Scholarlink

<p>Proposals of artificial intelligence (AI) solutions based on more complex and accurate predictive models are becoming ubiquitous across many disciplines. As the complexity of these models increases, there is a tendency for transparency and users’ understanding to decrease. This means accurate prediction alone is insufficient to make an AI-based solution truly useful. For the development of healthcare systems, this raises new issues for accountability and safety. How and why an AI system made a recommendation may necessitate complex explanations of the inner workings and reasoning processes. While research on explainable AI (XAI) has grown significantly in recent years, and the demand for XAI in medicine is high, determining what constitutes a good explanation is ad hoc and providing adequate explanations remains a challenge. To realise the potential of AI, it is critical to shed light on two fundamental questions of explanation for safety–critical AI such as health-AI that remain unanswered: (1) What is an explanation in health-AI? And (2) What are the attributes of a good explanation in health-AI? In this study and possibly for the first time we studied published literature, and expert opinions from a diverse group of professionals reported from a two-round Delphi study. The research outputs include (1) a proposed definition of explanation in health-AI, and (2) a comprehensive set of attributes that characterize a good explanation in health-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

Explainable AI: definition and attributes of a good explanation for health AI

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月4日

查看全文
  • Evangelia Kyrimi,
  • Scott McLachlan,
  • Jared M. Wohlgemut,
  • Zane B. Perkins,
  • David A. Lagnado,
  • William Marsh,
  • Alexander Gimson,
  • Ali Shafti,
  • Ari Ercole,
  • Amitava Banerjee,
  • Ben Glocker,
  • Burkhard Schafer,
  • Constantine Gatsonis,
  • Crina Grosan,
  • Danielle Sent,
  • David S. Berman,
  • David Glass,
  • Declan P. O’Regan,
  • Dimitrios Letsios,
  • Dylan Morrissey,
  • Erhan Pisirir,
  • Francesco Leofante,
  • Hamit Soyel,
  • Jon Williamson,
  • Keri Grieman,
  • Kudakwashe Dube,
  • Max Marsden,
  • Myura Nagendran,
  • Nigel Tai,
  • Olga Kostopoulou,
  • Owain Jones,
  • Paul Curzon,
  • Rebecca S. Stoner,
  • Sankalp Tandle,
  • Shalmali Joshi,
  • Somayyeh Mossadegh,
  • Stefan Buijsman,
  • Tim Miller,
  • Vince Istvan Madai

摘要

Proposals of artificial intelligence (AI) solutions based on more complex and accurate predictive models are becoming ubiquitous across many disciplines. As the complexity of these models increases, there is a tendency for transparency and users’ understanding to decrease. This means accurate prediction alone is insufficient to make an AI-based solution truly useful. For the development of healthcare systems, this raises new issues for accountability and safety. How and why an AI system made a recommendation may necessitate complex explanations of the inner workings and reasoning processes. While research on explainable AI (XAI) has grown significantly in recent years, and the demand for XAI in medicine is high, determining what constitutes a good explanation is ad hoc and providing adequate explanations remains a challenge. To realise the potential of AI, it is critical to shed light on two fundamental questions of explanation for safety–critical AI such as health-AI that remain unanswered: (1) What is an explanation in health-AI? And (2) What are the attributes of a good explanation in health-AI? In this study and possibly for the first time we studied published literature, and expert opinions from a diverse group of professionals reported from a two-round Delphi study. The research outputs include (1) a proposed definition of explanation in health-AI, and (2) a comprehensive set of attributes that characterize a good explanation in health-AI.