Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes

TL;DR

Infherno is an end-to-end LLM-based framework that converts free-form clinical notes into structured FHIR resources, improving healthcare data interoperability.

Contribution

It introduces a novel integrated approach using LLM agents, code execution, and healthcare terminology tools to generate FHIR resources from unstructured text.

Findings

Infherno competes well with human performance in resource prediction.

The system supports local and proprietary models for clinical data integration.

Evaluation shows effectiveness on synthetic and clinical datasets.

Abstract

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 address narrowly defined tasks and rely on modular approaches or LLMs with instruction tuning and constrained decoding. As those solutions 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. Gemini 2.5-Pro excels in our evaluation on synthetic and clinical datasets, yet ambiguity and feasibility of collecting ground-truth data remain open problems.