Road accidents and mobility patterns during the first official lockdown period in Dhaka city: A case of Covid-19

There are several prescribed preventive measures that have brought changes in mode choice patterns due to the COVID-19 pandemic. This study is focused specifically on the distribution of the travelers' modal choice pattern amidst lockdown period in Dhaka city. A comprehensive questionnaire survey with the 224 responders (Male 34.8%, Female 65.2%) has been conducted and the participants chosen their modes based on five factors i.e., transmission risk, comfort, safety, cost effectiveness and timeliness. Additionally, their travel frequencies, ride sharing preferences and overall trip satisfactions have also been documented. The study performed a number of statistical tests including frequency distribution, chi square test etc. Also, accident statistics is incorporated to understand the relativity of modal choices with the accident frequencies. © 2023 Author(s).

Erratum: 523 Effect of the COVID-19 UK Lockdown on Lower Limb Tendon Ruptures (British Journal of Surgery (2022) 109:Supplement_6 (znac269.466) DOI: 10.1093/bjs/znac269.466)

In the originally published version of this manuscript, 5 authors were inadvertently omitted: Dr Saad Islam, MBChB, Barts Health NHS Trust, Orthopaedics Dr Adil Hasnain MD, Barts Health NHS Trust, Orthopaedics Mr Shahanoor Ali, MBChB, Barts Health NHS Trust, Orthopaedics Mr Hassan Raja, MBChB, Barts Health NHS Trust, Orthopaedics Mr Konstantinos Tsitskaris, MD MSc FRCS(ortho), Barts Health NHS Trust, Orthopaedics This error has now been corrected.Copyright © The Author(s) 2022. Published by Oxford University Press on behalf of BJS Society Ltd. All rights reserved.

A Hand Gesture-Based Contact-less Interface for Electronic Health Records

Clinical data monitoring and storing are essential components of continuous and preventive healthcare systems. Data such as blood pressure, pulse rate, temperature, etc., can be recorded by the hospital staff daily for in-patient subjects. The usual way of noting them down is to check different parameters using various medical instruments and write it on paper with the corresponding patient's details (e.g., name, patient-id, or government identity card number). However, after the outbreak of COVID-19, there is a set of World Health Organization (WHO) guidelines to behave in public places. Ordinary people and professionals feel hesitant to touch any media even if they have some protection such as gloves and sanitizer. In this crisis, there is a natural demand for contact-less activities instead of touch-based traditional ways. Gesture-based activities might be one of the low-cost alternatives to some sensor-based systems. This paper uses a profound learning-based finger point gesture to capture writing in the air and realize it on the screen through a predictive model. Here, the proposed framework has been demonstrated as a proof of concept to record blood pressure data for multiple patients without touching any electronic screen or paper. The proposed architecture is developed based on the gesture recognition and metric learning, which have been used to recognize different digits trained from the MNIST digit dataset. The mean test accuracy is reached 99.47% on the same dataset. © 2022 IEEE.

COVID-19 Vaccine Hesitancy Among Health care Workers and Medical Students

Background: Health care workers (HCW) assume a significant part in teaching the overall population about the origin of the immunization and its implications and subsequently, vaccination hesitancy among them presents existential dangers to the stoppage and control of this pandemic. It will likewise impede endeavours to reduce COVID-19 pandemic. Objective(s):To comprehend coronavirus vaccine acceptance and specific attitudes toward vaccine hesitancy among HCWs and medical students at Jinnah hospital, Lahore. Method(s):200 HCWs employed by Jinnah Hospital, Lahore and 200 asymptomatic medical students to access attitudes toward vaccine acceptance and hesitancy. A cross-sectional survey was designed and the questionnaire was administered during May, 2022 while it was completed online throughout the month of May, 2022. Vaccination hesitancy was defined as procrastination or denial of vaccination although the services and the doses are available. Tabulated form was given to the descriptive statistics and the reported attitudes towards COVID-19 vaccine of the participants. Data was entered and analysed statistically by using SPSS software, IBM version 27. Qualitative data was shown as frequencies and percentages. For data analysis a chi-square test was used with P < .05 as statistical significance. Result(s):In total, 400 enrolees, completed the questionnaire, a majority of participants were doctors (98.5%), were vaccinated by choice (90.5%), had Chinese vaccination (80.5%), and had booster dose (34%). Almost all respondents were aware of COVID-19 vaccination (100%).Vaccination hesitancy was shown by health care workers right away due to fear of vaccine (1%). Conclusion(s):Vaccine intake was adequate among health care workers and satisfactory among medical students. Awareness regarding vaccination was good among both groups with low level of hesitancy.Copyright © 2022, Anka Publishers. All rights reserved.

