Wilmer Eye Institute, Johns Hopkins University School of Medicine, Baltimore, MD, United States of America.
Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, United States of America.
PLoS One. 2021 Apr 16;16(4):e0249856. doi: 10.1371/journal.pone.0249856. eCollection 2021.
OBJECTIVE: To assess whether machine learning algorithms (MLA) can predict eyes that will undergo rapid glaucoma progression based on an initial visual field (VF) test. DESIGN: Retrospective analysis of longitudinal data. SUBJECTS: 175,786 VFs (22,925 initial VFs) from 14,217 patients who completed ≥5 reliable VFs at academic glaucoma centers were included. METHODS: Summary measures and reliability metrics from the initial VF and age were used to train MLA designed to predict the likelihood of rapid progression. Additionally, the neural network model was trained with point-wise threshold data in addition to summary measures, reliability metrics and age. 80% of eyes were used for a training set and 20% were used as a test set. MLA test set performance was assessed using the area under the receiver operating curve (AUC). Performance of models trained on initial VF data alone was compared to performance of models trained on data from the first two VFs. MAIN OUTCOME MEASURES: Accuracy in predicting future rapid progression defined as MD worsening more than 1 dB/year. RESULTS: 1,968 eyes (8.6%) underwent rapid progression. The support vector machine model (AUC 0.72 [95% CI 0.70-0.75]) most accurately predicted rapid progression when trained on initial VF data. Artificial neural network, random forest, logistic regression and naïve Bayes classifiers produced AUC of 0.72, 0.70, 0.69, 0.68 respectively. Models trained on data from the first two VFs performed no better than top models trained on the initial VF alone. Based on the odds ratio (OR) from logistic regression and variable importance plots from the random forest model, older age (OR: 1.41 per 10 year increment [95% CI: 1.34 to 1.08]) and higher pattern standard deviation (OR: 1.31 per 5-dB increment [95% CI: 1.18 to 1.46]) were the variables in the initial VF most strongly associated with rapid progression. CONCLUSIONS: MLA can be used to predict eyes at risk for rapid progression with modest accuracy based on an initial VF test. Incorporating additional clinical data to the current model may offer opportunities to predict patients most likely to rapidly progress with even greater accuracy.
目的：评估机器学习算法（MLA）是否可以基于初始视野（VF）测试预测即将快速进展的眼睛。
设计：纵向数据的回顾性分析。
受试者：纳入了来自 14217 名患者的 175786 份 VF（22925 份初始 VF），这些患者在学术青光眼中心完成了≥5 次可靠的 VF。
方法：使用初始 VF 的汇总测量值和可靠性指标以及年龄，训练旨在预测快速进展可能性的 MLA。此外，神经网络模型还使用逐点阈值数据以及汇总测量值、可靠性指标和年龄进行了训练。80%的眼睛用于训练集，20%用于测试集。使用接收器工作特征曲线下的面积（AUC）评估 MLA 测试集的性能。比较了仅基于初始 VF 数据训练的模型与基于前两个 VF 数据训练的模型的性能。
主要观察指标：预测未来快速进展的准确性，定义为 MD 恶化超过 1 dB/年。
结果：1968 只眼睛（8.6%）发生了快速进展。支持向量机模型（AUC 0.72[95%CI 0.70-0.75]）在基于初始 VF 数据进行训练时最准确地预测了快速进展。人工神经网络、随机森林、逻辑回归和朴素贝叶斯分类器的 AUC 分别为 0.72、0.70、0.69、0.68。基于前两个 VF 的数据进行训练的模型并不比仅基于初始 VF 进行训练的最佳模型表现更好。基于逻辑回归的比值比（OR）和随机森林模型的变量重要性图，初始 VF 中年龄较大（OR：每增加 10 岁增加 1.41[95%CI：1.34 至 1.08]）和模式标准差较高（OR：每增加 5dB 增加 1.31[95%CI：1.18 至 1.46]）是与快速进展最相关的变量。
结论：基于初始 VF 测试，MLA 可用于预测具有中等准确性的快速进展风险的眼睛。将额外的临床数据纳入当前模型可能为更准确地预测快速进展的患者提供机会。
Ophthalmology. 2017-11-2
Graefes Arch Clin Exp Ophthalmol. 2024-7
Taiwan J Ophthalmol. 2024-9-13
Taiwan J Ophthalmol. 2024-9-13
Medicina (Kaunas). 2024-3-2
Prog Retin Eye Res. 2019-4-29
PLoS One. 2019-4-5
Curr Opin Ophthalmol. 2019-3
Stud Health Technol Inform. 2017
Trans Am Ophthalmol Soc. 2017-8-22
Ophthalmology. 2017-11
Am J Ophthalmol. 2017-4
Zotero 插件