Abstract
The BioNLP ACL’24 Shared Task on Streamlining Discharge Documentation aims to reduce the administrative burden on clinicians by automating the creation of critical sections of patient discharge letters. This paper presents our approach using the Llama3 8B quantized model to generate the “Brief Hospital Course” and “Discharge Instructions” sections. We employ a zero-shot method combined with Retrieval-Augmented Generation (RAG) to produce concise, contextually accurate summaries. Our contributions include the development of a curated template-based approach to ensure reliability and consistency, as well as the integration of RAG for word count prediction. We also describe several unsuccessful experiments to provide insights into our pathway for the competition. Our results demonstrate the effectiveness and efficiency of our approach, achieving high scores across multiple evaluation metrics.- Anthology ID:
- 2024.bionlp-1.58
- 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:
- 664–674
- Language:
- URL:
- https://aclanthology.org/2024.bionlp-1.58
- DOI:
- Cite (ACL):
- Rui Guo, Greg Farnan, Niall McLaughlin, and Barry Devereux. 2024. QUB-Cirdan at “Discharge Me!”: Zero shot discharge letter generation by open-source LLM. In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pages 664–674, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- QUB-Cirdan at “Discharge Me!”: Zero shot discharge letter generation by open-source LLM (Guo et al., BioNLP-WS 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.bionlp-1.58.pdf