人工智能能否预测青光眼视野进展?空间-序数卷积神经网络模型
本研究基于6047例原发性开角型青光眼患者的9212只眼、43260个视野块,构建空间-序数卷积神经网络模型预测视野进展,最佳模型AUROC为0.864(敏感度0.42、特异度0.95),显著优于点wise线性回归的0.611(敏感度0.28、特异度0.84)。
要点
- 空间-序数神经网络模型预测青光眼视野进展的AUROC达0.864,优于线性模型。
- 最佳神经网络模型在特异度0.95时敏感度为0.42,点wise线性回归在特异度0.84时敏感度0.28。
核心结论
- 纳入空间-序数特征的神经网络模型在预测青光眼视野进展方面显著优于线性模型。
研究设计与样本
- 队列研究,纳入6047例原发性开角型青光眼患者的9212只眼,均接受超过4年的规律可靠视野检查。
- 通过堆叠3次连续视野检查构建所有可能的空间-序数张量(视野块),随访至少3年。
- 采用基于趋势、基于事件及联合标准定义进展,若3年内发生进展则视野块视为进展,并在3年后进一步确认。
- 构建6个卷积神经网络模型和2个线性模型(全局指数回归和点wise线性回归)。
主要发现
- 43260个视野块中,基于趋势、基于事件及联合标准分别有4406个(10.2%)、4376个(10.1%)和2394个(5.5%)视野块被分类为进展。
- 最佳神经网络模型的AUROC为0.864,在特异度0.95时敏感度为0.42。
- 点wise线性回归的AUROC为0.611,在特异度0.84时敏感度为0.28。
关键数值与推荐
- 进展定义采用基于趋势、基于事件及联合标准,具体阈值原文未报告。
- 视野块若3年内发生进展则视为进展,并在3年后进一步确认。
临床怎么用
- 空间-序数神经网络模型可辅助预测青光眼视野进展,但敏感度有限(0.42),需结合临床评估。
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
PURPOSE: To develop an artificial neural network model incorporating both spatial and ordinal approaches to predict glaucomatous visual field (VF) progression. DESIGN: Cohort study. Methods From a cohort of primary open-angle glaucoma patients, 9212 eyes of 6047 patients who underwent regular reliable VF examinations for >4 years were included. We constructed all possible spatial-ordinal tensors by stacking 3 consecutive VF tests (VF-blocks) with at least 3 years of follow-up. Trend-based, event-based, and combined criteria were defined to determine the progression. VF-blocks were considered "progressed" if progression occurred within 3 years; the progression was further confirmed after 3 years. We constructed 6 convolutional neural network (NN) models and 2 linear models: regression on global indices and pointwise linear regression (PLR). We compared area under the receiver operating characteristic curve (AUROC) of each model for the prediction of glaucomatous VF progression. RESULTS: Among 43,260 VF-blocks, 4406 (10.2%), 4376 (10.1%), and 2394 (5.5%) VF-blocks were classified as progression-based on trend-based and event-based and combined criteria. For all 3 criteria, the progression group was significantly older and had worse initial MD and VF index (VFI) than the nonprogression group (P < .001 for all). The best-performing NN model had an AUROC of 0.864 with a sensitivity of 0.42 at a specificity of 0.95. In contrast, an AUROC of 0.611 was estimated from a sensitivity of 0.28 at a specificity of 0.84 for the PLR. CONCLUSIONS: The NN models incorporating spatial-ordinal characteristics demonstrated significantly better performance than the linear models in the prediction of glaucomatous VF progression.
引用
- Shon K, Sung KR, Shin JW, et al. Can Artificial Intelligence Predict Glaucomatous Visual Field Progression? A Spatial-Ordinal Convolutional Neural Network Model. Am J Ophthalmol. 2021. PMID: 34283982. doi:10.1016/j.ajo.2021.06.025
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。