Detection of Persistent vs. Non-Persistent Drugs in Pharmacy Using Decision Tree Classification Based on Gini, Entropy, and Log Loss Criteria

This study evaluates the performance of Decision Tree methods in classification, utilizing three different criteria: Entropy, Gini, and Log Loss. The objective is to determine which criterion is most effective in achieving high classification accuracy using prescription data from the UCI repository, comprising 3,424 prescription records with 67 variables. The analysis results show that the Entropy criterion delivers the best performance with an accuracy of 79.1%, followed by the Gini criterion at 78%, and the Log Loss criterion at 77.9%. These findings indicate that the Entropy criterion is superior in reducing uncertainty and capturing the underlying data structure, while both Gini and Log Loss criteria also provide competitive, though slightly lower, results. The main contribution of this research is a comparative evaluation of decision tree criteria using real-world prescription data to support accurate classification of medication adherence, which can be beneficial for developing intelligent pharmacy systems. This research offers valuable insights into the effectiveness of various criteria within the Decision Tree method and can aid in selecting the most appropriate criterion for future classification applications.