Transfer Learning Model in Deep Neural Network for COVID-19 Prediction from CT Images

Deep learning models are often used to process radi-ological images automatically and can accurately train networks' weights on appropriate datasets. One of the significant benefits of the network is that it is possible to use the weight of a pre-trained network for other applications by fine-tuning the current weight. The primary purpose of this work is to employ a pre-trained deep neural framework known as transfer learning to detect and diagnose COVID-19 in CT images automatically. This paper uses a popular deep neural model, ResNet152, as a neural transfer approach. The presented framework uses the weight obtained from the ImageNet dataset, fine-tuned by the dataset used in the work. The effectiveness of the suggested COVID-19 prediction system is evaluated experimentally and compared with DenseNet, another transfer learning model. The recommended ResNet152 transfer learning model exhibits improved performance and has a 99% accuracy when analogized with the DenseNet201 transfer learning model. © 2022 IEEE.

Islamic Social Funds to Foster Yunusian Social Business and Conventional Social Enterprises

This paper proposes an integrated, comprehensive financial model that can provide startup capital to socially committed business ventures, such as social enterprises and Yunus Social Business (YSB), by using Islamic social funds (ISFs), Zakat (almsgiving), Waqf (endowments), Sadaqat (charity), and Qard Hasan (interest-free benevolent loans). The literature review method was adopted to explain this model's architecture, applications, implications, and viability. On the basis of logical reasoning, it concludes that ISFs can yield greater social wellbeing if utilised in SEs and YSB than in unconditional charity because both business models work for social betterment in entrepreneurial ways while remaining operationally self-reliant and economically sustainable. Additionally, ISFs can complement Yunus Social Business's zero-return investment approach to make it more robust towards social contributions. The implementation of the model orchestrated in this paper would enhance societal business practices and, hence, scale up social wellbeing while helping rejuvenate pandemic-stricken economies. It paves the way for new research too. © 2023 by the authors.

COVID-19 Induced Impacts on Women Workers of Fish and Shellfish Processing Plants in Bangladesh

The coronavirus disease (COVID-19) adversely impacted the fisheries sector of Bangladesh, particularly affecting the outcomes for women workers of the fish and shellfish processing plants (FSPPs). This study aimed to assess the impacts of COVID-19 on the women workers of the FSPPs by collecting data through 151 questionnaire surveys and two focus group discussions (FGDs) from September to December 2021. During COVID-19, 32.1 % of respondents' food consumption decreased slightly, and 16.6 % reduced drastically. Children of 18.2 % of the respondents had no access, and 16.9 % had insufficient access to online class facilities. Increased livelihood costs and decreased household income posed adverse economic impacts on women. Formal paid hours and overtime job opportunities were reduced because foreign buyers cancelled orders during the pandemic. Gender-based violence and social insecurity increased. Respondents (13.2 %) reported increased mistreatment by their husbands during the pandemic. Women workers' mental health deteriorated as their anxiety and insecurity about life increased during the pandemic. This study recommends overcoming the adverse effect of COVID-19 or COVID-like pandemics in the future. To ensure proper food consumption and reduce adverse economic impacts, the government should offer a special relief package, financial incentives and flexible low-interest loans. Related authorities should ensure that every child has the opportunity and access to participate in online classes during COVID-19 or COVID, like pandemics in the future. © Asian Fisheries Society.

Potential Improvement in a Portable Health Clinic for Community Health Service to Control Non-Communicable Diseases in Indonesia

The COVID-19 pandemic has limited routine community health services, including screening for non-communicable diseases (NCDs). An adaptive and innovative digital approach is needed in the health technology ecosystem. A portable health clinic (PHC) is a community-based mobile health service equipped with telemonitoring and teleconsultation using portable medical devices and an Android application. The aim of this study was to assess the challenges and potential improvement in PHC implementation in Indonesia. This study was conducted in February–April 2021 in three primary health centers, Mlati II in Sleman District, Samigaluh II in Kulon Progo, and Kalikotes in Klaten. In-depth interviews were conducted with 11 health workers and community health workers. At the baseline, 268 patients were examined, and 214 patients were successfully followed-up until the third month. A proportion of 32% of the patients required teleconsultations based on automatic triage. Implementation challenges included technical constraints such as complexity of applications;unstable networks;and non-technical constraints, such as the effectivity of training, the availability of doctors, and the workload at the primary health center. PHCs were perceived as an added value in addition to existing community-based health services. The successful implementation of PHCs should not only be considered with respect to technology but also in terms of human impact, organization, and legality. © 2023 by the authors.

