Assessing Glaucoma Progression Using Machine Learning Trained on Longitudinal Visual Field and Clinical Data

Date Published:

2020 Dec 24


PURPOSE: 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. DESIGN: Retrospective analysis of longitudinal clinical and visual field data. SUBJECTS: 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. METHODS: 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. OUTCOME MEASURES: 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. RESULTS: 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) CONCLUSIONS: 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.

Last updated on 12/31/2020