Curran Katie, Whitestone Noelle, Zabeen Bedowra, Ahmed Munir, Husain Lutful, Alauddin Mohammed, Hossain Mohammad Awlad, Patnaik Jennifer L, Lanoutee Gabriella, Cherwek David Hunter, Congdon Nathan, Peto Tunde, Jaccard Nicolas
Centre for Public Health, Queens University Belfast, Belfast, UK.
Orbis International, New York, NY, USA.
Clin Med Insights Endocrinol Diabetes. 2023 Oct 9;16:11795514231203867. doi: 10.1177/11795514231203867. eCollection 2023.
Artificial intelligence (AI) appears capable of detecting diabetic retinopathy (DR) with a high degree of accuracy in adults; however, there are few studies in children and young adults.
Children and young adults (3-26 years) with type 1 diabetes mellitus (T1DM) or type 2 diabetes mellitus (T2DM) were screened at the Dhaka BIRDEM-2 hospital, Bangladesh. All gradable fundus images were uploaded to Cybersight AI for interpretation. Two main outcomes were considered at a patient level: 1) Any DR, defined as mild non-proliferative diabetic retinopathy (NPDR or more severe; and 2) Referable DR, defined as moderate NPDR or more severe. Diagnostic test performance comparing Orbis International's Cybersight AI with the reference standard, a fully qualified optometrist certified in DR grading, was assessed using the Matthews correlation coefficient (MCC), area under the receiver operating characteristic curve (AUC-ROC), area under the precision-recall curve (AUC-PR), sensitivity, specificity, positive and negative predictive values.
Among 1274 participants (53.1% female, mean age 16.7 years), 19.4% (n = 247) had any DR according to AI. For referable DR, 2.35% (n = 30) were detected by AI. The sensitivity and specificity of AI for any DR were 75.5% (CI 69.7-81.3%) and 91.8% (CI 90.2-93.5%) respectively, and for referable DR, these values were 84.2% (CI 67.8-100%) and 98.9% (CI 98.3%-99.5%). The MCC, AUC-ROC and the AUC-PR for referable DR were 63.4, 91.2 and 76.2% respectively. AI was most successful in accurately classifying younger children with shorter duration of diabetes.
Cybersight AI accurately detected any DR and referable DR among children and young adults, despite its algorithms having been trained on adults. The observed high specificity is particularly important to avoid over-referral in low-resource settings. AI may be an effective tool to reduce demands on scarce physician resources for the care of children with diabetes in low-resource settings.
人工智能（AI）似乎能够在成年人中高度准确地检测出糖尿病视网膜病变（DR）；然而，针对儿童和青年的研究较少。
在孟加拉国达卡BIRDEM - 2医院对患有1型糖尿病（T1DM）或2型糖尿病（T2DM）的儿童和青年（3 - 26岁）进行筛查。所有可分级的眼底图像被上传至Cybersight AI进行解读。在患者层面考虑两个主要结果：1）任何糖尿病视网膜病变，定义为轻度非增殖性糖尿病视网膜病变（NPDR）或更严重病变；2）可转诊的糖尿病视网膜病变，定义为中度NPDR或更严重病变。使用马修斯相关系数（MCC）、受试者工作特征曲线下面积（AUC - ROC）、精确召回率曲线下面积（AUC - PR）、灵敏度、特异度、阳性预测值和阴性预测值，评估将奥比斯国际的Cybersight AI与参考标准（一位具备DR分级资质的完全合格验光师）相比较时的诊断测试性能。
在1274名参与者中（53.1%为女性，平均年龄16.7岁），根据AI检测，19.4%（n = 247）患有任何糖尿病视网膜病变。对于可转诊的糖尿病视网膜病变，AI检测出2.35%（n = 30）。AI对任何糖尿病视网膜病变的灵敏度和特异度分别为75.5%（置信区间69.7 - 81.3%）和91.8%（置信区间90.2 - 93.5%），对于可转诊的糖尿病视网膜病变，这些值分别为84.2%（置信区间67.8 - 100%）和98.9%（置信区间98.3% - 99.5%）。可转诊的糖尿病视网膜病变的MCC、AUC - ROC和AUC - PR分别为63.4、91.2和76.2%。AI在准确分类糖尿病病程较短的年幼儿童方面最为成功。
尽管Cybersight AI的算法是基于成年人进行训练的，但它能准确检测儿童和青年中的任何糖尿病视网膜病变以及可转诊的糖尿病视网膜病变。观察到的高特异度对于在资源匮乏地区避免过度转诊尤为重要。在资源匮乏地区，AI可能是一种有效工具，可减少糖尿病患儿护理对稀缺医生资源的需求。