Deep Convolutional Neural Networks for Detecting COVID-19 Using Medical Images: A Survey.

Coronavirus Disease 2019 (COVID-19), which is caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2), surprised the world in December 2019 and has threatened the lives of millions of people. Countries all over the world closed worship places and shops, prevented gatherings, and implemented curfews to stand against the spread of COVID-19. Deep Learning (DL) and Artificial Intelligence (AI) can have a great role in detecting and fighting this disease. Deep learning can be used to detect COVID-19 symptoms and signs from different imaging modalities, such as X-Ray, Computed Tomography (CT), and Ultrasound Images (US). This could help in identifying COVID-19 cases as a first step to curing them. In this paper, we reviewed the research studies conducted from January 2020 to September 2022 about deep learning models that were used in COVID-19 detection. This paper clarified the three most common imaging modalities (X-Ray, CT, and US) in addition to the DL approaches that are used in this detection and compared these approaches. This paper also provided the future directions of this field to fight COVID-19 disease.

Discriminating COVID-19 from Pneumonia using Machine Learning Algorithms and Chest X-ray Images

Reverse Transcription Polymerase Chain Reaction (RT-PCR) test is commonly used to detect COVID-19. However, the RT-PCR test necessitates person-to-person contact to administer and is expensive. Not only that, the diagnostic tests are still unreachable to the majority of the global population. The chest X-ray images are helpful for this purpose as the X-ray machines are available in almost all healthcare facilities. However, the chest X-ray images of COVID-19 and viral pneumonia patients are very similar and often lead to misdiagnosis. This paper presents automated noninvasive algorithms that can identify the X-ray images of COVID patients from that of pneumonia patients. This investigation has employed two algorithms based on machine learning and deep learning approaches. The lower dimension encoded features are extracted from the X-ray images and machine learning algorithms are applied. On the other hand, the deep learning algorithm relies on the inbuilt feature extractor networks to classify the original X-ray images. The simulation results show that the proposed algorithms can discriminate COVID patients from pneumonia patients with the best accuracies of 100% and 98.1% based on pre-trained deep learning and machine learning algorithms, respectively. © 2022 IEEE.

Gastrointestinal Symptoms in Covid-19 Patients

Aim: Gastrointestinal (GI) symptoms have been reported with coronavirus disease (COVID-19), but our understanding of their clinical significance is limited and this can be a safety concern for surgeons as patients might present with GI symptoms only. Method(s): A prospectively maintained database of emergency patients was reviewed between 20/03/2020 and 20/04/2020 (Cohort A) and 05/01/2021-26/ 01/2021. (Cohort B) All of them had a positive Polymerase Chain Reaction (PCR) COVID-19 test. We evaluated the prevalence of GI symptoms and their association with the severity of COVID-19 and looked at the prevalence of symptoms in different ethnicities. Chi-squared test in R software environment was used to analyse the data. Result(s): Cohort A consisted of 189 patients (100 male) 14 had nausea, 18 vomiting, 39 diarrhoea and 9 abdominal pain. 17 had ITU admissions and 68 died. Cohort B consisted of 348 patients (185 male) 50 had nausea, 46 vomiting, diarrhoea 84 and 23 had abdominal pain. 30 had ITU admissions and 75 died. In this cohort the COVID-19 Alpha Variant was making up nearly 100% of cases. Nausea was more common in Cohort B 50/348 (P = 0.01641) There was no difference in vomiting (18/189 Cohort A P = 0.198898), diarrhoea (39/189 Cohort A, P = 0.3385) and abdominal pain (9/189 Cohort A P = 0.379). There was no difference in GI symptoms for the severe and non-severe cases in Cohort A (P = 0.150813) but they were more prevalent in the non-severe group of Cohort B (P = 0.008). There was no diifference between ethnic groups in terms of GI symptoms (Cohort A 35 Black patients,17 Asian, 102 White and 35 Other Ethnicities, Cohort B 40 Black, 33 Asian, 174 White and 101 Other Ethnicities). Conclusion(s): Acute GI symptoms associated with COVID-19 are highly prevalent and were seen more often in non-severe cases of Cohort B. The SARS-CoV- 2 Alpha Variant was endemic in our region and the UK vaccination programme was being rolled out at the time of our study. More research is required to establish the significance of these factors.

