AI-driven automation of cross-sectoral communication

When patients move from hospital care to municipal care, ensuring accurate and timely communication is essential for a seamless treatment process. Currently, nurses manually prepare care plans and discharge reports, a task that can take 1-2 hours per patient, often leading to interruptions in their primary responsibilities— direct patient care. The existing method is time-consuming, highlighting the need for a solution that can streamline report generation and alleviate the administrative burden on healthcare staff.

Aim

This project aims to develop and test an AI-based Danish language model designed to automate the creation of cross-sectoral communication reports and discharge letters using data from electronic health records. The model will be trained to recognise healthcare-specific terminology and ensure all critical information is captured, minimising the risk of human error.

By generating draft reports that nurses only need to proofread, the model aims to significantly reduce the time spent on documentation. The system will be initially implemented and tested in the Department of Geriatric Medicine at Odense University Hospital. Through this initiative, we aim to free up nurses’ time for patient care and improve overall workflows, with the potential to expand this solution to other departments in the future.

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.