{"slug":"cliniques-universitaires-saint-luc-deploys-an-on-premises-qwen3-235b-assistant-inside-its-epic-ehr-adopted-by-1-028-users","url":"https://findausecase.com/use-cases/cliniques-universitaires-saint-luc-deploys-an-on-premises-qwen3-235b-assistant-inside-its-epic-ehr-adopted-by-1-028-users","title":"Cliniques universitaires Saint-Luc deploys an on-premises Qwen3-235B assistant inside its Epic EHR, adopted by 1,028 users","description":"A Brussels university hospital (Cliniques universitaires Saint-Luc) deployed a GDPR-compliant, on-premises LLM assistant integrated into its Epic EHR, running Qwen3-235B with retrieval-augmented generation over patient data, internal documents and medical literature on a server with 8 NVIDIA H200 GPUs. After a one-month pilot with 28 physicians (64% daily use, 482 conversations), it was deployed hospital-wide and used by 1,028 users who generated 14,910 conversations over five months. The study measured adoption, not clinical outcomes or time savings.","company":"Cliniques universitaires Saint-Luc","industry":"Healthcare","country":"Belgium","aiCapabilities":["Retrieval-Augmented Generation","Generative AI","Conversational AI"],"technology":["Qwen3-235B","Epic","vLLM","NVIDIA H200","Apache Solr","OpenWebUI","LiteLLM"],"deployment":"On-Premise","problemStatement":"Electronic health records have improved access to patient information but substantially increased clinicians' documentation workload; physicians spend more time documenting and must process a large volume of information when preparing consultations.","solutionApproach":"The hospital implemented a secure, GDPR-compliant, on-premises LLM assistant integrated into its Epic EHR. It uses Qwen3-235B with Retrieval Augmented Generation over structured patient data, internal and regional clinical documents, and medical literature, served with vLLM on a server with 8 NVIDIA H200 GPUs.","businessValue":"After a one-month pilot with 28 physicians, the system was deployed hospital-wide and adopted by 1,028 users who generated 14,910 conversations over five months, with more than half of clinicians using it at least weekly. The study deliberately did not measure clinical outcomes or time savings.","evidence":{"band":"high"},"sourceUrl":"https://journals.plos.org/digitalhealth/article?id=10.1371%2Fjournal.pdig.0001141","dates":{"publishedAt":"2026-11-12T05:46:42.277Z","publishedAtSource":"pipeline","updatedAt":"2026-11-12T05:46:42.277Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/cliniques-universitaires-saint-luc-deploys-an-on-premises-qwen3-235b-assistant-inside-its-epic-ehr-adopted-by-1-028-users. Bulk republication requires permission."}