An Objective and Easy-to-Use Glaucoma Functional Severity Staging System Based on Artificial Intelligence.
Huang Xiaoqin, Saki Fatemeh, Wang Mengyu, Elze Tobias, Boland Michael V, Pasquale Louis R, Johnson Chris A, Yousefi Siamak
AI Summary
AI developed a glaucoma staging system using visual fields, finding four severity levels based on specific MD thresholds. This objective, easy-to-use system aids clinical practice and research.
Abstract
Objective
The objective of this study was to develop an objective and easy-to-use glaucoma staging system based on visual fields (VFs).
Subjects and participants: A total of 13,231 VFs from 8077 subjects were used to develop models and 8024 VFs from 4445 subjects were used to validate models.
Methods
We developed an unsupervised machine learning model to identify clusters with similar VF values. We annotated the clusters based on their respective mean deviation (MD). We computed optimal MD thresholds that discriminate clusters with the highest accuracy based on Bayes minimum error principle. We evaluated the accuracy of the staging system and validated findings based on an independent validation dataset.
Results
The unsupervised k -means algorithm discovered 4 clusters with 6784, 4034, 1541, and 872 VFs and average MDs of 0.0 dB (±1.4: SD), -4.8 dB (±1.9), -12.2 dB (±2.9), and -23.0 dB (±3.8), respectively. The supervised Bayes minimum error classifier identified optimal MD thresholds of -2.2, -8.0, and -17.3 dB for discriminating normal eyes and eyes at the early, moderate, and advanced stages of glaucoma. The accuracy of the glaucoma staging system was 94%, based on identified MD thresholds with respect to the initial k -means clusters.
Conclusions
We discovered that 4 severity levels based on MD thresholds of -2.2, -8.0, and -17.3 dB, provides the optimal number of severity stages based on unsupervised and supervised machine learning. This glaucoma staging system is unbiased, objective, easy-to-use, and consistent, which makes it highly suitable for use in glaucoma research and for day-to-day clinical practice.
MeSH Terms
Shields Classification
Key Concepts4
An unsupervised k-means algorithm identified 4 clusters of visual fields (VFs) with average mean deviations (MDs) of 0.0 dB (±1.4 SD), -4.8 dB (±1.9), -12.2 dB (±2.9), and -23.0 dB (±3.8) from 13,231 VFs from 8077 subjects.
A supervised Bayes minimum error classifier identified optimal mean deviation (MD) thresholds of -2.2, -8.0, and -17.3 dB for discriminating normal eyes and eyes at the early, moderate, and advanced stages of glaucoma.
The accuracy of the glaucoma staging system, based on identified mean deviation (MD) thresholds (-2.2, -8.0, and -17.3 dB), was 94% with respect to the initial k-means clusters.
A glaucoma staging system, developed using unsupervised and supervised machine learning on visual fields from 13,231 VFs from 8077 subjects, provides 4 severity levels based on mean deviation (MD) thresholds of -2.2, -8.0, and -17.3 dB.
Related Articles5
A Hybrid Deep Learning-Based Approach for Visual Field Test Forecasting.
Cohort StudyRepeatability of Online Circular Contrast Perimetry Compared to Standard Automated Perimetry.
Observational StudySystematic Underestimation of Visual Sensitivity Loss on Microperimetry: Implications for Testing Protocols in Clinical Trials.
Clinical TrialEvaluation of the Consistency of Glaucomatous Visual Field Defects Using a Clustered SITA-Faster Protocol.
Cross-Sectional StudyVisual fields in glaucoma: Where are we now?
ReviewIs this article assigned to the wrong chapter(s)? Let us know.