人工智能:私立执业机构的视角
本文从私立放射执业机构的视角回顾其作为人工智能早期采用者的经验,涵盖识别有价值的用例、选择AI产品与供应商、试点算法、自研算法、实施优化维护、获得放射科医生接受并整合到日常工作流程,指出需准备数据、系统和放射科医生以确保成功且可扩展的AI实施。
要点
- 放射AI仍不成熟,采用者有限且以学术机构为主,普通执业中用例少。
- 成功且可扩展的AI实施需准备数据、系统和放射科医生。
- 本机构经验涵盖选择AI产品、试点算法、自研算法及整合到日常工作流程。
核心结论
- 放射AI仍不成熟,采用者有限,以学术机构为主,普通执业中用例少。
- 本机构作为早期采用者积累了识别用例、选择产品与供应商、试点及自研算法、实施优化维护、获得医生接受并整合工作流程的经验。
- 确保成功且可扩展的AI实施需要多个步骤,包括准备数据、系统和放射科医生。
研究设计与样本
- 本文为私立执业机构的经验回顾性文章,非研究论文,未报告样本量、中心数或参考标准。
临床应用与阅片要点
- 本机构的做法是识别为患者和执业提供价值的用例,选择AI产品与供应商,试点供应商的AI算法,创建自己的AI算法,实施、优化并维护这些算法,获得放射科医生接受并整合到日常工作流程。
- 作者认为确保成功且可扩展的AI实施需要多个步骤,包括准备数据、系统和放射科医生,并描述了每一步的重要性。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
Artificial intelligence (AI) is an exciting technology that can transform the practice of radiology. However, radiology AI is still immature with limited adopters, dominated by academic institutions, and few use cases in general practice. With scale and a focus on innovation, our practice has had the opportunity to be an early adopter of AI technology. We have gained experience identifying use cases that provide value for our patients and practice; selecting AI products and vendors; piloting vendors' AI algorithms; creating our own AI algorithms; implementing, optimizing, and maintaining these algorithms; garnering radiologist acceptance of these tools; and integrating AI into our radiologists' daily workflow. With this experience, our practice has both managed challenges and identified unexpected benefits of AI. To ensure a successful and scalable AI implementation, multiple steps are required, including preparing the data, systems, and radiologists. This article reviews our experience with AI and describes why each step is important.
引用
- Kottler N. Artificial Intelligence: A Private Practice Perspective. J Am Coll Radiol. 2020. PMID: 33010212. doi:10.1016/j.jacr.2020.09.029
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。