文献速递眼底病与葡萄膜炎小儿眼科与斜弱视

智能手机远程筛查早产儿视网膜病变在印度有无人工智能辅助的效能

Efficacy of Smartphone-Based Telescreening for Retinopathy of Prematurity With and Without Artificial Intelligence in India.
PubMed 文献 · JAMA Ophthalmol · 2023-01-01

该前瞻性横断面比较研究在印度单中心远程眼科项目中纳入156名早产儿(312眼),比较智能手机眼底成像(SBFI)与宽视野数字眼底成像(WDFI)由技师用于早产儿视网膜病变(ROP)筛查的效能。人工阅片者使用SBFI检测需治疗ROP的敏感度为100%、特异度为83.49%;人工智能系统检测需治疗ROP的敏感度为100%、特异度为58.6%。结论认为SBFI系统对需治疗ROP高度敏感,结合人工智能可能成为提升全球ROP筛查能力的成本效益方法。

要点

  • 人工阅片者使用SBFI检测需治疗ROP的敏感度为100%、特异度为83.49%。
  • 人工智能系统检测需治疗ROP的敏感度为100%、特异度为58.6%。
  • 两种SBFI系统之间的敏感度和特异度无统计学差异。

核心结论

  • 在该横断面研究中,技师在ROP筛查项目中使用两种不同的SBFI系统对需治疗ROP均高度敏感。
  • SBFI系统结合人工智能可能成为提升全球ROP筛查能力的成本效益方法。

研究设计与样本

  • 前瞻性横断面比较研究,在印度单中心ROP远程眼科项目中开展,时间为2021年1月至2022年4月。
  • 纳入符合常规ROP筛查标准并加入远程眼科筛查项目的早产儿,已接受ROP治疗者排除。
  • 共纳入156名婴儿(312眼),平均(标准差)胎龄33.0(3.0)周,女性75名(48%),均接受配对检查。
  • 所有参与者均采集WDFI图像及两种SBFI设备之一(Make-In-India(MII)Retcam或Keeler单目间接检眼镜(MIO))的图像。
  • 两名设盲阅片者评估所有图像的分区、分期、附加病变和血管严重度评分(VSS,1-9分);智能手机图像按患者分为训练集(70%)、验证集(10%)和测试集(20%),用于训练ResNet18深度学习架构进行正常与附加病变前或附加病变的二分类,并用于患者层面的需转诊ROP和需治疗ROP预测。

主要发现

  • 两种SBFI系统之间的敏感度和特异度未发现统计学差异。
  • 人工阅片者使用SBFI检测需治疗ROP的敏感度为100%、特异度为83.49%。
  • 仅基于阅片者评估的VSS,需转诊ROP和需治疗ROP的AUC分别为0.95(95%CI,0.91-0.99)和0.96(95%CI,0.93-0.99)。
  • 人工智能系统检测需治疗ROP的敏感度为100%、特异度为58.6%;检测需转诊ROP的敏感度为80.0%、特异度为59.3%。

关键数值与推荐

  • 人工阅片者使用SBFI检测需治疗ROP:敏感度100%,特异度83.49%。
  • 阅片者评估VSS预测需转诊ROP的AUC为0.95(95%CI,0.91-0.99),预测需治疗ROP的AUC为0.96(95%CI,0.93-0.99)。
  • 人工智能系统检测需治疗ROP:敏感度100%,特异度58.6%。
  • 人工智能系统检测需转诊ROP:敏感度80.0%,特异度59.3%。

临床怎么用

  • 原文未据此给出推荐。

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) telemedicine screening programs have been found to be effective, but they rely on widefield digital fundus imaging (WDFI) cameras, which are expensive, making them less accessible in low- to middle-income countries. Cheaper, smartphone-based fundus imaging (SBFI) systems have been described, but these have a narrower field of view (FOV) and have not been tested in a real-world, operational telemedicine setting. OBJECTIVE: To assess the efficacy of SBFI systems compared with WDFI when used by technicians for ROP screening with both artificial intelligence (AI) and human graders. DESIGN, SETTING, AND PARTICIPANTS: This prospective cross-sectional comparison study took place as a single-center ROP teleophthalmology program in India from January 2021 to April 2022. Premature infants who met normal ROP screening criteria and enrolled in the teleophthalmology screening program were included. Those who had already been treated for ROP were excluded. EXPOSURES: All participants had WDFI images and from 1 of 2 SBFI devices, the Make-In-India (MII) Retcam or Keeler Monocular Indirect Ophthalmoscope (MIO) devices. Two masked readers evaluated zone, stage, plus, and vascular severity scores (VSS, from 1-9) in all images. Smartphone images were then stratified by patient into training (70%), validation (10%), and test (20%) data sets and used to train a ResNet18 deep learning architecture for binary classification of normal vs preplus or plus disease, which was then used for patient-level predictions of referral warranted (RW)- and treatment requiring (TR)-ROP. MAIN OUTCOME AND MEASURES: Sensitivity and specificity of detection of RW-ROP, and TR-ROP by both human graders and an AI system and area under the receiver operating characteristic curve (AUC) of grader-assigned VSS. Sensitivity and specificity were compared between the 2 SBFI systems using Pearson χ2testing. RESULTS: A total of 156 infants (312 eyes; mean [SD] gestational age, 33.0 [3.0] weeks; 75 [48%] female) were included with paired examinations. Sensitivity and specificity were not found to be statistically different between the 2 SBFI systems. Human graders were effective with SBFI at detecting TR-ROP with a sensitivity of 100% and specificity of 83.49%. The AUCs with grader-assigned VSS only were 0.95 (95% CI, 0.91-0.99) and 0.96 (95% CI, 0.93-0.99) for RW-ROP and TR-ROP, respectively. For the AI system, the sensitivity of detecting TR-ROP sensitivity was 100% with specificity of 58.6%, and RW-ROP sensitivity was 80.0% with specificity of 59.3%. CONCLUSIONS AND RELEVANCE: In this cross-sectional study, 2 different SBFI systems used by technicians in an ROP screening program were highly sensitive for TR-ROP. SBFI systems with AI may be a cost-effective method to improve the global capacity for ROP screening.

来源:JAMA Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Young BK, Cole ED, Shah PK, et al. Efficacy of Smartphone-Based Telescreening for Retinopathy of Prematurity With and Without Artificial Intelligence in India. JAMA Ophthalmol. 2023. PMID: 37166816. doi:10.1001/jamaophthalmol.2023.1466

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。