FHIR-Starter
FHIR-Starter is a German research project launched in February 2025, led by Fraunhofer IESE in collaboration with the Berlin Institute of Health @ Charité and Insiders Technologies. It develops an AI-powered software service that uses large language models (LLMs) and natural language processing to automatically analyze and structure unstructured medical records, like doctor’s letters, into standardized, interoperable FHIR resources.
The primary aim is to improve healthcare by reducing manual data transcription, support clinicians with automatically generated structured information (e.g., lab curves, medication lists), and make anonymized patient data securely and reliably available for research. The service emphasizes minimizing hallucinations in AI with mechanisms like the Uncertainty Wrapper and strictly complies with GDPR by running exclusively on the users’ own servers with open source LLMs. Funded by the German Federal Ministry for Economic Affairs and Energy, the project supports digitization in the health sector and enables advanced secondary use of medical data for research and innovation
