ABSTRACT
Automatic lung infection segmentation in computed tomography (CT) scans can offer great assistance in radiological diagnosis by improving accuracy and reducing time required for diagnosis. The biggest challenges for deep learning (DL) models in segmenting infection region are the high variances in infection characteristics, fuzzy boundaries between infected and normal tissues, and the troubles in getting large number of annotated data for training. To resolve such issues, we propose a Modified U-Net (Mod-UNet) model with minor architectural changes and significant modifications in the training process of vanilla 2D UNet. As part of these modifications, we updated the loss function, optimization function, and regularization methods, added a learning rate scheduler and applied advanced data augmentation techniques. Segmentation results on two Covid-19 Lung CT segmentation datasets show that the performance of Mod-UNet is considerably better than the baseline U-Net. Furthermore, to mitigate the issue of lack of annotated data, the Mod-UNet is used in a semi-supervised framework (Semi-Mod-UNet) which works on a random sampling approach to progressively enlarge the training dataset from a large pool of unannotated CT slices. Exhaustive experiments on the two Covid-19 CT segmentation datasets and on a real lung CT volume show that the Mod-UNet and Semi-Mod-UNet significantly outperform other state-of-theart approaches in automated lung infection segmentation. IEEE
ABSTRACT
The breakout of the COVID-19 infection caused a worldwide pandemic in recent years. Traditional healthcare measures and infrastructure are unable to properly manage the detection, prevention and treatment of the infection. Since the onset of the pandemic, researchers have tried to implement various deep learning approaches to counter COVID-19 with much success. Novel architectures and new ideas are being developed to this day. Motivated by this, we have reviewed the different ways deep learning can be applied in real-world COVID-19 problems. We present the challenges these implementations face. Finally, we discuss the future directions that can be taken to improve upon these DL methods to control the COVID-19 pandemic as well as future pandemics, which will result in a healthier and safer environment. © 2022 IEEE.
ABSTRACT
In this paper, we study the long memory behavior of the hourly cryptocurrency returns during the COVID-19 pandemic period. Initially, we apply different tests against the spurious long memory, with the results indicating the presence of true long memory for most cryptocurrencies. Yet, using the multivariate test, the series are found to be contaminated by level shifts or smooth trends. Then, we adopt the wavelet-based multivariate long memory approach suggested by Achard and Gannaz (2016) to model their long memory connectivity. The findings indicate a change in persistence for all series during the sample period. The fractal connectivity clustering indicates a similarity among Ethereum (ETH) and Litecoin (LTC), Monero (XMR), Bitcoin (BTC), and EOC token (EOS), while Stellar (XLM) is clustered away from the remaining series, indicating the absence of any interdependence with other crypto returns. Overall, shocks arising from COVID-19 crisis have led to changes in long-run correlation structure. © 2022 Elsevier B.V.
ABSTRACT
COVID-19 came with a sudden surge, harshly affecting the day-to-day lives of the entire world. Social and economic problems affected almost every nation, wreaking havoc on people's health, society, and economy everywhere. Although the pandemic is currently in control, the emergence of another pandemic is not unlikely. As technological breakthroughs accelerate, the possibility of controlling virological dangers becomes highly plausible. Better virus containment is attainable with the confluence of technologies such as Blockchain and AI. The newly growing fields and application cases of futuristic technologies for tackling upcoming pandemics are emerging. Several researchers are contributing to COVID-19 management with current and futuristic technologies, and such tools have room for additional improvement. This paper extensively highlights the work done in tackling COVID-19 using Blockchain and AI, illustrating the role of this collaborative approach in dealing with biological threats. We also discuss the prospects and obstacles in combining these technologies to tackle COVID-19-like situations. © 2022 IEEE.
