Enhancing Summarization Performance Through Transformer-Based Prompt Engineering in Automated Medical Reporting

Daphne van Zandvoort, Laura Wiersema, Tom Huibers, Sandra van Dulmen, Sjaak Brinkkemper

2024

Abstract

Customized medical prompts enable Large Language Models (LLM) to effectively address medical dialogue summarization. The process of medical reporting is often time-consuming for healthcare professionals. Imple-menting medical dialogue summarization techniques presents a viable solution to alleviate this time constraint by generating automated medical reports. The effectiveness of LLMs in this process is significantly influenced by the formulation of the prompt, which plays a crucial role in determining the quality and relevance of the generated reports. In this research, we used a combination of two distinct prompting strategies, known as shot prompting and pattern prompting to enhance the performance of automated medical reporting. The evaluation of the automated medical reports is carried out using the ROUGE score and a human evaluation with the help of an expert panel. The two-shot prompting approach in combination with scope and domain context outperforms other methods and achieves the highest score when compared to the human reference set by a general practitioner. However, the automated reports are approximately twice as long as the human references, due to the addition of both redundant and relevant statements that are added to the report.

Paper Citation

in Harvard Style

van Zandvoort D., Wiersema L., Huibers T., van Dulmen S. and Brinkkemper S. (2024). Enhancing Summarization Performance Through Transformer-Based Prompt Engineering in Automated Medical Reporting. In Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF; ISBN 978-989-758-688-0, SciTePress, pages 154-165. DOI: 10.5220/0012422600003657

in Bibtex Style

@conference{healthinf24,
author={Daphne van Zandvoort and Laura Wiersema and Tom Huibers and Sandra van Dulmen and Sjaak Brinkkemper},
title={Enhancing Summarization Performance Through Transformer-Based Prompt Engineering in Automated Medical Reporting},
booktitle={Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF},
year={2024},
pages={154-165},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012422600003657},
isbn={978-989-758-688-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF
TI - Enhancing Summarization Performance Through Transformer-Based Prompt Engineering in Automated Medical Reporting
SN - 978-989-758-688-0
AU - van Zandvoort D.
AU - Wiersema L.
AU - Huibers T.
AU - van Dulmen S.
AU - Brinkkemper S.
PY - 2024
SP - 154
EP - 165
DO - 10.5220/0012422600003657
PB - SciTePress