Development and Comparison of Machine Learning Algorithms to Determine Visual Field Progression

Abstract

Purpose: To develop and test machine learning classifiers (MLCs) for determining visual field progression.

Methods: 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.

Results: 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).

Conclusions: MLCs showed a moderate to high level of accuracy, sensitivity, and specificity and were more balanced than conventional algorithms.

Translational relevance: MLCs may help to determine visual field progression.

Figure 1.

Principal component analysis: Principal component analysis shows that progressing cases (red) and stable cases (green) are generally segregated with undecided cases between the two (yellow).

Figure 2.

Biased and balanced classifiers: Graphical illustration displaying class bias and overfitting on the left and a balanced classifier on the right. Yellow crosses represent progressing cases, blue dots symbolize stable cases, and blue triangles represent unclear cases. In the biased classifier on the left, the boundary cases are all considered progressing whereas in the balanced classifier on the right, the boundary cases are more evenly split between progressing and stable.