Modern telemedicine requires advanced analytical solutions for efficient management of chronic diseases. This study presents the development of a comprehensive business intelligence (BI) framework using Microsoft Power BI, applied to the optimization of diabetes mellitus management. The methodology integrates Power Query transformations, 35 DAX measures organized into five functional categories, and Python 3.14.2. capabilities for advanced statistical analysis. The framework was implemented and demonstrated using a public clinical dataset of 100,000 patient records, generating five interactive dashboards covering epidemiological, demographic, clinical, geographical, and equity perspectives. A global prevalence of 8.5%, exponential growth with age, gender differences (9.75% males against 7.62% females), and substantial connections between metabolic indicators (BMI, HbA1c, and blood glucose) are all confirmed by the results. Heart disease rates are 6.2 times higher in diabetic people, according to comorbidity research. Complete methodological openness through thorough documentation, Python integration for sophisticated visualizations, and interactive multidimensional drill-down features are some of the major additions. The predictive elements are included as interpretable, exploratory components embedded in the BI environment rather than as clinically validated prediction models. This approach provides an affordable and user-friendly approach that makes advanced analytical capabilities accessible to a broader range of healthcare organizations managing chronic diseases.
Pop et al. (2026) studied this question.