CVD19-Net: An Automated Deep Learning Model for COVID-19 Screening using Chest CT Images

COVID-19 is the most recent coronavirus-related disease that has been declared a pandemic by the World Health Organization (WHO), causing a global emergency that has resulted in a large number of deaths and is rapidly spreading around the world. It causes respiratory illness and is highly contagious, putting a strain on health and medical systems worldwide. With the help of various deep learning (DL) techniques, chest CT scans are considered an effective tool for diagnosing COVID-19 because it directly affects the lungs. In addition, the visual similarities between COVID-19 and pneumonia make identification even more challenging, as COVID-19 is also a virus. In this paper, we designed a unique lightweight DL model named CVD19-Net with fewer layers as an accurate diagnostic method for COVID-19. Different regularization techniques such as dropout layers, batch normalization layers and data augmentation are injected into the CVD19-Net model to improve classification accuracy and reduce overfitting. We considered three different publicly available datasets for our experiments. (1) Dataset 1: 2482 CT images were collected;(2) Dataset 2: 7544 CT images were collected;(3) Dataset 3: 3190 CT images were collected. The experimental results show that the proposed model achieves 98.59% accuracy on dataset 1, 98.21% on dataset 2, and 95.61% on dataset 3, which is better than the existing methods. The proposed model requires less training time and storage space, which makes it computationally efficient while maintaining a high level of accuracy, which can help clinicians quickly identify COVID-19 patients. © 2022 IEEE.

Fungal osteomylitus in diabetic patients and COVID-19

Background: COVID-19 pandemic has become a big medical problem worldwide. In this era, COVID-19 along with diabetes mellitus are at an increased risk of developing opportunistic infections. This study demonstrate association of COVID-19 infection in patients having uncontrolled diabetes with the fungal osteomyelitis. Subjects and methods: This prospective cross-sectional study was done at a Nishter Institute of Dentistry, Multan. Patients diagnosed with fungal osteomyelitis of jaw bones presented during April to December 2021 were included in this study. Data was collected from the patients regarding history of the disease, clinical diagnosis, imaging findings by plain radiographs and CT scans, histopathology. Association of disease process with diabetes and COVID-19 was analyzed in SPSS. Results: Between the period April 2021 to December 2021, 23 cases presented in Nishter Institute of Dentistry Multan with fungal osteomylitus were diagnosed clinically and fungal organism was identified by immunohistochemical studies by PAS and GMA stains. 22/23 (95.6%) patients were with uncontrolled diabetes mellitus and 18/23(78.2%) gave the history of Covid 19 infection 2 to 3 months before with moderate to severe symptoms.11/23 (47.8%) gave the history of treatment with systemic steroid. Age range was 38-72 years of age with mean age 53.26. 12/23(52.1%) were males and 11/23 (47.8%) were females. 17/23 (73.9%) patients presented with pain in jaws with exposed bone and 6/23(23%) complained of pain and loose teeth in arch. In 22/23 (95.6%) involved jaw was maxilla. In one patient associated medical condition was hepatitis C virus infection also with diabetes. 2 patients were cardiac and 3 were hypertensive along with diabetes. One patient was previously treated with radiotherapy of mandible due to alveolar cancer. Only one (0.04%) patient was non diabetic. She was on chemotherapy for renal cancer. Conclusion: There is increased incidence of fungal osteomyelitis of jaws mostly maxilla in diabetic and COVID-19 infected patients. © 2022 Authors.

Based on the Classification of X-ray Images, an Effective CNN Model for COVID-19 Disease Detection

Convolutional neural networks (CNNs) in particular have achieved successful outcomes in the categorization and analysis of medical image data using artificial intelligence (AI) approaches. This research proposes a deep CNN architecture for the classification of chest X-ray images in the diagnosis of COVID-19.An efficient and precise CNN classification was difficult since there was no chest X-ray picture dataset of a size and quality that was enough.The dataset has been preprocessed in different stages using different techniques to achieve an effective training dataset for the proposed CNN model to achieve its best performance. To deal with these complexities, such as the availability of a very-small-sized, imbalanced dataset with image-quality issues, the preprocessing stages of the datasets performed in this study include dataset balancing, medical experts' image analysis, and data augmentation.Experimental findings revealed an overall accuracy of up to 99.5%, showing the proposed CNN model's strong suit in the current application domain.) Two different scenarios were used to evaluate the CNN model.In the first case, the model was tested using 100 X-ray pictures from the original, properly processed dataset, and it was 100% accurate.The model has been tested in the second scenario using an independent dataset of COVID-19 X-ray pictures.Up to 99.5 percent of the test scenario's performance was achieved.An examination of the suggested model's performance in comparison to other models has been conducted using several machine learning methods.)When the proposed model was tested using an independent testing set, it outperformed all other models both generally and specifically.

