LLM-Integrated Normalization and Knowledge for FHIR (LINK-FHIR)
Zhen Hou, Ming Jiang, Hao Liu, Yan Zhuang · Studies in health technology and informatics · 2025
Current approaches lack efficient methods to convert diverse healthcare data formats into standardized Fast Healthcare Interoperability Resources (FHIR). LINK-FHIR is a novel system for converting diverse Electronic Health Records into FHIR-compliant resources. The system leverages fine-tuned Large Language Models through a unified pipeline to efficiently process unstructured clinical notes, semi-structured lab reports, and structured tables. LINK-FHIR features dual interfaces that offer automated machine-to-machine integration and an intuitive user interface for data visualization and management. The system offers flexible deployment options to ensure compliance with healthcare security and privacy regulations. Comprehensive evaluation demonstrates LINK-FHIR's robust performance across diverse data formats. LINK-FHIR has the potential to enhance Health Information Exchange interoperability significantly, operational efficiency across healthcare institutions.