Abràmoff Michael D, Lavin Philip T, Jakubowski Julie R, Blodi Barbara A, Keeys Mia, Joyce Cara, Folk James C
Department of Ophthalmology and Visual Sciences, University of Iowa, Iowa City, IA, USA.
Veterans Administration Medical Center, Iowa City, IA, USA.
NPJ Digit Med. 2024 Dec 19;7(1):369. doi: 10.1038/s41746-024-01389-x.
Where adopted, Autonomous artificial Intelligence (AI) for Diabetic Retinal Disease (DRD) resolves longstanding racial, ethnic, and socioeconomic disparities, but AI adoption bias persists. This preregistered trial determined sensitivity and specificity of a previously FDA authorized AI, improved to compensate for lower contrast and smaller imaged area of a widely adopted, lower cost, handheld fundus camera (RetinaVue700, Baxter Healthcare, Deerfield, IL) to identify DRD in participants with diabetes without known DRD, in primary care. In 626 participants (1252 eyes) 50.8% male, 45.7% Hispanic, 17.3% Black, DRD prevalence was 29.0%, all prespecified non-inferiority endpoints were met and no racial, ethnic or sex bias was identified, against a Wisconsin Reading Center level I prognostic standard using widefield stereoscopic photography and macular Optical Coherence Tomography. Results suggest this improved autonomous AI system can mitigate AI adoption bias, while preserving safety and efficacy, potentially contributing to rapid scaling of health access equity. ClinicalTrials.gov NCT05808699 (3/29/2023).
在采用自主人工智能用于糖尿病视网膜病变（DRD）的情况下，可解决长期存在的种族、民族和社会经济差异问题，但人工智能的采用存在偏差。这项预先注册的试验确定了一种先前获得美国食品药品监督管理局（FDA）授权的人工智能的敏感性和特异性，该人工智能已得到改进，以补偿一种广泛使用的、成本较低的手持式眼底相机（RetinaVue700，百特医疗，伊利诺伊州迪尔菲尔德）对比度较低和成像区域较小的问题，用于在初级保健中识别无已知糖尿病视网膜病变的糖尿病患者中的糖尿病视网膜病变。在626名参与者（1252只眼睛）中，男性占50.8%，西班牙裔占45.7%，黑人占17.3%，糖尿病视网膜病变患病率为29.0%，所有预先设定的非劣效性终点均达到，并且未发现种族、民族或性别偏差，对照威斯康星阅读中心使用广角立体摄影和黄斑光学相干断层扫描的I级预后标准。结果表明，这种改进的自主人工智能系统可以减轻人工智能采用偏差，同时保持安全性和有效性，可能有助于快速扩大医疗公平性。ClinicalTrials.gov NCT05808699（2023年3月29日）。