Exploring Prediction of COVID-19 and its Severity using Machine Learning

COVID-19 has crippled the lives of millions in the world and is continuously doing so without any sight of relief. Even after the roll out of effective vaccines against COVID-19 and more than half of the population inoculated, it is still a widespread concern. This has led to extensive research around the world regarding the prediction of the COVID-19 disease, its diagnosis, developing drugs for its treatment and its forecasting, etc. Machine Learning has proved its significance in almost every domain and its techniques are also being actively used against COVID-19 by the researchers giving satisfactory results. In this paper, we have highlighted some of the efficient research that have been done using machine learning techniques to predict COVID-19 disease and its severity in patients. The performance of those techniques has been discussed and analyzed. We also carried out a comparative analysis of the most common techniques used in terms of accuracy obtained by them. It has been found that Support Vector Machines, Neural Networks and K-Nearest Neighbor models give the best performance in most of the research works. © 2022 IEEE.

Responding To The Covid 19 Pandemic In A Resource Constrained Country: The Case Of Pakistan

Pakistan, like the rest of the world has not been spared by COVID-19, with the cases escalating nationwide. Being a developing country, Pakistan has had meagre resources and weak health systems to tackle the menace. We analysed the national response of Pakistan to the pandemic by critically analysing the interventions taken at community, health systems and multi-sectoral level and identifying the response gaps. The fragile health system of Pakistan performed fairly well according to its ability - the bed capacity was expanded, health professionals' capacity building strategies were adopted, telemedicine was put into practice, indigenous production of required personal protective equipment started, testing capacity was increased, and attempts were made to improve the surveillance mechanisms. However, the strategies adopted at the community level proved in-adequate. The severity of the disease was not communicated clearly to the public, religious leaders were not effectively on board, social distancing measures were not strictly followed specially during religious festivities, contact tracing was not extensively carried out specially in the rural areas - overall awareness of the community to COVID-19 remained low. The educational institutions were closed in time but the intermittent lockdown procedures and easing of transport restrictions led to community spread of the virus. Overall, Pakistan's performance has been acceptable, but community engagement and participation need to be improved.

Networked systems as witnesses: Association between content demand, human mobility and an infection spread

While non-pharmaceutical interventions (NPIs) such as stay-at-home, shelter-in-place, and school closures are considered the most effective ways to limit the spread of infectious diseases, their use is generally controversial given the political, ethical, and socioeconomic issues they raise. Part of the challenge is the non-obvious link between the level of compliance with such measures and their effectiveness. In this paper, we argue that users' demand on networked services can act as a proxy for the social distancing behavior of communities, offering a new approach to evaluate these measures' effectiveness. We leverage the vantage point of one of the largest worldwide CDNs together with publicly available datasets of mobile users' behavior, to examine the relationship between changes in user demand on the CDN and different interventions including stay-at-home/shelter-in-place, mask mandates, and school closures. As networked systems become integral parts of our everyday lives, they can act as witnesses of our individual and collective actions. Our study illustrates the potential value of this new role. © 2021 ACM.

Association of abo and rh blood groups with covid-19 pcr positive status: A case control study

Objective: To determine association of ABO and Rh blood groups with COVID-19 RT-PCR positive status. Study Design: Case control study. Place and Duration of the Study: Department of Pathology, Margalla Hospital Taxila, from Apr 2020 to Dec 2020. Methodology: The sample comprised of 436 cases and 500 controls. Out of 3936 RT-PCR done during the study duration, 436 RT-PCR positives were enrolled in study as cases. 500 age and gender matched controls were selected from same population. Study variables (age, gender, blood groups, RT-PCR result) were obtained from Hospital data (HIMS). Data was analyzed using SPSS version 25. Mean and SD was calculated for age. Frequencies were calculated for categorical variables. p-value calculated applying chi square test. Odds ratios calculated to determine association. Results: The mean age of cases was 37.3 ± 16.3. Statistically significant association was observed between age, gender and COVID-19 RT-PCR positive status. B+ blood group was most frequent both among cases (35.4%) and controls (36.2%), followed by O+ and A+. However, no significant association was observed between blood groups and COVID-19 RT-PCR positivity. Odds ratios calculated for blood group O and non-O (OR=0.95), A antigen (OR=0.97) and Rh factor (OR 0.93) among cases and controls showed week negative association. Whereas a weak positive association of B antigen + and B antigen-with PCR positivity (1.07) was observed between cases and controls. Conclusion: Susceptibility to acquire COVID-19 infection is not associated with ABO and Rh blood groups according to this study. © 2021, Army Medical College. All rights reserved.

