Exchange of Quantitative Computed Tomography Assessed Body Composition Data Using Fast Healthcare Interoperability...

Area of Science:

• Medical Informatics
• Artificial Intelligence in Radiology
• Health Data Standards

Background:

• Fast Healthcare Interoperability Resources (FHIR) is a standard for health data exchange.
• AI models quantify body structures from medical images (CT/MRI).
• Integrating AI measurements into FHIR is crucial for personalized medicine.

Purpose of the Study:

• To present the integration of CT-derived body organ and composition measurements with FHIR.
• To establish a paradigm for storing image-based biomarkers within FHIR.

Main Methods:

• Integrated the Body and Organ Analysis (BOA) AI model results into FHIR profiles.
• Developed FHIR profiles for Body Composition Analysis (BCA Observation) and Body Structure Observation.
• Ensured interoperability by mapping labels to SNOMED CT or RadLex and using FHIR Shorthand (FSH) and SUSHI.

Main Results:

• Presented 4 BOA FHIR profiles: Body Composition Analysis Observation, Body Structure Volume Observation, Diagnostic Report, and Imaging Study.
• These profiles cover 104 anatomical landmarks, 8 body regions, and 8 tissues.
• Enabled interoperable use of AI segmentation model results, linking image studies to measurements.

Conclusions:

• BOA profiles provide a framework for integrating AI imaging biomarkers into FHIR.
• Facilitates structured, interoperable representation of body composition and organ measurements for clinical and research workflows.
• Adaptable to other imaging modalities and AI models, advancing precision medicine and digital health ecosystems.