Scholarlink

<p>Synoptic reporting, the documenting of clinical information in a structured manner, enhances patient care by improving accuracy, readability, and report completeness, but imposes significant administrative burdens on physicians. The potential of Large Language Models (LLMs) for automating synoptic reporting remains underexplored. In this study, we explore state-of-the-art LLMs for automatic synoptic reporting, using 7774 pathology reports from 8 cancer types, paired with physician annotated synoptic reports from the Mayo Clinic EHR. We developed a comprehensive automation framework, combining state-of-the-art LLMs, incorporating parameter-efficient optimization, scalable prompt templates, and robust evaluation strategies. We validate our results on both internal and external data, ensuring alignment with pathologist responses. Using our framework, fine-tuned LLAMA-2 achieved BERT F1 scores above 0.86 across all data elements and exceeding 0.94 over 50% (11 of 22) of the data elements, translating to manually assessed mean semantic accuracies of 77% and up to 81% for short clinical reports.</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

Synoptic reporting by summarizing cancer pathology reports using large language models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月1日

查看全文
  • Sivaraman Rajaganapathy,
  • Shaika Chowdhury,
  • Xiaodi Li,
  • Vincent Buchner,
  • Zhe He,
  • Rui Zhang,
  • Xiaoqian Jiang,
  • Ping Yang,
  • James R. Cerhan,
  • Nansu Zong

摘要

Synoptic reporting, the documenting of clinical information in a structured manner, enhances patient care by improving accuracy, readability, and report completeness, but imposes significant administrative burdens on physicians. The potential of Large Language Models (LLMs) for automating synoptic reporting remains underexplored. In this study, we explore state-of-the-art LLMs for automatic synoptic reporting, using 7774 pathology reports from 8 cancer types, paired with physician annotated synoptic reports from the Mayo Clinic EHR. We developed a comprehensive automation framework, combining state-of-the-art LLMs, incorporating parameter-efficient optimization, scalable prompt templates, and robust evaluation strategies. We validate our results on both internal and external data, ensuring alignment with pathologist responses. Using our framework, fine-tuned LLAMA-2 achieved BERT F1 scores above 0.86 across all data elements and exceeding 0.94 over 50% (11 of 22) of the data elements, translating to manually assessed mean semantic accuracies of 77% and up to 81% for short clinical reports.