Frequency of Depression, Anxiety and Stress among Gynae Residents during Covid Pandemic

Objective: To find the frequency of depression, anxiety and stress among Gynae residents during covid pandemic. Methodology: This Cross-sectional survey was carried out in different Teaching Hospitals of Khyber Pakhtunkhwa during the period of six months i.e from August 2020 to January 2021. After the ethical approval from the research community, data was collected from Post Graduate Gynae Residents of Teaching Hospitals. Sample size for the study was 405 participants. Depression, anxiety and gross scale shorten version DASS-21 containing 21 items was standard research to use in study i.e. depression, anxiety and stress was identified on the basis of their cutoff scores i.e. normal scores were >= 10, >= 8 and for >= 15 depression, anxiety and stress respectively. Result: In depression, 136 (34%) participants were normal followed by moderate level having frequency 121 (30.25%). In the anxiety category, 116 (29%) participants were normal followed by moderate level having frequency 101 (25.5). In the category of stress, 179 (44.75%) participants were normal followed by mild levels having frequency 106 (26.50%). Only COVID positive status was statistically significant with depression, anxiety and stress as their P-valve was 0.02 less than 0.05. Conclusion: Considerable number of post graduate Gynae trainees working in different tertiary care hospitals have varying degrees of depression, anxiety and stress due to COVID-19 pandemic.

Pattern of ABO and Rh blood groups distribution among COVID-19 patients

Objective: This study was conducted to find out the pattern of blood group distribution among Covid-19 patients in this part of world. Study Design: cross-sectional study Place and Duration of Study: This study was conducted at the department of Pathology, Margalla Hospital Taxila from April to June during first phase of Corona followed by second wave in October to December 2020. Materials and Methods: In this study, 3936 participants were included using non-purposive consecutive sampling technique, who were tested for COVID 19 by real-time reverse RT-PCR. Data was analyzed using SPSS version 26. Frequencies for different blood groups were calculated. Cross tabulation was done for RT-PCR positive and negative blood groups and chi square test of significance was applied. Results: Out of 3936, 436 (11.1%) tested positive by RT-PCR. Majority of males tested positive (64%, p=.001). Most frequent blood group among covid patients was B (38.7%, p= .001), followed by O (29.3%), A (22.7%) and AB (9.1%). Out of total 436, 399 (91.5%) were Rh positives. Conclusion: Blood group B and Rh positives were more frequent among study population;however, it doesn’t conclude that these blood groups increase susceptibility to covid infection.

Real Time Face Mask Detection System using Transfer Learning with Machine Learning Method in the Era of Covid-19 Pandemic

The rapid development of computer vision has attracted more attention to the global epidemic Covid-19 to enable human-computer interaction and improve public health services. Due to the rapid spread of the (Covid-19), various countries are facing a major health crisis. According to the World Health Organization (WHO) an effective way to protect people from Covid-19 is to wear medical masks in public areas. It is very difficult to manually monitor people in public places and detect the face mask in the video. which is mainly because the mask itself acts as an obstruction to the face detection algorithm, because there are no face signs in the mask area. Therefore, automatic face mask detection system helps authorities to identify people who may be susceptible to infections disease. This research aims to use deep learning to automatically detect face masks in videos. The proposed framework consists of two components. The first component is designed for face detection and tracking using OpenCV and machine learning, and in the second component, these facial frames are then processed into our proposed deep transfer learning model MobileNetV2 to identify the mask area. The proposed framework was tested on different videos and images using the smartphone camera. The purpose is to achieve high-precision real-time detection and classification. The model achieved 99.2% accuracy during training and 99.8% validation accuracy. which is better than other recently proposed methods. Experimental results show that the work proposed in this paper can effectively recognize face masks with multiple targets and provide effective personnel surveillance. This research is useful for controlling the spread of the virus and preventing exposure to the virus. © 2021 IEEE.

Leveraging demand data as a proxy for understanding large-scale events

Although, the internet opens an exceptional possibility for researchers conducting empirical studies on large-scale events by lowering the cost of collecting data and increasing the amount of information, there is a need to be cautious about not breaching the privacy of the users involved. Some types of internet data such as demand on networked systems (demand data) alleviate privacy concerns to some degree. To gauge the utility of demand data in understanding community behaviors during large scale events, we investigate its use in understanding quarantine compliance during Covid-19 pandemic. We analyse CDN demand data, google mobility data, and daily infection cases to see the pattern of correlation, and degree of influence of one variable on the others. © 2020 ACM.