ADASEML: Hospitalization Period Prediction of COVID-19 Patients Using ADASYN and Stacking Based Ensemble Learning

The COVID-19 pandemic places additional constraints on hospitals and medical services. Understanding the period for support requirements for COVID-19 infected admitted to hospitals is critical for resource distribution planning in hospitals, particularly in resource-reserved settings. Machine Learning techniques are being used to approximate a patient's duration of stay in the hospital. This research uses Decision Tree, Random Forest and K-Nearest Neighbors, Voting classifiers, and Stacking classifiers to predict patients' length of stay in the hospital. Due to the imbalance in the dataset, Adaptive Synthetic (ADASYN) was used to resolve the issue, and the permutation feature importance method was employed to find the feature importance scores in identifying important features during the models' development process. The proposed "ADASEML” has shown superior performance to the earlier works, with an accuracy of 80%, precision of 78%, and recall of 80%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

AI-Enabled Wearable Medical Internet of Things in Healthcare System: A Survey

Technology has played a vital part in improving quality of life, especially in healthcare. Artificial intelligence (AI) and the Internet of Things (IoT) are extensively employed to link accessible medical resources and deliver dependable and effective intelligent healthcare. Body wearable devices have garnered attention as powerful devices for healthcare applications, leading to various commercially available devices for multiple purposes, including individual healthcare, activity alerts, and fitness. The paper aims to cover all the advancements made in the wearable Medical Internet of Things (IoMT) for healthcare systems, which have been scrutinized from the perceptions of their efficacy in detecting, preventing, and monitoring diseases in healthcare. The latest healthcare issues are also included, such as COVID-19 and monkeypox. This paper thoroughly discusses all the directions proposed by the researchers to improve healthcare through wearable devices and artificial intelligence. The approaches adopted by the researchers to improve the overall accuracy, efficiency, and security of the healthcare system are discussed in detail. This paper also highlights all the constraints and opportunities of developing AI enabled IoT-based healthcare systems. © 2023 by the authors.

Clinical Characteristics and Predictors of Mortality in Elderly Patients Hospitalized with COVID-19 in Bangladesh: A Multicenter, Retrospective Study.

Purpose: Elderly patients are at high risk of fatality from COVID-19. The present work aims to describe the clinical characteristics of elderly inpatients with COVID-19 and identify the predictors of in-hospital mortality at admission. Materials and Methods: In this retrospective, multicenter cohort study, we included elderly COVID-19 inpatients (n = 245) from four hospitals in Sylhet, Bangladesh, who had been discharged between October 2020 and February 2021. Demographic, clinical, and laboratory data were extracted from hospital records and compared between survivors and nonsurvivors. We used univariable and multivariable logistic regression analysis to explore the risk factors associated with in-hospital death. Principal Results. Of the included patients, 202 (82.44%) were discharged and 43 (17.55%) died in hospital. Except hypertension, other comorbidities like diabetes, chronic kidney disease, ischemic heart disease, and chronic obstructive pulmonary disease were more prevalent in nonsurvivors. Nonsurvivors had a higher prevalence of leukocytosis (51.2 versus 30.7; p=0.01), lymphopenia (72.1 versus 55; p=0.05), and thrombocytopenia (20.9 versus 9.9; p=0.07). Multivariable regression analysis showed an increasing odds ratio of in-hospital death associated with older age (odds ratio 1.05, 95% CI 1.01-1.10, per year increase; p=0.009), thrombocytopenia (OR = 3.56; 95% CI 1.22-10.33, p=0.019), and admission SpO2 (OR 0.91, 95% CI 0.88-0.95; p=0.001). Conclusions: Higher age, thrombocytopenia, and lower initial level of SpO2 at admission are predictors of in-hospital mortality in elderly patients with COVID-19.

Clinical characteristics and outcomes of vaccinated critical COVID-19 patients: A case series from a low middle-income country

