Scholarlink

<p>We developed a named entity (NE) framework for information extraction from semi-structured clinical notes retrieved from The Cancer Genome Atlas—Thyroid Cancer (TCGA-THCA) database and examined Large Language Models (LLMs) strategies to classify the 8<sup>th</sup> edition of American Joint Committee on Cancer (AJCC) staging and American Thyroid Association (ATA) risk category for patients with well-differentiated thyroid cancer. The NE framework consisted of annotation guidelines development, ground truth labelling, prompting approaches, and evaluation codes. Four LLMs (Mistral-7B-Instruct, Llama-3.1-8B-Instruct, Gemma-2-9B-Instruct, and Qwen2.5-7B-Instruct) were offline utilised for information extraction, comparing with expert-curated ground truth. Our framework was developed using 50 TCGA-THCA pathology notes. 289 TCGA-THCA notes and 35 pseudo-clinical cases were used for validation. Taking an ensemble-like majority-vote strategy achieved satisfactory performance for AJCC and ATA in both development and validation sets. Our framework and ensemble classifier optimised efficiency and accuracy of classifying stage and risk category in thyroid cancer patients.</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

Developing a named entity framework for thyroid cancer staging and risk level classification using large language models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月1日

查看全文
  • Matrix M. H. Fung,
  • Eric H. M. Tang,
  • Tingting Wu,
  • Yan Luk,
  • Ivan C. H. Au,
  • Xiaodong Liu,
  • Victor H. F. Lee,
  • Chun Ka Wong,
  • Zhili Wei,
  • Wing Yiu Cheng,
  • Isaac C. Y. Tai,
  • Joshua W. K. Ho,
  • Jason W. H. Wong,
  • Brian H. H. Lang,
  • Kathy S. M. Leung,
  • Zoie S. Y. Wong,
  • Joseph T. Wu,
  • Carlos K. H. Wong

摘要

We developed a named entity (NE) framework for information extraction from semi-structured clinical notes retrieved from The Cancer Genome Atlas—Thyroid Cancer (TCGA-THCA) database and examined Large Language Models (LLMs) strategies to classify the 8th edition of American Joint Committee on Cancer (AJCC) staging and American Thyroid Association (ATA) risk category for patients with well-differentiated thyroid cancer. The NE framework consisted of annotation guidelines development, ground truth labelling, prompting approaches, and evaluation codes. Four LLMs (Mistral-7B-Instruct, Llama-3.1-8B-Instruct, Gemma-2-9B-Instruct, and Qwen2.5-7B-Instruct) were offline utilised for information extraction, comparing with expert-curated ground truth. Our framework was developed using 50 TCGA-THCA pathology notes. 289 TCGA-THCA notes and 35 pseudo-clinical cases were used for validation. Taking an ensemble-like majority-vote strategy achieved satisfactory performance for AJCC and ATA in both development and validation sets. Our framework and ensemble classifier optimised efficiency and accuracy of classifying stage and risk category in thyroid cancer patients.