Senior Data Scientist Analyst

Indiana University Health – healthcare ML, cohort development, sickle cell disease research.

Senior Data Scientist Analyst

Indiana University Health | February 2021 – Present

What I Do

Driving data-driven decision-making in healthcare by developing patient cohorts and implementing advanced data analysis techniques. My primary focus is sickle cell disease research under a grant-funded project led by Dr. Gerard Hills.

Key Contributions

• SCD Mortality Prediction: Built random forest models for 5-year mortality risk using multi-site EHR data, with SHAP-based clinical interpretation and external validation
• Cohort Development: Automated patient cohort extraction from Azure Data Warehouse using R, replacing manual SQL workflows
• Student Mentorship: Collaborated with students on capstone projects in healthcare analytics
• Analytical Infrastructure: Established reproducible analysis pipelines using targets, Quarto, and tidymodels

Tools & Methods

R, tidymodels, ranger, SHAP (kernelshap), Azure Data Warehouse, SQL, Quarto, targets, survival analysis, gtsummary