Advances in Healthcare and Protective Textiles

Advances in Healthcare and Protective Textiles addresses technologies that have had a major impact in industry for decades, but which are currently attracting unprecedented attention due to their applications in the fight against the Coronavirus epidemic. Recent advances in textile technology have opened new possibilities for textile researchers and scientists in antiviral textiles, flame-retardant textiles, antimicrobial textiles, insect repellent textiles, breathable medical textiles, aroma-protective textiles, high tech-textiles, smart textiles, nano textiles, and more. This book provides systematic and comprehensive coverage of cutting-edge research and developments on material design, methodologies, characterizations, processes, properties and applications of medical healthcare and protective textiles. In addition, sections pay special attention to advanced fabrication methodologies and materials used in apparel engineering. © 2023 Elsevier Ltd. All rights reserved.

Psychometric Validation of the Bangla Fear of COVID-19 Scale: Confirmatory Factor Analysis and Rasch Analysis.

The recently developed Fear of COVID-19 Scale (FCV-19S) is a seven-item uni-dimensional scale that assesses the severity of fears of COVID-19. Given the rapid increase of COVID-19 cases in Bangladesh, we aimed to translate and validate the FCV-19S in Bangla. The forward-backward translation method was used to translate the English version of the questionnaire into Bangla. The reliability and validity properties of the Bangla FCV-19S were rigorously psychometrically evaluated (utilizing both confirmatory factor analysis and Rasch analysis) in relation to socio-demographic variables, national lockdown variables, and response to the Bangla Health Patient Questionnaire. The sample comprised 8550 Bangladeshi participants. The Cronbach α value for the Bangla FCV-19S was 0.871 indicating very good internal reliability. The results of the confirmatory factor analysis showed that the uni-dimensional factor structure of the FCV-19S fitted well with the data. The FCV-19S was significantly correlated with the nine-item Bangla Patient Health Questionnaire (PHQ-90) (r = 0.406, p < 0.001). FCV-19S scores were significantly associated with higher worries concerning lockdown. Measurement invariance of the FCV-19S showed no differences with respect to age or gender. The Bangla version of FCV-19S is a valid and reliable tool with robust psychometric properties which will be useful for researchers carrying out studies among the Bangla speaking population in assessing the psychological impact of fear from COVID-19 infection during this pandemic.

Data-Driven Estimation of Effectiveness of COVID-19 Non-pharmaceutical Intervention Policies

Non-pharmaceutical Interventions (NPIs), such as Stay-at-Home, and Face-Mask-Mandate, are essential components of the public health response to contain an outbreak like COVID-19. However, it is very challenging to quantify the individual or joint effectiveness of NPIs and their impact on people from different racial and ethnic groups or communities in general. Therefore, in this paper, we study the following two research questions: 1) How can we quantitatively estimate the effectiveness of different NPI policies pertaining to the COVID-19 pandemic?;and 2) Do these policies have considerably different effects on communities from different races and ethnicity? To answer these questions, we model the impact of an NPI as a joint function of stringency and effectiveness over a duration of time. Consequently, we propose a novel stringency function that can provide an estimate of how strictly an NPI was implemented on a particular day. Next, we applied two popular tree-based discriminative classifiers, considering the change in daily COVID cases and death counts as binary target variables, while using stringency values of different policies as independent features. Finally, we interpreted the learned feature weights as the effectiveness of COVID-19 NPIs. Our experimental results suggest that, at the country level, restaurant closures and stay-at-home policies were most effective in restricting the COVID-19 confirmed cases and death cases respectively;and overall, restaurant closing was most effective in hold-down of COVID-19 cases at individual community levels such as Asian, White, Black, AIAN and, NHPI. Additionally, we also performed a comparative analysis between race-specific effectiveness and country-level effectiveness to see whether different communities were impacted differently. Our findings suggest that the different policies impacted communities (race and ethnicity) differently. © 2022 IEEE.

