Data model / schema · CDM 5.4

OMOP Common Data Model

Maintained by OHDSI

What it helps you do

OMOP CDM supports relational structure, conventions, and standardized vocabularies for longitudinal observational health data.

  • Real-world evidence
  • Clinical
PlanAcquireHarmonizeExchangeLearn + reuse

01

Where it fits and where it does not

Use these four checks before committing implementation time.

Use it when
Multi-source cohort analytics, patient-level prediction, characterization, and network studies after ETL.
Limits
ETL is expensive, source nuance can be compressed, and vocabulary maintenance is an ongoing operational dependency.
Best for
Real-world evidence and Clinical teams working across Harmonize → Learn + reuse.
Maturity
EstablishedSuitable for production assessment. Pin the exact release and any implementation profile.

02

See it in the workflow

This view shows the input, the change the standard introduces, and the resulting output.

  1. InputWhat starts

    Real-world evidence and Clinical source data, metadata, and local mappings

  2. OMOP CDMWhat changes

    Use OMOP CDM as a pinned data model / schema across Harmonize → Learn + reuse

  3. OutputWhat becomes possible

    A handoff the next system or team can validate against the same release

Readiness gateETL is expensive, source nuance can be compressed, and vocabulary maintenance is an ongoing operational dependency.

03

A concrete example

Hospitals transform EHR and claims sources into a common CDM to run a shared phenotype and outcomes protocol.

Why it matters: A consistent longitudinal feature surface is valuable for ML, but label design, missingness, site shift, and temporal leakage remain local responsibilities.

04

What it fits with

Source vocabularies map to OHDSI standard concepts; FHIR and claims data commonly feed ETL; analysis tools consume the CDM.

05

Implementation starter

Start with one bounded handoff. Pin, test, and review it before scaling.

  1. Define one handoff, its accountable owner, and the decision OMOP CDM must support.

  2. Pin the exact version and companion artifacts: CDM 5.4.

  3. Map one representative input to the required data model / schema artifacts.

  4. Test the result against the canonical source and record every exception.

  5. Preserve the source data, mappings, and review evidence before scaling.

06

Test the main limitation

Risk

ETL is expensive, source nuance can be compressed, and vocabulary maintenance is an ongoing operational dependency.

Test

Run one representative end-to-end pilot and record exactly where OMOP CDM loses context, needs an extension, or depends on another standard.

Risk

Machine-readable output may still be unfit for analysis or ML.

Test

Test the output for missing context, provenance, terminology alignment, time leakage, and the intended downstream decision. A consistent longitudinal feature surface is valuable for ML, but label design, missingness, site shift, and temporal leakage remain local responsibilities.

07

Official resources

Specifications, diagrams, examples, and guides from the organizations that maintain them.

  • Primary sourceCDM 5.4

    OHDSI OMOP CDM documentation

    Official publisher or steward guidance for this data model / schema profile.

    Publisher
    OHDSI
    Open official source

Next action

Put this profile in context

Compare its role with adjacent standards or place it inside an end-to-end data pathway before choosing an implementation.