Scholarlink

Purpose <p>In this short communication, we consider the need for explainable AI from the perspective of a large multi-disciplinary research project for predicting cachexia in cancer patients.</p> Materials and methods <p>In a series of meetings, comprising expertise from medicine, data science, sociology, and philosophy, project participants discussed the need for explainability.</p> Results <p>We distinguish between contexts in which a black box AI tool undertakes tasks that users can perform or validate themselves and contexts in which this is not the case.</p> Conclusion <p>We conclude that explanations are likely required when a black box AI tool undertakes tasks that users cannot perform or validate themselves. If the user can verify outputs manually, documented reliability and accuracy may suffice, but explainability can still add value when outputs are uncertain or errors occur. More generally, close collaboration among physicians, AI developers, and other stakeholders is crucial to ensure that AI tools are trustworthy and useful in clinical practice.</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

Explainable AI in nuclear medicine

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月25日

查看全文
  • Sune Holm,
  • Daria Ferrara,
  • Miriam Pepponi,
  • Elisabetta Abenavoli,
  • Armin Frille,
  • Shaul Duke,
  • Stefan Grünert,
  • Marcus Hacker,
  • Bengt Hennig,
  • Swen Hesse,
  • Lukas Hofmann,
  • Thomas B. Lund,
  • Osama Sabri,
  • Peter Sandøe,
  • Roberto Sciagrà,
  • Lalith Kumar Shiyam Sundar,
  • Josef Yu,
  • Thomas Beyer

摘要

Purpose

In this short communication, we consider the need for explainable AI from the perspective of a large multi-disciplinary research project for predicting cachexia in cancer patients.

Materials and methods

In a series of meetings, comprising expertise from medicine, data science, sociology, and philosophy, project participants discussed the need for explainability.

Results

We distinguish between contexts in which a black box AI tool undertakes tasks that users can perform or validate themselves and contexts in which this is not the case.

Conclusion

We conclude that explanations are likely required when a black box AI tool undertakes tasks that users cannot perform or validate themselves. If the user can verify outputs manually, documented reliability and accuracy may suffice, but explainability can still add value when outputs are uncertain or errors occur. More generally, close collaboration among physicians, AI developers, and other stakeholders is crucial to ensure that AI tools are trustworthy and useful in clinical practice.