Executive Vice Chair, Department of Radiology, Stanford University Medical Center, Stanford, California; Chair, Quality and Safety Commission, ACR; and Member, ACR Board of Chancellors.
Director of Innovation, University of Maryland Medical Intelligent Imaging (UM2ii) Center, Baltimore, Marlyand. Electronic address: https://twitter.com/flo_doo.
J Am Coll Radiol. 2024 Jul;21(7):1119-1129. doi: 10.1016/j.jacr.2024.01.024. Epub 2024 Feb 13.
Despite the surge in artificial intelligence (AI) development for health care applications, particularly for medical imaging applications, there has been limited adoption of such AI tools into clinical practice. During a 1-day workshop in November 2022, co-organized by the ACR and the RSNA, participants outlined experiences and problems with implementing AI in clinical practice, defined the needs of various stakeholders in the AI ecosystem, and elicited potential solutions and strategies related to the safety, effectiveness, reliability, and transparency of AI algorithms. Participants included radiologists from academic and community radiology practices, informatics leaders responsible for AI implementation, regulatory agency employees, and specialty society representatives. The major themes that emerged fell into two categories: (1) AI product development and (2) implementation of AI-based applications in clinical practice. In particular, participants highlighted key aspects of AI product development to include clear clinical task definitions; well-curated data from diverse geographic, economic, and health care settings; standards and mechanisms to monitor model reliability; and transparency regarding model performance, both in controlled and real-world settings. For implementation, participants emphasized the need for strong institutional governance; systematic evaluation, selection, and validation methods conducted by local teams; seamless integration into the clinical workflow; performance monitoring and support by local teams; performance monitoring by external entities; and alignment of incentives through credentialing and reimbursement. Participants predicted that clinical implementation of AI in radiology will continue to be limited until the safety, effectiveness, reliability, and transparency of such tools are more fully addressed.
尽管人工智能 (AI) 在医疗保健应用领域，特别是在医学影像应用领域的发展势头迅猛，但此类 AI 工具在临床实践中的采用率仍然有限。在 2022 年 11 月由 ACR 和 RSNA 共同组织的为期 1 天的研讨会上，参与者概述了在临床实践中实施 AI 的经验和问题，确定了 AI 生态系统中各个利益相关者的需求，并提出了与 AI 算法的安全性、有效性、可靠性和透明度相关的潜在解决方案和策略。参与者包括来自学术和社区放射科的放射科医生、负责 AI 实施的信息学领导者、监管机构员工和专业学会代表。出现的主要主题分为两类：(1) AI 产品开发和 (2) 在临床实践中实施基于 AI 的应用。特别是，参与者强调了 AI 产品开发的关键方面，包括明确的临床任务定义；来自不同地理、经济和医疗保健环境的精心策划的数据；监测模型可靠性的标准和机制；以及关于模型在受控和真实环境中的性能的透明度。在实施方面，参与者强调需要强大的机构治理；由当地团队进行系统的评估、选择和验证方法；无缝集成到临床工作流程中；由当地团队进行性能监测和支持；由外部实体进行性能监测；以及通过认证和报销来调整激励措施。参与者预测，放射科的 AI 临床实施将继续受到限制，直到此类工具的安全性、有效性、可靠性和透明度得到更充分的解决。
