A Survey of Deep Learning Techniques for the Analysis of COVID-19 and their usability for Detecting Omicron

The Coronavirus (COVID-19) outbreak in December 2019 has drastically affected humans worldwide, creating a health crisis that has infected millions of lives and devastated the global economy. COVID-19 is ongoing, with the emergence of many new strains. Deep learning (DL) techniques have proven helpful in efficiently analysing and delineating infectious regions in radiological images. This survey paper draws a taxonomy of deep learning techniques for detecting COVID-19 infection in radiographic imaging modalities Chest X-Ray, and Computer Tomography. DL techniques are broadly categorised into classification, segmentation, and multi-stage approaches for COVID-19 diagnosis at the image and region-level analysis. These techniques are further classified as pre-trained and custom-made Convolutional Neural Network architectures. Furthermore, a discussion is drawn on radiographic datasets, evaluation metrics, and commercial platforms provided for detection. In the end, a brief look is paid to emerging ideas, gaps in existing research, and challenges in developing diagnostic techniques. This survey provides insight into the promising areas of research in DL and is likely to guide the research community on the upcoming development of deep learning techniques for COVID-19. This will pave the way to accelerate the research in designing customised DL-based diagnostic tools for effectively dealing with new variants of COVID-19 and emerging challenges. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

Detection of SARS-CoV-2 by RT-LAMP assay in Human COVID-19 patients

Background: The novel COVID-19 outbreak has infected human population all around the world. Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) diagnosis in a rapid manner remains challenging for health care professionals. Currently, RT-qPCR technique is extensively practiced in SARS-CoV-2 diagnosis and is considered as gold standard. The constraints of RT-qPCR, high cost and need for trained technician, longer detection time, highlighted the need for alternate healthcare diagnostic approaches. They follow the WHO assured standard and offer the health-care sector optimism. One of them is the Loop Mediated isothermal amplification system (LAMP). There is no need for costly equipment like thermal cycler since LAMP assay is performed at a fixed temperature. It can also be implemented as a point of care testing device. RT-LAMP is one of the extensively used isothermal amplification system in pathogen diagnostics.Aims: The current study aims to validate and standardize RT-LAMP assay for rapid diagnosis of SARS-CoV-2 in both lab and field conditions. The reactions can be carried out using a heating vessel including the use of a water bath and end-point detection by colorimetry. A rising middle ground of tiny, more portable technology, that provides most of the capability at less cost and time.Methods and Results: 20 Samples were taken from COVID-19 positive patients. RNA extraction from COVID-19 samples was followed up by one-step reverse transcription and loop-mediated isothermal amplification (LAMP). LAMP primers were designed to amplify the conserved regions of SARS-COV-2 specific genes. The target regions for primer design were selected after genome-wide sequence alignment of SARS-CoV-2 strains isolated in various regions of the world i.e., Europe, Africa, Asia, and North America. RT-LAMP assays were performed at the specific incubation temperature (60°C) for 50 minutes. Assay was optimized as per consumable compatibility, COVID template integrity, primer concentration, template concentration, primer ratio, testing time etc. Sensitivity and specificity of the assay was elucidated. Finally, different end-point analysis i.e., Agarose Gel Electrophoresis and Colorimetry have been used to interpret the results.Conclusion: RT-LAMP assay has shown to be a quick and accurate diagnostic method that can be put to use for SARS-CoV-2 detection in laboratories and Point-of- Care settings. © 2022 IEEE.

EVALUATING LEARNING EXPERIENCE AND EMOTIONAL TRIGGERS OF VIRTUAL LEARNING ENVIRONMENTS (VLES) USING PSYCHOGALVANIC REFLEXES AND BEHAVIOURAL ANALYSIS

Virtual Environments (VEs) are on the rise as an instrument in various sectors involving emotional states and educational research. Studies till date have tried to explore the effectiveness of VR in a variety of emotional health interventions, treatment of learning phobias, and providing virtual support to students worldwide. Research has demonstrated that VR immersive environments and VR experiences create a significant impact on the users' psyche. A learning experience is related to the emotional state of the person (O'Regan, K. (2003). Therefore, it would be interesting to study the influence of VR experience on the emotional states of the learners. Students around the globe were already struggling with emotional crises even before the pre-covid situation as reported by multiple agencies but now the situation has turned more grievous. Here comes the need for magnified learning experiences in virtual learning environments (VLEs). This study investigates the impact of two different VR-3D learning environments. It draws a comparison between students' emotional states, VR experience, and VR design elements using neurophysiological tools like Galvanic Skin Response (GSR) and self-reporting questionnaires. In the experiment, participants were asked to go through two different VR learning simulations and their physiological responses were recorded for analysis. The two simulations were differentiated based on space and interaction design elements. The study suggests that well-designed Virtual 3D-Environments in an educational setup can help students in reducing stress levels and ways how we can elicit positive emotions and facilitate a better learning experience. © Proceedings of the 24th International Conference on Engineering and Product Design Education: Disrupt, Innovate, Regenerate and Transform, E and PDE 2022. All rights reserved.

