Discharge Documentation Generator
by UMC Utrecht
The Discharge Documentation Generator is an in-house tool of UMC Utrecht's Digital Health team that drafts the course-of-admission section of clinical discharge letters, which go to the next treating physician, often the GP. UMC Utrecht says it is in use in the Intensive Care Unit and the Neonatal ICU; its public code repository says it was developed for the ICU, NICU and Cardiology. Notes from the patient's record are sent to a large language model, which writes a draft summary of the admission. UMC Utrecht says the draft is always reviewed and completed by a physician (assistant) and checked by a supervisor. Its model card warns that the model can omit relevant facts, add irrelevant ones or hallucinate, and must not be used for diagnosis or clinical reasoning. ChipSoft says the module is built into HiX, marks AI-generated text and logs edits. UMC Utrecht says the model runs in a secure environment on a European server it manages, that OpenAI and Microsoft have no access to patient data, and that data are not used to train the model.
Transparency Score
Weighted across four pillars · updated October 20, 2026
Capabilities
AI Models
Underlying AI models powering this application
Vendor Information
Complete information about the vendor/provider of this AI application
Infrastructure
Platforms hosting this application — each inherits its own transparency grade.
EU AI Act Provider Information
Get insights into risk by running assessments on this AI application.
Work at UMC Utrecht? Claim this listing to correct or complete the data.
Ready to manage AI applications?
Track, assess, and govern your AI applications with Anove.