Predicting Study or Work from Home Satisfaction using Data Mining Technique: A Case Study in Malaysia

The COVID-19 pandemic has urged the government of Malaysia to implement Movement Control Order (MCO) which forces working people to work from home while students to study from home. People's satisfaction on work from home is crucial in determining their work productivity and efficiency whereas student's satisfaction on study from home is important for their learning effectiveness. There is no work has been done yet for exploring data mining techniques to build a model for predicting work or study from home satisfaction using Malaysia as a case study. This paper aimed to identify the best data mining model for predicting the work or study from home satisfaction. The prediction model is learned by analyzing the demographic, the personality traits, and the work from home experience collected from a group of Malaysia people. This study attempts to investigate four data mining techniques that are the decision tree, linear kernel support vector machine, polynomial support vector machine, and radial basis support vector machine. Experiment results show that the radial basis support vector machine outperformed other techniques in predicting the work or study from home satisfaction of Malaysia's community. © 2022 IEEE.

Acute pericarditis as a clinical manifestation in COVID-19 infection in a district hospital setting.

The global outbreak of coronavirus disease 2019(COVID-19) pandemic has heavily impacted the health service, leading to increased mortality and morbidity. Although known to manifest primarily as a respiratory illness, there are reports of cardiac involvement as extrapulmonary manifestation. We are reporting a case of pericarditis in a young patient who presented with only cardiac symptoms in COVID-19. He was admitted to the hospital for observation and treated with oral colchicine and oral ibuprofen. His conditions improved and subsequently discharged well. Acute pericarditis can present as part of the COVID-19 extrapulmonary spectrum. Therefore, it is important and challenging for clinicians to recognise the atypical presentations of COVID-19 to reduce morbidity and mortality.

Drug Repurposing Using Link Prediction on Knowledge Graphs with Applications to Non-volatile Memory

The active global SARS-CoV-2 pandemic caused more than 167 million cases and 3.4 million deaths worldwide. The development of completely new drugs for such a novel disease is a challenging, time intensive process and despite researchers around the world working on this task, no effective treatments have been developed yet. This emphasizes the importance of drug repurposing, where treatments are found among existing drugs that are meant for different diseases. A common approach to this is based on knowledge graphs, that condense relationships between entities like drugs, diseases and genes. Graph neural networks (GNNs) can then be used for the task at hand by predicting links in such knowledge graphs. Expanding on state-of-the-art GNN research, Doshi et al. recently developed the Dr-COVID model. We further extend their work using additional output interpretation strategies. The best aggregation strategy derives a top-100 ranking of candidate drugs, 32 of which currently being in COVID-19-related clinical trials. Moreover, we present an alternative application for the model, the generation of additional candidates based on a given pre-selection of drug candidates using collaborative filtering. In addition, we improved the implementation of the Dr-COVID model by significantly shortening the inference and pre-processing time by exploiting data-parallelism. As drug repurposing is a task that requires high computation and memory resources, we further accelerate the post-processing phase using a new emerging hardware—we propose a new approach to leverage the use of high-capacity Non-Volatile Memory for aggregate drug ranking. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A retrospective cross-sectional study on the risk factors and survival outcome of End Stage Kidney Disease patients receiving regular maintenance haemodialysis with COVID-19 infection in Hospital Enche' Besar Hajjah Khalsom, Kluang

