文献速递眼底病与葡萄膜炎小儿眼科与斜弱视

基于血管严重度定量评估的远程医疗筛查精准风险模型

Precision Risk Model Using Quantitative Assessment of Vascular Severity in Telemedicine-Based Screening.
PubMed 文献 · JAMA Ophthalmol · 2026-01-01

该诊断研究整合胎龄、矫正月龄与血管严重度(AI衍生的VSS或临床医生P评分),构建并外部验证了预测2周内需治疗早产儿视网膜病变(TR-ROP)的可解释风险模型。在i-ROP与SUNDROP队列中,加入血管严重度较单用胎龄显著提升判别力,风险导向的随访模拟在保持100%敏感度下分别减少28%和39%的检查。

要点

  • 整合胎龄、矫正月龄与血管严重度可个体化预测2周内TR-ROP风险。
  • 风险导向随访模拟在保持100%敏感度下分别减少28%和39%的检查。
  • 以P评分替代VSS后模型性能保持,AUROC为0.87。

核心结论

  • 该模型提供就诊层面的个体化TR-ROP风险评估,有望在不漏诊TR-ROP的前提下减少不必要检查、提升筛查效率。
  • 模型将公开供进一步验证,但常规实施前需在明确临床工作流程中开展前瞻性评估。

研究设计与样本

  • 诊断研究,使用i-ROP联盟(2011-2022)与SUNDROP(2013-2021)数据,i-ROP分为训练、验证与测试子集,SUNDROP为外部验证队列。
  • i-ROP训练集559名婴儿,SUNDROP 1544名婴儿;另分析i-ROP中带临床医生P评分的检查子集以评估临床适配性。
  • 数据分析时间为2024年9月1日至2025年9月1日。

主要发现

  • 发生TR-ROP的婴儿平均胎龄低2.9周(95%CI,2.3-3.5),出生体重低391 g(95%CI,328-454)。
  • 加入血管严重度较单用胎龄提升判别力,AUROC差值在i-ROP为0.13(95%CI,0.06-0.19),在SUNDROP为0.08(95%CI,0.03-0.14)。
  • 某一决策阈值下敏感度达100%,特异度中等(i-ROP 63%;SUNDROP 73%)。
  • 模拟风险导向排程在i-ROP减少28%(376/1384)、在SUNDROP减少39%(2356/6090)的检查,且未漏诊TR-ROP。
  • 以P评分替代VSS后模型性能保持:AUROC 0.87(95%CI,0.76-0.97),敏感度100%(95%CI,63%-100%)。

关键数值与推荐

  • 预测目标为2周内发生TR-ROP,输入变量为胎龄、矫正月龄与血管严重度(VSS或P评分)。
  • 判别力评价指标为AUROC与AUPRC,并报告敏感度、特异度及可推迟检查比例。
  • 模拟中要求维持100%敏感度以评估可减少的检查比例。

临床怎么用

  • 可用于远程医疗筛查中对早产儿进行就诊层面的TR-ROP风险分层,辅助安排随访间隔。
  • 在无AI血管严重度评估时,可用临床医生P评分替代以保持模型性能。
  • 模型拟公开,但应用于临床前需在本地工作流程中前瞻性验证。

局限性

  • 为诊断研究,筛查频率的影响来自回顾性模拟而非前瞻性干预。
  • 常规实施前仍需在明确临床工作流程中开展前瞻性评估。

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) screening requires frequent examinations to avoid missed treatment-requiring disease, but this approach is burdensome for infants, families, and health systems. Whether precision risk models could reduce examination burden without compromising safety is not known. OBJECTIVE: To develop and externally validate an interpretable risk model integrating gestational age (GA), postmenstrual age (PMA), and vascular severity (artificial intelligence-derived VSS or clinician-assigned P-score) to predict 2-week risk of treatment-requiring retinopathy of prematurity (TR-ROP) and estimate its impacts in screening frequency. DESIGN, SETTING, AND PARTICIPANTS: This diagnostic study used data from the Imaging and Informatics in ROP (i-ROP) consortium (2011-2022) and the Stanford University Network for Diagnosis of ROP (SUNDROP; 2013-2021). The i-ROP dataset was split into training, validation, and test subsets, and SUNDROP served as an external validation cohort. A subset of i-ROP examinations with clinician assessment scores (P-scores) was analyzed for clinical adaptability. Data were analyzed from September 1, 2024, to September 1, 2025. EXPOSURES: GA, PMA, and vascular severity (VSS or P-score). MAIN OUTCOMES AND MEASURES: Discrimination (area under the receiver operating characteristic curve [AUROC], area under the precision-recall curve [AUPRC]), sensitivity, specificity for predicting TR-ROP within 2 weeks, and the proportion of examinations that could be deferred in a retrospective simulation while maintaining 100% sensitivity. RESULTS: Among 559 infants in the i-ROP training dataset and 1544 in SUNDROP, infants who developed TR-ROP had a mean GA of 2.9 (95% CI, 2.3-3.5) weeks lower and birth weight of 391 (95% CI, 328-454) g than those who did not. Adding vascular severity improved discrimination vs GA alone (AUROC difference 0.13 [95% CI, 0.06-0.19] in i-ROP; 0.08 [95% CI, 0.03-0.14] in SUNDROP). A decision threshold achieved 100% sensitivity with moderate specificity (i-ROP 63%; SUNDROP 73%). Simulated risk-based scheduling reduced 28% (376 of 1384) of examinations in i-ROP and 39% (2356 of 6090 ) in SUNDROP without missing TR-ROP. Substituting P-scores for VSS preserved model performance (AUROC 0.87; 95% CI, 0.76-0.97; sensitivity 100%; 95% CI, 63%-100%). CONCLUSIONS AND RELEVANCE: In this study, this validated clinically adaptable model provided individualized visit-level TR-ROP risk assessment with potential to improve screening efficiency by reducing unnecessary examinations without missing TR-ROP. The model will be made publicly available for further validation; however, prospective evaluation within a defined clinical workflow is required prior to routine implementation.

来源:JAMA Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Placide J, Coyner AS, Ostmo SR, et al. Precision Risk Model Using Quantitative Assessment of Vascular Severity in Telemedicine-Based Screening. JAMA Ophthalmol. 2026. PMID: 41926091. doi:10.1001/jamaophthalmol.2026.0510

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。