The period-2 meeting of the Utrecht NLP Hub (NLP@U) will be hosted by the Faculty of Science. The event is also posted on the UU events site.
Programme:
| 9:30 – 10:30 | Presentation by the UMC Utrecht. Speakers: Tuur Leeuwenberg, Anne de Hond, Ruben Peters, and Laura Veerhoek |
| 10:30 – 11:00 | Coffee break and networking |
| 11:00 – 11:15 | Updates from the team |
| 12:30 – 13:00 | Lunch |
Title and Abstract
Title
Implementing and Validating LLM-Generated Discharge Letters: Reducing administrative burden in routine hospital care
Abstract
Large language models (LLMs) like GPT possess significant potential for transforming the healthcare sector, particularly by reducing the administrative burden. At UMCU, we have developed and implemented a solution that automatically generates draft discharge letters for patients in the Intensive Care and Neonatal Intensive Care Units. In this talk, data scientists from AI for Health will outline the development and implementation process of this solution, highlighting the role of prompt engineering in collaboration with healthcare professionals. Additionally, researchers from the Julius Center will discuss the validation of the quality of GPT-generated discharge letters and present preliminary results.
Pitches and discussion:
We are inviting submissions for the pitches-and-discussion section. Participants may submit a tentative title and a description. Each selected participant will have two (2) minutes to either:
- Describe an idea you are working on, and ask if anyone is interested in discussing this idea with you, or
- Propose a topic for debate immediately afterwards.
Each pitch will be followed by thirteen (13) minutes of discussion. Please fill out this form to submit your pitch.