Major Drugs Used in COVID-19 Treatment: Molecular Mechanisms, Vali-dation and Current Progress in Trials

Background: Currently, the present world is facing a new deadly challenge from a pandemic disease called COVID-19, which is caused by a coronavirus named SARS-CoV-2. To date, no drug or vaccine can treat COVID-19 completely, but some drugs have been used primarily, and they are in different stages of clinical trials. This review article discussed and compared those drugs which are running ahead in COVID-19 treatments. Method(s): We have explored PUBMED, SCOPUS, WEB OF SCIENCE, as well as press releases of WHO, NIH and FDA for articles related to COVID-19 and reviewed them. Result(s): Drugs like favipiravir, remdesivir, lopinavir/ritonavir, hydroxychloroquine, azithromycin, ivermectin, corticosteroids and interferons have been found effective to some extent, and partially approved by FDA and WHO to treat COVID-19 at different levels. However, some of these drugs have been disapproved later, although clinical trials are going on. In parallel, plasma therapy has been found fruitful to some extent too, and a number of vaccine trials are going on. Conclusion(s): This review article discussed the epidemiologic and mechanistic characteristics of SARS-CoV-2, and how drugs could act on this virus with the comparative discussion on progress and drawbacks of major drugs used till date, which might be beneficial for choosing therapies against COVID-19 in different countries.Copyright © 2022 Bentham Science Publishers.

Pharmaceutically Active Compounds in Water Bodies—Occurrence, Fate, and Toxicity

The presence of pharmaceutically active compounds (PhACs) in water bodies has been considered an issue of global concern due to their high consumption and release into the environment, especially under pandemic conditions such as current COVID-19 situations. Additionally, the appearance of antibiotic-resistant bacteria (ARBs) and antibiotic resistance genes (ARGs) threatens the effectiveness of the pharmaceuticals developed to treat certain diseases. To address this problem, there have been efforts to develop efficient and cost-effective (waste)water treatment methods or to upgrade the existing facilities to regenerate clean water resources. According to the reports available in the literature, the effectiveness of these methods is highly dependent on the applied technology and the type and concentration of the PhACs. The efficiency of these systems can also determine the environmental and ecotoxicological effects expected from the release of these compounds. This chapter aims to summarize and discuss the available literature on the occurrence, environmental concentrations, fate, and possible effects of typical PhACs when introduced into receiving environments. The existing research gaps have also been discussed, and recommendations have been provided for further studies. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Identification of Clinical Features Associated with Mortality in COVID-19 Patients

Understanding clinical features and risk factors associated with COVID-19 mortality is needed to early identify critically ill patients, initiate treatments and prevent mortality. A retrospective study on COVID-19 patients referred to a tertiary hospital in Iran between March and November 2020 was conducted. COVID-19-related mortality and its association with clinical features including headache, chest pain, symptoms on computerized tomography (CT), hospitalization, time to infection, history of neurological disorders, having a single or multiple risk factors, fever, myalgia, dizziness, seizure, abdominal pain, nausea, vomiting, diarrhoea and anorexia were investigated. Based on the investigation outcome, decision tree and dimension reduction algorithms were used to identify the aforementioned risk factors. Of the 3008 patients (mean age 59.3 ± 18.7 years, 44% women) with COVID-19, 373 died. There was a significant association between COVID-19 mortality and old age, headache, chest pain, low respiratory rate, oxygen saturation < 93%, need for a mechanical ventilator, having symptoms on CT, hospitalization, time to infection, neurological disorders, cardiovascular diseases and having a risk factor or multiple risk factors. In contrast, there was no significant association between mortality and gender, fever, myalgia, dizziness, seizure, abdominal pain, nausea, vomiting, diarrhoea and anorexia. Our results might help identify early symptoms related to COVID-19 and better manage patients according to the extracted decision tree. The proposed ML models identified a number of clinical features and risk factors associated with mortality in COVID-19 patients. These models if implemented in a clinical setting might help to early identify patients needing medical attention and care. However, more studies are needed to confirm these findings. © 2023, The Author(s).

