Harnessing Machine Learning in Early COVID-19 Detection and Prognosis: A Comprehensive Systematic Review.

During the early phase of the COVID-19 pandemic, reverse transcriptase-polymerase chain reaction (RT-PCR) testing faced limitations, prompting the exploration of machine learning (ML) alternatives for diagnosis and prognosis. Providing a comprehensive appraisal of such decision support systems and their use in COVID-19 management can aid the medical community in making informed decisions during the risk assessment of their patients, especially in low-resource settings. Therefore, the objective of this study was to systematically review the studies that predicted the diagnosis of COVID-19 or the severity of the disease using ML. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA), we conducted a literature search of MEDLINE (OVID), Scopus, EMBASE, and IEEE Xplore from January 1 to June 31, 2020. The outcomes were COVID-19 diagnosis or prognostic measures such as death, need for mechanical ventilation, admission, and acute respiratory distress syndrome. We included peer-reviewed observational studies, clinical trials, research letters, case series, and reports. We extracted data about the study's country, setting, sample size, data source, dataset, diagnostic or prognostic outcomes, prediction measures, type of ML model, and measures of diagnostic accuracy. Bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). This study was registered in the International Prospective Register of Systematic Reviews (PROSPERO), with the number CRD42020197109. The final records included for data extraction were 66. Forty-three (64%) studies used secondary data. The majority of studies were from Chinese authors (30%). Most of the literature (79%) relied on chest imaging for prediction, while the remainder used various laboratory indicators, including hematological, biochemical, and immunological markers. Thirteen studies explored predicting COVID-19 severity, while the rest predicted diagnosis. Seventy percent of the articles used deep learning models, while 30% used traditional ML algorithms. Most studies reported high sensitivity, specificity, and accuracy for the ML models (exceeding 90%). The overall concern about the risk of bias was "unclear" in 56% of the studies. This was mainly due to concerns about selection bias. ML may help identify COVID-19 patients in the early phase of the pandemic, particularly in the context of chest imaging. Although these studies reflect that these ML models exhibit high accuracy, the novelty of these models and the biases in dataset selection make using them as a replacement for the clinicians' cognitive decision-making questionable. Continued research is needed to enhance the robustness and reliability of ML systems in COVID-19 diagnosis and prognosis.

Mental health impact of the first wave of COVID-19 pandemic on healthcare workers in 12 Arab countries.

Background: The COVID-19 pandemic has had a significant impact on public health, including healthcare workers and healthcare systems, worldwide. Aims: To investigate COVID-19-related psychological impact on healthcare workers in 12 Arab countries. Methods: This was a cross-sectional, hospital-based online survey conducted between 4 May and 8 June 2020. We evaluated stress, depression, anxiety, and insomnia using the Depression Anxiety Stress Scale and Insomnia Severity Index. Results: A total of 2879 respondents from 12 Arab countries completed the survey. Anxiety, depression, stress, and insomnia were reported by 48.9%, 50.6%, 41.4% and 72.1% of respondents, respectively. Lower-middle- and lower-income countries had a significantly higher prevalence of all the psychological outcomes than high-income countries. The prevalence of mental health symptoms was higher among healthcare workers aged 30-39 years, those who worked > 44 hours per week, and those in contact with COVID-19 cases, as well as healthcare workers who were not satisfied with the preventive measures. The prevalence of mental health symptoms was lower among male healthcare workers. Conclusion: COVID-19 had a considerable impact on the mental and psychological health of healthcare workers in Arab countries. This was aggravated by the geopolitical location of some Arab countries and social norms usually observed during the month of Ramadan. Being a physician or a young healthcare worker, and long working hours were risk factors for greater psychological impact of the outbreak.

Predictors of healthcare workers' intention to vaccinate against COVID-19: A cross sectional study from Saudi Arabia.

BACKGROUND: Vaccination is considered the best way to prevent the spread of COVID-19 and to prevent the complications of the disease. Nevertheless, no awareness campaigns were conducted in Saudi Arabia until March 1, 2021, when the Vaxzevria, or ChAdOx1 nCoV-19 (AZD1222), vaccine became available. OBJECTIVES: This study aims to determine the factors that can predict healthcare workers' acceptance of the COVID-19 vaccine. METHODS: A cross-sectional study was conducted from July to September 2021, in our university tertiary hospital (King Saud University Medical City [KSUMC]), Riyadh, Saudi Arabia. The study targeted potential participants among healthcare workers at KSUMC. We assessed healthcare workers' perceptions and beliefs about the COVID-19 vaccine via a questionnaire that was distributed via social media applications such as WhatsApp, Twitter, and Google. Participants were informed about the questionnaire before they filled it out, and they were asked to respond to three screening questions before beginning the main questionnaire. These screening questions ensured that the participants met the inclusion criteria. Included participants were over the age of 18, agreed to answer the questions, and were residents of Saudi Arabia. The participants filled out the self-administered questionnaire. RESULTS: A total of 529 participants completed the questionnaires. All participants were vaccinated, 68% were female, 55% were married, 35% had been working for less than five years, and 65% had a bachelor's degree. More than half of participants had not previously been infected with COVID-19, and most did not interact with COVID-19 patients. More convenient access to the vaccine increased the odds ratio of participant vaccination by 0.39. An increase in the number of vaccinated friends and family members increased the odds ratio of participant vaccination by 0.30. However, COVID- 19 vaccination mandates decreased the odds ratio of participant vaccination by 0.27. The fitted linear regression model explained 32% of the variation observed in the dependent variable, acceptance of the COVID-19 vaccine, and the adjusted R squared was 0.32. The fitted regression model was statistically significant at a 95% confidence interval; the p-value was 0.00001. CONCLUSION: In Saudi Arabia, there is an immense need to increase uptake of the COVID-19 vaccine. This requires encouraging more positive beliefs and attitudes regarding vaccination in general and the COVID-19 vaccine in particular.

International alliance and AGREE-ment of 71 clinical practice guidelines on the management of critical care patients with COVID-19: a living systematic review.

OBJECTIVE: We aimed to systematically identify and critically assess the clinical practice guidelines (CPGs) for the management of critically ill patients with COVID-19 with the AGREE II instrument. STUDY DESIGN AND SETTING: We searched Medline, CINAHL, EMBASE, CNKI, CBM, WanFang, and grey literature from November 2019 - November 2020. We did not apply language restrictions. One reviewer independently screened the retrieved titles and abstracts, and a second reviewer confirmed the decisions. Full texts were assessed independently and in duplicate. Disagreements were resolved by consensus. We included any guideline that provided recommendations on the management of critically ill patients with COVID-19. Data extraction was performed independently and in duplicate by two reviewers. We descriptively summarized CPGs characteristics. We assessed the quality with the AGREE II instrument and we summarized relevant therapeutic interventions. RESULTS: We retrieved 3,907 records and 71 CPGs were included. Means (Standard Deviations) of the scores for the 6 domains of the AGREE II instrument were 65%(SD19.56%), 39%(SD19.64%), 27%(SD19.48%), 70%(SD15.74%), 26%(SD18.49%), 42%(SD34.91) for the scope and purpose, stakeholder involvement, rigor of development, clarity of presentation, applicability, editorial independence domains, respectively. Most of the CPGs showed a low overall quality (less than 40%). CONCLUSION: Future CPGs for COVID-19 need to rely, for their development, on standard evidence-based methods and tools.