Researchers have developed an artificial intelligence (AI) system capable of predicting whether individuals at high risk of glaucoma, known as “glaucoma suspects,” will eventually develop the condition.
This breakthrough could assist clinicians in diagnosing and managing glaucoma more effectively.
The Challenge of Glaucoma Diagnosis: Glaucoma is a leading cause of blindness globally.
However, diagnosing it can be challenging, particularly when individuals display early signs of optic nerve damage but lack the typical high intraocular pressure (IOP) associated with the condition.
AI-Based Solution: To address this diagnostic gap, researchers employed AI to analyze clinical data from 12,458 eyes with early signs of glaucoma.
They focused on 210 eyes that progressed to glaucoma and 105 that did not over a monitoring period of at least seven years.
The AI system used retinal images and 15 clinical features, including age, sex, IOP, corneal thickness, retinal nerve layer thickness, blood pressure, and BMI, to predict glaucoma progression.
Three machine learning classifiers were trained to categorize this data.
Promising Results: All three algorithms demonstrated a high degree of accuracy, ranging from 91% to 99%, in predicting glaucoma progression and estimating when it would occur.
Key predictive clinical features included baseline IOP, diastolic blood pressure, and average retinal nerve fiber layer thickness.
Age as a Factor: Although age did not emerge as a key predictive factor, individuals who progressed to glaucoma were generally younger than those who did not.
This observation underscores the importance of considering multiple clinical variables in glaucoma risk assessment.
Limitations and Future Prospects: The study has some limitations, such as a relatively small dataset and the exclusion of patients receiving glaucoma treatment.
However, the researchers believe that with additional training and a larger dataset, their AI models can be further improved.
Tailored Management Options: The AI system’s potential lies in its ability to predict glaucoma progression on an individual basis.
This could empower clinicians to offer tailored management options to glaucoma suspects, including personalized follow-up plans and decisions regarding IOP-lowering treatment.
Conclusion: This research showcases the potential of AI in enhancing glaucoma diagnosis and management.
While further refinement and testing are necessary, the AI system offers hope for more precise and effective approaches to tackle glaucoma, ultimately preserving the vision of those at risk.
If you care about eye health, please read studies about how vitamin B may help fight vision loss, and MIND diet may reduce risk of vision loss disease.
For more information about eye disease, please see recent studies about how to protect your eyes from glaucoma, and results showing this eye surgery may reduce dementia risk.
The research findings can be found in the British Journal of Ophthalmology.
Follow us on Twitter for more articles about this topic.
Copyright © 2023 Knowridge Science Report. All rights reserved.
