Scholarlink

Due to the sensitive nature of medicine, it is particularly important and highly demanded that AI methods are explainable. This need has been recognised and there is great research interest in xAI solutions with medical applications. However, there is a lack of user-centred evaluation regarding the actual impact of the explanations. We evaluate attribute- and prototype-based explanations with the Proto-Caps model [1].

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

Abstract: Evaluating the Explainability of Attributes and Prototypes for a Medical Classification Model

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Luisa Gallée,
  • Catharina S. Lisson,
  • Christoph G. Lisson,
  • Daniela Drees,
  • Felix Weig,
  • Daniel Vogele,
  • Meinrad Beer,
  • Michael Götz

摘要

Due to the sensitive nature of medicine, it is particularly important and highly demanded that AI methods are explainable. This need has been recognised and there is great research interest in xAI solutions with medical applications. However, there is a lack of user-centred evaluation regarding the actual impact of the explanations. We evaluate attribute- and prototype-based explanations with the Proto-Caps model [1].