From 784abae549b4763e3c4b519b401225e6df346eb6 Mon Sep 17 00:00:00 2001 From: "Richard D Boyce, PhD" Date: Wed, 18 Mar 2026 05:36:32 -0500 Subject: [PATCH] Update 'create_new_phenotype_definition' description Enhanced the description of the 'create_new_phenotype_definition' feature to include reasoning over semantic relationships and validation processes. --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index b37ac5c..2c6c881 100644 --- a/README.md +++ b/README.md @@ -18,7 +18,7 @@ Here are some ways: - `data_quality_interpretation` : study agent provides interpretation from Data Quality Dashboard, Achilles Heel data quality checks, and Achilles data source characterizations over one or more sources that a user intends to use within a study. In this mode, the study agent derive insights from those sources based on the user's study intent. This is important because it will make the information in the characterizations and QC reports more relevant and actionable to users than static and broad-scope reports (current state). Users will use this tool from R initially. -- `create_new_phenotype_definition` : Study agent will guide the user through the creation of a definition for an EHR phenotype for the target or outcome cohort relevant to their study intent. This workflow involves selection of concepts, organization of concepts into concept sets, and organization into cohort definition logic. Users will use this tool from R or Atlas initially. +- `create_new_phenotype_definition` : Study agent will guide the user through the creation of a definition for an EHR phenotype for the target or outcome cohort relevant to their study intent. This workflow involves selection of concepts, organization of concepts into concept sets, and assembly into cohort definition logic. In addition to concept retrieval, the agent will support reasoning over the semantic relationships encoded in the OMOP vocabulary system (via identity, hierarchical, compositional, associative and attribute links) to help users identify appropriate inclusions, exclusions, and boundary conditions. This enables deterministic validation of constructed concept sets, supports principled disambiguation of similar concepts during grounding, and provides traceable justification for why specific concepts or groups are included in a phenotype definition. Users will use this tool from R or Atlas initially. - `keeper_design_sample` : Study agent helps the user to create the createKeeper function to pull cases matching a clinical definition. This will guide the user through building the set of symptoms, related differential diagnoses (those that need to be ruled out), diagnostic procedures, complications, exposures, and measurements for the clinical definition.