van Leeuwen Kicky G, Schalekamp Steven, Rutten Matthieu J C M, van Ginneken Bram, de Rooij Maarten
Department of Medical Imaging, Radboud university medical center, P.O. Box 9101, 6500 HB, Nijmegen, The Netherlands.
Department of Radiology, Jeroen Bosch Hospital, 's-Hertogenbosch, The Netherlands.
Eur Radiol. 2021 Jun;31(6):3797-3804. doi: 10.1007/s00330-021-07892-z. Epub 2021 Apr 15.
Map the current landscape of commercially available artificial intelligence (AI) software for radiology and review the availability of their scientific evidence.
We created an online overview of CE-marked AI software products for clinical radiology based on vendor-supplied product specifications ( www.aiforradiology.com ). Characteristics such as modality, subspeciality, main task, regulatory information, deployment, and pricing model were retrieved. We conducted an extensive literature search on the available scientific evidence of these products. Articles were classified according to a hierarchical model of efficacy.
The overview included 100 CE-marked AI products from 54 different vendors. For 64/100 products, there was no peer-reviewed evidence of its efficacy. We observed a large heterogeneity in deployment methods, pricing models, and regulatory classes. The evidence of the remaining 36/100 products comprised 237 papers that predominantly (65%) focused on diagnostic accuracy (efficacy level 2). From the 100 products, 18 had evidence that regarded level 3 or higher, validating the (potential) impact on diagnostic thinking, patient outcome, or costs. Half of the available evidence (116/237) were independent and not (co-)funded or (co-)authored by the vendor.
Even though the commercial supply of AI software in radiology already holds 100 CE-marked products, we conclude that the sector is still in its infancy. For 64/100 products, peer-reviewed evidence on its efficacy is lacking. Only 18/100 AI products have demonstrated (potential) clinical impact.
• Artificial intelligence in radiology is still in its infancy even though already 100 CE-marked AI products are commercially available. • Only 36 out of 100 products have peer-reviewed evidence of which most studies demonstrate lower levels of efficacy. • There is a wide variety in deployment strategies, pricing models, and CE marking class of AI products for radiology.
梳理当前市场上可供使用的放射学人工智能（AI）软件情况，并评估其科学证据的可得性。
我们基于供应商提供的产品规格（www.aiforradiology.com），创建了一份关于临床放射学CE标志AI软件产品的在线概述。收集了诸如模态、亚专业、主要任务、监管信息、部署方式和定价模式等特征。我们对这些产品的现有科学证据进行了广泛的文献检索。文章根据疗效的分层模型进行分类。
该概述包括来自54个不同供应商的100种CE标志AI产品。对于64/100的产品，没有经过同行评审的疗效证据。我们观察到在部署方式、定价模式和监管类别方面存在很大的异质性。其余36/100产品的证据包括237篇论文，这些论文主要（65%）关注诊断准确性（疗效水平2）。在这100种产品中，有18种有证据表明达到3级或更高水平，证实了对诊断思维、患者结局或成本的（潜在）影响。现有证据的一半（116/237）是独立的，并非由供应商（共同）资助或（共同）撰写。
尽管放射学AI软件的商业供应已经有100种CE标志产品，但我们得出结论，该领域仍处于起步阶段。对于64/100的产品，缺乏关于其疗效的同行评审证据。只有18/100的AI产品显示出（潜在的）临床影响。
• 尽管已有100种CE标志的AI产品可供商业使用，但放射学中的人工智能仍处于起步阶段。• 100种产品中只有36种有同行评审的证据，其中大多数研究显示疗效水平较低。• 放射学AI产品的部署策略、定价模式和CE标志类别存在很大差异。
