Understanding Differences in Behaviour Patterns of Healthcare Service Elements Among Regions Applying Data Mining

Abstract

Maternal and child healthcare (MCH) has always been regarded as one of the important issues globally. The aim of this article is to find out all frequently occurring healthcare service elements along with their availability conditions and their interactions with other health system (HS) elements, when coverage of priority MCH intervention was either poor or moderate or good in any region. Association rule mining technique has been used to understand the probability of occurrences of different healthcare service elements among regions. Along with the proposed analytical framework, an interactive decision support system (DSS) has also been developed on a web platform, which would help healthcare policymakers to integrate the analytical framework easily in their processes of decision-making. The system has been developed by using Shiny package on R software. Data for all variables are collected for 584 Indian districts from the third phase of district-level household and facility survey. From results, it is observed that community healthcare services, sub-centre (SC)-level healthcare services and PHC-level healthcare services of a region are very much interlinked with each other, and their relationships define the healthcare condition of that region.