Understanding the COVID-19 pandemic prevalence in Africa through optimal feature selection and clustering: evidence from a statistical perspective

Abstract

The COVID-19 pandemic, which outbroke in Wuhan (China) in December 2019, severely hit almost all sectors of activity in the world as a consequence of the restrictive measures imposed. Two years later, Africa still emerges as the least affected continent by the pandemic. This study analyzed COVID-19 prevalence across African countries through country-level variables prior to clustering. Using Spearman-rank correlation, multicollinearity analysis and univariate filtering, 9 country-level variables were identified from an initial set of 34 variables. These variables relate to socioeconomic status, population structure, healthcare system and environment and the climatic setting. A clustering of the 54 African countries is further carried out through the use of agglomerative hierarchical clustering (AHC) method, which generated 3 distinctive clusters. Cluster 1 (11 countries) is the most affected by COVID-19 (median of 63,508.6 confirmed cases and 946.5 deaths per million) and is composed of countries with the highest socioeconomic status. Cluster 2 (27 countries) is the least affected (median of 4473.7 confirmed cases and 81.2 deaths per million), and mainly features countries with the least socioeconomic features and international exposure. Cluster 3 (16 countries) is intermediate in terms of COVID-19 prevalence (median of 2569.3 confirmed cases and 35.7 deaths per million) and features countries the least urbanized and geographically close to the equator, with intermediate international exposure and socioeconomic features. These findings shed light on the main features of COVID-19 prevalence in Africa and might help refine effectively coping management strategies of the ongoing pandemic. Supplementary Information The online version contains supplementary material available at 10.1007/s10668-022-02646-3.

LSTM-Powered COVID-19 prediction in central Thailand incorporating meteorological and particulate matter data with a multi-feature selection approach

“…Wrapper methods have gained attention in COVID-19 research as a powerful approach for selecting relevant features and optimizing predictive models. Several studies have explored the application of wrapper methods in the context of COVID-19 analysis [ [40] , [41] , [42] , [43] ]. Researchers have utilized techniques like Recursive Feature Elimination (RFE), Genetic Algorithms (GA), Selection by Filtering (SBF), and Sequential Feature Selection (SFS) to identify factors such as demographic information, comorbidities, and environmental variables that significantly impact COVID-19 outcomes.…”

“…Researchers have utilized techniques like Recursive Feature Elimination (RFE), Genetic Algorithms (GA), Selection by Filtering (SBF), and Sequential Feature Selection (SFS) to identify factors such as demographic information, comorbidities, and environmental variables that significantly impact COVID-19 outcomes. By selecting the most informative features, these studies aim to enhance the accuracy of predictive models [ 40 , 41 ].…”

Climate and COVID-19 transmission: a cross-sectional study in Africa

“…Meteorological conditions can influence how the virus survives and persists within a given environment, which in turn might affect the likelihood of transmission of the disease 12 . Overall, most of the available studies tend to report lower transmission rates at warmer temperatures but higher transmission in colder and dry environments 9 , 13 , along with exacerbating effects of humidity, higher air concentration in fine particles 14 , lower wind speeds 15 or lower solar radiation 9 . For example, in South Asia, Hossain et al 12 identified a positive association between COVID-19 confirmed cases and minimum, maximum and average temperatures, rainfall, relative air humidity, wind speed and surface pressure.…”

“…Meanwhile, the top five hard-hit countries ( in decreasing order of severity : South Africa, Morocco, Tunisia, Egypt and Libya) reported 60.3% and 69.7% of the total confirmed cases and deaths (respectively) 5 . These figures are thought to be due to specific traits of the African context, including the low rate of urbanization, the limited transport network hindering the mobility of people, and the young age of the population 8 , 9 . Also, the lower case fatality rate in Africa of non-communicable diseases such as cancer, cardiovascular accidents and diabetes (already known as comorbidities in this pandemic) has been often put forward 7 , 10 .…”

“…Other meteorological parameters, such as wind speed and air pollutants are also reported as likely influential on COVID-19 transmission rates 12 , 20 . Solar radiation and geographical latitude (representing the distance to the equator) have also been identified as significant in explaining COVID-19 deaths 9 , 13 . Moreover, the relationship between climate and COVID-19 transmission is thought to be complex because weather patterns in a year affect human behaviour, therefore affecting the observation of lifting of containment measures.…”