Assessment of challenges and problems in supply chain among retailers during COVID-19 epidemic through AHP-TOPSIS hybrid MCDM technique

Framework and objectives: COVID-19 epidemic has sparked concern and has elevated the need for therapeutic tools, health equipment's, and day-to-day necessities for healthcare workers' well-being. The goal of this study is to uncover the operational problems that suppliers encounter when it comes to offering effective services. The research also intends to offer an Industry 4.0 strategy for reducing COVID-19's effect. The problems are weighed and priority is assigned by multi-criteria decision making to identify the most essential parameter which impacts the suppliers. Methods: A comprehensive literature assessment on the rampant eruption of COVID 19 and supply chain is conducted with the aid of literatures available on SCOPUS, Science Direct, and Google Scholar using appropriate keywords. To get further insights, certain pertinent and applicable industry reports and blogs are also used. Problems were analysed with AHP method and priority was assigned by technique for order performance by similarity to ideal solution (TOPSIS). Weights are calculated by AHP method and assigned to each criteria attribute. Results: We recognized eleven key problems that serve as an operational obstacle in the retail industry and proposed the use of Industry 4.0 technology to address them. The contemporary study is accomplished by using hybrid combination of two Multi Criteria Estimators methods- Analytical Hierarchical Process (AHP) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). Further, the most significant problem comes out to be Maintenance of an appropriate balance among supply and demand followed by Lack of Viability. Key findings: Prioritization of supply chain problems are arranged in descending order Maintenance of an appropriate balance among supply and demand ​> ​Lack of Viability ​> ​Absence of government funding ​> ​Lack of access ​> ​Absence of Confidence ​> ​Scarcity of work force ​> ​Lack of security and safety ​> ​Deficiency of surplus medical amenities ​> ​Consumer attitude ​> Absence of Supply Chain flexibility ​> ​Communication problems. Conclusion: In order to combat the pandemic, Industry 4.0 can play a key role in lowering the effect of identified issues on retailers. For the successful administration of healthcare basics, trust and openness are required. To enhance services, suppliers, distributors and policy makers should make informed decisions during COVID-19 and other comparable events. Therefore, suggested guidelines and framework will offer upcoming directions for research in fields of pandemic check, business logistics management, and catastrophe administration. Balance in supply and demand is the most significant attribute as its percentage contribution is the maximum (27.52%) followed by Safety of employees (26.51%). Furthermore, the research then ranks these models on the basis of their attributes with the aid of TOPSIS. Among all these problems, Maintenance of an appropriate balance among supply and demand and lack of viability are identified as the prime most and common concern for retailers in supply chain management during the COVID-19 pandemic. © 2022 The Authors

Pre-text Representation Transfer for Deep Learning with Limited and Imbalanced Data: Application to CT-Based COVID-19 Detection

Annotating medical images for disease detection is often tedious and expensive. Moreover, the available training samples for a given task are generally scarce and imbalanced. These conditions are not conducive for learning effective deep neural models. Hence, it is common to ‘transfer' neural networks trained on natural images to the medical image domain. However, this paradigm lacks in performance due to the large domain gap between the natural and medical image data. To address that, we propose a novel concept of Pre-text Representation Transfer (PRT). In contrast to the conventional transfer learning, which fine-tunes a source model after replacing its classification layers, PRT retains the original classification layers and updates the representation layers through an unsupervised pre-text task. The task is performed with (original, not synthetic) medical images, without utilizing any annotations. This enables representation transfer with a large amount of training data. This high-fidelity representation transfer allows us to use the resulting model as a more effective feature extractor. Moreover, we can also subsequently perform the traditional transfer learning with this model. We devise a collaborative representation based classification layer for the case when we leverage the model as a feature extractor. We fuse the output of this layer with the predictions of a model induced with the traditional transfer learning performed over our pre-text transferred model. The utility of our technique for limited and imbalanced data classification problem is demonstrated with an extensive five-fold evaluation for three large-scale models, tested for five different class-imbalance ratios for CT based COVID-19 detection. Our results show a consistent gain over the conventional transfer learning with the proposed method. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Proximal Tubular Dysfunction as a Predictor of Aki in Hospitalized Covid-19 Patients