A Federated Learning Approach to Pneumonia Detection

Pneumonia Detection has been a real problem for the last few centuries. Detecting Pneumonia has been a job for the skilled, such as doctors and medical practitioners. Visiting doctors in this time in many countries is very tough with Covid-19 on the rise and stricter lockdown regulations. Deep Learning has helped build many systems and algorithms over the years to detect pneumonia using X-ray images. Such Deep Learning models are first trained on many X-ray images that would be collected from multiple hospitals and diagnostic centers and then can be deployed centrally for people to use them. However, building such models is impeded by the problem of garnering mass data from hospitals due to data confidentiality between patients and hospitals. For that, we propose a system where detecting Pneumonia would be done using a Deep Learning model with a Federated Learning approach and achieve an accuracy of around 90%. This will build a central model by training local models in different hospitals with their own data, maintaining all patient data privacy. © 2021 IEEE.

Factors Affecting Willingness to Receive COVID-19 Vaccine Among Adults: A Cross-sectional Study in Bangladesh

The COVID-19 vaccine has been made available for emergency use in Bangladesh. However, willingness to receive the vaccine may be affected by varying factors across the country. Therefore, this study aimed to investigate the factors that influence willingness to receive the vaccine among Bangladeshi adults. A population-based cross-sectional online survey was conducted among a sample of 1,725 Bangladesh adults (age 18 years and older). The statistical analysis included univariate, bivariate and multivariate regression model. Findings show that 85% (n = 1463) of respondents were willing to receive the vaccine. Respondents with 1–2 children (aOR: 1.77, 95% CI: 1.00–3.13, P =. 048), perceived risk of being infected (aOR: 1.48, 95% CI: 1.03–2.14, P =. 03), perceived impact on daily life (aOR: 2.53, 95%CI: 1.45–4.44, P =. 001), history of co-morbidities (aOR: 2.04, 95% CI: 1.37–3.04, P <. 01), price of the vaccine (aOR: 3.58, 95% CI: 2.34–5.47), physician’s recommendation to receive vaccine (aOR: 2.06, 95% CI: 1.38–3.06, P <. 01), vaccines supplied by government (aOR: 2.31, 95% CI: 1.64–3.25, P <. 01) were found to be motivating factors for willingness to receive the vaccine. Findings indicate that willingness to receive the vaccine is likely to be affected by socio-demographic, and health system factors. This should be carefully considered in the rollout of the vaccination plans in Bangladesh. © 2021 SAGE Publications.

Beyond the ICU: The association between post intensive care syndrome and survivors of severe COVID-19

Introduction: Severe COVID-19 is associated with high rates of intensive care unit (ICU) delirium and prolonged mechanical ventilation due to acute respiratory distress syndrome. We hypothesize that COVID-19 ICU survivors are at high risk for developing post-intensive care syndrome (PICS), namely long-term cognitive, psychiatric, and physical impairments which persist after ICU hospitalization. Methods: We conducted a prospective observational study at two sites of 49 patients who met the following inclusion criteria: age 18 or older, admitted to the medical ICU, had a positive COVID-19 nasopharyngeal swab, and attended at least one outpatient visit at the Indiana University School of Medicine's Critical Care Recovery Center (CCRC). Patients were administered assessments by trained personnel of cognition (Mini Mental State Exam [MMSE] or Montreal Cognitive Assessment [MoCA]) and self-reported scales for depression (Patient Health Questionarre-9 [PHQ-9]), anxiety (General Anxiety Disorder-7 [GAD-7]), post-traumatic stress disorder (Post Traumatic Symptom Scale-10 [PTSS-10]), quality of life and physical functioning (EuroQol-5D Quality of Life questionnaire [EQ5D QoL], EuroQol-5D5L [EQ5D5L], Healthy Age Brain Care Monitor Self Report [HABC-SR]). Descriptive statistics were computed as frequency, mean, and standard deviation using SPSS. Results: A total of 49 patients were included in the study with 30.6% female, mean age of 51.89 (SD 13.95). Nearly all patients (93.9%) required mechanical ventilation while hospitalized. The average hospital length of stay was 23.06 days (SD 12.3) and the mean days from discharge to initial evaluation in the CCRC was 87.3 (SD 43.2). Scores suggestive of mild cognitive impairment were seen in 23.3% (n = 36) of patients who performed the MMSE and in 37.5% (n = 16) of patients who completed the MoCA. Of the patients who participated in the PHQ-9, 33.3% (n = 36) had an abnormal score consistent with at least mild depression. 21.1% (n = 47) of the patients had abnormal scores on the functional subscale of the HABC-SR. Most notably, the mean quality of life score was 67.8 (SD 19.08) using the EQ5D QoL. Conclusions: ICU hospitalization for severe COVID-19 symptoms may be associated with long-term impairments in cognition, mental health, and physical function consistent with PICS. Larger observational cohort studies are needed to have a deeper understanding of COVID-19-related PICS, risk factors for COVID-19 PICS, and factors affecting recovery from PICS. These results emphasize the importance of continued focused assessment of ICU survivors to help identify and treat impairments in these domains in order to improve quality of life.