COVID-19 Detection Through Deep Learning Algorithms using Chest X-ray Images

COVID-19 became a pandemic affecting the lives of every human globally by the end of 2019. The disease impaired the lungs of infected patients. Precise prediction and diagnosis of COVID-19 disease are challenging due to its resemblance to viral pneumonia. Using multiple deep learning approaches, the researchers used chest X-ray (CXR) imaging to diagnose COVID-19. The X-ray image dataset from Kaggle is used for the study by selecting the COVID-19 and normal class. InceptionV3, MobileNetV2, VGG19,VGG16 and ResNet50 are the five neural networks used for binary classification of COVID-19. The accuracy of MobileNetV2 surpasses that of the remainder of the model by 93.02%. However, it has a compilation time of 1836 seconds per epoch. Besides, VGG16 has an accuracy of 92.37%, with a compilation time of 603 seconds per epoch. Compared to these models, Inceptonv3, Resnet50 and VGG19 perform with an accuracy score of 86.42%, 68.34% and 91.79%. Applying deep learning techniques to COVID-19 radiological imaging holds great promise for enhancing the accuracy of diagnosis when in comparison to the gold standard RT-PCR test and assisting healthcare professionals in making decisions quickly © 2022 IEEE.

Framework for behavioral disorder detection using machine learning and application of virtual cognitive behavioral therapy in COVID-19 pandemic

In this modern world, people are becoming more self-centered and unsocial. On the other hand, people are stressed, be -coming more anxious during COVID-19 pandemic situation and exhibiting symptoms of behavioral disorder. To measure the symptoms of behavioral disorder, usually psychiatrist use long hour sessions and inputs from specific questionnaire. This process is time consuming and sometime is ineffective to detect the right behavioral disorder. Also, reserved people sometime hesitate to follow this process. We have created a digital framework which can detect behavioral disorder and prescribe virtual cognitive behavioral therapy (vCBT) for recovery. By using this framework people can input required data that are highly responsible for the three behavioral disorders namely depression, anxiety and internet addiction. We have applied machine learning technique to detect specific behavioral disorder from samples. This system guides the user with basic understanding and treatment through vCBT from anywhere any time which would potentially be the stepping-stone for the user to be conscious and pursue right treatment.

Explainable Text Classification Model for COVID-19 Fake News Detection

Artificial intelligence has achieved notable advances across many applications, and the field is recently concerned with developing novel methods to explain machine learning models. Deep neural networks deliver the best performance accuracy in different domains, such as text categorization, image classification, and speech recognition. Since the neural network models are black-box types, they lack transparency and explainability in predicting results. During the COVID-19 pandemic, Fake News Detection is a challenging research problem as it endangers the lives of many online users by providing misinformation. Therefore, the transparency and explainability of COVID-19 fake news classification are necessary for building the trustworthiness of model prediction. We proposed an integrated LIME-BiLSTM model where BiLSTM assures classification accuracy, and LIME ensures transparency and explainability. In this integrated model, since LIME behaves similarly to the original model and explains the prediction, the proposed model becomes comprehensible. The performance of this model in terms of explainability is measured by using Kendall’s tau correlation coefficient. We also employ several machine learning models and provide a comparison of their performances. Therefore, we analyzed and compared the computation overhead of our proposed model with the other methods because the model takes the integrated strategy. © 2022, Innovative Information Science and Technology Research Group. All rights reserved.

