🔍 Project Overview This Power BI report provides a comprehensive exploratory and analytical view of a diabetes dataset, focusing on medical indicators and demographic factors associated with diabetes risk. The goal of this project is to transform raw clinical data into actionable insights that help understand patterns, correlations, and potential risk drivers for diabetes. This dashboard is designed for: • Data analytics portfolios • Healthcare data exploration • Demonstrating Power BI storytelling & visualization skills • Learning medical data analysis concepts
🧩 Dataset Description The dataset contains medical and demographic variables commonly used in diabetes research, including: • Glucose level • Insulin level • BMI (Body Mass Index) • Skin thickness • Blood pressure • Age • Pregnancy count • Diabetes outcome (target variable) These variables are widely used in predictive modeling and health risk assessment.
📄 Report Pages 1️⃣ Overview The overview page provides a high-level snapshot of the dataset, including: • Total records • Diabetes vs non-diabetes distribution • Key KPIs and summary metrics • Quick visual trends across core variables This page helps users quickly understand dataset composition and outcome distribution.
2️⃣ Glucose & Insulin Analysis This page focuses on two critical biomarkers: • Glucose distribution and its relation to diabetes • Insulin trends across patient groups • Correlation patterns between glucose, insulin, and outcomes 👉 Purpose: Identify how glucose and insulin levels influence diabetes likelihood.
3️⃣ BMI & Skin Thickness Explores body composition metrics: • BMI distribution by outcome • Skin thickness patterns • Relationship between obesity indicators and diabetes risk 👉 Purpose: Highlight how body fat indicators correlate with diabetes.
4️⃣ Blood Pressure & Health Risk Analyzes cardiovascular-related indicators: • Blood pressure trends • Risk segmentation by pressure ranges • Association between hypertension and diabetes 👉 Purpose: Understand links between blood pressure and diabetic risk.
5️⃣ Demographic & Age Insights Focuses on population trends: • Age-group analysis • Diabetes prevalence by age • Distribution comparisons across demographics 👉 Purpose: Reveal how diabetes risk changes across age groups.
6️⃣ Pregnancy as a Factor Investigates pregnancy-related impact: • Diabetes prevalence vs number of pregnancies • Risk patterns in higher pregnancy counts • Combined view with age and BMI 👉 Purpose: Study pregnancy as a contributing factor to diabetes risk.
7️⃣ AI-Generated Key Influencers Uses Power BI’s AI visuals to automatically identify: • Top drivers influencing diabetes • Variable importance ranking • Influencer pathways and explanations 👉 Purpose: Provide AI-assisted insights beyond manual analysis.
✨ Key Features ✅ Clean and interactive visual design ✅ Drill-down and filtering capability ✅ AI-powered insights ✅ Health-focused analytical storytelling ✅ Business Intelligence best practices applied
🛠 Tools & Technologies • Power BI Desktop • Data modeling & DAX measures • AI visuals (Key Influencers) • Data cleaning & transformation
🎯 Learning Outcomes Through this project: • Applied EDA concepts in Power BI • Practiced health-data storytelling • Built multi-page analytical dashboards • Used AI visuals for automated insights • Strengthened data modeling skills
📌 How to Use
- Open the .pbix file in Power BI Desktop
- Navigate through report pages
- Use slicers and filters for deeper exploration
- Interact with visuals for drill-down insights
👤 Author Shorya Bisht Data Science | Analytics | AI Enthusiast Sharing practical, insight-driven data projects that make analytics meaningful. https://www.linkedin.com/in/shorya-bisht-a20144349/