Healthcare data scientist and Associate Director, VA Health Economics Resource Center
I turn claims, EHR, and clinical trial data into real-world evidence and tools that shape care for Veterans.
Current roles, held concurrently. B.A., Economics, UCLA.
Led adoption of the open-source Tuva healthcare data model to put VA community care claims into one analysis-ready structure, taking it from discovery to production. Owned data quality validation with QA dashboards.
Azure Databricks, dbt, SQL
Led annotation teams and built reference datasets to develop, validate, and monitor an LLM-based framework that flags emerging drug threats in clinical text. Wrote SQL procedures that track pipeline output weekly.
LLMs, NLP, SQL, Python
Launched the first VA nationwide clinical operations dashboard to use NLP data, combining structured records with information extracted from patient notes. Trained 24 subject matter experts to use it.
Power BI, NLP, SQL
Built a pipeline that identifies pregnancy episodes, births, and losses from VA and community care claims. It feeds a national dashboard and congressionally mandated quarterly reports on severe maternal morbidity.
SQL, SAS, Power BI, ICD-10, CPT, DRG
20+ peer-reviewed articles on maternal health, opioid use disorder, health care costs, and statistical methods. Full list on Google Scholar.
I'm based in the San Francisco Bay Area. Email is the best way to reach me.