Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes
This addresses the challenge of limited generalizability and structural conformity in clinical data integration for healthcare institutions, though it appears incremental as it builds on existing LLM and agent methods.
The paper tackled the problem of translating free-form clinical notes into structured FHIR resources for healthcare interoperability, proposing an end-to-end LLM agent-based framework called Infherno that competes well with a human baseline in prediction.
For clinical data integration and healthcare services, the HL7 FHIR standard has established itself as a desirable format for interoperability between complex health data. Previous attempts at automating the translation from free-form clinical notes into structured FHIR resources rely on modular, rule-based systems or LLMs with instruction tuning and constrained decoding. Since they frequently suffer from limited generalizability and structural inconformity, we propose an end-to-end framework powered by LLM agents, code execution, and healthcare terminology database tools to address these issues. Our solution, called Infherno, is designed to adhere to the FHIR document schema and competes well with a human baseline in predicting FHIR resources from unstructured text. The implementation features a front end for custom and synthetic data and both local and proprietary models, supporting clinical data integration processes and interoperability across institutions.