Grzybowski Andrzej, Brona Piotr, Krzywicki Tomasz, Ruamviboonsuk Paisan
Institute for Research in Ophthalmology, Foundation for Ophthalmology Development, Poznan, Poland.
Department of Ophthalmology, Poznan City Hospital, Szwajcarska 3, 60-285, Poznan, Poland.
Ophthalmol Ther. 2025 Jan;14(1):73-84. doi: 10.1007/s40123-024-01049-z. Epub 2024 Nov 6.
Automated diabetic retinopathy (DR) screening using artificial intelligence has the potential to improve access to eye care by enabling large-scale screening. However, little is known about differences in real-world performance between available algorithms. This study compares the diagnostic accuracy of two AI screening platforms, IDx-DR and RetCAD, for detecting referable diabetic retinopathy (RDR).
Retinal images from 758 patients with diabetes were collected during screening from various clinics in Poland. Each patient was graded by three graders with 320 patients graded by Polish and 438 patients graded by Indian graders, with the majority decision serving as the reference standard. The images were evaluated independently by the IDx-DR and RetCAD algorithms. Sensitivity, specificity, positive and negative predictive values, and agreement between algorithms and human graders were calculated and statistically compared.
IDx-DR demonstrated higher sensitivity of 99.3% but lower specificity of 68.9% for RDR detection compared to RetCAD which had 89.4% sensitivity and 94.8% specificity. The positive predictive value was higher for RetCAD (96.4% vs 48.1% for IDx-DR) while the negative predictive value was higher for IDx-DR (99.5% vs 83.1% for RetCAD). Both algorithms achieved high sensitivity (> 95%) for sight-threatening diabetic retinopathy detection.
In this direct comparison using the same patient cohort, the two algorithms showed differences in their operating parameters for RDR screening. IDx-DR prioritized avoiding false negatives over false positives while RetCAD maintained a more balanced trade-off. These results highlight the variable performance of current artificial intelligence screening solutions and suggest the importance of considering algorithm performance metrics when deploying automated diabetic retinopathy screening programs, based on available healthcare resources.
利用人工智能进行糖尿病视网膜病变（DR）自动筛查，有潜力通过大规模筛查改善眼科护理服务的可及性。然而，对于现有算法在实际应用中的性能差异，我们了解甚少。本研究比较了两种人工智能筛查平台IDx-DR和RetCAD在检测可转诊糖尿病视网膜病变（RDR）方面的诊断准确性。
从波兰各诊所的筛查中收集了758例糖尿病患者的视网膜图像。每位患者由三名分级人员进行分级，其中320例患者由波兰分级人员分级，438例患者由印度分级人员分级，以多数人的判断作为参考标准。这些图像由IDx-DR和RetCAD算法独立评估。计算并统计比较了敏感性、特异性、阳性和阴性预测值，以及算法与人工分级人员之间的一致性。
与RetCAD相比，IDx-DR在检测RDR时表现出更高的敏感性（99.3%），但特异性较低（68.9%），RetCAD的敏感性为89.4%，特异性为94.8%。RetCAD的阳性预测值更高（96.4%，而IDx-DR为48.1%），而IDx-DR的阴性预测值更高（99.5%，而RetCAD为83.1%）。两种算法在检测威胁视力的糖尿病视网膜病变时均达到了较高的敏感性（>95%）。
在使用同一患者队列的直接比较中，两种算法在RDR筛查的操作参数上存在差异。IDx-DR优先避免假阴性而非假阳性，而RetCAD保持了更平衡的权衡。这些结果凸显了当前人工智能筛查解决方案的性能差异，并表明在基于可用医疗资源部署糖尿病视网膜病变自动筛查项目时，考虑算法性能指标的重要性。
