The Diabetic Health Analysis project focuses on uncovering key clinical, behavioral, and demographic factors that influence the progression, management, and possible remission of diabetes. Using patient-level data, the analysis evaluates trends across critical health indicators such as HbA1c, fasting glucose, blood pressure, lipid levels, and BMI, offering a comprehensive view of metabolic health. The study also examines how medication adherence, age, gender, and lifestyle behaviors such as diet, physical activity, and smoking affect outcomes. By combining clinical and behavioral dimensions, this analysis aims to support early identification of risk patterns and personalized care strategies for diabetic individuals.

The project integrates multiple tools and analytical layers—Power BI for data visualization and dashboard design, Python and Power Query (M language) for data cleaning, transformation, and modeling. The resulting dashboards visualize insights across several domains: medication effectiveness by BMI group, cognitive and cardiovascular health relationships, longitudinal progress tracking, and risk stratification models. Through advanced DAX calculations and interactive visuals, the analysis highlights how factors such as BMI, medication type, and age interact to influence glucose control, cardiovascular risk, and overall patient outcomes. This project demonstrates the power of data analytics in improving healthcare decision-making—translating raw data into actionable insights that can inform precision treatment, preventive intervention, and lifestyle-based management.