Enhancing Healthcare Efficiency in Iran: A Comprehensive Analysis of Health-Oriented APIs Using Machine Learning Techniques

This study examines the efficiency of health-oriented APIs in Iran, analyzing their performance across various categories. Using a combined approach of Data Envelopment Analysis (DEA), machine learning techniques, and statistical analysis, we evaluated 149 APIs to determine their efficiency scores and identify areas for improvement.The DEA analysis revealed that many APIs, particularly those in the "Health and Wellness" and "Genetic Data" categories, operate at high-efficiency levels. The scores were calculated using an input variable derived from Principal Component Analysis (PCA) and Exploratory Factor Analysis (EFA), while the output was determined using the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). The Kruskal-Wallis test showed significant differences in efficiency scores among the macro-categories, with "Clinical and Patient Management" demonstrating notable superiority. Pairwise comparisons confirmed these differences, indicating the need for improvement in some categories.We applied a k-means clustering algorithm to classify the APIs into efficiency gradients. Validation through logistic regression confirmed the significant influence of categories on efficiency, supported by SHAP analysis. The results suggest that "Patient Management" APIs are the most efficient.Future implications include optimizing less efficient APIs and adopting more advanced techniques. These findings provide valuable guidance for improving technological performance and optimizing efficiency in the healthcare sector, contributing to a more innovative and responsive system.