A curated list of awesome OHDSI (Observational Health Data Sciences and Informatics) tools, packages, resources, and community projects for working with the OMOP Common Data Model.
Contributions welcome! Read the contribution guidelines first.
- Official Resources
- Core OHDSI Tools
- HADES R Packages
- Vocabulary Tools
- ETL & Data Transformation
- Python Tools
- Visualization & Dashboards
- Infrastructure & Deployment
- FHIR Integration
- Sample Data & Testing
- Learning Resources
- Community
Official OHDSI websites, documentation, and community resources.
- OHDSI Website - Official OHDSI organization website.
- The Book of OHDSI - Comprehensive guide to OHDSI methods and tools.
- OMOP CDM Documentation - Official Common Data Model specification.
- ATHENA - OHDSI standardized vocabularies browser and download.
- OHDSI Forums - Community discussion forums.
- OHDSI GitHub - Official OHDSI repositories.
- HADES - Health Analytics Data-to-Evidence Suite documentation.
Essential tools for working with OMOP CDM data.
- ATLAS - Web-based tool for cohort definition, characterization, and study design.
- WebAPI - Backend services for ATLAS providing REST APIs for OMOP CDM.
- Achilles - Database characterization and data quality tool that powers ATLAS Data Sources.
- Usagi - Application for mapping source codes to OMOP standard concepts.
- WhiteRabbit - Tool for profiling source data before ETL.
- RabbitInAHat - ETL design and documentation tool (bundled with WhiteRabbit).
- Perseus - Web-based vocabulary mapping tool.
- DataQualityDashboard - Tool to evaluate data quality of OMOP CDM instances.
R packages from the Health Analytics Data-to-Evidence Suite.
- DataQualityDashboard - Evaluate and visualize data quality.
- Achilles - Database characterization and profiling.
- DbDiagnostics - Database diagnostics for OMOP CDM.
- FeatureExtraction - Extract features from OMOP CDM for machine learning.
- Characterization - Cohort characterization studies.
- CohortDiagnostics - Evaluate cohort definitions.
- OmopSketch - Quickly characterize and visualize OMOP CDM instances.
- CohortMethod - New-user cohort studies for causal effect estimation.
- SelfControlledCaseSeries - Self-controlled case series analysis.
- SelfControlledCohort - Self-controlled cohort design.
- CaseControl - Case-control studies.
- CaseCrossover - Case-crossover design.
- EvidenceSynthesis - Meta-analysis and evidence synthesis.
- PatientLevelPrediction - Build and validate patient-level prediction models.
- DeepPatientLevelPrediction - Deep learning extensions for PLP.
- EnsemblePatientLevelPrediction - Ensemble methods for PLP.
- EvidenceSynthesis - Combine evidence from multiple studies.
- Cyclops - Large-scale regularized regression.
- DatabaseConnector - Connect R to various database platforms.
- SqlRender - Translate SQL across database dialects.
- Eunomia - Standard dataset manager for sample OMOP CDM datasets.
Tools for working with OHDSI standardized vocabularies.
- ATHENA - Official vocabulary browser and download service.
- Usagi - Semi-automated vocabulary mapping.
- Perseus - Web-based vocabulary mapping.
- OMOPHub Python SDK - Python client for querying ATHENA vocabularies via API.
- OMOPHub R SDK - R client for querying ATHENA vocabularies via API.
- omopcept - R package for accessing OMOP concepts with tidyverse-compatible functions.
Tools for transforming source data to OMOP CDM.
- WhiteRabbit - Source data profiling for ETL planning.
- RabbitInAHat - ETL specification and documentation.
- ETL-CDMBuilder - .NET application for ETL to OMOP CDM.
- carrot - Streamlined data transformation to OMOP.
- carrot-mapper - Streamlined data mapping to OMOP.
- carrot-transform - Streamlined data transformation to OMOP.
- oxford-omop-data-mapper - DuckDB-based ETL tool for clinical datasets.
- Eos - ETL engine to transform openEHR into OMOP.
- kotobuki - Update Usagi mappings programmatically.
- convert-pheno - Interconversion of standard phenotypic data models including OMOP.
Python libraries and tools for OMOP CDM.
- OMOPHub Python SDK - Query ATHENA vocabularies via API.
- dzd-omop-cdm-python-models - Python/Pydantic/SQLAlchemy data class representation of OMOP CDM.
- omop-learn - Machine learning pipelines for OMOP CDM data.
Tools for visualizing OMOP CDM data.
- Cohort360 - Web application for cohort building and health record visualization.
- omopcat - Summary of OMOP data with public data catalogue.
- Data2Evidence - End-to-end solution for management and analysis of OMOP data.
- OmopSketch - Characterize and visualize OMOP CDM instances.
Tools for deploying OHDSI infrastructure.
- OHDSIonAWS - Deploy OHDSI toolstack on AWS.
- Broadsea - Docker-based deployment of OHDSI tools.
- OHDSI-in-a-Box - Single-server OHDSI learning environment.
- CommonDataModel - DDL scripts for creating OMOP CDM tables.
Tools bridging FHIR and OMOP.
- OMOP on FHIR - FHIR server backed by OMOP CDM.
- recruit - Clinical trial recruitment system using FHIR and OMOP.
- cql-on-omop - Apply CQL libraries to OMOP databases.
Sample datasets and testing tools.
- Eunomia - Standard dataset manager with sample OMOP CDM datasets.
- SynPUF - CMS synthetic patient data.
- Synthea - Synthetic patient generator (can output to OMOP).
- ETL-Synthea - ETL from Synthea to OMOP CDM.
Tutorials, courses, and educational materials.
- The Book of OHDSI - Comprehensive guide covering all aspects of OHDSI.
- OHDSI Academy - Free online courses and tutorials.
- HADES Documentation - Package documentation and tutorials.
- OHDSI YouTube - Video tutorials and community calls.
- Guide to N3C - Research with the National COVID Cohort Collaborative.
OHDSI community resources.
- OHDSI Forums - Ask questions, share knowledge.
- OHDSI Teams - Real-time community chat.
- OHDSI Symposium - Annual conference.
- OHDSI Working Groups - Contribute to specific areas.
- OHDSI Studies - Network study repositories.
Contributions are welcome! Please read the contribution guidelines first.
To the extent possible under law, the authors have waived all copyright and related rights to this work.