Electronic Health Record Data Warehouse Project

• Developed a Snowflake-based data warehouse to process, analyze, and manage synthetic EHR data
• Designed and implemented a star schema with dimension and fact tables to track patient demographics, conditions, procedures, and other clinical events
• Leveraged views, foreign key constraints, and UUID-based unique identifiers for efficient data modeling and querying

Future Directions:

• interactive Tableau dashboard -- visualizations
• SAS or Python ML forcasting

Data source: Synthea Dataset Jsons - EHR (10 GB)

• deeply nested JSON files https://www.kaggle.com/datasets/krsna540/synthea-dataset-jsons-ehr