Background: Vaccination plays an important role in the prevention of some infectious diseases but does it change the outcome in critically ill patients is obscure. Though vaccination leads to decreased emergency and hospital admission, still the vaccinated patients with severe diseases requiring intensive care are being reported. This case series reports the outcome of 20 critically ill patients admitted to the COVID Intensive Care Unit (ICU). Methodology: All vaccinated patients admitted to COVID-ICU at the University Hospital between January 2021 and June 2021 were reviewed. The demographics, comorbidities, vaccination status, systemic manifestations, organ support, complications, pharmacological therapy, outcome and length of ICU as well as hospital stay were recorded. To draw a comparison for all the demographics and clinical characteristics of patients, stratification analysis was performed for the outcome variables. Result(s): A total of 20 patients were included in the study among which only 7 (35%) survived. The mortality rate for patients over 60 was 84.6 %. Four of the patients had no comorbidities and all of them survived. Among the complications, acute kidney injury was the most common (70%). The median (IQR) ICU stay was 10 (7) days and hospital stay was 13.5 (11) days. Conclusion(s): The vaccinated patients admitted with COVID-19 ICU had a poor outcome and irrespective of the type of vaccine. The factors leading to increased mortality in this group of patients were male gender, age >= 60 years, and associated chronic medical illness. Copyright © 2022 Faculty of Anaesthesia, Pain and Intensive Care, AFMS. All rights reserved.

Comparison of the Performance of Machine Learning-based Algorithms for Predicting Depression and Anxiety among University Students in Bangladesh: A Result of the First Wave of the COVID-19 Pandemic

Introduction: The purpose of this research was to predict mental illness among university students using various machine learning (ML) algorithms. Methods: A structured questionnaire-based online survey was conducted on 2121 university students (private and public) living in Bangladesh. After obtaining informed consent, the participants completed a web-based survey examining sociodemographic variables and behavioral tests (including the Patient Health Questionnaire (PHQ-9) scale and the Generalized Anxiety Disorder Assessment-7 scale). This study applied six well-known ML algorithms, namely logistic regression, random forest (RF), support vector machine (SVM), linear discriminate analysis, K-nearest neighbors, Naive Bayes, and which were used to predict mental illness among university students from Dhaka city in Bangladesh. Results: Of the 2121 eligible respondents, 45% were male and 55% were female, and approximately 76.9% were 21-25 years old. The prevalence of severe depression and severe anxiety was higher for women than for men. Based on various performance parameters, the results of the accuracy assessment showed that RF outperformed other models for the prediction of depression (89% accuracy), while SVM provided the best result than other models for the prediction of anxiety (91.49% accuracy). Conclusion: Based on these findings, we recommend that the RF algorithm and the SVM algorithm were more moderate than any other ML algorithm used in this study to predict the mental health status of university students in Bangladesh (depression and anxiety, respectively). Finally, this study proposes to apply RF and SVM classification when the prediction of mental illness status is the core interest.

Determinants of regional prevalence and variations in handwashing practices among households in Bangladesh: An application of generalized mixed-effects model

Introduction: Handwashing practice is an effective way to minimize severe infectious diseases such as COVID-19, diarrhea, and pneumonia. The study aimed to explore the prevalence of handwashing behavior and associated determinants in rural and urban areas of Bangladesh. Methods: The research was performed using cross-sectional survey data from the 2019 Bangladesh Multiple Indicator Cluster Survey, and 61,242 household members were the sample for this study. The Chi-square test was applied for the bivariate analysis. A generalized linear mixed-effects model was used to identify the risk factors of practicing handwashing in both urban and rural areas of Bangladesh. Results: Only 65% of the country's households had access to handwashing facilities (place, water, and materials). While urban dwellers were more likely to wash their hands, rural dwellers were only 63% likely to do so. The level of education of household heads, wealth status, division, number of family members, sanitation facilities, and water source were the key factors associated with handwashing behavior. This study revealed that the odds were significantly lower among illiterate respondents compared to those with secondary and above-secondary education in both areas of Bangladesh, and a positive association was found between wealth status and handwashing behavior practiced in both urban and rural areas. In this study, the size of the family was statistically significant for both rural and urban areas of Bangladesh. Conclusion: Handwashing is the most prominent consideration for controlling COVID-19. Policymakers are striving to improve handwashing facilities by increasing awareness-raising programs, especially among rural residents of Bangladesh. © 2022 Asian Journal of Social Health and Behavior ;Published by Wolters Kluwer - Medknow.

VALVE-ENABLED SEQUENTIAL REAGENT DELIVERY AND PAPER-BASED ENRICHMENT FOR SIMULTANEOUS DETECTION OF SARS-COV-2 AND INFLUENZA VIRUSES

We report a point-of-care (POC) testing platform for simultaneous detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and influenza A virus. The POC device integrates sample preparation using ball-based valves for sequential delivery of reagents, viral RNA isolation and enrichment by paper-based filtration, with reverse transcription loop-mediated isothermal amplification (RT-LAMP) and colorimetric detection. The device is capable of detecting both viruses, showing high sensitivity and specificity. © 2021 MicroTAS 2021 - 25th International Conference on Miniaturized Systems for Chemistry and Life Sciences. All rights reserved.

