COMPARISON OF CHANGE-POINTS DETECTION OF COVID-19 INFECTIONS AND DEATHS WITHIN THE PANDEMIC PERIOD IN FIVE SELECTED AFRICAN COUNTRIES

Abstract

Coronavirus disease (COVID-19) has significantly affected global health, leading to increased morbidity, mortality, and strain on healthcare systems. Although numerous studies have examined COVID-19 globally, shifts in infection and death patterns during the pandemic remain underexplored in Africa. This study identifies multiple change-points in COVID-19 infections and deaths across five African countries. Kenya, Egypt, South Africa, Nigeria, and the Democratic Republic of Congo, to better understand the region’s pandemic dynamics.

This secondary data analysis utilized publicly available COVID-19 data from the World Health Organization, covering the period from March 11, 2020, to May 5, 2023. The five countries were selected to represent the major subregions of Africa based on their reported case magnitude. Daily data on infections and deaths were aggregated to weekly counts. Descriptive statistics, including medians, interquartile ranges, and time-series plots, summarized the trends. Multiple change-point detection was performed using the E-divisive method implemented in R (version 4.1.1) via the ecp package, while the Mann Kendall and Sen’s slope tests were applied to assess trends at a 5% significance level.

Results revealed distinct temporal patterns across the countries. Four major change-points were detected in each, except Nigeria, which had one for deaths. Peaks in infection occurred around February–March 2022, with South Africa consistently recording the highest infection and death rates.

These findings provide valuable insights into the temporal progression of COVID-19 in Africa, identifying critical phases that correspond with public health interventions. The study emphasizes the usefulness of change-point analysis in evaluating disease trends and guiding evidence-based responses to future outbreaks.