Description
This issue proposes the addition of an AI-powered feature allowing users to create cohort definitions in D2E Cohorts from natural language descriptions. By supporting the direct transformation of plain text criteria into valid OMOP CDM cohort definitions, this feature will make cohort building more rapid, intuitive, and accessible to users with varying levels of technical expertise.
There is relevant previous work by OHDSI, specifically the Criteria2Query project, which explored the use of natural language processing and AI to translate narrative cohort definitions into computable representations. (Criteria2Query 3.0: Leveraging generative large language models for clinical trial eligibility query generation)
These publications can serve as valuable references and guidance for implementing similar AI-driven cohort definition capabilities in D2E.