Scholarlink

<p>In recent years, large language models (LLMs) have shown significant potential in various fields, including healthcare. This paper presents the development and application of a diabetes diagnosis system based on LLMs, focusing on improving doctor–patient communication. We propose a novel multitask fine-tuning strategy using low-rank adaptation to enhance the model’s performance in medical dialogue and report generation. The system integrates advanced prompt engineering techniques, such as Chain-of-Thought and Retrieval-Augmented Generation, to improve the accuracy and efficiency of medical text generation. Experimental results demonstrate that our approach significantly enhances the model’s ability to generate structured medical reports and conduct patient consultations. This study highlights the potential of LLMs in transforming diabetes management and provides a foundation for future research in medical AI applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A visual-language foundation model for disease diagnosis and doctor–patient co-decision

  • 期刊论文

  • 发表日期：

    2025年3月25日

查看全文
  • Yuanqi Yao,
  • Zehua Jiang,
  • Zhouyu Guan,
  • Yilun Luxue,
  • Seungmin Lee,
  • Xiang Chen,
  • Haodong Yang,
  • Yiming Qin

摘要

In recent years, large language models (LLMs) have shown significant potential in various fields, including healthcare. This paper presents the development and application of a diabetes diagnosis system based on LLMs, focusing on improving doctor–patient communication. We propose a novel multitask fine-tuning strategy using low-rank adaptation to enhance the model’s performance in medical dialogue and report generation. The system integrates advanced prompt engineering techniques, such as Chain-of-Thought and Retrieval-Augmented Generation, to improve the accuracy and efficiency of medical text generation. Experimental results demonstrate that our approach significantly enhances the model’s ability to generate structured medical reports and conduct patient consultations. This study highlights the potential of LLMs in transforming diabetes management and provides a foundation for future research in medical AI applications.