Dos Reis Mateus A, Künas Cristiano A, da Silva Araújo Thiago, Schneiders Josiane, de Azevedo Pietro B, Nakayama Luis F, Rados Dimitris R V, Umpierre Roberto N, Berwanger Otávio, Lavinsky Daniel, Malerbi Fernando K, Navaux Philippe O A, Schaan Beatriz D
Graduate Program in Medical Sciences: Endocrinology, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil.
Universidade Feevale, Novo Hamburgo, RS, Brazil.
Diabetol Metab Syndr. 2024 Aug 29;16(1):209. doi: 10.1186/s13098-024-01447-0.
In healthcare systems in general, access to diabetic retinopathy (DR) screening is limited. Artificial intelligence has the potential to increase care delivery. Therefore, we trained and evaluated the diagnostic accuracy of a machine learning algorithm for automated detection of DR.
We included color fundus photographs from individuals from 4 databases (primary and specialized care settings), excluding uninterpretable images. The datasets consist of images from Brazilian patients, which differs from previous work. This modification allows for a more tailored application of the model to Brazilian patients, ensuring that the nuances and characteristics of this specific population are adequately captured. The sample was fractionated in training (70%) and testing (30%) samples. A convolutional neural network was trained for image classification. The reference test was the combined decision from three ophthalmologists. The sensitivity, specificity, and area under the ROC curve of the algorithm for detecting referable DR (moderate non-proliferative DR; severe non-proliferative DR; proliferative DR and/or clinically significant macular edema) were estimated.
A total of 15,816 images (4590 patients) were included. The overall prevalence of any degree of DR was 26.5%. Compared with human evaluators (manual method of diagnosing DR performed by an ophthalmologist), the deep learning algorithm achieved an area under the ROC curve of 0.98 (95% CI 0.97-0.98), with a specificity of 94.6% (95% CI 93.8-95.3) and a sensitivity of 93.5% (95% CI 92.2-94.9) at the point of greatest efficiency to detect referable DR.
A large database showed that this deep learning algorithm was accurate in detecting referable DR. This finding aids to universal healthcare systems like Brazil, optimizing screening processes and can serve as a tool for improving DR screening, making it more agile and expanding care access.
在一般的医疗保健系统中，糖尿病视网膜病变（DR）筛查的可及性有限。人工智能有潜力增加医疗服务的提供。因此，我们训练并评估了一种用于自动检测DR的机器学习算法的诊断准确性。
我们纳入了来自4个数据库（初级和专科护理机构）中个体的彩色眼底照片，排除了无法解读的图像。数据集由巴西患者的图像组成，这与之前的研究不同。这种修改使得模型能够更有针对性地应用于巴西患者，确保充分捕捉这一特定人群的细微差别和特征。样本被分为训练样本（70%）和测试样本（30%）。训练一个卷积神经网络用于图像分类。参考测试是三位眼科医生的联合诊断结果。估计了该算法检测可转诊DR（中度非增殖性DR；重度非增殖性DR；增殖性DR和/或临床显著性黄斑水肿）的敏感性、特异性和ROC曲线下面积。
共纳入15816张图像（4590例患者）。任何程度DR的总体患病率为26.5%。与人类评估者（眼科医生手动诊断DR的方法）相比，深度学习算法在检测可转诊DR的最大效率点处，ROC曲线下面积为0.98（95%CI 0.97 - 0.98），特异性为94.6%（95%CI 93.8 - 95.3），敏感性为93.5%（95%CI 92.2 - 94.9）。
一个大型数据库表明，这种深度学习算法在检测可转诊DR方面是准确的。这一发现有助于像巴西这样的全民医疗保健系统优化筛查流程，并且可以作为改善DR筛查的工具，使其更加灵活并扩大医疗服务的可及性。
