AI for Clinical Trials
Automating the drafting of clinical trial eligibility criteria using retrieval-augmented generation over real oncology trial data.
A research project at USC's AI for Healthcare Lab building tooling that reduces the manual effort researchers spend writing inclusion and exclusion criteria for oncology trials. A Python ETL pipeline pulls from the ClinicalTrials.gov REST API to bulk-download, parse, and structure a corpus of real trial records into a queryable format.
When a researcher begins drafting criteria for a new trial, a RAG pipeline using Sentence-Transformers and ChromaDB retrieves the most semantically similar existing trials from the corpus. Those retrieved examples are passed to Llama 3 running locally via Ollama, which synthesizes grounded, citation-backed eligibility criteria drafts — reducing blank-page friction and anchoring output in real precedent rather than hallucinated structure.
tech
- Python
- ETL
- REST API
- ClinicalTrials.gov
- Sentence-Transformers
- ChromaDB
- RAG
- Llama 3
- Ollama
- NLP