Understanding of Post Covid Mucormycosis through the Lens of Ayurveda

Mucormycosis is fungal disease caused by fungus Mucor. It has been seen as a life-threatening complication of disease Covid-19. It has 70 times higher prevalence rate in India as compared to the world, having only few but expensive treatment options. The triggers of Mucor infection in Covid-19 patients are immune deficiency and hyperglycaemia caused by the use of corticosteroid, which favours Mucorales tissue Penetration. Mucormycosis has mainly six different types viz pulmonary, rhino-orbital-cerebral, gastrointestinal, widely disseminated, cutaneous, & miscellaneous infection, the commonest clinical presentation is rhino-orbito-cerebral in Covid-19 pandemic. Ayurveda though an ancient science of healing, has strength to treat newer diseases from several decades. Mucormycosis disease is not mentioned in Ayurveda text directly, it is Un uttered disease (Anukta Vyadhi) but it can be treated with help of basic principles of Ayurveda. By understanding the pathogenesis, it can be stated that, it is an Abhishangaja Vyadhi (diseased caused by Virus/ Bacteria/ Parasite) and categorised as Raktapitta Pradhan Tridoshaja Vyadhi (disease caused by vitiation of all three humors with rakta pitta predominance). Prevention of Mucormycosis can be achieved by following daily (Dincharya) and seasonal (Ritucharya) regimens. The treatment protocol include Krimighna (Antimicrobial), Tridoshashamak (normalise all three humors) and Raktashodhaka / Pittashamak (blood purifier), Agnideepak (improve digestion) & Aampachak (improve metabolism), Pramehhar (treatment of diabetes/hyperglycaemia) and Rasayana (Rejuvenation) drugs.

Twitter Sentiment Analysis for COVID-19

With the current onset of the Coronavirus pandemic social interaction has been deeply affected. However, social media and micro-blogging platforms like Twitter are becoming more of relevance to the masses to express their feelings, opinions, concerns and problems. A large amount of data is generated in this process which may be highly valuable in deriving deep insights about the effects of the pandemic on the people. With modern technological tools like data mining, data processing and APIs, harnessing this sea of data has become more of a possibility. Moreover, with the application of advanced machine learning tools like sentiment analysis, understanding the people’s mindset behind the tweet has also become a possibility. The study oversees the development of a web based interface for connecting two sections of the society: one which is in need of help and the other with the desire to help. In this study, we aim to utilise data analysis and advanced machine learning techniques like RoBERTa(Robustly Optimised BERT pre-training Approach) and CNN-RoBERTa Sentiment Extraction to incorporate methods like sentiment analysis, frequency distribution and comparative analysis on data found from social media for efficient comparison on the effects of COVID-19 in India while also developing a web-based interface for effective exposition and insights over the crisis. © 2021 IEEE

Comparison of Classification Models Based on Deep learning on COVID-19 Chest X-Rays

COVID -19, is a deadly, dangerous and contagious disease caused by the novel corona virus. It is very important to detect COVID-19 infection accurately as quickly as possible to avoid the spreading. Deep learning methods can significantly improve the efficiency and accuracy of reading Chest X-Rays (CXRs). The existing Deep learning models with further fine tune provide cost effective, rapid, and better classification results. This paper tries to deploy well studied AI tools with modification on X-ray images to classify COVID 19. This research performs five experiments to classify COVID-19 CXRs from Normal and Viral Pneumonia CXRs using Convolutional Neural Networks (CNN). Four experiments were performed on state-of-the-art pre-trained models using transfer learning and one experiment was performed using a CNN designed from scratch. Dataset used for the experiments consists of chest X-Ray images from the Kaggle dataset and other publicly accessible sources. The data was split into three parts while 90% retained for training the models, 5% each was used in validation and testing of the constructed models. The four transfer learning models used were Inception, Xception, ResNet, and VGG19, that resulted in the test accuracies of 93.07%, 94.8%, 67.5%, and 91.1% respectively and our CNN model resulted in 94.6%. © 2022 Institute of Physics Publishing. All rights reserved.

Impact of training on Knowledge, Attitude and Perceived Barriers for Compliance Regarding use of Protective Equipment Kit among Frontline Healthcare Workers during COVID-19 Pandemic

Introduction: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the novel Coronavirus is the causative agent of Coronavirus Disease-2019 (COVID-19) pandemic has grasped the whole world. Healthcare Workers (HCWs) are at an increased risk. The usage and awareness of entire Personal Protective Equipment (PPE) kit in hospitals on such wide scale has not been seen for some time in healthcare setting. Improper use of these equipment may result in the spread of infection. Aim: To assess the knowledge and attitude of HCWs regarding the correct use of PPE at the beginning of COVID-19 pandemic in order to find the gap in knowledge and to address the perceived barriers in compliance and further to assess the same after training and reinforcement to ensure the HCWs safety. Materials and Methods: A cross-sectional hospital based study was carried out in a designated COVID-19 hospital of Shaheed Hasan Khan Mewati Government Medical College from April 2020 to October 2020 on frontline HCWs posted in various areas of hospital. Sample size was calculated as a minimum of 500 HCWs using appropriate statistical formula. A predesigned, pretested structured questionnaire both online and offline mode was used. The data that was obtained was analysed using SPSS version 20. Results: Seven hundred frontline HCWs were included in the study. Mean age of study population was 30.5 years. A total of 52% of the participants were males and 48% were females. Knowledge level of PPE kit and its use varied across doctors, nursing staff and housekeeping staff. Knowledge about donning and doffing was largely lacking with only 9% doctors and none of other staff were aware which improved to more than 80% post-training. Attitude regarding PPE kit usage was largely positive. Conclusion: The study concludes that there is a constant need of training and re-training of HCWs in order to keep them safe from not only COVID-19 but future infections. An active infection prevention training program is crucial to ensure HCWs safety.

IoT Based UV Disinfection Machine

The rising amount of imminent and ongoing biological threats increases risks at public places. Disinfection is the major chain breaker in the COVID-19 pandemic with UVC source and appropriate intensity. At the same time human safety is a major concern while dealing with actual intense UVC light. We develop a disinfection machine which will be operated automatically and with a contact less system. Intense UV-C radiations will disinfect all the human belongings inside the close chamber of the machine. The project targets public places such as airports, railway stations, Hospitals, Schools, Colleges, Corporates and malls where average footfall is greater to maintain the social distancing norms. Physical implementation of this project at least one of the above places will ensure complete destruction of COVID-19 virus. Time of the disinfection can be varied automatically using IOT and depending on the real time active cases in the locality. Weight sensors, bag detection, battery back up and automation are few added advantages. © 2021 IEEE.