Monitoring Glaucomatous Functional Loss Using an Artificial Intelligence-Enabled Dashboard

Area of Science:

• Ophthalmology
• Artificial Intelligence
• Medical Imaging

Background:

• Glaucoma is a progressive optic neuropathy leading to functional vision loss.
• Monitoring disease progression and severity is crucial for effective glaucoma management.
• Current methods for assessing visual field loss can be complex and time-consuming.

Purpose of the Study:

• To develop an artificial intelligence (AI) dashboard for monitoring glaucomatous functional loss.
• To create a user-friendly tool for assessing glaucoma severity and progression.
• To visualize patterns of visual field loss in glaucoma patients.

Main Methods:

• Retrospective analysis of 31,591 visual fields (VFs) from 8,077 subjects.
• Development of an AI dashboard using principal component analysis, manifold learning, and unsupervised clustering.
• Validation of the dashboard using benchmark datasets for progression and non-progression.

Main Results:

• The AI dashboard identified 32 distinct clusters representing patterns of visual field loss.
• Specificity for detecting likely non-progression was 94%.
• Sensitivity for detecting likely progression was 77%.

Conclusions:

• The AI-enabled glaucoma dashboard offers a potential tool for clinicians.
• It aids in determining the severity and spatial extent of glaucomatous vision deficit.
• The dashboard facilitates monitoring disease progression.