Artificial Intelligence Diagnostic Tool Available to Predict the Risk of Age-Related Macular Degeneration

Licensing/Collaboration: AI Diagnostic Tool Available to Predict the Risk of Age-Related Macular Degeneration

Age-related macular degeneration (AMD) affects approximately 200 million people worldwide and is the leading cause of blindness in all developed countries. Identifying eyes at high risk of progression to late-stage AMD would allow timely medical treatments, lifestyle interventions, more tailored home monitoring, and improved clinical trials for patients.

NIH inventors have used artificial intelligence (AI) to predict the risk of progression to late-stage AMD using over 80,000 images from almost 3,300 patients from the Age-Related Eye Disease Studies, AREDS and AREDS2. Using independent test data, the deep learning algorithm produced a 5% higher prognostic accuracy compared to existing clinical standards,  AREDS Simplified Severity Scale, and  the Casey AMD online calculator.

This approach is superior to other diagnostic methods:
 

AI Diagnostic ToolAREDS Simplified Severity Scale
  • Can make predications over a wide range of time intervals (1-12 years)
  • Can only make predictions for one fixed interval (5 years)
  • Can make predictions separately by subtype
  • Can only make predictions for late AMD
  • Final predictions are more explainable and biologically plausible, and error analysis is possible
  • End-to-end “black-box” deep learning approaches are less transparent and may be more susceptible to failure


A fully automated device that contains this novel image processing method has also been developed. 
 

If you are interested in learning more about this technology or contacting the licensing manager, please view the abstract: Using Artificial Intelligence to Predict the Risk of Age-Related Macular Degeneration