Active Projects
OMOP Learning Environment
A Docker-based setup for learning OHDSI tools with synthetic patient data.
- PostgreSQL with OMOP CDM 5.4
- Synthea-generated patient data
- Pre-configured ATLAS and WebAPI
- Achilles data quality reports
Clinical NLP Pipeline
End-to-end pipeline for extracting structured data from clinical notes.
- BioBERT-based named entity recognition
- SNOMED CT concept normalization
- OMOP CDM output format
- Streamlit visualization dashboard
Tools & Utilities
- Vocabulary Explorer — Interactive tool for navigating OMOP vocabularies
- Cohort JSON Validator — Validate ATLAS cohort definition JSON
- ETL Template — Starter template for Synthea-to-OMOP transformations
More projects coming soon. Check my GitHub for the latest.