concept-mapping-ai

Community

Map clinical concepts to OMOP with confidence.

AuthorBorisDelange
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It reduces the manual effort and inconsistency of mapping source clinical concepts (measurements, conditions, procedures, observations) to the correct OMOP standard concepts by generating candidate matches and providing structured reasoning.

Core Features & Use Cases

  • Agentic OMOP Concept Mapping: Produces ranked candidates for each source concept using DuckDB search, precomputed similarity scores, and clinical reasoning.
  • SSSOM-graded Equivalence: Assigns equivalence levels (skos:exactMatch, closeMatch, broadMatch, narrowMatch, relatedMatch) with evidence-oriented comments to support reviewer decisions.
  • Two Write Destinations: Saves results either as UI-reviewable suggestions in similarity-scores.parquet or as reviewer-confirmed authored mappings in mappings.json.
  • Batch Processing with Guardrails: Operates on prepared DuckDB session context, supports per-batch review modes, and handles edge cases like missing matches or non-standard concepts.

Quick Start

Ask the concept-mapping orchestrator to run the concept-mapping-ai skill for your selected source concept batch with an existing DuckDB session context and a chosen destination mode (suggestions or mappings).

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: concept-mapping-ai
Download link: https://github.com/BorisDelange/Linkr/archive/main.zip#concept-mapping-ai

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.