Mathematical Model for Anisotropic diffusion Filter and GLRLM Feature Extraction to Detect Covid-19 from Chest X-Ray Images

In December 2019, the SARS-CoV-2 virus, often referred to as COVID-19, was discovered in Wuhan, China. It is very virulent and has spread very quickly throughout the world. With COVID-19, people have described a wide variety of symptoms, from little discomfort to life-threatening respiratory illness. In this study, chest X-ray scan images are preprocessed using an anisotropic diffusion filter and three classifiers, and the Covid-19 cases are classified from the chest X-ray images using the GLRLM feature extraction approach. Common metrics like sensitivity, selectivity, and accuracy are utilized to compare the performance of the classifiers. When compared to other classifiers in this study, the Gaussian Mixture Model had the best accuracy of 91.07%. © 2022 IEEE.

Deep Learning Models to Predict Covid-19 Cases in India Using Air Pollution and Meteorological Data

A worldwide pandemic caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), known as coronavirus disease 2019 (COVID-19), has killed many people. More than 31.6 million cases have been recorded in India alone till 2021. The main aim of this study is to identify the relationship between COVID-19 and air pollution concerning geographical location. Considerably air pollution also increases the cases, and COVID-19 disease causes damage to the respiratory system. Applying the Long short-term memory (LSTM) and Bidirectional Long short-term memory (BiLSTM) deep Learning model, this work attempts at giving insight into the connection between the various factors impacting COVID-19 mortality rates, i.e., the dispersion between the confirmed number of cases and the air pollution levels in major urban centres, namely Delhi, Bengaluru, Chennai, Mumbai, and Kolkata in India COVID-19 infections discovered that there is an association between high PM10 and PM2.5 pollution levels and having confirmed diseases are high. There is a concrete relationship between PM2.5 and COVID-19 mortality, which confirmed by the developed deep learning model that uses multiple regression analysis. The research model estimate, forecast and track COVID-19 case infections effects on air pollution, particularly in metropolitan cities. The BiLSTM model gives better score values between 0.903 and 0.951, whereas the LSTM model scores between 0.754 and 0.829. This research reveals a link between health and air pollutions parameters during this pandemic period. The results obtained from the research show a constructive co-relationship between the level of air pollution and diffusion of coronavirus.

Effective COVID Monitoring Process to Observe Patients Status using Blockchain

Collecting important information helps physicians, specialists, and health care providers to simplify the care of their patients. However, because patients do not explicitly retain their data, autonomous possession and the right to protect personal data develop. This paper discovers the block chain's potential to improve health care by placing the patient at the center of the system and improving health data protection and collaboration. The main goal of this research work is to discover the vast power of BitCoin technology that can be applied to patient records and health record protection management. As a dispensed era, Blockchain can be very beneficial, giving sufferers control over their statistics and impartial identification. With the COVID-19 pandemic, existing health information exchange systems are being put through the ringer. There is an increase in patient information sharing, as well as the need to respond to medical data requests more efficiently. There are some limitations in the current health information technologies, including the inability to remotely share medical data beyond their protected, local data stores. As a result, a secure and user-centric approach to accessing and controlling sensitive medical data is provided that is based on Blockchain immutability and decentralization. An innovative peer-to-peer system underpins the framework. Information is distributed through smart contracts that are connected to a blockchain-based protocol to ensure data integrity and traceability. Implementing the framework over a pilot study demonstrates its effectiveness. © 2022 IEEE.

Clinical characteristics and immunosuppression management in kidney transplant recipients infected with severe acute respiratory syndrome coronavirus 2 infection - An observational study

