Technical Skills
Data Analysis & Visualization
- Tableau Desktop
- Microsoft Excel (Advanced)
- Statistical Analysis
- Data Cleaning & Transformation
- Dashboard Development
Statistical Methods
- Regression Analysis
- Hypothesis Testing
- Correlation Analysis
- Predictive Modeling
- Clinical Data Interpretation
Healthcare Analytics
- Patient Outcome Analysis
- Healthcare Metrics
- Clinical Data Analysis
- Risk Assessment
- Population Health Insights
Business Systems
- SAP
- Oracle ERP
- Microsoft Office Suite
- Process Optimization
- Data Quality Management
Analytics Projects
Diabetes Patient Outcome Analysis
Project Overview: Comprehensive statistical analysis of 2,768 diabetes patients examining relationships between BMI, Age, Glucose levels, and Blood Pressure using advanced Tableau visualizations and Excel data processing. This project demonstrates proficiency in healthcare analytics, statistical interpretation, and data-driven insights for clinical decision-making.
Key Clinical Insights
- Diabetes diagnosis increases baseline glucose levels by 35-40 mg/dL, independent of other factors
- BMI and Age are significant predictors of glucose levels in non-diabetic patients (R² = 22.3% and 21.1% respectively)
- These predictive relationships break down in diabetic patients, suggesting diabetes fundamentally alters glucose metabolism
- Diabetic patients experience twice the rate of cardiovascular aging compared to non-diabetics (2.0 mmHg vs 1.0 mmHg per year)
- All regression models showed statistical significance (p < 0.0001), confirming robust relationships
Technical Implementation
Data Processing: Cleaned and validated 2,768 patient records in Excel, created calculated fields for risk categorization, and performed comprehensive data quality checks to ensure 99.9% accuracy.
Statistical Analysis: Implemented three distinct regression models in Tableau analyzing BMI-Glucose, Age-Glucose, and Blood Pressure-Age relationships. Calculated R² values, p-values, regression equations, and confidence intervals for each model. Performed comparative analysis to identify differential patterns between diabetic and non-diabetic populations.
Visualization Design: Created an interactive dashboard with five coordinated visualizations including scatter plots with regression lines, comparative bar charts, and box plots. Implemented color-coding by diabetes status and interactive filtering capabilities for dynamic analysis.
Clinical Interpretation: Translated statistical findings into actionable healthcare insights, including identification of high-risk patient populations, cardiovascular risk acceleration in diabetic patients, and evidence-based recommendations for clinical monitoring protocols.
Deliverables
- Interactive Tableau dashboard with 5 coordinated visualizations
- Five comprehensive analysis reports with statistical interpretations
- Cleaned and validated dataset with calculated risk categories
- Comparative regression analysis across patient populations
- Clinical recommendations based on statistical findings
Healthcare Operations Analytics
Coming Soon - Analyzing operational efficiency and resource optimization in healthcare settings
Patient Flow & Capacity Planning
Coming Soon - Predictive modeling for hospital capacity and patient flow optimization
Financial Performance Analysis
Coming Soon - Healthcare financial metrics and revenue cycle analysis
Let's Connect
I'm actively seeking opportunities in healthcare analytics where I can apply my analytical skills and healthcare domain knowledge to drive data-informed decisions and improve patient outcomes.