Available Datasets
Komodo Research Dataset (KRD)
This large-scale health claims dataset contains pharmacy and medical claims data (including race, ethnicity, mortality, and location fields) for over 100 million patient lives. For information about specific fields or gaining access to the KRD, please reach out via [email protected].
OMOP Common Data Model
The following datasets are accessible through the OHDSI Lab in via a range of analytical tools, including R / RStudio, SQL / DBeaver, Python, and ATLAS (the OHDSI community’s point-and-click cohort characterization tool). The datasets have been converted to the OMOP Common Data Model (CDM) for easy integration with ATLAS and the HADES Analytical Suite (the OHDSI community’s library of open-source R packages).
DE-SynPUF 100k
A Synthetic dataset, created with the goal of providing a realistic set of publicly available claims data while providing the very highest degree of protection to the Medicare beneficiaries’ protected health information.
OHDSI Data Network
Researchers interested in data elements not contained within one of the OHDSI Lab’s internal databases can initiate an OHDSI network study, engaging the OHDSI community’s wide system of collaborators and databases to achieve the necessary analyses. OHDSI network study processes can be designed and tested within the OHDSI Lab before being dispersed to external data collaborators for the generation of results.