Scholarlink

<p>US health systems receive up to 200 M monthly website visitors. Connecting patient searches to the appropriate workflow requires accurate classification. A dataset of searches on ~15 US health system websites was annotated, characterized, and used to train and evaluate a multi-label, multi-class, deep neural network. This classifier was deployed to health systems touching patients in all 50 states and compared to an LLM. The training dataset contained 504 unique classes with performance of the model in classifying searches among those classes ranging from ~0.90 to ~0.70 across metrics depending on the number of classes included. GPT-4 performed similarly if given a master list and demonstrated value in providing added coverage to augment the supervised classifier’s performance. The collected data revealed characteristics of patient searches in the largest, multi-center, national study of US health systems to date.</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

LLM enabled classification of patient self-reported symptoms and needs in health systems across the USA

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月1日

查看全文
  • Bilal A. Naved,
  • Shravan Ravishankar,
  • Georges E. Colbert,
  • Andrew Johnston,
  • Quintan M. Slott,
  • Yuan Luo

摘要

US health systems receive up to 200 M monthly website visitors. Connecting patient searches to the appropriate workflow requires accurate classification. A dataset of searches on ~15 US health system websites was annotated, characterized, and used to train and evaluate a multi-label, multi-class, deep neural network. This classifier was deployed to health systems touching patients in all 50 states and compared to an LLM. The training dataset contained 504 unique classes with performance of the model in classifying searches among those classes ranging from ~0.90 to ~0.70 across metrics depending on the number of classes included. GPT-4 performed similarly if given a master list and demonstrated value in providing added coverage to augment the supervised classifier’s performance. The collected data revealed characteristics of patient searches in the largest, multi-center, national study of US health systems to date.