Background: COVID-19 infected kidney transplant patients need specialist care in tailoring their immunosuppression drugs alongside routine care. Methods and Materials: This is an observational data from a single center of 12 kidney transplant recipients (KTR) who were hospitalized with COVID-19 from April 2020 to November 2020. The demographics, COVID treatment including immunosuppressive drug regimen were reviewed. Their graft function during the stay, at the time of discharge, and 30 days after discharge was also reviewed. Results: Of 12 patients included, 83% were male patients. The median age was 37 years and the median time since transplant was 42 months. Common comorbidities were diabetes (50%), hypertension (50%), and cardiovascular disease (8%). Ninety-two percent had triple immunosuppressive regimen whereas 8% were in steroid-free protocol. Fifty percent had mild COVID, 8% had moderate disease, and 41% has severe COVID which was managed with institution-specified protocol. Steroids dose was increased in all patients. Antimetabolite was uniformly withdrawn in all patients irrespective of disease severity. Acute kidney injury was noted in 50% of patients which recovered to baseline at discharge. Graft function at 2 weeks and 30 days after discharge was stabilized close to their baseline value. Mortality was 8%. Conclusion: Reduction of immunosuppression, especially the withdrawal of antimetabolites, was found to be safe without graft rejection in KTRs.

Accuracy of tympanic versus digital infra-red thermometers for measuring core body temperature in critical care department-a quality improvement project during covid-19 redeployment at a district general hospital in Surrey, England

Aim: Accurate determination of core body temperature in critically ill patients is required for initiating diagnosis and management. (1) Ideally, temperature measurement should be non-invasive, hygienic, convenient, and affordable. Infrared thermometers are convenient and noninvasive but sensitive to environmental factors. Alternatively, tympanic thermometers are cost effective but invasive. Various observational studies have concluded that tympanic thermometers have high specificity/ sensitivity compared to infrared thermometers (2,3). We aimed to demonstrate accuracy of tympanic over infrared thermometers. Method: In this observational prospective study, eighty patients (forty each) admitted in intensive care from February 2021 - July 2021 were included. Temperature measurements with were conducted - measuring differences between digital and tympanic thermometers. A Plan Do Study Act cycle was used to facilitate change. Excel and SPSS software were used for data analysis. Results: Our study concluded a statistically significant (p,0.01) difference in readings with mean difference of 1.18°C (highest -6°C, lowest- 0.5°C). Pyrexia was undetected in 4 of 40 patients with digital thermometers. Additionally, two patients undergoing hypothermia correction were not adequately measured. Therefore, infrared thermometers were significantly less sensitive and were replaced with tympanic thermometers. A second cycle conducted again demonstrated significant (p<0.01) difference with mean difference of 1.92°C. (highest -6.5°C, lowest -1°C). Conclusions: Tympanic thermometers have higher accuracy and precision over digital thermometers. We managed to establish change during our audit with concluding evidence showing infrared thermometers procure false observations affecting patient care, hence, unsafe. In conclusion, tympanic thermometers should be encouraged in critical care settings for vigilant care.

Novel artificial intelligence learning models for covid-19 detection from x-ray and ct chest images

Covid-19 was first found in Wuhan, China, in December 2019. Covid-19 spreads very fast around the world, and it became a pandemic disease. Specific medicines were discovered yet to cure covid-19. It affects the day to day lives of humans and also the economy of all the countries. It remains a challenge in the early diagnosis of covid-19. Polymerase Chain Reaction (PCR) test is the most commonly used test for detecting covid-19, but it produces significant false positives and false negatives, not reliable. Recently, X-Ray and CT imaging of lungs were used to detect covid-19. In this paper, we propose three artificial intelligence (AI) models for COVID-19 image analysis. These three models include a simple artificial neural network model under machine learning (sANN_ML), a proposed convolutional neural network model under deep learning (pCNN_DL), and a proposed VGGNET based model under transfer learning (pVGG_TL). Besides, we also developed a novel activation function E-Tanh, by extending the Tanh activation function. For all our models, we used ReLU and E-Tanh activation functions. These AI models are used to analyze X-ray and CT images of the chest to detect COVID-19. The COVID-19 datasets experimented with the proposed models were collected Copyrights from public image repositories maintained by research and medical centers. Among three models, sANN_ML and pVGG_TL models performed well and produced 100% accuracy in detecting COVID-19 from X-ray images. The performance of pCNN_DL, which comes under the family of convolutional neural networks (CNN), did not perform well due to the availability of a small number of datasets for training. The performances of all three models for CT images are low when compared to the detection of COVID-19 in X-ray images. The proposed E-Tanh activation function is performed at par with the ReLU activation function. © Muk Publications.