ABSTRACT
Background: The COVID-19 pandemic has presented a series of new challenges to governments and healthcare systems. Testing is one important method for monitoring and controlling the spread of COVID-19. Yet with a serious discrepancy in the resources available between rich and poor countries, not every country is able to employ widespread testing. Methods and Objective: Here, we have developed machine learning models for predicting the prevalence of COVID-19 cases in a country based on multilinear regression and neural network models. The models are trained on data from US states and tested against the reported infections in European countries. The model is based on four features: Number of tests, Population Percentage, Urban Population, and Gini index. Result(s): The population and the number of tests have the strongest correlation with the number of infections. The model was then tested on data from European countries for which the correlation coefficient between the actual and predicted cases R2 was found to be 0.88 in the multi-linear regression and 0.91 for the neural network model Conclusion(s): The model predicts that the actual prevalence of COVID-19 infection in countries where the number of tests is less than 10% of their populations is at least 26 times greater than the reported numbers. Copyright © 2022 Hashim et al.
ABSTRACT
Background: It is well accepted that specific micronutrients can enhance the immune response to improve resistance to viral respiratory tract infections (RTIs), such as COVID-19. The primary objective of this systematic review was to evaluate the evidence for primary prevention of any respiratory viral infection through supplementation with nutrients that already have a recognized role in immune function. Method: We conducted a systematic search in EMBASE, AMED, CAB International, MEDLINE, Scopus, and ISI Web of Science papers, published from the inception of these respective databases until 10th of April 2020. Our primary outcome was the incidence of RTIs with (potential) viral origins in subjects without increased risk of RTIs. Results: The search produced 15,163 records of which 93 papers (based on 115 studies) met the criteria to be included in the review. These studies included 199,055 study participants (191,636 children and 7,419 adults) in 37 countries around the world on supplementation with multiple micronutrients, vitamin A, folic acid, vitamin B12, C, D, E, beta-carotene, zinc, iron and long-chain polyunsaturated fatty acids. The overall ROB across all studies was moderate. Sixty-three studies were included in the meta-analyses, which was performed for children and adults separately. Supplementation with zinc in children showed a non-significant decreased risk of incidence of RTI (RR 0.91, 95%CI 0.82-1.01, I2 = 83.70% p = 0.000.) By stratifying the meta-analysis by regions of the world, only studies performed in Asia showed a significant (RR 0.86, 95%CI 0.7-0.96, I2 = 79.1%, p = 0.000) protective effect of zinc supplementation on RTI. Vitamin D supplementation in adults showed a significant decreased incidence of RTI (RR 0.89, 95%CI 0.79-0.99, I2 = 20.7%), p = 0.272). However, when subdivided by world regions, studies performed in North America showed a significant effect (RR 0.82 95%CI 0.68-0.97), but not those from Europe (RR 1.02, 95%CI 0.60-1.44) or Oceania (RR 0.97, (95%CI 0.84-1.10). Conclusion: Based on the systematic review and meta-analyses, supplementation of vitamins, multiple nutrients or fatty acids in the general population has no, or at least very limited, effect in the prevention of respiratory infections, such as COVID-19. However, there was some evidence that zinc supplementation among children in Asia, and vitamin D among adults in the USA and Canada might potentially confer protection.