University of Maryland Department of Ophthalmology and Visual Sciences, Baltimore, MD, USA.
Massachusetts Eye and Ear, Boston, MA, USA.
Transl Vis Sci Technol. 2021 Jun 1;10(7):27. doi: 10.1167/tvst.10.7.27.
To develop and test machine learning classifiers (MLCs) for determining visual field progression.
In total, 90,713 visual fields from 13,156 eyes were included. Six different progression algorithms (linear regression of mean deviation, linear regression of the visual field index, Advanced Glaucoma Intervention Study algorithm, Collaborative Initial Glaucoma Treatment Study algorithm, pointwise linear regression [PLR], and permutation of PLR) were applied to classify each eye as progressing or stable. Six MLCs were applied (logistic regression, random forest, extreme gradient boosting, support vector classifier, convolutional neural network, fully connected neural network) using a training and testing set. For MLC input, visual fields for a given eye were divided into the first and second half and each location averaged over time within each half. Each algorithm was tested for accuracy, sensitivity, positive predictive value, and class bias with a subset of visual fields labeled by a panel of three experts from 161 eyes.
MLCs had similar performance metrics as some of the conventional algorithms and ranged from 87% to 91% accurate with sensitivity ranging from 0.83 to 0.88 and specificity from 0.92 to 0.96. All conventional algorithms showed significant class bias, meaning each individual algorithm was more likely to grade uncertain cases as either progressing or stable (P ≤ 0.01). Conversely, all MLCs were balanced, meaning they were equally likely to grade uncertain cases as either progressing or stable (P ≥ 0.08).
MLCs showed a moderate to high level of accuracy, sensitivity, and specificity and were more balanced than conventional algorithms.
MLCs may help to determine visual field progression.
开发和测试机器学习分类器（MLC），以确定视野进展。
共纳入 13156 只眼的 90713 份视野。应用六种不同的进展算法（平均偏差的线性回归、视野指数的线性回归、高级青光眼干预研究算法、合作初始青光眼治疗研究算法、逐点线性回归[PLR]和 PLR 的置换）对每只眼进行分类，以确定其是进展还是稳定。应用 6 种 MLC（逻辑回归、随机森林、极端梯度提升、支持向量分类器、卷积神经网络、全连接神经网络）进行训练和测试。对于 MLC 输入，将给定眼的视野分为前半部分和后半部分，并在每一半内按时间平均每个位置。使用来自 161 只眼的三位专家小组标记的视野子集测试每种算法的准确性、敏感性、阳性预测值和分类偏差。
MLC 的性能指标与某些传统算法相似，准确率在 87%至 91%之间，敏感性在 0.83 至 0.88 之间，特异性在 0.92 至 0.96 之间。所有传统算法均显示出显著的分类偏差，这意味着每种单独的算法更有可能将不确定的病例分类为进展或稳定（P≤0.01）。相反，所有 MLC 均平衡，这意味着它们同样有可能将不确定的病例分类为进展或稳定（P≥0.08）。
MLC 具有较高的准确性、敏感性和特异性，并且比传统算法更平衡。
胡碟
