早产儿视网膜病变自主筛查的多国外部验证
这项诊断研究评估了基于自主人工智能(AI)的早产儿视网膜病变(ROP)筛查在检测重于轻度ROP(mtmROP)和1型ROP方面的性能。AI算法在i-ROP研究的2530次检查(843名婴儿)上训练和校准,并在两个外部数据集上验证:美国SUNDROP(6245次检查,1545名婴儿)和印度AECS远程医疗项目(5635次检查,2699名婴儿)。在检查层面,mtmROP和1型ROP的AUROC分别为0.896和0.985(SUNDROP)以及0.920和0.982(AECS);所有发展为1型ROP的婴儿在诊断前筛查均为阳性(SUNDROP 100%,AECS 100%)。结论认为,在能够实施ROP远程医疗项目的地方和时候,自主ROP筛查可能成为ROP二级预防的有效力量倍增器。
要点
- 在SUNDROP数据集,检查层面mtmROP和1型ROP的AUROC分别为0.896和0.985。
- 在AECS数据集,检查层面mtmROP和1型ROP的AUROC分别为0.920和0.982。
- 患者层面,所有发展为1型ROP的婴儿在诊断前筛查均为阳性(SUNDROP 100%,AECS 100%)。
核心结论
- 在能够实施ROP远程医疗项目的地方和时候,自主ROP筛查可能成为ROP二级预防的有效力量倍增器。
研究设计与样本
- 这项诊断研究评估了基于自主人工智能(AI)的ROP筛查算法,该算法使用i-ROP研究的2530次检查(843名婴儿)进行训练和校准。
- 外部验证使用两个数据集:美国SUNDROP的6245次检查(1545名婴儿)和印度AECS远程医疗项目的5635次检查(2699名婴儿),分别来自美国和印度的11个和48个新生儿监护病房。
- 数据收集时间为2012年1月至2021年7月,数据分析时间为2023年7月至12月。
主要发现
- SUNDROP数据集中mtmROP和1型ROP的患病率分别为5.9%(91/1545)和1.2%(18/1545);AECS数据集中分别为6.2%(168/2699)和2.5%(68/2699)。
- 检查层面mtmROP和1型ROP的AUROC在SUNDROP数据集分别为0.896和0.985,在AECS数据集分别为0.920和0.982。
- 横断面检查层面,mtmROP检测的敏感度:SUNDROP中mtmROP为83.5%(95% CI, 76.6-87.7),1型ROP为82.2%(95% CI, 81.2-83.1);AECS中mtmROP为80.8%(95% CI, 76.2-84.9),1型ROP为87.8%(95% CI, 86.8-88.7)。
- 患者层面,所有发展为1型ROP的婴儿在诊断前筛查均为阳性(SUNDROP:100%;95% CI, 81.4-100;AECS:100%;95% CI, 94.7-100)。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
IMPORTANCE: Retinopathy of prematurity (ROP) is a leading cause of blindness in children, with significant disparities in outcomes between high-income and low-income countries, due in part to insufficient access to ROP screening. OBJECTIVE: To evaluate how well autonomous artificial intelligence (AI)-based ROP screening can detect more-than-mild ROP (mtmROP) and type 1 ROP. DESIGN, SETTING, AND PARTICIPANTS: This diagnostic study evaluated the performance of an AI algorithm, trained and calibrated using 2530 examinations from 843 infants in the Imaging and Informatics in Retinopathy of Prematurity (i-ROP) study, on 2 external datasets (6245 examinations from 1545 infants in the Stanford University Network for Diagnosis of ROP [SUNDROP] and 5635 examinations from 2699 infants in the Aravind Eye Care Systems [AECS] telemedicine programs). Data were taken from 11 and 48 neonatal care units in the US and India, respectively. Data were collected from January 2012 to July 2021, and data were analyzed from July to December 2023. EXPOSURES: An imaging processing pipeline was created using deep learning to autonomously identify mtmROP and type 1 ROP in eye examinations performed via telemedicine. MAIN OUTCOMES AND MEASURES: The area under the receiver operating characteristics curve (AUROC) as well as sensitivity and specificity for detection of mtmROP and type 1 ROP at the eye examination and patient levels. RESULTS: The prevalence of mtmROP and type 1 ROP were 5.9% (91 of 1545) and 1.2% (18 of 1545), respectively, in the SUNDROP dataset and 6.2% (168 of 2699) and 2.5% (68 of 2699) in the AECS dataset. Examination-level AUROCs for mtmROP and type 1 ROP were 0.896 and 0.985, respectively, in the SUNDROP dataset and 0.920 and 0.982 in the AECS dataset. At the cross-sectional examination level, mtmROP detection had high sensitivity (SUNDROP: mtmROP, 83.5%; 95% CI, 76.6-87.7; type 1 ROP, 82.2%; 95% CI, 81.2-83.1; AECS: mtmROP, 80.8%; 95% CI, 76.2-84.9; type 1 ROP, 87.8%; 95% CI, 86.8-88.7). At the patient level, all infants who developed type 1 ROP screened positive (SUNDROP: 100%; 95% CI, 81.4-100; AECS: 100%; 95% CI, 94.7-100) prior to diagnosis. CONCLUSIONS AND RELEVANCE: Where and when ROP telemedicine programs can be implemented, autonomous ROP screening may be an effective force multiplier for secondary prevention of ROP.
引用
- Coyner AS, Murickan T, Oh MA, et al. Multinational External Validation of Autonomous Retinopathy of Prematurity Screening. JAMA Ophthalmol. 2024. PMID: 38451496. doi:10.1001/jamaophthalmol.2024.0045
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。