Ixa-Med at Discharge Me! Retrieval-Assisted Generation for Streamlining Discharge Documentation

Jordan C. Koontz, Maite Oronoz, Alicia Pérez


Abstract
In this paper we present our system for the BioNLP ACL’24 “Discharge Me!” task on automating discharge summary section generation. Using Retrieval-Augmented Generation, we combine a Large Language Model (LLM) with external knowledge to guide the generation of the target sections. Our approach generates structured patient summaries from discharge notes using an instructed LLM, retrieves relevant “Brief Hospital Course” and “Discharge Instructions” examples via BM25 and SentenceBERT, and provides this context to a frozen LLM for generation. Our top system using SentenceBERT retrieval achieves an overall score of 0.183, outperforming zero-shot baselines. We analyze performance across different aspects, discussing limitations and future research directions.
Anthology ID:
2024.bionlp-1.57
Volume:
Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Dina Demner-Fushman, Sophia Ananiadou, Makoto Miwa, Kirk Roberts, Junichi Tsujii
Venues:
BioNLP | WS
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
658–663
Language:
URL:
https://aclanthology.org/2024.bionlp-1.57
DOI:
10.18653/v1/2024.bionlp-1.57
Bibkey:
Cite (ACL):
Jordan C. Koontz, Maite Oronoz, and Alicia Pérez. 2024. Ixa-Med at Discharge Me! Retrieval-Assisted Generation for Streamlining Discharge Documentation. In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pages 658–663, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Ixa-Med at Discharge Me! Retrieval-Assisted Generation for Streamlining Discharge Documentation (Koontz et al., BioNLP-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.bionlp-1.57.pdf