AI-driven automation of cross-sectoral communication

When patients transition from hospital to community care, accurate and timely information exchange is essential for a seamless care process. However, current manual processes, where nurses prepare reports, are time-consuming and often filled with interruptions. Nurses spend up to 1-2 hours per patient preparing care plans and discharge reports, which diverts time from patient-centered care. Therefore, a solution is needed that can streamline this process and reduce workload.

Aim

The goal of this project is to develop and test an AI-based Agentic RAG system that can automate the preparation of cross-sectoral communication reports and discharge letters based on data from electronic patient records. The system will include an advanced search system to retrieve relevant information from the patient record, as well as a validation agent that will keep up with the factual content of the generated document. It is built in such a way that any guideline for a given documentation can be followed, thereby providing the opportunity to use the system in the future for other documentation forms such as discharge summaries.

The AI ​​system will generate drafts with references to the patient record, which only require proofreading by nurses, and it will be tested at the Department of Geriatric Medicine at Odense University Hospital. By integrating this technology, we will free up nurse time for patient-centered care and improve workflows, with the potential for scaling up to other departments.

Partners

• CAI-X
• Department of Geriatric Medicine, OUH
• Research Unit of Geriatrics, University of Southern Denmark

Funding

The project is funded by the innovation fund and co-financed by the project’s partners.