Department of endocrinology, Huangshan city People's Hospital, Huangshan 245000, China.
Department of endocrinology, Huangshan city People's Hospital, Huangshan 245000, China.
Photodiagnosis Photodyn Ther. 2024 Oct;49:104331. doi: 10.1016/j.pdpdt.2024.104331. Epub 2024 Sep 7.
To assess the feasibility of using non-mydriatic fundus photography in conjunction with an artificial intelligence (AI) reading platform for large-scale screening of diabetic retinopathy (DR).
In this study, we selected 120 patients with diabetes hospitalized in our institution from December 2019 to April 2021. Retinal imaging of 240 eyes was obtained using non-mydriatic fundus photography. The fundus images of these patients were divided into two groups based on different interpretation methods. In Experiment Group 1, the images were analyzed and graded for DR diagnosis using an AI reading platform. In Experiment Group 2, the images were analyzed and graded for DR diagnosis by an associate chief physician in ophthalmology, specializing in fundus diseases. Concurrently, all patients underwent the gold standard for DR diagnosis and grading-fundus fluorescein angiography (FFA)-with the outcomes serving as the Control Group. The diagnostic value of the two methods was assessed by comparing the results of Experiment Groups 1 and 2 with those of the Control Group.
Keeping the control group (FFA results) as the gold standard, no significant differences were observed between the two experimental groups regarding diagnostic sensitivity, specificity, false positive rate, false negative rate, positive predictive value, negative predictive value, Youden's index, Kappa value, and diagnostic accuracy (X = 0.371, P > 0.05).
Compared with the manual reading group, the AI reading group revealed no significant differences across all diagnostic indicators, exhibiting high sensitivity and specificity, as well as a relatively high positive predictive value. Additionally, it demonstrated a high level of diagnostic consistency with the gold standard. This technology holds potential for suitability in large-scale screening of DR.
评估非散瞳眼底照相术联合人工智能（AI）阅读平台用于糖尿病视网膜病变（DR）大规模筛查的可行性。
本研究选取 2019 年 12 月至 2021 年 4 月在我院住院的 120 例糖尿病患者，使用免散瞳眼底照相仪获取 240 只眼的视网膜图像。根据不同的解释方法，将这些患者的眼底图像分为两组。在实验组 1 中，使用 AI 阅读平台对图像进行分析和分级，以诊断 DR。在实验组 2 中，由专门从事眼底疾病的副主任医师对图像进行分析和分级，以诊断 DR。同时，所有患者均接受 DR 诊断和分级的金标准——眼底荧光血管造影（FFA）——作为对照组。通过将实验组 1 和 2 的结果与对照组进行比较，评估两种方法的诊断价值。
以对照组（FFA 结果）为金标准，两组在诊断敏感性、特异性、假阳性率、假阴性率、阳性预测值、阴性预测值、约登指数、Kappa 值和诊断准确性方面均无显著差异（X=0.371，P>0.05）。
与手动阅读组相比，AI 阅读组在所有诊断指标上均无显著差异，具有较高的敏感性和特异性，以及较高的阳性预测值。此外，它与金标准具有较高的诊断一致性。该技术在 DR 的大规模筛查中具有适用性的潜力。
