{"slug":"polish-university-hospital-runs-an-on-premise-gemma-based-ai-platform-for-documentation-medication-recommendations-and-demand-forecasting","url":"https://findausecase.com/use-cases/polish-university-hospital-runs-an-on-premise-gemma-based-ai-platform-for-documentation-medication-recommendations-and-demand-forecasting","title":"Polish university hospital runs an on-premise Gemma-based AI platform for documentation, medication recommendations and demand forecasting","description":"A university clinical hospital in Poland with 32 clinical departments needed AI under GDPR Article 9 constraints, so InTechHouse delivered an on-premise platform running Gemma on local GPU servers with MLOps tooling. The LLM is used only in a content-preparation layer; validated outputs are published to a local reference database that the hospital information system queries. Source reports precision@k of 0.80 against a 0.70 contractual requirement for medication recommendations, and 320 documentation schemas across 32 departments.","company":"Unnamed Polish university hospital (delivered by InTechHouse)","industry":"Healthcare","country":"Poland","aiCapabilities":["Generative AI","Predictive Analytics"],"businessFunctions":["Supply Chain & Logistics"],"technology":["Gemma"],"deployment":"On-Premise","problemStatement":"A university clinical hospital in Poland with 32 clinical departments needed production AI for documentation, medication recommendations and demand forecasting, but GDPR Article 9 special category data could not leave its own infrastructure.","solutionApproach":"InTechHouse delivered an on-premise platform running Gemma on local GPU servers, with MLOps tooling and a validated reference database that production systems query instead of the LLM. The LLM is used only in the content-preparation layer.","businessValue":"At handover, medication recommendations reached precision@k of 0.80 against a contractual requirement of 0.70, and 320 documentation schemas were generated across all 32 departments. Forecasting achieved hospital-wide WAPE in the 15 to 17 percent range. Results are reported by the delivery firm.","evidence":{"band":"high"},"sourceUrl":"https://intechhouse.com/case-studies/production-ai-for-a-regulated-hospital-with-full-data-sovereignty","dates":{"publishedAt":"2026-11-08T05:46:35.078Z","publishedAtSource":"pipeline","updatedAt":"2026-11-08T05:46:35.078Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/polish-university-hospital-runs-an-on-premise-gemma-based-ai-platform-for-documentation-medication-recommendations-and-demand-forecasting. Bulk republication requires permission."}