OHDSI / OHDSI/StudyAgent

Fallback to Ad Hoc Phenotype Creation Given Poor/No Recommendations

Open
#52 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
12
Forks
7
Avg merge
2m
Merged PRs (30d)
12

Description

@rkboyce et al - this is amazing work. We chatted on the phenotype workgroup call a few weeks ago, and I'd be very interested in contributing some work I'll present at OHDSI global this fall on CAPR-based iterative phenotype development using LLMs. I'm not sure if that fits within your vision for the StudyAgent, but after some initial testing with this tool I do see scenarios where it may be advantageous to develop fresh phenotypes on the fly when there are no suitable definitions available in the index/catalog. Please let me know if you'd like to setup a brief call to discuss further.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are identified. Start by reviewing how StudyAgent handles phenotype recommendations and its index/catalog, then clarify the desired CAPR-based iterative phenotype workflow and what should happen when no suitable definition is available; done should include an agreed fallback scope and validation criteria.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.