Scholarlink

<p>‘Black box’ deep learning models for medical image interpretation limit clinical trust and analysis of performance degradation. Here we introduce Concept-Level Embeddings for Auditable Radiology (CLEAR), an auditable foundation model based on clinical concepts. Trained on over 0.87 million image–report pairs from 239,391 patients, CLEAR learns a visual representation and projects chest X-rays into a semantically rich space defined by large language model embeddings, making every prediction decomposable into weighted contributions from individual radiological observations. External validation on four large, physician-annotated datasets from the United States, Europe and Asia shows that CLEAR not only achieves state-of-the-art classification performance but also enables applications: auditable zero-shot pathology detection, systematic identification of radiological confounders and the creation of expert-level concept bottleneck models from data-driven concepts. By integrating clinical knowledge directly into its reasoning process, CLEAR offers a framework for robust model auditing, safer deployment and enhanced physician–AI collaboration, advancing towards trustworthy medical AI.</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

CLEAR: an auditable foundation model for radiology grounded in clinical concepts

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月22日

查看全文
  • Tianyu Han,
  • Riga Wu,
  • Yu Tian,
  • Firas Khader,
  • Lisa C. Adams,
  • Keno K. Bressem,
  • Christos Davatzikos,
  • Jakob Nikolas Kather,
  • Li Shen,
  • David A. Mankoff,
  • Eduardo Mortani Barbosa Jr,
  • Daniel Truhn

摘要

‘Black box’ deep learning models for medical image interpretation limit clinical trust and analysis of performance degradation. Here we introduce Concept-Level Embeddings for Auditable Radiology (CLEAR), an auditable foundation model based on clinical concepts. Trained on over 0.87 million image–report pairs from 239,391 patients, CLEAR learns a visual representation and projects chest X-rays into a semantically rich space defined by large language model embeddings, making every prediction decomposable into weighted contributions from individual radiological observations. External validation on four large, physician-annotated datasets from the United States, Europe and Asia shows that CLEAR not only achieves state-of-the-art classification performance but also enables applications: auditable zero-shot pathology detection, systematic identification of radiological confounders and the creation of expert-level concept bottleneck models from data-driven concepts. By integrating clinical knowledge directly into its reasoning process, CLEAR offers a framework for robust model auditing, safer deployment and enhanced physician–AI collaboration, advancing towards trustworthy medical AI.