Evaluation of provinces in Türkiye with health indicators by density-based spatial clustering analysis

Abstract

This study aims to evaluate the health resource distribution of provinces in Turkey using DBSCAN cluster analysis method. The optimum values of DBSCAN parameters (epsilon and minPts) were tested by simulation and the clustering silhouette value was taken as the basis for selecting the appropriate parameter set. The results of the descriptive statistical analysis of the dataset show a high coefficient of variation, indicating inequalities in the distribution of health resources. By dividing provinces into two clusters, the study reveals the similarity of local dynamics in the inequality of resource distribution. The findings provide important insights for relevant stakeholders to address the disparities between provinces in Turkey. The fact that the study adopts a method other than the hierarchical and k-means clustering methods dominant in the literature and that the codes of the algorithm are shared in Python language broadens the horizons of the relevant researchers and increases the transparency and reproducibility of the study.