N95 mask related skin disease amongst healthcare workers-A cross sectional study

N95 masks are worn daily by healthcare workers, and have become a part of mandatory PPE in many hospitals during this COVID-19 pandemic. It is well established that adverse skin reactions (ie. pressure sores, dermatitis, acne, cheilitis, etc) are associated with N95 mask use. There is, however, little information as to which N95 masks are more closely associated with these adverse reactions. Aim: This cross sectional study analyses the association between the different N95 masks, the rate and type of skin reactions reported, and the involvement of general practitioners and dermatologists in their management. Method: Healthcare workers (ie. doctors, nurses, allied health professionals etc.) at three major. Melbourne metropolitan health care networks were sent a digital survey questionnaire. The questionnaire contained 52 questions regarding the frequency, duration and type of N95 mask worn, as well as the frequency, severity and type of adverse skin reactions experienced. The survey also asks about the use of preventative measures for adverse skin reactions, and whether management was initiated by a general practitioner, dermatologist or the participant themself. Results: Different N95 masks have variable frequency and nature of adverse skin reactions. Fit testing has allowed healthcare workers to choose between masks that will provide the best seal to protect from airborne and aerosol disease spread. In addition, selecting fit appropriate N95 masks based on frequency of adverse skin reactions, may provide further guidance on mask selection, and reduce the frequency of N95 mask related adverse skin reactions.

Low-Cost Smart COVID-19 Patient Monitoring and Support System

Social distancing, isolation, and quarantining are very familiar words since the outbreak of the coronavirus (COVID-19). COVID - 19 is a highly contagious pathogenic viral infection. It is very risky to get close contact with people who have COVID-19 symptoms or COVID-19 positive;nevertheless, covid patient monitoring is also significant for saving his/her life. To solve the Covid-19 pandemic situation accentuates a focus on remote patient monitoring. A small smart healthcare support system is built to monitor COVID-19 patients' health status and the patient emergency abet. This system can also trace the patient location;thus, aid can be provided to the patient promptly. This system uses a respiration sensor, oxygen saturation sensor, temperature sensor, heart rate sensor, GPS. All the sensors, as well as GPS, are connected with Arduino-Uno. By processing sensor data, the smart system can discern the patient's critical condition and forward this information to the doctor/nurse or hospital in charge and patient relative's smartphone as a text message. This paper aims to develop a system to support COVID-19 patients and develop a remote healthcare platform for monitoring pandemic situations and providing emergency aid promptly as a text to the smartphone. © 2021 IEEE.

Automatic Classification of COVID-19 from Chest X-Ray Image using Convolutional Neural Network

COVID-19 has become one of the most virulent, acute, and life-Threatening diseases in recent times. No clinically approved drug is available till now for its treatment. Therefore, early and swift detection is very essential for reducing overall mortality. The chest x-ray image is one of the possible alternative methods for detecting COVID-19. Researchers are exploring image processing techniques along with deep learning-based models like AlexNet, VGGNet, SqueezeNet, GoogleNet, etc.To detect COVID-19. This study aims to formulate, implement and investigate deep learning-based models and their probable hyperparameters tuning for obtaining the best results when identifying COVID-19 using chest x-ray images. To meet this objective, images from different publicly available databases were collected. In this paper, ResNet18, ResNet50V2, DenseNet121, DenseNet201, modified DenseNet201 and VGG16 were used to detect COVID-19. From the experimental results, modified DenseNet201 showed the best performance with 99.5% mean accuracy, 99.5% mean F1 score and 100% mean sensitivity in binary (COVID-19 and normal) classification and 98.33% mean accuracy, 98.34 mean F1 score, and 98.34% mean sensitivity (98% sensitivity for COVID-19) in 3-class (COVID-19, pneumonia, normal) classification. This may contribute to the process of designing and implementing a system that can detect COVID-19 automatically in the near future and enhance the quality of healthcare services. © 2021 IEEE.