COVID-19 mRNA vaccine-associated encephalopathy, myocarditis, and thrombocytopenia with excellent response to methylprednisolone: A case report.

INTRODUCTION: Large-scale vaccination is considered one of the most effective strategies to control the pandemic of COVID-19. Since its start, different complications have been described thought to be related to vaccination. Here, we present a rare case where encephalopathy, myocarditis, and thrombocytopenia developed simultaneously following the second dose of Pfizer-BioNTech mRNA vaccine (BNT162b2). CASE PRESENTATION: A 15-years-old female presented with fever, altered consciousness, and convulsions after taking the second shot of the vaccine. Clinical and laboratory workup was notable for the presence of thrombocytopenia and myocarditis. No alternative causes of encephalitis were found. The patient responded significantly to methylprednisolone suggesting underlying immune pathogenesis responsible for the clinical features. The diagnostic criteria for possible autoimmune encephalitis were also fulfilled. CONCLUSION: Although rare, the clinician should be aware of the possible adverse events following COVID-19 vaccination. Further research with large pooled data is needed to get more insight into its pathogenesis and causal relationship.

The outcome of COVID-19 positive patients in a COVID dedicated ICU, associated with comorbid diseases: a cross-sectional study

Background: Patients with Coronavirus Disease (COVID-19) have a significant death rate due to comorbid diseases. As a result, identifying risk factors associated with poor outcomes in COVID-19 patients is important.

Social Distance Measurement and Face Mask Detection Using Deep Learning Models

The coronavirus disease 2019 has caused a worldwide catastrophe with its destructive spreading and causing death of more than 2.47 million people around the globe. In the current circumstance, most of the countries are trying to implement social distancing, wearing masks, extensive testing, and contact tracing strategies to curb the virus outbreaks. Maintaining adequate social or physical distance is believed to be a sufficient precautionary measure (standard) against the spread of the pandemic infection. This research paper has two different contributions of social distance measurement and face mask detection using various deep learning approaches. In the first section, we have monitored the social distance where we have detected people by examining a video feed with SSD-MobileNet and Faster R-CNN ResNet50 deep learning algorithms. Next, the image is converted into an overhead view to measure the specific distance among people to ensure safe physical distancing. In the second section, we have detected the face masks used by the people by implementing MobileNetV2 convolutional neural network architecture. Hence, we have used computer vision to find the region of interest of a face, and finally, we have found that the mask is in the face or not. Both of our social distance measurement and face mask detection systems offer high accuracy. As for the social distance monitoring, the accuracy greatly depends on the people detection, and the execution time is 30 ms and 89 ms for SSD-MobileNet and Faster R-CNN ResNet50, respectively. For the face mask detection, we obtained 99% accuracy, and it is checked in real-time so that we can prove that our model is not overfitting and it performs well outside our dataset in real-time camera. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Findings of the WMT Shared Task on Machine Translation Using Terminologies

Language domains that require very careful use of terminology are abundant and reflect a significant part of the translation industry. In this work we introduce a benchmark for evaluating the quality and consistency of terminology translation, focusing on the medical (and COVID-19 specifically) domain for five language pairs: English to French, Chinese, Russian, and Korean, as well as Czech to German. We report the descriptions and results of the participating systems, commenting on the need for further research efforts towards both more adequate handling of terminologies as well as towards a proper formulation and evaluation of the task. © 2021 Association for Computational Linguistics

Design of a Low-Cost Wearable Heart and Respiratory Rate Measurement Device Using an Arduino and Bluetooth Module

