Infections in Hemodialysis Centers: A Multicenter Retrospective Study in Wuhan, China.

RATIONALE & OBJECTIVE: Patients receiving maintenance hemodialysis (MHD) are highly vulnerable to infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The current study was designed to evaluate the prevalence of SARS-CoV-2 infection based on both nucleic acid testing (NAT) and antibody testing in Chinese patients receiving MHD. STUDY DESIGN: Cross-sectional study. SETTING & PARTICIPANTS: From December 1, 2019, to March 31, 2020, a total of 1,027 MHD patients in 5 large hemodialysis centers in Wuhan, China, were enrolled. Patients were screened for SARS-CoV-2 infection by symptoms and initial computed tomography (CT) of the chest. If patients developed symptoms after the initial screening was negative, repeat CT was performed. Patients suspected of being infected with SARS-CoV-2 were tested with 2 consecutive throat swabs for viral RNA. In mid-March 2020, antibody testing for SARS-CoV-2 was obtained for all MHD patients. EXPOSURE: NAT and antibody testing results for SARS-CoV-2. OUTCOMES: Morbidity, clinical features, and laboratory and radiologic findings. ANALYTICAL APPROACH: Differences between groups were examined using t test or Mann-Whitney U test, comparing those not infected with those infected and comparing those with infection detected using NAT with those with infection detected by positive serology test results. RESULTS: Among 1,027 patients receiving MHD, 99 were identified as having SARS-CoV-2 infection, for a prevalence of 9.6%. Among the 99 cases, 52 (53%) were initially diagnosed with SARS-CoV-2 infection by positive NAT; 47 (47%) were identified later by positive immunoglobulin G (IgG) or IgM antibodies against SARS-CoV-2. There was a spectrum of antibody profiles in these 47 patients: IgM antibodies in 5 (11%), IgG antibodies in 35 (74%), and both IgM and IgG antibodies in 7 (15%). Of the 99 cases, 51% were asymptomatic during the epidemic; 61% had ground-glass or patchy opacities on CT of the chest compared with 11.6% among uninfected patients (P<0.001). Patients with hypertensive kidney disease were more often found to have SARS-CoV-2 infection and were more likely to be symptomatic than patients with another primary cause of kidney failure. LIMITATIONS: Possible false-positive and false-negative results for both NAT and antibody testing; possible lack of generalizability to other dialysis populations. CONCLUSIONS: Half the SARS-CoV-2 infections in patients receiving MHD were subclinical and were not identified by universal CT of the chest and selective NAT. Serologic testing may help evaluate the overall prevalence and understand the diversity of clinical courses among patients receiving MHD who are infected with SARS-CoV-2.