INTRODUCTION: COVID-19 pandemic has affected healthcare services around the globe as hospitals were turned into designated hospitals to accommodate high risk groups of patients with COVID-19 infection including end stage kidney disease (ESKD) patients. In Malaysia, there was insufficient data on COVID-19 infection among ESKD patients. This study aims to determine factors and survival outcomes associated with COVID-19 infection among ESKD patients in a designated COVID-19 hospital in Malaysia. METHODS AND MATERIALS: A retrospective cross-sectional study involving 80 haemodialysis (HD) patients recruited from March 2020 till March 2021. Patients' information and results was retrieved and evaluated. Risk factors affecting the COVID-19 mortality were analysed using a one-way analysis of variance (ANOVA) and binary logistic regression. RESULTS: The mean age of the patients was 54 years who were predominantly Malays (87.5%) and living in rural areas. Majority of them had comorbidities such as diabetes mellitus (71%) and hypertension (90%). The most common presentations were fever (46%) and cough (54%) with chest radiographs showing bilateral lower zone ground glass opacities (45%). A quarter of the study population were admitted to the intensive care unit, necessitating mechanical ventilation. This study found that 51% of the patients were given steroids and 45% required oxygen supplementation. The COVID-19 infection mortality among the study population was 12.5%. Simple logistic regression analysis showed that albumin, Odd Ratio, OR=0.85 (95% Confidence Interval, 95%CI: 0.73, 0.98)) and absolute lymphocyte count OR=0.08 (95%CI: 0.11, 0.56) have inverse association with COVID-19 mortality. C-reactive protein OR=1.02 (95%CI: 1.01, 1.04), lactate dehydrogenase OR=1.01 (95%CI: 1.00, 1.01), mechanical ventilation OR=17.21 (95%CI: 3.03, 97.67) and high dose steroids OR=15.71 (95%CI: 1.80, 137.42) were directly associated with COVID-19 mortality. CONCLUSION: The high mortality rate among ESKD patients receiving HD was alarming. This warrants additional infection control measures to prevent the spread of COVID- 19 infection among this vulnerable group of patients. Expediting vaccination efforts in this group of patients should be advocated to reduce the incidence of complications from COVID-19 infection.

Guided release of a breath (GRAB)

Background and Aim: UBTs are normally performed in the hospital under the guidance of trained technicians. However, COVID-19 has reduced access to within-hospital UBTs. Self-conducted UBTs at home by patients have been suggested as an alternative. This study aims to compare the efficacy of written versus video instructions in performing unsupervised UBT well. Methods: In the first arm of this prospective study, 20 consecutive first-time UBT patients were randomized to receive either written or video instructions. Competency for self-conducted UBTs were determined by an observer assessing their technique for 5 key steps and scored upon 5. In the subsequent study, a second enhanced video was created learning from common pitfalls from the first study and tested on a separate group of 10 patients. Results: There was no difference in the completion rate at 30% but there was a lower mean score 2.3 versus 3.9 (p = 0.29) for written versus video group respectively. The most common errors found were mixing up the steps and no inflation of the bag, all of which were addressed in the enhanced video. The enhanced video group had a higher completion rate of 60%. There was a significant difference between enhanced video and written instruction (mean score of 4.6 versus 2.3;p = 0.04). Older participants and those less educated had a lower completion rate. Conclusion: Video instructions can enhance the successful collection of a breath during UBT and should therefore be considered for use to improve both completion and accuracy of self-conducted UBTs at home.

What Drives Excess Trading during the COVID-19 Pandemic?

Manuscript type: Research paper Research aims: This study aims to examine the underlying psychological and sociological factors that drive excess trading in the Malaysian stock market during a global health crisis such as the COVID-19 pandemic. Design/Methodology/Approach: A self-administered online questionnaire was collected from 271 individual investors to examine the association between big-five personality traits and trading frequency. Demographic information and investment behaviours of investors were also included in the study. The multinomial logit regression model was used to test the research hypotheses. Research findings: Findings show that personality traits such as openness to experience and agreeableness have a significant influence on trading frequency. Demographic factors and investment behaviours such as gender, household income level, years of investment experience and type of investor all have a significant positive relationship with trading frequency. Theoretical contribution/Originality: This study contributes to the current investor behaviour literature in Malaysia, which remains to be very limited, especially during a global health crisis. The study indicates that personality traits, demographic, socio-economic factors, and investment behaviours affect the trading frequency of Malaysian investors. Practitioner/Policy implication: This study offers insights for financial institutions and individual investors on the type of personality traits, demographic, socio-economic factors, and investment behaviours that drive excess trading during a global health crisis. The findings provide important contributions to avoid serious mistakes in investment analysis and trading profitable investment strategies, thus improving individual and team performance. Research limitation/Implications: Some results are not significant and may be limited due to the small sample size used in this study. Future research could recruit more retail investors to confirm the significance level of those variables. Besides, the study can be conducted after the COVID-19 pandemic to explore whether there is any significant difference in the variables during and after the global health crisis.