Full cycle audit on definitive management of biliary pancreatitis

Aim: To reaudit the practice of definitive management of gall stones pancreatitis in our trust for the period of 1st May-31st October and compare the result with previous one (1st June 2019-31st Dec 2019). Method: It was a retrospective collection of data of patients admitted to our trust with biliary pancreatitis. Electronic notes, PACS for US report, Electronic discharge summary and Operative notes analysed. Results: We identified 4 patients admitted with biliary pancreatitis during the re-audit period. US report was checked for confirmation of diagnosis of gall stones. The EDN was checked for date for Laparoscopic cholecystectomy. Unfortunately, none of them had their procedure time in 2 weeks' time of their diagnosis. The reason behind this was because of COVID-19 pandemic, we were backlogging with our elective list. All the patients eventually underwent their procedure, but not in 2 weeks' time as per the guidelines. All suitable patients had their cholecystectomy in a timely manner during first audit. None had it in timely manner during second audit. Conclusions: Early Laparoscopic cholecystectomy for simple gallstone pancreatitis prevents life threatening Pancreatitis and readmissions. The UK guidelines on management of pancreatitis issued by British society guidelines (BSG) states that all mild gall stones pancreatitis should have definitive management of lithiasis on the same admission or within 2 weeks (Recommendation B). In our practice, all our suitable patients during first audit had timely Laparoscopic cholecystectomy, however, no one had it in timely manner on the next audit for COVID-19 pandemic.

Implementation of an At-Home, First-Semester Biochemistry Lab Course: A Module Based on Banana Tyrosinase

This paper describes the development of a fully remote upper-class biochemistry lab course. The sudden change to online teaching in the middle of spring semester 2020 had a primarily negative impact on laboratory teaching. These effects were mitigated because the students had done many of the basic hands-on procedures before the switch. A true "at-home"biochemistry lab module was implemented in the fall semester of 2020 to ensure students could have a hands-on lab experience in a remote setting despite the remaining COVID-19 restrictions placed upon universities. The module covered several fundamental concepts and techniques found in a first semester biochemistry lab sequence: extraction and purification of a protein from a sample, and further analysis of the protein. Tyrosinase was isolated and purified from a banana extract followed by kinetic analysis of the enzyme. A key component to the module is an LED light board that, in combination with a cell-phone app, made a simple at-home colorimeter. The module was implemented in three sections of a first semester biochemistry lab course (81 students total) in the fall of 2020, and components of it have been used periodically since. Some of the procedures are now being implemented into normal in-lab sessions. An assessment in terms of a student survey showed that most of the students were able to adapt to this format and felt that their learning was not impeded. © 2022 American Chemical Society.

Early Detection of COVID-19 Patients using Chromagram Features of Cough Sound Recordings with Machine Learning Algorithms

This paper presents a cough sound-based fast, automated, and noninvasive COVID-19 detection system to discriminate the cough sounds of the COVID-19 patients from the healthy individuals. The proposed system extracts an acoustic feature called chromagram from the cough sound samples and applies it to the input of a classifier algorithm. Two artificial neural network (ANN) based classifiers namely convolutional neural network (CNN) and deep neural network (DNN) are modeled for this purpose. The simulation results show that the proposed system achieves an accuracy of 92.9% and 91.7% with CNN and DNN respectively. The performance comparison of the proposed system with two popular machine learning algorithms namely support vector machine (SVM) and k-nearest neighbor (kNN) are also presented in this work. © 2021 IEEE.

Experiences of Stigma in the United States During the COVID-19 Pandemic

An increasing number of U.S. news headlines report violence targeting Asian populations and harassment of health care workers, which suggests growing coronavirus disease (COVID-19)-related stigmatization of certain groups across the country. Empirical research characterizing the breadth of COVID-19-related stigma in the U.S. is lacking and yet is critically needed to inform interventions that mitigate known negative health impacts of such stigma. Using mixed methods, we explored experiences of COVID-19-related stigma reported in an online U.S.-based survey conducted in April 2020 (N = 1,366). Forty-two respondents (3.1%) reported experiencing COVID-19-related stigma. Qualitative analysis of open-ended responses revealed that perceived race and ethnicity was the characteristic most frequently connected to experiencing stigma followed by COVID-19 guideline adherence, suspected or confirmed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, profession or place of employment, and age. Most COVID-19-related stigma connected to race and ethnicity was specific to anti-Asian, specifically anti-Chinese, sentiment. Exploratory quantitative analysis found identifying as Asian (OR = 6.96) and testing positive for COVID-19 (OR = 4.99) were associated with the highest odds of experiencing stigma (all p < .001). Employment as a health care worker and/or first responder, working with COVID-19 patients, being at high-risk of serious illness, or having COVID-19 symptoms (OR range = 2.50-2.94, all p < .01) were also associated with greater odds of experiencing stigma. Together, our quantitative and qualitative results suggest that Asian populations in the U.S. may be disproportionately affected by COVID-19-related stigma. Our findings also suggest associations between experiences of stigma and COVID-19-related health factors and vulnerability. This study may help inform future research that demonstrates the extent of COVID-19-related stigma and interventions to combat adverse effects.

