METHODS: A total of 1028 confirmed cases of COVID-19 from Africa with definite survival outcomes were identified retrospectively from an open-access individual-level worldwide COVID-19 database. The live version of the dataset is available at https://github.com/beoutbreakprepared/nCoV2019 . Multivariable logistic regression was conducted to determine the risk factors that independently predict mortality among patients with COVID-19 in Africa.
RESULTS: Of the 1028 cases included in study, 432 (42.0%) were females with a median (interquartile range, IQR) age of 50 (24) years. Older age (adjusted odds ratio {aOR} 1.06; [95% confidence intervals {95% CI}, 1.04-1.08]), presence of chronic disease (aOR 9.63; [95% CI, 3.84-24.15]), travel history (aOR 2.44; [95% CI, 1.26-4.72]), as well as locations of Central Africa (aOR 0.14; [95% CI, 0.03-0.72]) and West Africa (aOR 0.12; [95% CI, 0.04-0.32]) were identified as the independent risk factors significantly associated with increased mortality among the patients with COVID-19.
CONCLUSIONS: The COVID-19 pandemic is evolving gradually in Africa. Among patients with COVID-19 in Africa, older age, presence of chronic disease, travel history, and the locations of Central Africa and West Africa were associated with increased mortality. A regional response should prioritize strategies that will protect these populations. Also, conducting a further in-depth study could provide more insights into additional factors predictive of mortality in COVID-19 patients.
RESEARCH DESIGN AND METHODS: Data on 132,373 individuals aged 35-70 years from 21 countries were analyzed. White rice consumption (cooked) was categorized as <150, ≥150 to <300, ≥300 to <450, and ≥450 g/day, based on one cup of cooked rice = 150 g. The primary outcome was incident diabetes. Hazard ratios (HRs) were calculated using a multivariable Cox frailty model.
RESULTS: During a mean follow-up period of 9.5 years, 6,129 individuals without baseline diabetes developed incident diabetes. In the overall cohort, higher intake of white rice (≥450 g/day compared with <150 g/day) was associated with increased risk of diabetes (HR 1.20; 95% CI 1.02-1.40; P for trend = 0.003). However, the highest risk was seen in South Asia (HR 1.61; 95% CI 1.13-2.30; P for trend = 0.02), followed by other regions of the world (which included South East Asia, Middle East, South America, North America, Europe, and Africa) (HR 1.41; 95% CI 1.08-1.86; P for trend = 0.01), while in China there was no significant association (HR 1.04; 95% CI 0.77-1.40; P for trend = 0.38).
CONCLUSIONS: Higher consumption of white rice is associated with an increased risk of incident diabetes with the strongest association being observed in South Asia, while in other regions, a modest, nonsignificant association was seen.
METHODS: This study used available under-five nutritional secondary data from the Demographic and Health Surveys performed in sub-Saharan African countries. The research used bagging, boosting, and voting algorithms, such as random forest, decision tree, eXtreme Gradient Boosting, and k-nearest neighbors machine learning methods, to generate the MVBHE model.
RESULTS: We evaluated the model performances in contrast to each other using different measures, including accuracy, precision, recall, and the F1 score. The results of the experiment showed that the MVBHE model (96%) was better at predicting malnutrition than the random forest (81%), decision tree (60%), eXtreme Gradient Boosting (79%), and k-nearest neighbors (74%).
CONCLUSIONS: The random forest algorithm demonstrated the highest prediction accuracy (81%) compared with the decision tree, eXtreme Gradient Boosting, and k-nearest neighbors algorithms. The accuracy was then enhanced to 96% using the MVBHE model. The MVBHE model is recommended by the present study as the best way to predict malnutrition in under-five children.