{"slug":"university-hospital-bonn-deploys-an-isolated-on-premise-open-weights-llm-for-radiology-piloted-with-22-radiologists","url":"https://findausecase.com/use-cases/university-hospital-bonn-deploys-an-isolated-on-premise-open-weights-llm-for-radiology-piloted-with-22-radiologists","title":"University Hospital Bonn deploys an isolated on-premise open-weights LLM for radiology, piloted with 22 radiologists","description":"University Hospital Bonn built an isolation-first, self-hosted LLM service on a single on-premise server with eight NVIDIA A100 80 GB GPUs, serving DeepSeek-R1 via vLLM behind Open WebUI, with network segmentation and egress filtering so unanonymized patient data can be processed. In a one-week pilot in July 2025, 22 radiologists used ten prompt templates; stability was rated high and source-anchored tasks such as translation and report correction rated best, while open-ended conclusion generation produced the most critical errors. Median time-to-first-token was 3.13 seconds. The authors state the system is the basis for an official service for a hospital with over 10,000 employees.","company":"University Hospital Bonn","industry":"Healthcare","country":"Germany","aiCapabilities":["Generative AI"],"technology":["DeepSeek-R1","vLLM","Open WebUI"],"deployment":"Unknown","problemStatement":"Data protection and information security requirements are a major barrier to using LLMs in clinical workflows: well-known proprietary LLMs are offered through cloud APIs that require data to leave the hospital network, and hospitals in many countries do not permit external LLM services with clinical data.","solutionApproach":"The hospital designed an isolation-first, containerized LLM inference stack on a single on-premise server with eight NVIDIA A100 80 GB PCIe GPUs. It relies on strict network segmentation, host-enforced egress filtering and active isolation monitoring, and serves the open-weights DeepSeek-R1 model via vLLM behind an Open WebUI frontend. The architecture is model-agnostic, and the intended use is radiology text support without autonomous clinical decision-making.","businessValue":"In a one-week pilot with 22 radiologists, participants rated system stability exceptionally high and usability strong, and no external connectivity events were detected. Source-anchored tasks such as report translation, linguistic correction and radiology guideline recommendations received the highest ratings, while open-ended conclusion generation produced the most critical errors. The authors note it was a single-centre pilot with user-reported errors.","evidence":{"band":"high"},"sourceUrl":"https://arxiv.org/pdf/2604.22768","dates":{"publishedAt":"2026-10-16T05:47:15.205Z","publishedAtSource":"pipeline","updatedAt":"2026-10-16T05:47:15.205Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/university-hospital-bonn-deploys-an-isolated-on-premise-open-weights-llm-for-radiology-piloted-with-22-radiologists. Bulk republication requires permission."}