arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.11978cs.HCcs.AI
收藏

“视情况而定”:配置AI以提升跨情境的临床实用性

"It depends": Configuring AI to Improve Clinical Usefulness Across Contexts

University of Copenhagen(哥本哈根大学);Rigshospitalet Copenhagen University Hospital(哥本哈根大学医院 Rigshospitalet);The Nairobi Hospital(内罗毕医院);Aga Khan University Hospital(阿迦汗大学医院)

Hubert D. Zając, Jorge M. N. Ribeiro, Silvia Ingala, Simona Gentile, Ruth Wanjohi, Samuel N. Gitau, Jonathan F. Carlsen, Michael B. Nielsen, Tariq O. Andersen

AI总结:

本文通过多站点设计研究,提出AI在放射学中需按临床情境配置功能、医学焦点、决策阈值和可解释性四个维度,并给出四项设计建议以提升临床实用性。

摘要:

人工智能(AI)在实验室实验中反复达到或超越放射科医生的表现。然而,现实世界中基于放射学AI系统的实施被发现几乎不提供或完全不提供临床价值。本文探讨了如何在不同情境下设计具有临床实用性的AI。我们基于一个功能性AI原型的三个迭代版本,在丹麦和肯尼亚的7个临床站点与13名放射科医生进行了19次设计会议和设计干预。我们确定了十项社会技术依赖关系,这些关系对于放射学中AI的设计至关重要。我们概念化了四个必须根据预期临床使用情境进行配置的技术维度:AI功能、AI医学焦点、AI决策阈值和AI可解释性。我们提出了四项设计建议,以解决与医学知识、诊所类型、用户专业水平、患者情境和用户状况相关的依赖关系,这些依赖关系制约着这些技术维度的配置。

英文摘要:

Artificial Intelligence (AI) repeatedly match or outperform radiologists in lab experiments. However, real-world implementations of radiological AI-based systems are found to provide little to no clinical value. This paper explores how to design AI for clinical usefulness in different contexts. We conducted 19 design sessions and design interventions with 13 radiologists from 7 clinical sites in Denmark and Kenya, based on three iterations of a functional AI-based prototype. Ten sociotechnical dependencies were identified as crucial for the design of AI in radiology. We conceptualised four technical dimensions that must be configured to the intended clinical context of use: AI functionality, AI medical focus, AI decision threshold, and AI Explainability. We present four design recommendations on how to address dependencies pertaining to the medical knowledge, clinic type, user expertise level, patient context, and user situation that condition the configuration of these technical dimensions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