Skip to main content
Back to challenges
Challenge

Build an OMOP Common Data Model Extraction Pipeline for Public Sector Health Care

Municipal employers face escalating healthcare costs due to fragmented, non-standardized claims data. Construct an ETL transformation microservice using Python and DuckDB to extract unstructured clinical billing data and map them into standardized OMOP CDM tables with 98% schema mapping fidelity.

Data ScienceHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Construct a DuckDB and Python ETL transformation pipeline converting raw public sector health claims to OMOP CDM v5.4 standard.

Delivery guide

How work is evaluated

Evaluation

Evaluates schema mapping fidelity and concept translation accuracy for OMOP CDM transformation.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

valid_concept_id_test

Ensures mapped concept ID is non-zero valid OMOP standard concept.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

mapping_accuracy

Accuracy of mapped procedure concept IDs. • target: 0.98 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Design high-speed ETL workflows using DuckDB and PyArrow.

  • Map ICD-10-CM diagnosis codes and CPT procedure codes to OMOP Concept IDs.

  • Construct standardized OMOP `PERSON`, `DRUG_EXPOSURE`, and `PROCEDURE_OCCURRENCE` tables.

Resources and assets

Reference links and supporting material

Dataset notes

Dataset of 5,000 raw municipal healthcare claim records with ICD-10 and CPT codes.

Challenge setup

Evaluates schema mapping fidelity and concept translation accuracy for OMOP CDM transformation.

Challenge input

JSON raw claim record

DuckDB

Fast in-process analytical SQL database engine.

OMOP CDM

Standardized observational medical outcome partnership data model.

Evaluated output

JSON compliant with OMOP PROCEDURE_OCCURRENCE standard table row

Evaluation checks
  • Ensures mapped concept ID is non-zero valid OMOP standard concept.
  • Accuracy of mapped procedure concept IDs. • target: 0.98 • range: 0-1
Configured evaluation evidence
  • Benchmark: OMOP-Bench
  • Mapping Accuracy target: 0.98
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Zed · Required
  • Aim · Optional
Policy Serving
  • Hunyuan · Optional

Evaluation contract

  • valid_concept_id_test · Weight 1
  • mapping_accuracy · Weight 1

Metrics

  • mapping_accuracy · Target 0.98

Benchmarks

  • OMOP-Bench
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON raw claim record

    Output: JSON compliant with OMOP PROCEDURE_OCCURRENCE standard table row

    Execution harness: Python

Evaluation tools

  • DuckDB · database_engine
  • OMOP CDM · data_standard

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build an OMOP Common Data Model Extraction Pipeline for Public Sector Health Care