108 Using the CARG prediction score to influence patient decision to proceed with chemotherapy based on the predicted incidence of toxicity in lung cancer

Introduction: The CARG (Cancer and Aging Research Group) score is a predictive model for patients 65 years and over experiencing grade 3-5 toxicity from chemotherapy. It uses factors such as the number of chemotherapeutic drugs and serological factors such as haemoglobin level. It also incorporates geriatric social factors. Studies have shown mixed results for its usefulness in Oncology practice. Methods: In this study we selected 10 suitable patients from Southend University Hospital who presented to clinic with a new diagnosis of lung cancer. If we offered chemotherapy, we calculated their CARG score and asked them if their predicted percentage of experiencing toxicity affected their decision to proceed with treatment. Results: 10/10 patients did not find the score influenced their decision. Their scores ranged from 32-50%. All patients wanted to proceed with treatment regardless of their CARG score. Participants felt that the score did not provide any additional beneficial information towards their informed decision to proceed with treatment. Conclusions: There are a number of identified flaws with the CARG score. For example, the clinician would be unlikely to offer treatment to a patient who would be at high risk of experiencing severe toxicity based in factors such as performance status. Also, the score did not take account the emergence of combination treatments with immunotherapy, which has a different toxicity profile. The study was done during the COVID-19 pandemic, which understandably has limited the social activity of elderly patients, thereby affecting their score. We conclude that the CARG score may be useful to clinicians but does not appear to influence patient decision. Disclosure: No significant relationships.

A BRBES to Support Diagnosis of COVID-19 Using Clinical and CT Scan Data

In the prevailing COVID-19 pandemic, accurate diagnosis plays a vital role in preventing the mass transmission of the SARS-CoV-2 virus. Especially patients with pneumonia need correct diagnosis for proper treatment of their respiratory distress. However, the current standard diagnosis method, RT-PCR testing has a significant false negative and false positive rate. As alternatives, diagnosis methods based on artificial intelligence can be applied for faster and more accurate diagnosis. Currently, various machine learning and deep learning techniques are being researched on to develop better COVID-19 diagnosis system. However, these approaches do not consider the uncertainty in data. Deep learning approaches use backpropagation. It is an unexplainable black box approach and is prone to problems like catastrophic forgetting. This article applies a belief rule-based expert system (BRBES) for diagnosis of COVID-19 on hematological data and CT scan data of lung tissue infection of adult pneumonia patients. The system is optimized with nature-inspired optimization algorithm—BRBES-based adaptive differential evolution (BRBaDE). This model has been evaluated on a real-world dataset of COVID-19 patients published in a previous work. Also, performance of the BRBaDE has been compared with BRBES optimized with genetic algorithm and MATLAB’s fmincon function where BRBaDE outperformed genetic algorithm and fmincon and showed best accuracy of 73.91%. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Detecting malicious COVID-19 URLs using machine learning techniques

Throughout the COVID-19 outbreak, malicious attacks have become more pervasive and damaging than ever. Malicious intruders have been responsible for most of the cybercrimes committed recently and are the cause for a growing number of cyber threats, including identity and IP thefts, financial crimes, and cyber-attacks to critical infrastructures. Machine learning (ML) has proven itself as a prominent field of study over the past decade due to solving highly complex and sophisticated real-world problems. This paper proposes an ML-based classification technique to detect the growing number of malicious URLs, due to the COVID-19 pandemic, which is currently considered a threat to IT users. We have used a large volume of Open Source data and preprocessed it using our developed tool to generate feature vectors and trained the ML model using an apprehensive malicious threat weight. Our ML model has been tested, with and without entropy to forecast the threatening factors of COVID-19 URLs. The empirical evidence proves our methods to be a promising mechanism to mitigate COVID-19 related threats early in the attack lifecycle.