ABSTRACT
Aim: To determine the level of attitude and awareness regarding biomedical waste management (BMWM) policy and practice among healthcare workers (HCWs) in tertiary level hospitals in Uttar Pradesh. Materials and methods: This is a questionnaire-based study which was done among 1,000 members of the hospital including undergraduate students, doctors (faculty members and postgraduate students), and class IV employees (cleaners and maintenance personnel). It consisted a total of 33 questions intended to obtain information about knowledge of BMWM practices grouped under three headings: (a) knowledge of biomedical waste (BMW) generation, segregation, and categorization;(b) knowledge of BMWM practice in hospitals on procedure and disposal;and (c) awareness regarding best management practices in dental office. Results: The mean scores were calculated and it was found that regarding knowledge of BMW generation, segregation, and categorization, the doctors had significantly more knowledge and dental students were having comparatively least knowledge among all groups, whereas mean value of attitude of BMWM practice in hospitals on procedure and disposal and practice regarding best waste management in dental office has shown statistically significant results with doctors. Conclusion: This study showed that there was a good, satisfactory, and poor level of knowledge, attitude, and practice about BMW generation hazards, legislation, and management among doctors (faculty members and postgraduate students), class IV employees, and dental students, respectively. Clinical significance: The awareness of these BMWM laws among the public, as well as development of policies and enforcement that respect those laws, is essential. Appropriate measures should be taken to minimize hazardous waste where possible or action should be taken to ensure that all generated waste is managed according to the correct norms and regulations. © The Author(s). 2022.
ABSTRACT
Background:Medical interns develop apprehensions about the vulnerability of their exposure to infection while treating Covid-19 patients which may further affect their work pattern and efficiency. Studies have shown that the outbreak of infectious diseases would result in mental health issues. In view of this our study aims to assess the psychosocial factors such as anxiety, depression, stress, relationship with peers and change in personal roles among medical interns of a private medical college. Methodology:This cross-sectional was carried among 248 medical interns working in tertiary care hospitals by using simple random sampling method. Depression, anxiety, and stress were assessed using a standardized 21-item depression, anxiety, and stress questionnaire (DASS– 21). To acquire information regarding the study participants' socio-demographic data and social elements, a pretested semi-structured questionnaire was used. Results:The overall prevalence of Depression [58%], Anxiety [70%] and Stress [44%] were found among the 248 study participants.Around [70.6%] of the study participants reported thattheir social lifehad been affected. The prevalence of various factors associated with depression, anxiety and stress were assessed. Conclusion:This study reports higher levels of psychosocial distress among the study participants. Adequate knowledge about the pandemic and stress management measures will be the top priority among these budding medicos during such unfavourable pandemic situations.
ABSTRACT
In this paper, we study the long memory behavior of Bitcoin, Litecoin, Ethereum, Ripple, Monero, and Dash with a focus on the COVID-19 period. Initially, we apply a time-varying Lifting method to estimate the Hurst exponent for each cryptocurrency. Then we test for a change in persistence over time. To model the multivariate con-nectivity, the wavelet-based multivariate long memory approach proposed by Achard and Gannaz (2016) is implemented. Our results indicate a change in the long-range dependence for the majority of cryptocurrencies, with a noticeable downward trend in persistence after the 2017 bubble and then a dramatic drop after the outbreak of COVID-19. The drop in persistence after COVID-19 is further illustrated by the Fractal connectivity matrix obtained from the Wavelet long-memory model. Our findings provide important implications regarding the evolution of market efficiency in the cryptocurrency market and the associated fractal structure and dy-namics of the crypto prices over time
ABSTRACT
The pandemic that arose due to the novel Corona Virus Disease of 2019 (COVID) has become the biggest challenge of all time. The entire world’s population has stormed social media to express their opinions, emotions, and sentiments. This manuscript implements classical machine and deep learning approaches with static and stacked word embeddings to identify the sentiments of the COVID-19 tweets extracted from Twitter. The problem we have tackled in this manuscript is the multi-class classification problem for three and five classes, respectively. Our proposed deep learning model with stacked word embeddings has outperformed the individual static pre-trained embeddings representation, classical machine, and deep learning approaches altogether. The proposed model has proven useful in complex classification tasks such as identifying classes belonging to the same group of sentiments namely Extremely Negative and Negative, Extremely Positive and Positive. The experimental results also show the superior performance of stacked word embeddings for the peculiar contextual semantic comprehension from small tweets and dealing with the unbalancedness of the experimental dataset. We achieved the accuracy with stacked embeddings with accuracy being 73.01% and 84.25% for three and five classes, respectively. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
