Artificial Intelligence for Vision Impairment from Diabetes

This trial tests whether artificial intelligence (AI) can enhance eye care for people with diabetes by detecting eye disease during regular doctor visits. Participants will either receive usual care, involving a referral for a separate eye exam, or undergo AI screening, which includes taking eye photos and using AI to check for eye issues directly in the clinic. The trial aims to make important eye checks easier and faster. Suitable candidates include those with type 1 or 2 diabetes who haven't had an eye exam in the past year and have no known diabetic eye disease. As an unphased trial, this study provides a unique opportunity to contribute to innovative research that could simplify and accelerate eye care for diabetic patients.

The trial information does not specify whether you need to stop taking your current medications. It is best to consult with the trial coordinators for specific guidance.

Research has shown that using artificial intelligence (AI) to detect diabetic eye disease is safe for patients. In one study, researchers used AI with a special camera to take pictures of the eyes without dilation, which can be uncomfortable. The AI analyzed these images to identify signs of eye disease. This method proved safe and effective for people with diabetes, including younger patients.

Researchers are excited about using artificial intelligence (AI) for vision impairment from diabetes because it offers a new approach to detecting eye disease. Unlike the usual care where patients need to visit an eye specialist for screenings, the AI intervention allows for autonomous identification of eye conditions right at the primary care clinic without needing a specialist's oversight. This method could potentially streamline the diagnostic process, making it faster and more accessible for patients. By simplifying the screening process, AI could lead to earlier detection and treatment, which is crucial for preventing vision loss in diabetes patients.

Research has shown that AI systems excel at detecting diabetic retinopathy, an eye disease related to diabetes. One study found that the AI system correctly identified the disease in most cases, achieving a sensitivity of 88.9% and a specificity of 98.7%. This trial will compare the AI Intervention, which includes autonomous AI-based identification of eye disease, with Usual Care, where patients follow the clinic's standard practice for eye exams. Previous studies suggest that AI can be as effective as, or even better than, traditional screening methods. Additionally, using AI in screening programs has reduced vision loss from this condition and increased the number of patients attending their yearly eye exams. These findings suggest AI could be a powerful tool in managing eye health for people with diabetes.²⁶⁷⁸⁹