AACR Project GENIE Data Model (GDM), developed by the AACR Project GENIE consortium, is an open-source, pan-cancer framework that standardizes longitudinal clinico-genomic data from diagnosis through long-term outcomes. The complete model specifications, value sets, and supporting documentation are publicly available on GitHub (CC-NC-SA license). Data elements can be mapped to established terminologies (SNOMED CT, LOINC, ICD-O, NCIt) and aligned with HL7 FHIR and OMOP CDM structures. A dual-pathway architecture supports both manual abstraction and programmatic collection, preserving data provenance while positioning the model for emerging NLP and automation capabilities.

Access the GENIE Data Model on Github

Creative Commons License