Introduction: Severe acute respiratory syndrome coronavirus 2 associated pneumonia (COVID-19) is a modern pandemic. Recent evidence suggests that kidney is an important target organ in COVID-19. High concentration of Angiotensin converting enzyme receptors in the proximal tubules make them an early target. Proximal tubular dysfunction (PTD) may act as an early predictor of acute kidney injury (AKI), need for renal replacement therapy (RRT), intensive care unit (ICU) transfer, mechanical ventilation, hospital length of stay (LOS) and death. Method(s): This prospective observational study was conducted in the COVID unit, Bangabandhu Sheikh Mujib Medical University. 87 COVID-19 patients without preexisting kidney disease were screened for markers of PTD on admission. Patients having at least 2 of the 4 defining markers of PTD (inappropriate uricosuria, renal phosphate leak, normoglycemic glycosuria and proteinuria) positive on admission were considered to have PTD. 35 patients with PTD and 35 without PTD were followed up throughout their hospital stay and compared. Result(s): 52.9% of the patients had at least 2 of the 4 defining markers of PTD positive on admission. The most prevalent markers were proteinuria (66.7%), followed by hyperuricosuria (42.5%), renal phosphate leak (28.7%) and normoglycemic glycosuria (20.7%). Also, 67% patients had renal sodium leak and 32.2% patients had renal potassium leak. Mean age was 55.7 years. 50% of the patients were diabetic. The PTD group had significantly lower oxygen saturation and higher parenchymal involvement on HRCT chest, CRP and LDH compared to the non PTD group on admission. 32.9% patients developed AKI during their hospital stay. PTD group had higher odds of developing AKI (odds ratio 17.5 for stage 1, 24.8 for stage 2 and 25.5 for stage 3;p<0.0001). The mean duration of hospital stay was 9 days higher in the PTD group (p<0.001). PTD group also had higher odds of transferring to ICU (OR=9.4, p=0.002), need for mechanical ventilation (OR=10.1, p=0.002) and death (OR=10.3, p=0.001). There was complete recovery of PTD in 32.6% and complete renal recovery in 47.8% of patients during their hospital stay. 26.1% of the patients who developed AKI required hemodialysis. 11.4% of all patients died. Conclusion(s): Proximal tubular dysfunction is highly prevalent in COVID-19 patients very early in the disease and may act as a predictor of AKI, ICU transfer, need for mechanical ventilation and death. No conflict of interestCopyright © 2023

Impacts of COVID-19 Pandemic Lockdown on Road Safety in Bangladesh

The purpose of this research is to demonstrate the trends of crashes, injuries, and fatalities under the effect of the lockdown and observe the deviation of these trends from the anticipated values that would have been seen without the impact of the lockdown. To that end, data on road collisions, injuries, and fatalities in Bangladesh were compiled over four years (from January 2016 to May 2020) using the dataset from the Accident Research Institute (ARI). The pre-pandemic and lockdown period during the pandemic were included in the selected study period. To compare the observed values of the number of crashes, injuries, and fatalities to the forecasted values, which were meant to show assumed conditions without the emergence of the COVID-19 pandemic, different Autoregressive Integrated Moving Average (ARIMA) time series models were developed for each first-level administrative divisions (Dhaka, Chattogram, Khulna, Barishal, Rajshahi, Sylhet, Rangpur, and Mymensingh). Due to the mobility restrictions, the observed number of collisions, injuries, and deaths remained below the expected values, with a discernible high difference throughout the entire lockdown in Dhaka and Chattogram. In contrast, in the case of other divisions (Khulna, Barishal, Rajshahi, Sylhet, Rangpur, and Mymensingh), it remained under the expected trend for most of the lockdown period but not entirely. The mobility was not eliminated, resulting in a non-zero crash, injury, and fatality records across all divisions. In multiple instances, we observed that actual collision, injury, and fatality rates were higher than expected. Additionally, various divisions exhibited varying patterns of crashes, injuries, and fatalities during stay-at-home orders. Poor performance has been noted in terms of overall road safety during the pandemic era. Given the possibility of future waves of COVID-19 cases and other pandemics, the results of the current study can be used by local authorities and policymakers to improve road safety. © 2023 by the authors.