The respiratory rate (RR) as well as the heart rate (HR) are two of the main vital signs that show how well a person's body is performing. The heart rate is defined as the number of times a person's heart beats in one minute, whereas the respiratory rate is defined as the number of times a person breathes in one minute (breaths per minute). Measurement of heart rate and respiratory rate often indicates a person's health condition and may identify any cardiovascular or respiratory illness. Existing wearable health smart devices are expensive and are often inaccurate. The objective of this manuscript is to develop a cheap, high-accuracy wearable heart rate and respiration rate monitoring system. A photoplethysmography (PPG) based heart rate monitor, and chest motion-based respiratory rate monitor has been used here. For the PPG-based heart rate monitor, we designed an efficient and accurate heartbeat sensor circuit. For the respiratory rate monitor, we used the concept of chest motion during exhalation and inhalation of air during the breathing process to design a chest belt module to measure a person's breathing activity. The prototype of these measurement devices was then tested on multiple test volunteers for evaluating the system's performance at various conditions. The materials used for designing this system and its performance make the device a cost-effective and reliable alternative to existing wearable smart health devices. The amount of breath completed per 60 seconds is known as the respiratory rate. When an individual is steady, the rate is typically calculated by calculating the number of breaths taken in one minute and noting the amount of times the chest rises. Fever, sickness, and other medical conditions will cause you to breathe faster. In the current situation of COVID-19, it is very necessary to check the respiratory rate to check the patient's current health status. Therefore, our project will be helpful for the COVID patients also. © 2021 IEEE.

VALVE-ENABLED SAMPLE PREPARATION AND ISOTHERMAL AMPLIFICATION FOR SARS-COV-2 DETECTION AT THE POINT-OF-CARE

Early and accurate detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) at the point-of-care (POC) is crucial for reducing the transmission of coronavirus disease 2019 (COVID-19). To address this need, we have developed a valve-enabled lysis, paper-based RNA enrichment, and RNA amplification device (VLEAD) for detecting SARSCoV-2. We have combined VLEAD with a smart coffee mug for sample preparation, nucleic acid isothermal amplification, and colorimetric detection using a smartphone camera or a naked eye. VLEAD enables two critical functions required for POC testing: sample preparation and detection. Since the reagents can be pre-packaged in the device, all operational steps can be carried out at POC. We have demonstrated the functions of the device by analyzing samples spiked with heat-inactivated SARSCoV-2, which were obtained from BEI Resources. This rapid and highly sensitive POC platform for SARS-CoV-2 detection has a potential to help reduce COVID-19 transmission. Copyright © 2021 by ASME

Influence of Mg substitution on structural, magnetic and electrical properties of Zn-Cu ferrites

Studies on Mg substituted Zn-Cu ferrites with chemical formula of Zn0.6Cu0.4−xMgxFe2O4 were synthesized by solid-state reaction technique. The structural phase of all the samples is characterized by XRD, show single phased cubic spinel structure. Density of the samples increases with the increase of Mg quantity. Average grain diameter decreases with increasing Mg content. All samples show soft ferromagnetic behavior as confirmed from the M-H hysteresis loop obtained from the VSM analysis. Thesaturation magnetization decreases with increasing Mg quantity. Increasing and decreasing trend of coercivity with the increase of Mg quantityis observed, which led to the slightly hard magnetic phase. The high frequencies create more effective for the ferrite grains of advanced conductivity and minor dielectric constant for all the samples but the AC electrical resistivity and dielectric constant are initiate to be more operational at lower frequencies. The variation of resistivity, dielectric constant with the Mg concentration is completely related to the porosity and bulk density.

Impact of COVID-19 on food safety and security in low and middle income countries

The occurrence of COVID-19 which causes severe acute respiratory infection has produced a large global outbreak with major public health concern. Since Chinese wet market (LBM) has been blamed to be linked with this global pandemic of COVID-19 as the noble virus has supposed to be transmitted from a wild species, however, this is not yet established the association of SARS-Cov-2 transmission via animal to human or food chain. Moreover, it has been recognized to spread human-to-human transmission by inhalation of droplets or direct contact. Besides the devastating effects of SARS-Cov-2, world has been experiencing the impact of food safety and security as the effect due to global lockdown resulting a wide range of new challenges of economic growth and societal burden. In this review, we have focused on effect of corona virus on food system that included food safety, food security during lockdown, and prevention and control options have been emphasized to keep normalcy of livelihood of general people in low and middle income countries (LMICs). Since the global economy has been downed deeper into a financial crunch, the government efforts are underway to bolster up the priorities with the limited resources, and further funding allocation decision is obligatory for the targeted communities those are affected most due to the swath of pandemic threat of COVID-19.

