Casey Eye Institute, Oregon Health & Science University, Portland.
Pediatric Retina and Ocular Oncology Division, Aravind Eye Hospital, Coimbatore, India.
JAMA Ophthalmol. 2022 Aug 1;140(8):791-798. doi: 10.1001/jamaophthalmol.2022.2135.
Retinopathy of prematurity (ROP) is a leading cause of preventable blindness that disproportionately affects children born in low- and middle-income countries (LMICs). In-person and telemedical screening examinations can reduce this risk but are challenging to implement in LMICs owing to the multitude of at-risk infants and lack of trained ophthalmologists.
To implement an ROP risk model using retinal images from a single baseline examination to identify infants who will develop treatment-requiring (TR)-ROP in LMIC telemedicine programs.
DESIGN, SETTING, AND PARTICIPANTS: In this diagnostic study conducted from February 1, 2019, to June 30, 2021, retinal fundus images were collected from infants as part of an Indian ROP telemedicine screening program. An artificial intelligence (AI)-derived vascular severity score (VSS) was obtained from images from the first examination after 30 weeks' postmenstrual age. Using 5-fold cross-validation, logistic regression models were trained on 2 variables (gestational age and VSS) for prediction of TR-ROP. The model was externally validated on test data sets from India, Nepal, and Mongolia. Data were analyzed from October 20, 2021, to April 20, 2022.
Primary outcome measures included sensitivity, specificity, positive predictive value, and negative predictive value for predictions of future occurrences of TR-ROP; the number of weeks before clinical diagnosis when a prediction was made; and the potential reduction in number of examinations required.
A total of 3760 infants (median [IQR] postmenstrual age, 37 [5] weeks; 1950 male infants [51.9%]) were included in the study. The diagnostic model had a sensitivity and specificity, respectively, for each of the data sets as follows: India, 100.0% (95% CI, 87.2%-100.0%) and 63.3% (95% CI, 59.7%-66.8%); Nepal, 100.0% (95% CI, 54.1%-100.0%) and 77.8% (95% CI, 72.9%-82.2%); and Mongolia, 100.0% (95% CI, 93.3%-100.0%) and 45.8% (95% CI, 39.7%-52.1%). With the AI model, infants with TR-ROP were identified a median (IQR) of 2.0 (0-11) weeks before TR-ROP diagnosis in India, 0.5 (0-2.0) weeks before TR-ROP diagnosis in Nepal, and 0 (0-5.0) weeks before TR-ROP diagnosis in Mongolia. If low-risk infants were never screened again, the population could be effectively screened with 45.0% (India, 664/1476), 38.4% (Nepal, 151/393), and 51.3% (Mongolia, 266/519) fewer examinations required.
Results of this diagnostic study suggest that there were 2 advantages to implementation of this risk model: (1) the number of examinations for low-risk infants could be reduced without missing cases of TR-ROP, and (2) high-risk infants could be identified and closely monitored before development of TR-ROP.
早产儿视网膜病变（ROP）是一种可导致失明的主要疾病，在中低收入国家（LMICs）的发生率过高。通过进行面对面或远程医疗筛查检查可以降低这种风险，但由于高危婴儿数量众多且缺乏受过培训的眼科医生，在 LMICs 中实施这些检查非常具有挑战性。
利用单次基线检查的视网膜图像，实施 ROP 风险模型，以识别出在 LMIC 远程医疗计划中会发展为需要治疗的 ROP（TR-ROP）的婴儿。
设计、地点和参与者：在这项于 2019 年 2 月 1 日至 2021 年 6 月 30 日期间进行的诊断性研究中，从接受印度 ROP 远程医疗筛查计划的婴儿中收集了眼底图像。从胎龄 30 周后首次检查的图像中获得了一种人工智能（AI）衍生的血管严重程度评分（VSS）。使用 5 折交叉验证，使用 2 个变量（胎龄和 VSS）对 TR-ROP 进行预测，训练了逻辑回归模型。该模型在印度、尼泊尔和蒙古的测试数据集上进行了外部验证。数据于 2021 年 10 月 20 日至 2022 年 4 月 20 日进行分析。
主要结果指标包括对未来 TR-ROP 发生的预测的灵敏度、特异性、阳性预测值和阴性预测值；预测做出时距离临床诊断的周数；以及所需检查数量的潜在减少。
共纳入了 3760 名婴儿（中位 [IQR] 胎龄，37 [5] 周；1950 名男婴[51.9%]）。该诊断模型在每个数据集上的灵敏度和特异性分别为：印度，100.0%（95%CI，87.2%-100.0%）和 63.3%（95%CI，59.7%-66.8%）；尼泊尔，100.0%（95%CI，54.1%-100.0%）和 77.8%（95%CI，72.9%-82.2%）；蒙古，100.0%（95%CI，93.3%-100.0%）和 45.8%（95%CI，39.7%-52.1%）。使用 AI 模型，在印度，TR-ROP 诊断前 2.0（0-11）周内识别出 TR-ROP 婴儿，在尼泊尔，TR-ROP 诊断前 0.5（0-2.0）周内识别出 TR-ROP 婴儿，在蒙古，TR-ROP 诊断前 0（0-5.0）周内识别出 TR-ROP 婴儿。如果不再对低危婴儿进行筛查，那么印度、尼泊尔和蒙古的人群可以通过 45.0%（印度，664/1476）、38.4%（尼泊尔，151/393）和 51.3%（蒙古，266/519）的更少检查次数来有效地进行筛查。
这项诊断研究的结果表明，实施该风险模型有两个优势：（1）不会遗漏 TR-ROP 病例，同时可以减少对低危婴儿的检查次数；（2）可以在高危婴儿发展为 TR-ROP 之前对其进行识别并进行密切监测。