SARS-CoV-2 infection alters the gut microbiome in diabetes patients: A cross-sectional study from Bangladesh.

Populations of different South Asian nations including Bangladesh reportedly have a high risk of developing diabetes in recent years. This study aimed to investigate the differences in the gut microbiome of COVID-19-positive participants with or without type 2 diabetes mellitus (T2DM) compared with healthy control subjects. Microbiome data of 30 participants with T2DM were compared with 22 age-, sex-, and body mass index (BMI)-matched individuals. Clinical features were recorded while fecal samples were collected aseptically from the participants. Amplicon-based (16S rRNA) metagenome analyses were employed to explore the dysbiosis of gut microbiota and its correlation with genomic and functional features in COVID-19 patients with or without T2DM. Comparing the detected bacterial genera across the sample groups, 98 unique genera were identified, of which 9 genera had unique association with COVID-19 T2DM patients. Among different bacterial groups, Shigella (25%), Bacteroides (23.45%), and Megamonas (15.90%) had higher mean relative abundances in COVID-19 patients with T2DM. An elevated gut microbiota dysbiosis in T2DM patients with COVID-19 was observed while some metabolic functional changes correlated with bidirectional microbiome dysbiosis between diabetes and non-diabetes humans gut were also found. These results further highlight the possible association of COVID-19 infection that might be linked with alteration of gut microbiome among T2DM patients.

Single Minute Exchange Die (SMED): A sustainable and well-timed approach for Bangladeshi garments industry

Bangladesh is the second largest Ready-Made Garments (RMG) exporting country after China. The cost of cotton and other raw materials, labor cost, and subsidiary cost increased much in post COVID-19 with the comparison of pre-Covid-19 times, but from the prospect of buyer's price is not increasing that much. In this context, our study focused on the RMG's very first time extensive Quick Changeover (QCO) process to minimize cost reduction as well as wastage and time using Single Minute Exchange Die (SMED). Initially, concentrated on the learning period to make acknowledge the changing phase of one style to another. At the same time, tried to figure out the overall weekly performance before and after implementing QCO on the floors, efficiency, before and after implementing QCO hit rate and time consumption, and wastages. According to the case study, floor one had the best average weekly performance, action achieved percentage, and efficiency performance of 57%, 48%, and 46%, respectively, among the five, analyzed floors. From the investigated five floors, the third one had the lowest weekly performance, percentage of actions completed, and efficiency, at 52%, 40%, and 34%, respectively. In the case of hit styles, floor two and floor five both achieved 83% after QCO apply in the floors. During the QCO, the highest production loss on floor one was the alarming sign which was 21,940 pieces and on floor three loss production was the lowest 2605 pieces after QCO implementation. © 2022 The Authors

User Perspective Bangla Sentiment Analysis for Online Gaming Addiction using Machine Learning

Sentiment analysis is the modern Natural Language Processing (NLP) technique for determining the sentiment of a user. The recent COVID-19 pandemic has pushed people of all ages, particularly the youth to get directly or indirectly involved in internet activities, one of which is online gaming. People have become increasingly involved in online gaming since they have easy access to the internet via smartphones. This research study has attempted to investigate online gaming addiction using different machine learning classification algorithms from over 401 data points. People of all ages, particularly students in high school, college, and university, are considered for data collection. After preprocessing and feature engineering the collected data, six state-of-the-art machine learning classification algorithms viz. Decision Tree, Random Forest, Multinomial Naive Bayes, Extreme Gradient Boosting, Support Vector Machine and K Nearest Neighbor are used to train the model. All six classifiers predict with high accuracy, with Multinomial Naive Bayes (MNB) having the highest accuracy of 73.27%. © 2022 IEEE.

