Maternal and child health care quality assessment: An improved approach using K-means clustering

Abstract

High maternal and child deaths in developing countries are frequently linked<br/>to poor health services provided to pregnant women and children. To improve<br/>the quality of maternal, neonatal and child health (MNCH) services,<br/>the government and other stakeholders in MNCH emphasize the importance<br/>of quality assessment. However, effective quality assessment approaches are<br/>mostly lacking in most developing countries, particularly in Tanzania. This<br/>study, therefore, aimed at developing a quality assessment approach that can<br/>effectively assess and report on the quality of MNCH services. Due to the<br/>need for a good quality assessment approach that suits a resource-constrained<br/>environment, machine learning-based approach was proposed and developed.<br/>K-means algorithm was used to develop a clustering model that groups<br/>MNCH data and performs cluster summarization to discover the knowledge<br/>portrayed in each group on the quality of MNCH services. Results confirmed<br/>the clustering model’s ability to assign the data points into appropriate clusters;<br/>cluster analysis with the collaboration of MNCH experts successfully<br/>discovered insights on the quality of services portrayed by each group.