FDA批准的眼科AI医疗设备

引言：人工智能的概念于1956年首次提出。从那时起，该领域取得了显著的进展，以至于被定义为“人类历史上的第四次工业革命”。随着技术的进步，医疗设备越来越依赖包含人工智能 (AI) 的软件及信息系统。同时机器学习正在从医疗领域的应用中生成现实世界的证据，而这些证据又被集成到新兴的医疗设备中。

以下梳理了这些设备中在眼科方向的应用。

01、糖尿病性视网膜病变

1.1 Idx-DR v2.3– Idx-DR 与 Topcon NW400 结合使用，自动检测先前未诊断出患有糖尿病视网膜病变的成人糖尿病患者眼中的（超过轻度）糖尿病视网膜病变。

IDx公司的IDx-DR是世界上首个获批用于糖尿病视网膜病变诊断的自主式人工智能诊疗设备，对患有糖尿病视网膜病变和黄斑水肿的患者来说，它可以在无专业医生协助的情况下解读患者视网膜照片图像，实现对糖尿病视网膜病变患者的诊断、提高问诊的效率、进而有效减轻医疗资源压力。

相关阅读

IDx-DR v2.3. 510(k) Premarket Notification. US Food and Drug Administration. https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm?ID=K213037.

1. IDx-DR. 510(k) Premarket Notification. US Food and Drug Administration. https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K203629.

2. IDx-DR. Device Classification Under Section 513(f)(2)(De Novo). US Food and Drug Administration. https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm?ID=DEN180001.

3. Grzybowski A, Brona P. Analysis and Comparison of Two Artificial Intelligence Diabetic Retinopathy Screening Algorithms in a Pilot Study: IDx-DR and Retinalyze. J Clin Med 2021; 10.

4. Abràmoff MD, Lavin PT, Birch M, et al. Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices. NPJ Digit Med 2018; 1:39.

5. Abramoff MD, Mortensen Z, Tava C. Commentary: Diagnosing Diabetic Retinopathy With Artificial Intelligence: What Information Should Be Included to Ensure Ethical Informed Consent? Front Med (Lausanne) 2021; 8:765936.

6. Shah A, Clarida W, Amelon R, et al. Validation of Automated Screening for Referable Diabetic Retinopathy With an Autonomous Diagnostic Artificial Intelligence System in a Spanish Population. J Diabetes Sci Technol 2021; 15:655.

1.2 EyeArt – EyeArt 可自动检测先前未诊断出患有糖尿病视网膜病变的成人糖尿病患者眼睛中的（超过轻度）糖尿病视网膜病变以及更严重的糖尿病视网膜病变。EyeArt AI系统是Eyenuk在美国国立卫生研究院（NIH）的资助下开发用于DR自主检测的产品，经过英国国家卫生服务局（NHS）的验证，并在全球超过50万患者和近200万张视网膜图像的真实世界中进行了测试。该系统使医生能够在糖尿病患者的常规检查期间快速准确地识别可转诊的DR患者，从而使初级保健诊所、糖尿病中心和验光室的临床实时DR筛查成为可能。

相关阅读

EyeArt. 510(k) Premarket Notification. US Food and Drug Administration. https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K200667.

1. Ipp E, Liljenquist D, Bode B, et al. Pivotal Evaluation of an Artificial Intelligence System for Autonomous Detection of Referrable and Vision-Threatening Diabetic Retinopathy. JAMA Netw Open 2021; 4:e2134254.

2. Bhaskaranand M, Ramachandra C, Bhat S, et al. The Value of Automated Diabetic Retinopathy Screening with the EyeArt System: A Study of More Than 100,000 Consecutive Encounters from People with Diabetes. Diabetes Technol Ther 2019; 21:635.

02、视网膜和眼表的其他疾病

2.1 CLARUS – CLARUS 700 型是一种主动软件成像设备，可捕获、显示、存储和注释眼睛图像，以协助诊断和监测影响眼表、视网膜和其他可见附属器官的疾病。Clarus 700是第一款高分辨率的超宽视野成像设备，具有真实的色彩和完整的眼底成像方式，包括荧光素血管造影。

相关阅读

1. CLARUS. 510(k) Premarket Notification. US Food and Drug Administration.https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K191194.

2. Chen A, Dang S, Chung MM, et al. Quantitative Comparison of Fundus Images by 2 Ultra-Widefield Fundus Cameras. Ophthalmol Retina 2021; 5:450.

2.2 IRIS

智能视网膜成像系统– IRIS 软件是一种服务应用程序，允许临床医生使用眼底相机扫描患者的视网膜，将图像上传到网站并提供扫描结果的解释。

相关阅读

IRIS INTELLIGENT RETINAL IMAGING SYSTEM. 510(k) Premarket Notification. US Food and Drug Administration.:https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm?ID=K141922.

1. Naik S, Wykoff CC, Ou WC, et al. Identification of factors to increase efficacy of telemedicine screening for diabetic retinopathy in endocrinology practices using the Intelligent Retinal Imaging System (IRIS) platform. Diabetes Res Clin Pract 2018; 140:265

03、视觉追踪障碍

RightEye

视觉系统– RightEye 视觉系统可查看、记录和分析可能存在视觉跟踪障碍的患者的眼球运动。将该系统分类到医疗设备的标准中，这是因为该产品旨在用于疾病或其他状况的诊断。除此之外，它还可以用于治愈、缓解或预防疾病，同时对身体结构功能带来一定的影响。

相关阅读

1. RightEye Vision System. 510(k) Premarket Notification. US Food and Drug Administration. https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K181771.

2. Murray NP, Hunfalvay M, Bolte T. The Reliability, Validity, and Normative Data of Interpupillary Distance and Pupil Diameter Using Eye-Tracking Technology. Transl Vis Sci Technol 2017; 6:2.