Comparison of Provinces of Turkey In Terms of Accessing Health Care Services by Using Different Clustering Algorithms

Abstract

Having access to health care services is the most primary of the basic human rights. It is vital that all citizens in a country are able to get these services equally and homogeneously. Despite its importance, providing health services vary from both country to country and between different provinces or states in country. Similarly, it may cause severe disparities and negative effects between individuals in the society. The primary concern of this study is to determine whether there is any difference between Turkey provinces in terms of accessing health care services, or not. Several clustering algorithms including hierarchical clustering, k-means and partitioning around medoids (pam) were applied to the data set including 31 health indicators of all provinces in Turkey. After comparing these algorithms via using some measures for determining the number of clusters and cluster validity, the findings showed that there were four distinct and significant clusters based on k-means clustering algorithm. It seemed that these clustering results were in a a close reciprocal relationship with the economic development and geographical location of provinces. Clustering results were evaluated and interpreted according to these two important findings.