Bioactivity classification of SARS-CoV-2 Proteinase using Machine Learning Approaches

Machine learning has seen a considerable increase in performance and interest in scientific research and industrial applications over the previous decade. The success of most current state-of-the-art methods can be linked to recent deep learning advancements. Deep learning has been demonstrated to outperform not only standard machine learning but also highly specialized tools designed by domain specialists when applied to many scientific fields involving the processing of non-tabular data, such as pictures or text. This article will cover ML-based research on SARS-Co V-2 Proteinase Biological Activity classification, with an emphasis on the most recent successes and research trends. SARS-CoV-2 (Severe Acute Respiratory Syndrome Coronavirus 2) produced a global pandemic of coronavirus illness (COVID-19), which prompted a rush to find treatment options. Despite the attempts, no vaccine or medicine for therapy has been approved. In this paper, we mentioned some previous articles that have resulted in successful bioactivity prediction. The discussion of the machine having to learn technology that has been used for bioactivity prediction in general and has the potential to lead the way for successful working with complex molecules in the future is also a focus of this review. The study finishes with a brief viewpoint on contemporary machine learning research advances, including student engagement and semi-supervised learning, which offer considerable potential for increasing bioactive discovery. © 2022 IEEE.

Low-Dose Versus High-Dose Tocilizumab in Covid-19 Patients with Hypoxic Respiratory Failure

INTRODUCTION: Tocilizumab has been shown to decrease mortality when used concomitantly with steroids in COVID-19. Tocilizumab dose of 8 mg/kg (max: 800 mg), stemmed from the RECOVERY trial, has been the standard dose for COVID. Due to a drug shortage of tocilizumab, our study seeks to assess whether low dose (400 mg) shows similar benefit compared to high dose for COVID patients concurrently on same median dose of steroids. METHOD(S): This was a retrospective observational study of COVID-19 patients who received tocilizumab in conjunction with steroids. Between March 2020 and August 2021, adult patients with positive COVID-19 PCR, hypoxic respiratory failure defined as FiO2>70%, and received a dose of tocilizumab in conjunction with steroids were included. Patients were excluded if they have died within 24 hours of treatment initiation. Primary outcome was 28-day mortality and secondary outcomes included biomarker improvement and relative risk of infection. Propensity matched analysis between groups was performed. RESULT(S): A total of 407 patients met the study criteria and were analyzed. The low dose and high dose tocilizumab group had 222 and 185 patients respectively. Gender and age were similar between groups and all patients received steroids. The low dose group was significantly more ill at baseline as a higher percentage of patients received vasopressors, were admitted to the ICU and on mechanical ventilation. In the propensity-matched analysis of 56 patients in each group, with a median dose of steroid of 10 mg in both groups showed no difference in 28 day mortality (HR 0.82 [95% CI: 0.41-1.67];p=0.6138). A greater decrease to normalization of CRP (p< 0.0001) and downtrend of ferritin (p=0.503) was observed in the high dose group at day 14. The high dose group trended a higher rate of fungal and viral infections. CONCLUSION(S): Compared to low dose tocilizumab, high dose did not provide additional efficacy and mortality benefit but resulted in uptrend of fungal and viral infections. While a greater decrease in CRP was seen in the high dose group, it did not translate into lower mortality. This study illustrates that low dose tocilizumab can be an alternative to high dose during a drug shortage of tocilizumab without compensating for efficacy and safety, conserving resources for more patients.

Artificial Intelligence-Powered Contactless Face Recognition Technique for Internet of Things Access for Smart Mobility

A contactless system became necessary for smart mobility during the COVID-19 pandemic. There are many touchpoints in private and public areas where contact is essential, such as intelligent transportation systems for vaccine carriers, patient ambulances, elevators, metros, buses, hospitals, and banks. A secured contactless device reduces the chances of COVID-19 infection spread. Several devices use smart cards, fingerprint identification, or code-based access. Most of these devices require some form of touch. The cost of such devices varies, depending on their capability and intended use. Sensors developed by using artificial intelligence (AI) to provide secured access are an emerging area. This paper presents an AI-powered contactless face recognition system. The solution has the Internet of Things (IoT) enabled access system. To identify a person, it uses AI assistance for face recognition with the help of Python Dlib's facial recognition network. Dlib offers a wide range of functionality across several machine learning sectors and is open-source. The Arduino Uno (ATmega328P) and STK500 protocol has been used for communication to testify and validate the performance of the proposed technique. The objective is to detect and recognize faces by the proposed contactless approach. The obtained result shows 92% accuracy, 94% sensitivity, 96% precision and FRR 6% for face detection. There is a significant improvement in FRR in our work compared to the published 27.27%. The implemented solution in this paper provides accurate and secure contactless access to conventional, readily available techniques in public health safety.