文献速递青光眼

基于人工智能的预后模型:从临床与结构数据预测功能性青光眼进展

An Artificial Intelligence-Based Prognostic Model for Prediction of Functional Glaucoma Progression From Clinical and Structural Data.
PubMed 文献 · Am J Ophthalmol · 2026-01-01

本研究纳入1599只眼(908例患者),开发并验证了一种深度学习预后模型,整合基线临床与人口学数据、视盘照片及OCT测量的视网膜神经纤维层和黄斑厚度,预测青光眼功能进展。最佳模型AUC为0.839(0.771-0.906),准确率76.0%(62.0%-85.0%),显著优于两名临床医生(AUC分别为0.629和0.680,P<.001和P=.001)。验证队列AUC为0.754(0.671-0.837),预测快速进展(MD斜率<-1.0 dB/y)的AUC为0.869(0.792-0.947)。

要点

  • 深度学习模型整合基线临床与结构数据可预测青光眼功能进展,AUC 0.839。
  • 模型预测性能显著优于临床医生(AUC 0.629和0.680,P<.001和P=.001)。
  • 模型对快速进展(MD斜率<-1.0 dB/y)预测AUC达0.869。

核心结论

  • 新设计的深度学习模型可结合基线人口学与临床数据及常用结构测量,为青光眼进展预测提供临床相关信息。

研究设计与样本

  • 回顾性、比较性队列研究,纳入1599只眼(908例患者)的明确或疑似青光眼,随访≥3年且≥5次24-2视野检查。
  • 模型在291只使用不同OCT设备成像的独立队列眼上进行验证。

主要发现

  • 399只眼(25%)出现恶化,平均(SD)基线MD为-3.5(4.9)dB,视野检查次数为10.1(4.7)。
  • 最佳模型纳入基线视盘照片、视网膜神经纤维层和黄斑厚度,AUC为0.839(0.771-0.906),准确率76.0%(62.0%-85.0%),精确率-召回率曲线下面积为0.558(0.385-0.733)。
  • 验证队列模型性能相似,AUC为0.754(0.671-0.837),准确率77%(71%-82%),P=.122。
  • 模型预测快速进展(MD斜率<-1.0 dB/y)的AUC为0.869(0.792-0.947)。

临床怎么用

  • 该模型可利用基线临床与结构数据预测青光眼功能进展,辅助临床决策。

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

PURPOSE: Integration of various sources of information for prediction of disease progression is an unmet need in glaucoma diagnostics. We designed a deep learning-based prognostic model incorporating clinical and structural data for forecasting functional glaucoma progression and compared its performance to clinicians. DESIGN: Retrospective, comparative cohort study of prognostic accuracy. SUBJECTS: We included 1599 eyes (908 patients) with definite or suspected glaucoma with ≥5 24-2 visual fields (VF) and 3 or more years of follow-up. METHODS: VF mean deviation (MD) rates of change were estimated with linear regression. Sequential MD rates of change were estimated with each series spanning only 5 years of follow-up. VF progression was declared when four sequential statistically significant negative MD slopes were observed, and slope for the entire follow-up was significant. A convolutional neural network pretrained on ImageNet was designed to predict VF progression using baseline clinical and demographic data, disc photographs, and optical coherence tomography-derived global and sectoral retinal nerve fiber layer and macular thickness measurements. In addition, average intraocular pressure and treatment information during follow-up were put into the model. The same data for a subset of patients was provided to two clinicians to independently predict future progression. The model was validated on a separate cohort of eyes in which optical coherence tomography imaging was done with a different device (291 eyes). MAIN OUTCOME MEASURES: Model's area under receiver operating characteristic curves (AUC), accuracy, and area under the precision and recall curves. RESULTS: Average (SD) baseline MD and number of VF exams were -3.5 (4.9) dB and 10.1 (4.7). 399 eyes (25%) deteriorated. The best-performing model incorporated baseline disc photographs, and retinal nerve fiber layer and macular thickness: AUC, 0.839 (0.771-0.906), accuracy, 76.0% (62.0%-85.0%), and area under the precision and recall curves, 0.558 (0.385-0.733). Deep learning model significantly outperformed clinical graders (AUC : 0.629 [0.531-0738], P < .001 and 0.680 [0.584-0.776], P = .001, for grader one and two, respectively). Model performance was similar on the validation cohort (AUC: 0.754 [0.671-0.837], and accuracy: 77% [71%-82%], respectively, P = .122). The model performed well when predicting fast-progression, defined as MD rate <-1.0 dB/y (AUC: 0.869 [0.792-0.947]). CONCLUSIONS: Our newly designed deep learning model can combine baseline demographic and clinical data with widely available structural measurements and provide clinically relevant information for the prediction of glaucoma progression.

来源:Am J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Mohammadzadeh V, Wu S, Besharati S, et al. An Artificial Intelligence-Based Prognostic Model for Prediction of Functional Glaucoma Progression From Clinical and Structural Data. Am J Ophthalmol. 2026. PMID: 41483865. doi:10.1016/j.ajo.2025.12.026

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。