OMOP ETL Framework for Semi-Structured Health Data

TL;DR

This paper presents a flexible, schema-agnostic framework for transforming diverse healthcare data into the OMOP Common Data Model, supporting relational and document-based sources with validation on large-scale real-world data.

Contribution

The framework extends existing methods by using YAML specifications for schema-agnostic transformation and includes production features like provenance tracking and incremental updates.

Findings

Validated on 2.7 million patient records and 27 million encounters

Achieved 97% data quality passing rate

Supports both relational and document-based data sources

Abstract

Healthcare data are generated in many different formats, which makes it difficult to integrate and reuse across institutions and studies. Standardisation is required to enable consistent large-scale analysis. The OMOP-CDM, developed by the OHDSI community, provides one widely adopted standard. Our framework achieves schema-agnostic transformation by extending upon existing literature in using human-readable YAML specification to support both relational (Microsoft SQL Server (MSSQL)) and document-based (MongoDB) data sources. It also incorporates critical production readiness features: provenance-aware mapping and support for incremental updates. We validated the pipeline using 2.7 million patient records and 27 million encounters across six hospitals spanning two decades of records. The resulting OMOP-CDM dataset demonstrated an acceptable level of data quality with a 97% overall passing rate based on the OHDSI Data Quality Dashboard check. Our work provides a reusable blueprint for large-scale data harmonisation, directly supporting real-world medical data research.