Comparative Analysis of Open-Source Language Models in Summarizing Medical Text Data

TL;DR

This paper evaluates the performance of open-source large language models like Llama2 and Mistral in medical text summarization, using GPT-4 as an assessor, to improve quality control and model selection in digital health applications.

Contribution

It introduces a novel evaluation method for comparing open-source LLMs in medical summarization, addressing a gap in systematic performance assessment for domain-specific models.

Findings

Llama2 and Mistral show varying effectiveness in medical summarization.

GPT-4 can reliably assess LLM-generated medical summaries.

The evaluation approach supports better model selection for healthcare tasks.

Abstract

Unstructured text in medical notes and dialogues contains rich information. Recent advancements in Large Language Models (LLMs) have demonstrated superior performance in question answering and summarization tasks on unstructured text data, outperforming traditional text analysis approaches. However, there is a lack of scientific studies in the literature that methodically evaluate and report on the performance of different LLMs, specifically for domain-specific data such as medical chart notes. We propose an evaluation approach to analyze the performance of open-source LLMs such as Llama2 and Mistral for medical summarization tasks, using GPT-4 as an assessor. Our innovative approach to quantitative evaluation of LLMs can enable quality control, support the selection of effective LLMs for specific tasks, and advance knowledge discovery in digital health.