Lions Aravind Institute of Community Ophthalmology, Aravind Eye Care System, Madurai, India.
Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Vic, Australia.
Eye (Lond). 2023 Jun;37(8):1577-1582. doi: 10.1038/s41433-022-02190-4. Epub 2022 Jul 29.
To validate the fundus image grading results by a trained grader (Non-ophthalmologist) and an ophthalmologist grader for detecting diabetic retinopathy (DR) and diabetic macular oedema (DMO) against fundus examination by a retina specialist (gold standard).
A prospective diagnostic accuracy study was conducted using 2002 non-mydriatic colour fundus images from 1001 patients aged ≥40 years. Using the Aravind Diabetic Retinopathy Evaluation Software (ADRES) images were graded by both a trained non-ophthalmologist grader (grader-1) and an ophthalmologist (grader-2). Sensitivity, specificity, positive predictive value and negative predictive value were calculated for grader-1 and grader-2 against the grading results by an independent retina specialist who performed dilated fundus examination for every study participant.
Out of 1001 patients included, 42% were women and the mean ± (SD) age was 55.8 (8.39) years. For moderate or worse DR, the sensitivity and specificity for grading by grader-1 with respect to the gold standard was 66.9% and 91.0% respectively and the same for the ophthalmologist was 83.6% and 80.3% respectively. For referable DMO, grader-1 and grader-2 had a sensitivity of 74.6% and 85.6% respectively and a specificity of 83.7% and 79.8% respectively.
Our results demonstrate good level of accuracy for the fundus image grading performed by a trained non-ophthalmologist which was comparable with the grading by an ophthalmologist. Engaging trained non-ophthalmologists potentially can enhance the efficiency of DR diagnosis using fundus images. Further study with multiple non-ophthalmologist graders is needed to verify the results and strategies to improve agreement for DMO diagnosis are needed.
通过对一名受过培训的（非眼科医生）分级员和一名眼科医生分级员对糖尿病视网膜病变（DR）和糖尿病黄斑水肿（DMO）进行眼底检查，验证眼底图像分级结果，并与视网膜专家的检查（金标准）相对照。
前瞻性诊断准确性研究使用了来自 1001 名年龄≥40 岁的患者的 2002 张非散瞳彩色眼底图像。使用 Aravind 糖尿病视网膜病变评估软件（ADRES），由一名受过培训的非眼科医生分级员（分级员 1）和一名眼科医生（分级员 2）对图像进行分级。针对每位研究参与者进行散瞳眼底检查的独立视网膜专家的分级结果，计算分级员 1 和分级员 2 的敏感性、特异性、阳性预测值和阴性预测值。
在纳入的 1001 名患者中，42%为女性，平均年龄（±标准差）为 55.8（8.39）岁。对于中度或更严重的 DR，分级员 1 和分级员 2 的分级结果与金标准相比，敏感性分别为 66.9%和 91.0%，眼科医生的敏感性分别为 83.6%和 80.3%。对于可治疗的 DMO，分级员 1 和分级员 2 的敏感性分别为 74.6%和 85.6%，特异性分别为 83.7%和 79.8%。
我们的结果表明，受过培训的非眼科医生进行的眼底图像分级具有良好的准确性，与眼科医生的分级相当。使用眼底图像进行 DR 诊断时，让经过培训的非眼科医生参与可以提高效率。需要进一步进行多非眼科医生分级员的研究来验证结果，并需要制定提高 DMO 诊断一致性的策略。
