Augmenting Kalman Filter Machine Learning Models with Data from OCT to Predict Future Visual Field Loss: An Analysis Using Data from the African Descent and Glaucoma Evaluation Study and the Diagnostic Innovation in Glaucoma Study

Mohammad Zhalechian; Mark P Van Oyen; Mariel S Lavieri; Carlos Gustavo De Moraes; Christopher A Girkin; Massimo A Fazio; Robert N Weinreb; Christopher Bowd; Jeffrey M Liebmann; Linda M Zangwill; Christopher A Andrews; Joshua D Stein

doi:10.1016/j.xops.2021.100097

Augmenting Kalman Filter Machine Learning Models with Data from OCT to Predict Future Visual Field Loss: An Analysis Using Data from the African Descent and Glaucoma Evaluation Study and the Diagnostic Innovation in Glaucoma Study

Ophthalmol Sci. 2021 Dec 21;2(1):100097. doi: 10.1016/j.xops.2021.100097. eCollection 2022 Mar.

Authors

Affiliations

¹ Department of Industrial and Operations Engineering, University of Michigan College of Engineering, Ann Arbor, Michigan.
² Bernard and Shirlee Brown Glaucoma Research Laboratory, Edward S. Harkness Eye Institute, Columbia University Irving Medical Center, New York, New York.
³ Department of Ophthalmology, University of Alabama at Birmingham, Birmingham, Alabama.
⁴ Hamilton Glaucoma Center, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California, San Diego, La Jolla, California.
⁵ Department of Ophthalmology and Visual Sciences, University of Michigan Medical School, Ann Arbor, Michigan.
⁶ Center for Eye Policy and Innovation, University of Michigan, Ann Arbor, Michigan.
⁷ Department of Health Management and Policy, University of Michigan School of Public Health, Ann Arbor, Michigan.

Abstract

Purpose: To assess whether the predictive accuracy of machine learning algorithms using Kalman filtering for forecasting future values of global indices on perimetry can be enhanced by adding global retinal nerve fiber layer (RNFL) data and whether model performance is influenced by the racial composition of the training and testing sets.

Design: Retrospective, longitudinal cohort study.

Participants: Patients with open-angle glaucoma (OAG) or glaucoma suspects enrolled in the African Descent and Glaucoma Evaluation Study or Diagnostic Innovation in Glaucoma Study.

Methods: We developed a Kalman filter (KF) with tonometry and perimetry data (KF-TP) and another KF with tonometry, perimetry, and global RNFL data (KF-TPO), comparing these models with one another and with 2 linear regression (LR) models for predicting mean deviation (MD) and pattern standard deviation values 36 months into the future for patients with OAG and glaucoma suspects. We also compared KF model performance when trained on individuals of European and African descent and tested on patients of the same versus the other race.

Main outcome measures: Predictive accuracy (percentage of MD values forecasted within the 95% repeatability interval) differences among the models.

Results: Among 362 eligible patients, the mean ± standard deviation age at baseline was 71.3 ± 10.4 years; 196 patients (54.1%) were women; 202 patients (55.8%) were of European descent, and 139 (38.4%) were of African descent. Among patients with OAG (n = 296), the predictive accuracy for 36 months in the future was higher for the KF models (73.5% for KF-TP, 71.2% for KF-TPO) than for the LR models (57.5%, 58.0%). Predictive accuracy did not differ significantly between KF-TP and KF-TPO (P = 0.20). If the races of the training and testing set patients were aligned (versus nonaligned), the mean absolute prediction error of future MD improved 0.39 dB for KF-TP and 0.48 dB for KF-TPO.

Conclusions: Adding global RNFL data to existing KFs minimally improved their predictive accuracy. Although KFs attained better predictive accuracy when the races of the training and testing sets were aligned, these improvements were modest. These findings will help to guide implementation of KFs in clinical practice.

Keywords: AD, African descent; ADAGES, African Descent and Glaucoma Evaluation Study; Algorithm bias; CI, confidence interval; D, diopter; DIGS, Diagnostic Innovation in Glaucoma Study; ED, European descent; Glaucoma; IOP, intraocular pressure; KF, Kalman filter; KF-TP, Kalman filter with tonometry and perimetry data; KF-TPO, Kalman filter with tonometry, perimetry, and global retinal nerve fiber layer data; Kalman filter; LR1, linear regression model 1; LR2, linear regression model 2; MAE, mean absolute error; MD, mean deviation; Machine learning; OAG, open-angle glaucoma; OCT; PSD, pattern standard deviation; RMSE, root mean square error; RNFL, retinal nerve fiber layer; SD, standard deviation; VF, visual field.

Grants and funding

R01 EY029058/EY/NEI NIH HHS/United States