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

TL;DR

This paper explores how transformer-based prompt engineering, specifically shot and pattern prompting, improves automated medical report generation from dialogues, achieving high ROUGE scores and expert approval.

Contribution

It introduces a novel combination of shot and pattern prompting strategies to enhance LLM performance in medical dialogue summarization.

Findings

Two-shot prompting with scope and domain context outperforms other methods.

Automated reports are twice as long as human references, including redundant and relevant statements.

The approach achieves the highest ROUGE scores and expert approval compared to baseline methods.

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. Implementing 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.