Exploring the determinants of service quality of cloud elearning system for active system usage

E-Learning through a cloud-based learning management system, with its various added advantageous features, is a widely used pedagogy at educational institutions in general and more particularly during and post Covid-19 period. Successful adoption and implementation of cloud ELearning seems difficult without significant service quality. Aims: This study aims to identify the determinant of cloud E-Learning service quality. Methodology: A theoretical model was proposed to gauge the cloud E-Learning service quality by extensive literature search. The most important factors for cloud E-Learning service quality were screened. Instruments for each factor were defined properly, and its content validity was checked with the help of Group Decision Makers (GDMs). Empirical testing was used to validate the proposed theoretical model, the self-structured closedended questionnaire was used to conduct an online survey. Findings: Internal consistency of the proposed model was checked with reliability and composite reliability and found appropriate α ≥ 0.70 and CR ≥ 0.70. Indicator Reliability was matched with the help of Outer Loading and found deemed fit OL ≥ 0.70. To establish Convergent Validity Average Variance Extracted, Factor Loading and Composite Reliability were used and found deemed suitable with AVE ≥ 0.50. The HTMT and Fornell–Lacker tests were applied to assess discriminant validity and found appropriate (HTMT ≤ 0.85). Finally, the Variance Inflation Factor was used to detect multicollinearity if any and found internal and external VIF < 3. Conclusions: Theoretical model for cloud E-Learning service quality was proposed. Information Quality, Reliability, Perceived ease of use and Social Influence were considered as explanatory variables whereas actual system usage was the dependent variable. Empirical testing on all parameters stated that the proposed model was deemed fit in evaluating cloud E-Learning service quality. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.

Screening of drug databank against WT and mutant main protease of SARS-CoV-2: Towards finding potential compound for repurposing against COVID-19

Although several pharmacological agents are under investigation to be repurposed as therapeutic against COVID-19, not much success has been achieved yet. So, the search for an effective and active option for the treatment of COVID-19 is still a big challenge. The Spike protein (S), RNA-dependent RNA polymerase (RdRp), and Main protease (Mpro) are considered to be the primary therapeutic drug target for COVID-19. In this study we have screened the drugbank compound library against the Main Protease. But our search was not limited to just Mpro. Like other viruses, SARS-CoV-2, have also acquired unique mutations. These mutations within the active site of these target proteins may be an important factor hindering effective drug candidate development. In the present study we identified important active site mutations within the SARS-CoV-2 Mpro (Y54C, N142S, T190I and A191V). Further the drugbank database was computationally screened against Mpro and the selected mutants. Finally, we came up with the common molecules effective against the wild type (WT) and all the selected Mpro. The study found Imiglitazar, was found to be the most active compound against the wild type of Mpro. While PF-03715455 (Y54C), Salvianolic acid A (N142S and T190I), and Montelukast (A191V) were found to be most active against the other selected mutants. It was also found that some other compounds such as Acteoside, 4-Amino-N- {4-[2-(2,6-Dimethyl-Phenoxy)-Acetylamino]-3-Hydroxy-1-Isobutyl-5-Phenyl-Pentyl}-Benzamide, PF-00610355, 4-Amino-N-4-[2-(2,6-Dimethyl-Phenoxy)-Acetylamino]-3-Hydroxy-1-Isobutyl-5-Phenyl-Pentyl}-Benzamide and Atorvastatin were showing high efficacy against the WT as well as other selected mutants. We believe that these molecules will provide a better and effective option for the treatment of COVID-19 clinical manifestations.

E-learning services to achieve sustainable learning and academic performance: An empirical study

E-Learning has proven to be the only resort as a replacement of traditional face-to-face learning methods in the current global lockdown due to COVID-19 pandemic. Academic institutions across the globe have invested heavily into E-Learning and the majority of the courses offered in traditional classroom mode have been converted into E-Learning mode. The success of E-Learning initiatives needs to be ensured to make it a sustainable mode of learning. The objective of the current study is to propose a holistic E-Learning service framework to ensure effective delivery and use of E-Learning Services that contributes to sustainable learning and academic performance. Based on an extensive literature review, a proposed theoretical model has been developed and tested empirically. The model identifies a broad range of success determinants and relates them to different success measures, including learning and academic performance. The proposed model was validated with the response from 397 respondents involved with an E-Learning system in the top five public universities in the southern region of Saudi Arabia through the Partial Least Squares regression technique using SmartPLS software. Five main factors (Learner’s Quality, Instructor’s Quality, Information’s Quality, System’s Quality and Institutional Quality) were identified as a determinant of E-Learning service performance which together explains 48.7% of the variance of perceived usefulness of ELS, 71.2% of the variance of use of the E-Learning system. Perceived usefulness of ELS and use of ELS together explain 70.6% of learning and academic performance of students. Hence the framework will help achieve the sustainable and successful adoption of E-Learning services. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.