Glaucoma Center of Excellence, Wilmer Eye Institute, Johns Hopkins University, Baltimore, Maryland.
Invest Ophthalmol Vis Sci. 2014 Feb 20;55(2):1017-23. doi: 10.1167/iovs.13-13702.
To improve the neurological hemifield test (NHT) using visual field data from both eyes to detect and classify visual field loss caused by chiasmal or postchiasmal lesions.
Visual field and clinical data for 633 patients were divided into a training set (474 cases) and a validation set (159 cases). Each set had equal numbers of neurological, glaucoma, or glaucoma suspect cases, matched for age and for mean deviation between neurological and glaucoma cases. NHT scores as previously described and a new NHT laterality score were calculated. The ability of these scores to distinguish neurological from other fields was assessed with receiver operating characteristic (ROC) analysis. Three machine classifier algorithms were also evaluated: decision tree, random forest, and least absolute shrinkage and selection operator (LASSO). We also evaluated the ability of NHT to identify the type of neurological field defect (homonymous or bitemporal).
The area under the ROC curve (AUC) for the maximum NHT score was 0.92 (confidence interval [CI]: 0.87, 0.97). Using NHT laterality scores from each eye combined with the sum of NHT scores, the AUC improved to 0.93 (CI: 0.88, 0.98). The largest AUC for machine learning algorithms was for the LASSO method (0.96, CI: 0.92, 0.99). The NHT scores identified the type of neurological defect in 96% (158/164) of patients.
The new NHT distinguished neurological field defects from those of glaucoma and glaucoma suspects, providing accurate categorization of defect type. Its implementation may identify unsuspected neurological disease in clinical visual field testing.
利用双眼的视野数据改进神经视野测试（NHT），以检测和分类视交叉或视交叉后病变引起的视野损失。
将 633 名患者的视野和临床数据分为训练集（474 例）和验证集（159 例）。每个集合中均有等量的神经、青光眼或疑似青光眼病例，按年龄和神经与青光眼病例的平均偏差进行匹配。计算了先前描述的 NHT 评分和新的 NHT 偏侧性评分。使用受试者工作特征（ROC）分析评估这些评分区分神经与其他视野的能力。还评估了三种机器分类器算法：决策树、随机森林和最小绝对值收缩和选择算子（LASSO）。我们还评估了 NHT 识别神经视野缺损类型（同侧或双颞）的能力。
最大 NHT 评分的 ROC 曲线下面积（AUC）为 0.92（置信区间[CI]：0.87，0.97）。使用每只眼的 NHT 偏侧性评分与 NHT 评分总和，AUC 提高到 0.93（CI：0.88，0.98）。机器学习算法的 AUC 最大为 LASSO 方法（0.96，CI：0.92，0.99）。NHT 评分在 96%（158/164）的患者中识别出神经缺陷的类型。
新的 NHT 将神经视野缺损与青光眼和疑似青光眼患者区分开来，对缺损类型进行了准确分类。它的实施可能会在临床视野测试中发现未被怀疑的神经疾病。
