mCODE (Minimal Common Oncology Data Elements) is a consensus-driven, open-source data standard built on HL7 FHIR that defines a core set of structured oncology data elements for seamless electronic exchange across health systems. It standardizes the representation of a patient's cancer diagnosis, genomic markers, treatment history, and outcomes into a common computable format, enabling interoperability between disparate electronic health records (EHRs) and research databases.
Glossary
mCODE (Minimal Common Oncology Data Elements)

What is mCODE (Minimal Common Oncology Data Elements)?
A consensus-driven, FHIR-based data standard created to facilitate the exchange of essential oncology data for research, treatment, and patient care.
Developed by the American Society of Clinical Oncology (ASCO) in collaboration with MITRE, mCODE leverages FHIR profiles to model key clinical concepts like CancerPatient, PrimaryCancerCondition, and CancerRelatedSurgicalProcedure. By establishing a minimal yet comprehensive data layer, it directly supports use cases in federated learning, real-world evidence generation, and clinical decision support without requiring institutions to abandon their local data schemas.
Core Characteristics of mCODE
A consensus-driven, FHIR-based data standard created to facilitate the exchange of essential oncology data for research, treatment, and patient care.
FHIR-Based Interoperability
mCODE is built entirely on the HL7 FHIR (Fast Healthcare Interoperability Resources) standard, using modern RESTful APIs and web technologies. This ensures seamless integration with existing Electronic Health Records (EHRs) and other FHIR-compliant systems.
- Uses standard FHIR Resources like
Patient,Condition,Observation, andProcedure - Defines specific FHIR Profiles that constrain these resources for oncology use cases
- Enables plug-and-play interoperability across different vendor systems
Six Core Data Domains
mCODE organizes essential oncology data into six foundational domains, each representing a critical aspect of a patient's cancer journey. These domains were selected by a multidisciplinary expert panel as the minimal set necessary for care and research.
- Patient: Demographics and baseline characteristics
- Disease: Primary cancer diagnosis, staging, and histology
- Genomics: Somatic mutations, biomarkers, and genomic reports
- Treatment: Medications, surgeries, and radiation therapy
- Outcome: Survival status, disease progression, and performance status
- Assessment: Cancer staging evaluations and tumor marker tests
Consensus-Driven Governance
mCODE is developed and maintained through an open, multi-stakeholder governance process led by the American Society of Clinical Oncology (ASCO) and the MITRE Corporation. This ensures the standard reflects real-world clinical needs rather than any single vendor's priorities.
- Governed by an Executive Committee with representatives from oncology, informatics, and patient advocacy
- All development occurs in public GitHub repositories with community input
- Regular balloting and comment periods ensure transparency and clinical validity
Real-World Data Enablement
A primary goal of mCODE is to transform unstructured clinical data trapped in EHR narrative text into structured, computable data suitable for research. By standardizing data elements, mCODE enables:
- Pragmatic clinical trials using real-world evidence
- Cohort discovery for identifying eligible patients across institutions
- Quality reporting for value-based care programs
- Federated learning by providing a common data schema across sites without requiring centralized data aggregation
Extensible Profiling Architecture
While mCODE defines a minimal set of data elements, it is designed to be extended. Implementers can layer additional FHIR profiles on top of the mCODE base to capture specialty-specific or trial-specific data without breaking conformance.
- Uses FHIR's Extension mechanism for custom data elements
- Supports US Core profiles as a foundational layer
- Enables Implementation Guides (IGs) for specific cancer types or research protocols
- Maintains backward compatibility as extensions evolve
Genomics Integration
mCODE includes a dedicated Genomics Domain that standardizes how somatic mutations and biomarkers are represented, bridging the gap between molecular pathology and clinical oncology.
- Aligns with the Global Alliance for Genomics and Health (GA4GH) standards
- Uses FHIR's
Observationresource with specific genomic profiles - Captures gene studied, variant description, and clinical significance
- Enables structured reporting of next-generation sequencing (NGS) results for treatment decision support
Frequently Asked Questions
Clear, technical answers to the most common questions about the Minimal Common Oncology Data Elements (mCODE) standard and its role in interoperable cancer care and federated research.
mCODE, or Minimal Common Oncology Data Elements, is a consensus-driven, FHIR-based data standard created to facilitate the exchange of essential oncology data for research, treatment, and patient care. It works by defining a core set of structured data elements—such as cancer diagnosis, genomic variants, and treatment history—that are mapped to specific FHIR resources like Condition, Observation, and MedicationAdministration. This creates a universal 'lingua franca' for cancer data, allowing disparate electronic health record (EHR) systems to transmit a standardized, computable summary of a patient's cancer journey without requiring a complete data dump of the entire medical record.
mCODE vs. Other Oncology Data Standards
A feature-level comparison of mCODE against other prominent data standards used in oncology research and clinical care.
| Feature | mCODE | NAACCR | OMOP CDM |
|---|---|---|---|
Base Framework | FHIR R4 | Fixed-width text files | Relational database schema |
Primary Use Case | Real-time clinical care and research | Central cancer registry reporting | Large-scale observational analytics |
Data Exchange Mechanism | RESTful API | Batch file transfer | ETL and bulk export |
Granularity | Individual data elements | Summary case records | Standardized clinical concepts |
Extensibility | |||
Terminology Binding | Mandatory (SNOMED CT, LOINC) | NAACCR codes | Standardized vocabularies (SNOMED, RxNorm) |
Patient-Facing Access | |||
Real-Time Updates |
Enabling Efficiency, Speed & Accuracy
Intelligent Analysis, Decision & Execution
We build AI systems for teams that need search across company data, workflow automation across tools, or AI features inside products and internal software.
Talk to Us
Search across company data
Give teams answers from docs, tickets, runbooks, and product data with sources and permissions.
Useful when people spend too long searching or get different answers from different systems.

Automate internal workflows
Use AI to route work, draft outputs, trigger actions, and keep approvals and logs in place.
Useful when repetitive work moves across multiple tools and teams.

Add AI to products and internal tools
Build assistants, guided actions, or decision support into the software your team or customers already use.
Useful when AI needs to be part of the product, not a separate tool.
Related Terms
mCODE does not exist in isolation. It relies on a stack of foundational FHIR standards and complementary clinical data models to enable interoperable oncology research.

About the author
Prasad Kumkar
CEO & MD, Inference Systems
Prasad Kumkar is the CEO & MD of Inference Systems and writes about AI systems architecture, LLM infrastructure, model serving, evaluation, and production deployment. Over 5+ years, he has worked across computer vision models, L5 autonomous vehicle systems, and LLM research, with a focus on taking complex AI ideas into real-world engineering systems.
His work and writing cover AI systems, large language models, AI agents, multimodal systems, autonomous systems, inference optimization, RAG, evaluation, and production AI engineering.
Partnered with leading AI, data, and software stack.
How We Work
Custom AI workflows for your Business
One-fit-all AI don't work for modern businesses. At Inferensys, we aim to understand your business & custom requirements; which we use to define most efficient agentic workflows, the data, and the tools for your business.
01
Review the use case
We understand the task, the users, and where AI can actually help.
Read more02
Pick the right approach
We define what needs search, automation, or product integration.
Read more03
Build the first useful version
We implement the part that proves the value first.
Read more04
Improve from there
We add the checks and visibility needed to keep it useful.
Read moreThe first call is a practical review of your use case and the right next step.
Talk to Us