December 26, 2025
2 min read
Machine Learning Accurately Predicts Glaucoma Progression
New AI models, incorporating detailed eye scans, could personalize glaucoma care and help doctors intervene earlier.
- Researchers successfully used machine learning to forecast how glaucoma will progress.
- The models analyzed a wide range of eye health indicators, including those from advanced imaging techniques.
- This approach promises more tailored treatment plans and perhaps slower disease progression.
Artificial intelligence is showing remarkable promise in predicting the course of glaucoma, a leading cause of irreversible blindness. According to data published in EPMA Journal,machine learning models can accurately forecast glaucoma progression by analyzing structural,functional,and vascular biomarkers – including detailed scans from OCT angiography.
“Glaucoma’s growing prevalence and persistent underdiagnosis produce a profound and multifaceted burden for patients, families, health care systems and societies worldwide, underscoring the critical importance of early detection, individualized monitoring of disease progression and effective interventions,” wrote Natalia I. Kurysheva, of the Ophthalmological Center of the Federal and Medical Biological Agency of the Russian federation, and colleagues.
The researchers found that in early-stage disease, structural measurements of the optic nerve head were most predictive. “This highlights the anatomical susceptibility of nerve fibers entering the optic disc from this sector,” the researchers explained.
For more advanced disease, ganglion cell complex thickness proved to be the most notable predictor. “This reflects the critical importance of macular ganglion cell integrity assessment in advanced disease, where residual functional capacity directly correlates with remaining retinal ganglion cells,” they wrote.
The findings highlight the continued importance of vascular factors in glaucoma progression, even in its early stages, Kurysheva and colleagues concluded.
The researchers suggest that this machine learning approach could help clinicians personalize follow-up schedules and target preventive measures more effectively. “Rather then relying on a few key metrics, our optimized models for early and advanced cohorts incorporate all measured predictors … to capture the full spectrum of disease heterogeneity,” they wrote. “This comprehensive approach achieves high prognostic accuracy (AUC 0.90) and accommodates the continuous and multifaceted nature of glaucomatous damage.”
