Assessing Glaucoma Progression Using Machine Learning Trained on Longitudinal Visual Field and Clinical Data.
Assessing Glaucoma Progression Using Machine Learning Trained on Longitudinal Visual Field and Clinical Data.
复制标题
DOI：
10.1016/j.ophtha.2020.12.020
复制
发表时间：
2021-07
期刊：
影响因子：
13.7
通讯作者：
Boland MV
中科院分区：
文献类型：
--
作者：
Dixit A;Yohannan J;Boland MV
仅从视野确定青光眼进展的基于规则的方法是不一致的，并且具有权衡。为了更好地检测青光眼进展何时发生，我们利用合并VF和临床数据的纵向数据集来评估卷积长短期记忆（LSTM）神经网络的性能。纵向临床和视野数据的回顾性分析。从213，254只眼睛的672，123个视野的两个初始数据集和350，437个临床数据样本中，包括具有四个或更多视野和相应基线临床数据（杯盘比，中央角膜厚度和眼内压）的两个数据集交叉点的人。在排除标准之后，特别是去除具有高假阳性/阴性率的VF和具有缺失数据的条目，以确保可靠的数据，保留了11，242只眼睛。使用三种常用的青光眼进展算法（视野指数斜率、平均偏差斜率和逐点线性回归）将眼睛定义为稳定或进展。测试了两个机器学习模型，一个专门训练视野数据，另一个训练视野和临床数据。使用在保留测试集上计算的受试者操作特征（AUROC）曲线下面积和精确度-召回率曲线下面积（AUPR）以及来自3倍交叉验证的平均准确度来比较机器学习模型的性能。卷积LSTM网络相对于不同的传统青光眼进展算法表现出91-93%的准确性，对于每个受试者给出4个连续视野。在视野和临床数据上训练的模型（AUROC在0.89和0.93之间）比仅在视野上训练的模型（AUROC在0.79和0.82之间，p<0.001）具有更好的诊断能力。卷积LSTM架构可以捕捉视野随时间变化的局部和全局趋势。它非常适合评估青光眼进展，因为它能够提取其他算法无法提取的时空特征。用临床数据补充视野可以提高模型评估青光眼进展的能力，并更好地反映临床医生在管理青光眼时管理数据的方式。
Rule-based approaches to determining glaucoma progression from visual fields alone are discordant and have tradeoffs. To better detect when glaucoma progression is occurring, we utilized a longitudinal data set of merged VF and clinical data to assess the performance of a Convolutional Long Short-Term Memory (LSTM) neural network. Retrospective analysis of longitudinal clinical and visual field data. From two initial datasets of 672,123 visual fields from 213,254 eyes and 350,437 samples of clinical data, persons at the intersection of both datasets with four or more visual fields and corresponding baseline clinical data (cup-to-disc ratio, central corneal thickness, and intraocular pressure) were included. After exclusion criteria, specifically the removal of VFs with high false positive / negative rates and entries with missing data, were applied to ensure reliable data, 11,242 eyes remained. Three commonly used glaucoma progression algorithms (Visual Field Index slope, Mean Deviation slope, and Pointwise Linear Regression) were used to define eyes as stable or progressing. Two machine learning models, one exclusively trained on visual field data and another trained on both visual field and clinical data, were tested. Area under the receiver operating characteristic (AUROC) curve and area under the precision-recall curve (AUPR) calculated on a held-out test set and mean accuracies from 3-fold cross validation were used to compare the performance of the machine learning models. The convolutional LSTM network demonstrated 91–93% accuracy with respect to the different conventional glaucoma progression algorithms given 4 consecutive visual fields for each subject. The model that was trained on both visual field and clinical data (AUROC between 0.89 and 0.93) had better diagnostic ability than a model exclusively trained on visual fields (AUROC between 0.79 and 0.82, p<0.001). A convolutional LSTM architecture can capture local and global trends in visual fields over time. It is well suited to assessing glaucoma progression because of its ability to extract spatio-temporal features other algorithms cannot. Supplementing visual fields with clinical data improves the model’s ability to assess glaucoma progression and better reflects the way clinicians manage data when managing glaucoma.
登录
查看更多内容
影响因子：
13.7
作者：
Kazemian P;Lavieri MS;Van Oyen MP;Andrews C;Stein JD
通讯作者：
Stein JD
影响因子：
4.6
作者：
Park, Keunheung;Kim, Jinmi;Lee, Jiwoong
通讯作者：
Lee, Jiwoong
影响因子：
120.7
作者：
Ting, Daniel Shu Wei;Cheung, Carol Yim-Lui;Wong, Tien Yin
通讯作者：
Wong, Tien Yin
影响因子：
4.4
作者：
Wang, Mengyu;Shen, Lucy Q.;Elze, Tobias
通讯作者：
Elze, Tobias
影响因子：
3.6
作者：
Garway-Heath, David F.;Zhu, Haogang;Agiomyrgiannakis, Yannis
通讯作者：
Agiomyrgiannakis, Yannis