Scholarlink

<p>The applicability of vision-language models (VLMs) for acute care in emergency and intensive care units remains underexplored. Using a multimodal dataset of diagnostic questions involving medical images and clinical context, we benchmarked several small open-source VLMs against GPT-4o. While open models demonstrated limited diagnostic accuracy (up to 40.4%), GPT-4o significantly outperformed them (68.1%). Findings highlight the need for specialized training and optimization to improve open-source VLMs for acute care applications.</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

Benchmarking vision-language models for diagnostics in emergency and critical care settings

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月10日

查看全文
  • Christoph F. Kurz,
  • Tatiana Merzhevich,
  • Bjoern M. Eskofier,
  • Jakob Nikolas Kather,
  • Benjamin Gmeiner

摘要

The applicability of vision-language models (VLMs) for acute care in emergency and intensive care units remains underexplored. Using a multimodal dataset of diagnostic questions involving medical images and clinical context, we benchmarked several small open-source VLMs against GPT-4o. While open models demonstrated limited diagnostic accuracy (up to 40.4%), GPT-4o significantly outperformed them (68.1%). Findings highlight the need for specialized training and optimization to improve open-source VLMs for acute care applications.