As with many aspects of teaching, the COVID-19 pandemic forced soil judging teams to attempt new strategies towards achieving student learning outcomes. Soil judging Regions IV and V hosted remote regional contests in October 2020 in place of traditional, in-person contests typically held each fall. We conducted pre- and post-contest surveys to assess student learning outcomes, attitudes, and reflections on the remote contest experience compared to past, in-person contest experiences. We received 108 total responses from students who participated in the Region IV and Region V remote soil judging contests (>80% response rate). In self-reported learning outcomes, there were no significant gains post-contest and there were minimal differences between students in Regions IV and V. Female students, students with more soil judging experience, and students who had taken more soil science courses agreed more strongly that soil science is important, that they planned to pursue careers in soil science, and that they gained important skills from soil judging. Finally, students who previously participated in contests reported that they gained more knowledge and enjoyed in-person contests more than the remote contests held in Fall 2020. Thus, while it is possible to replicate some aspects of the soil judging experience in a remote contest, other aspects that are critical to student engagement are lost when teams are unable to gather at the contest location and examine soils in the field. © 2021 The Authors. Natural Sciences Education published by Wiley Periodicals LLC on behalf of American Society of Agronomy
ABSTRACT
IMPORTANCE: In December 2019, an infectious disease caused by severe acute respiratory syndrome coronavirus (SARS-CoV-2) emerged. There remains limited information regarding the epidemiology and clinical features of pediatric patients affected by COVID-19, particularly in the pulmonary sub-population. OBJECTIVE: Describe the clinical course of pediatric pulmonary patients with COVID-19 throughout the initial wave of infection at a single pediatric center. METHODS: Retrospective chart review was conducted on 1,350 patients, ≤ 35 years who tested positive for SARS-CoV-2 infection between March 1 and August 31, 2020. Patients followed by our pulmonary group, and evaluated at least once in the three years preceding study completion, were identified for additional chart review. Demographics, pulmonary diagnoses, co-morbidities, presenting symptoms, clinical course and management were collected for analysis. RESULTS: 70 pulmonary patients (mean age 8.3 years, range 8 months to 23 years;45% male;44% Black of African American;29% Hispanic or Latino) were identified from 1,350 patients who tested positive for COVID-19 via nasopharyngeal PCR testing through our hospital system. Most frequently reported symptoms were fever (49%), cough (49%), and nasal congestion (29%). Thirteen patients (19%, mean age 9.2 years, range 12 months to 18 years) required inpatient treatment for symptoms related to SARS-CoV-2 infection, one asymptomatic patient tested positive while admitted. Most common pulmonary diagnoses of those requiring admission were asthma (57%), prematurity (29%), sleepdisordered breathing (29%), and respiratory disorders with positive pressure requirement (29%). For those requiring inpatient care, extra-pulmonary co-morbidities included chronic neurological disorders (71%), gastrointestinal disease (43%), and allergic rhinitis (36%). Disease severity was defined as asymptomatic (17%), mild (67%), moderate (6%), severe (6%), or critical (3%). Mild disease was defined as cases managed outpatient or those admitted for observation and supportive care;moderate as those admitted for medical intervention or respiratory support via supplemental oxygen or high-flow nasal cannula;severe as those who received noninvasive ventilation or an increase in baseline respiratory support;critical were patients who received mechanical ventilation. Inpatient complications associated with SARS-CoV-2 included superinfection, thrombosis, refractory hypoxemia and tracheostomy placement. Seven experienced complications and required intensive care unit services;two required tracheostomy. No deaths were reported. CONCLUSIONS: Patients followed by our pediatric pulmonary group presented with similar symptoms compared to the general pediatric population. The majority of our patients were managed outpatient, however the rate of hospitalization was higher than those of the general pediatric population in existing studies. Of those admitted, few required invasive mechanical ventilation.
ABSTRACT
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causing COVID-19 utilizes the angiotensin-converting enzyme 2 (ACE-2) receptor of cells in order to gain entry and continue infection. Recent literature has focused on acute respiratory distress syndrome (ARDS) and other associated pulmonary complications;however, only a scarce amount of literature exists on neurological complications. Such complications also pose a high morbidity in these patients. The exact pathogenesis of nervous system involvement by COVID-19 still remains poorly understood. The aim of this article is to review the neurological symptoms seen in COVID-19 infection and discuss the probable pathogenesis, management and outcome of associated neurological complications.