Geospatial Analysis of Safe Delivery App Events Based on Geographically Weighted Regression Tool

Abstract

Abstract. This study explores the spatial relationship between the number of recorded events of the Safe Delivery App, which is a mobile learning tool to train midwives in developing countries, during three months, and several independent variables, including the number of health facilities, pregnancies, number of women of childbearing age, number of infants aged 0–1 years, mobile network coverage data and total population density. The study aims to identify and analyse the reach of the Safe Delivery App at the district level in Ghana country, considering the correlation between dependent and independent variables. The geospatial analysis of App usage events layered with several related explanatory variables is based on Geographically Weighted Regression. The explanatory variables were able to predict and explain the number of events with of accuracy score of 90 % at the district level. The results have provided valuable insights into the further roll-out of the App and helped to highlight the districts that need further support to roll out the Safe Delivery App considering the analysed independent variables.