Scholarlink

<p>Detailed social determinants of health (SDoH) is often buried within clinical text in EHRs. Most current NLP efforts for SDoH have limitations, investigating limited factors, deriving data from a single institution, using specific patient cohorts/note types, with reduced focus on generalizability. We aim to address these issues by creating cross-institutional corpora and developing and evaluating the generalizability of classification models, including large language models (LLMs), for detecting SDoH factors using data from four institutions. Clinical notes were annotated with 21 SDoH factors at two levels: level 1 (SDoH factors only) and level 2 (SDoH factors and associated values). Compared to other models, instruction tuned LLM achieved top performance with micro-averaged F1 over 0.9 on level 1 corpora and over 0.84 on level 2 corpora. While models performed well when trained and tested on individual datasets, cross-dataset generalization highlighted remaining obstacles. Access to trained models will be made available at <a href="https://github.com/BIDS-Xu-Lab/LLMs4SDoH">https://github.com/BIDS-Xu-Lab/LLMs4SDoH</a>.</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

Social determinants of health extraction from clinical notes across institutions using large language models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月17日

查看全文
  • Vipina K. Keloth,
  • Salih Selek,
  • Qingyu Chen,
  • Christopher Gilman,
  • Sunyang Fu,
  • Yifang Dang,
  • Xinghan Chen,
  • Xinyue Hu,
  • Yujia Zhou,
  • Huan He,
  • Jungwei W. Fan,
  • Karen Wang,
  • Cynthia Brandt,
  • Cui Tao,
  • Hongfang Liu,
  • Hua Xu

摘要

Detailed social determinants of health (SDoH) is often buried within clinical text in EHRs. Most current NLP efforts for SDoH have limitations, investigating limited factors, deriving data from a single institution, using specific patient cohorts/note types, with reduced focus on generalizability. We aim to address these issues by creating cross-institutional corpora and developing and evaluating the generalizability of classification models, including large language models (LLMs), for detecting SDoH factors using data from four institutions. Clinical notes were annotated with 21 SDoH factors at two levels: level 1 (SDoH factors only) and level 2 (SDoH factors and associated values). Compared to other models, instruction tuned LLM achieved top performance with micro-averaged F1 over 0.9 on level 1 corpora and over 0.84 on level 2 corpora. While models performed well when trained and tested on individual datasets, cross-dataset generalization highlighted remaining obstacles. Access to trained models will be made available at https://github.com/BIDS-Xu-Lab/LLMs4SDoH.