{"slug":"university-hospital-bonn-runs-an-isolated-on-premise-open-weights-llm-service-for-radiology","url":"https://findausecase.com/use-cases/university-hospital-bonn-runs-an-isolated-on-premise-open-weights-llm-service-for-radiology","title":"University Hospital Bonn runs an isolated on-premise open-weights LLM service for radiology","description":"University Hospital Bonn built a self-hosted, isolation-first LLM inference stack on a single on-premise server with eight NVIDIA A100 GPUs, serving DeepSeek-R1 via vLLM, and obtained governance approval to process unanonymized patient data. In a one-week pilot, 22 radiologists used ten prompt templates; source-anchored tasks such as report corrections and simplifications rated highest, while open-ended conclusion generation produced the most critical errors. The service is described as the base for an official service for a hospital with over 10,000 employees.","company":"University Hospital Bonn","industry":"Healthcare","country":"Germany","aiCapabilities":["Generative AI","Conversational AI"],"technology":["DeepSeek-R1","vLLM","Open WebUI"],"deployment":"On-Premise","problemStatement":"Data protection and information security requirements remain a major barrier to integrating LLMs into clinical workflows: popular proprietary LLMs are offered through cloud APIs that require data to leave the hospital network, raising confidentiality, sovereignty and regulatory compliance concerns.","solutionApproach":"The hospital built an isolation-first, containerized LLM inference stack on a single on-premise server with eight NVIDIA A100 80 GB GPUs, using strict network segmentation, host-enforced egress filtering and active isolation monitoring. It serves the open-weights DeepSeek-R1 model via vLLM behind an Open WebUI chat frontend, with users given ten predefined prompt templates.","businessValue":"The governance pathway achieved approval from clinic management, compliance, data protection and information security officers for processing unanonymized protected health information. In a one-week pilot with 22 radiologists, the system was rated stable and user friendly, source text-anchored tasks such as report corrections or simplifications received the highest utility ratings, and open-ended conclusion generation produced the most critical errors. The authors describe it as the current base for an official service for a German university hospital with over 10,000 employees.","evidence":{"band":"high"},"sourceUrl":"https://arxiv.org/html/2604.22768v1","dates":{"publishedAt":"2026-11-02T05:48:30.058Z","publishedAtSource":"pipeline","updatedAt":"2026-11-02T05:48:30.058Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/university-hospital-bonn-runs-an-isolated-on-premise-open-weights-llm-service-for-radiology. Bulk republication requires permission."}