Estimating the Severity of Visual Field Damage From Retinal Nerve Fiber Layer Thickness Measurements With Artificial Intelligence

Abstract

The purpose of this study was to assess the accuracy of artificial neural networks (ANN) in estimating the severity of mean deviation (MD) from peripapillary retinal nerve fiber layer (RNFL) thickness measurements derived from optical coherence tomography (OCT).Methods: Models were trained using 1796 pairs of visual field and OCT measurements from 1796 eyes to estimate visual field MD from RNFL data. Multivariable linear regression, random forest regressor, support vector regressor, and 1D convolutional neural network (CNN) models with sectoral RNFL thickness measurements were examined. Three independent subsets consisting of 698, 256, and 691 pairs of visual field and OCT measurements were used to validate the models. Estimation errors were visualized to assess model performance subjectively. Mean absolute error (MAE), root mean square error (RMSE), median absolute error, Pearson correlation, and R-squared metrics were used to assess model performance objectively. Results:The MAE and RMSE of the ANN model based on the testing dataset were 4.0 dB (95% confidence interval = 3.8-4.2) and 5.2 dB (95% confidence interval = 5.1-5.4), respectively. The ranges of MAE and RMSE of the ANN model on independent datasets were 3.3-5.9 dB and 4.4-8.4 dB, respectively. Conclusions:The proposed ANN model estimated MD from RNFL measurements better than multivariable linear regression model, random forest, support vector regressor, and 1-D CNN models. The model was generalizable to independent data from different centers and varying races. Translational Relevance: Successful development of ANN models may assist clinicians in assessing visual function in glaucoma based on objective OCT measures with less dependence on subjective visual field tests.

Prediction of visual field defects from macular optical coherence tomography in glaucoma using cluster analysis

“…However, methods predicting global VF metrics have generally outperformed those attempting to predict location‐specific VF thresholds from OCT data 17,19,23 . Qualitative topographic comparisons between OCT‐derived retinal nerve fibre layer (RNFL) and ganglion cell‐inner plexiform layer (GCIPL) thicknesses and VF thresholds have reported global agreement between abnormal structure and function in up to 88.7% of patients with early glaucoma 17,23 Moreover, various deep learning methods have been applied to RNFL and GCIPL data to enable prediction of summary VF metrics such as mean deviation and VF index, with moderate to strong correlations reported between predicted and actual VF parameters 24–26 . These indicate promising utility of these methods in predicting global functional results from OCT.…”

Comparison of machine learning approaches for structure–function modeling in glaucoma

“…We also observed that estimation performance in the external test set was better compared with the internal test set, which could be attributed to differences in the spatial distribution of focal severities in the two test sets. Strengths of our study include the use of a standardized, stratified approach for dataset construction, the There has been continued interest in the development and evaluation of models for the estimation VF loss in glaucoma from structural measurements of the retina [9][10][11][12][13][14]27,28 with reported MAEs in the range of 2-5 dB [11][12][13][14] for VF MD estimation. In most previous studies, comparisons with other approaches were largely limited to linear regression 9,11,12,28 or SVMs.…”

“…Strengths of our study include the use of a standardized, stratified approach for dataset construction, the There has been continued interest in the development and evaluation of models for the estimation VF loss in glaucoma from structural measurements of the retina [9][10][11][12][13][14]27,28 with reported MAEs in the range of 2-5 dB [11][12][13][14] for VF MD estimation. In most previous studies, comparisons with other approaches were largely limited to linear regression 9,11,12,28 or SVMs. 11,28 As data-driven ML models networks.…”

“…In most previous studies, comparisons with other approaches were largely limited to linear regression 9,11,12,28 or SVMs. 11,28 As data-driven ML models networks. Their findings demonstrated that on heterogeneous tabular data for disparate tasks, ranging from the estimation of gestures to sales figures, 29 to bioinformatics classification tasks, such as diagnosis and postoperative management, 30 XGB was found to perform relatively well compared with other machine learning networks or against more advanced deep networks.…”

Current and Future Implications of Using Artificial Intelligence in Glaucoma Care

“…10 Along with detection, if an AI algorithm was able to measure the RNFL thickness accurately, the diagnosis would be made more effective, as that is the most common parameter used for glaucoma diagnosis. 12 13 …”