Scholarlink

<p>Eviction is a significant yet understudied social determinants of health (SDoH), linked to housing instability, unemployment, and mental health. While eviction appears in unstructured electronic health records (EHRs), it is rarely coded in structured fields, limiting downstream applications. We introduce SynthEHR-Eviction, a scalable pipeline that adapts and integrates human-in-the-loop annotation, automated prompt optimization (APO), and reasoning-augmented fine-tuning for low-resource eviction-related SDoH extraction from clinical notes. Using this pipeline, we created a large public eviction-related SDoH dataset to date, comprising 14 fine-grained categories. Fine-tuned LLMs (e.g., Qwen2.5, LLaMA3) trained on SynthEHR-Eviction achieved Macro-F1 scores of 88.8% (eviction) and 90.3% (other SDoH) on human validated data, outperforming GPT-4o-APO (87.8%, 87.3%), GPT-4o-mini-APO (69.1%, 78.1%), and BioBERT (60.7%, 68.3%), while enabling cost-effective deployment across various model sizes. The pipeline reduces annotation effort by over 80%, accelerates dataset creation, enables scalable eviction detection, and generalizes to other information extraction tasks.</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

SynthEHR-eviction: enhancing eviction SDoH detection with LLM-augmented synthetic EHR data

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月27日

查看全文
  • Zonghai Yao,
  • Youxia Zhao,
  • Avijit Mitra,
  • David A. Levy,
  • Emily Druhl,
  • Jack Tsai,
  • Hong Yu

摘要

Eviction is a significant yet understudied social determinants of health (SDoH), linked to housing instability, unemployment, and mental health. While eviction appears in unstructured electronic health records (EHRs), it is rarely coded in structured fields, limiting downstream applications. We introduce SynthEHR-Eviction, a scalable pipeline that adapts and integrates human-in-the-loop annotation, automated prompt optimization (APO), and reasoning-augmented fine-tuning for low-resource eviction-related SDoH extraction from clinical notes. Using this pipeline, we created a large public eviction-related SDoH dataset to date, comprising 14 fine-grained categories. Fine-tuned LLMs (e.g., Qwen2.5, LLaMA3) trained on SynthEHR-Eviction achieved Macro-F1 scores of 88.8% (eviction) and 90.3% (other SDoH) on human validated data, outperforming GPT-4o-APO (87.8%, 87.3%), GPT-4o-mini-APO (69.1%, 78.1%), and BioBERT (60.7%, 68.3%), while enabling cost-effective deployment across various model sizes. The pipeline reduces annotation effort by over 80%, accelerates dataset creation, enables scalable eviction detection, and generalizes to other information extraction tasks.