Validation of a Visual Field Prediction Tool for Glaucoma: A Multicenter Study Involving Patients With Glaucoma in the United Kingdom

Purpose: A previously developed machine-learning approach with Kalman filtering technology accurately predicted the disease trajectory for patients with vari- ous glaucoma types and severities using clinical trial data. This study assesses performance of the KF approach with real-world data.

Design: Retrospective cohort study.

Methods: We tested the performance of a previ- ously validated KF model (PKF) initially trained using data from the African Descent and Glaucoma Evaluation Study and the Diagnostic Innovations in Glaucoma Study in patients with different types and severities of glaucoma receiving care in the United Kingdom (UK), comparing the predictive accuracy to 2 conventional linear regres- sion (LR) models and a newly developed KF trained on UK patients (UK-KF).

Results: A total of 3116 patients with open- angle glaucoma or suspects were divided into training (n = 1584) and testing (n = 1532) sets. The predictive ac- curacy for MD within 2.5 dB of the observed value at 60 months’ follow-up for PKF (75.7%) was substantially better than those for the LR models ( P < .01 for both) and similar to that for UK-KF (75.2%, P = .70). The proportion of MD predictions in the 95% repeatability intervals at 60 months’ follow-up for PKF (67.9%) was higher than those for the LR models (40.2%, 40.9%) and similar to that for UK-KF (71.4%).

Conclusions: This study validates the performance of our previously developed KF model on a real-world, multicenter patient population. Our model substantially outperforms the current clinical standard (LR) and fore- casts well for patients with different glaucoma types and severities. This study supports the generalizability of PKF performance and supports prospective study of imple- mentation into clinical practice. (Am J Ophthalmol 2025;272: 87–97. ©2025 Published by Elsevier Inc.)

*Author(s):ARLEN DEAN, DUN JACK FU, MOHAMMAD ZHALECHIAN, MARK P. VAN OYEN, MARIEL S. LAVIERI, ANTHONY P. KHAWAJA, AND JOSHUA D. STEIN

Doi: 10.1016/j.ajo.2025.01.006

Link: https://www.ajo.com/article/S0002-9394(25)00021-2/abstract

Clinical Paper of the Month manager: Rafael Correia Barão

Editors in Chief: Francesco Oddone, Manuele Michelessi