IDx-DR is an AI diagnostic system that autonomously analyzes images of the retina for signs of diabetic retinopathy

Every year, over 24,000 people go blind from diabetic retinopathy

- Designed and tested for use in primary care

- Immediate diagnosis at the point of care

- Requires minimal operator training

Clinical TrialCase StudyIndications for UsePerformanceImage Quality

How IDx-DR Works

1) Using a fundus camera, the trained operator captures two images per eye

2) The images are submitted to the IDx-DR Client on a local computer

3) IDx-DR analyzes images for signs of diabetic retinopathy, providing results in less than a minute.

Negative for more than mild diabetic retinopathy: Retest in 12 Months

More than mild diabetic retinopathy detected: Refer to an eye care professional

Interested in IDx-DR?

IDx-DR uses a series of deep learning detectors to search for lesions specific to diabetic retinopathy

Each image is run through a series of filters that evaluate for disease, exam protocol, and image quality. Once each image has gone through this process, IDx-DR combines the results to produce a final image quality and disease determination.

Autonomous AI algorithm based on biomarkers

Immediate point of care results with follow-up care instructions

IDx-DR Analysis Report

Within one minute, the operator will receive a results report with one of the following outputs:

Exam quality is insufficient
Low-quality images can be retaken while the patient is still at the camera
Negative for more than mild diabetic retinopathy
Retest in 12 months

More than mild diabetic retinopathy detected
Refer to an eye care professional

High performance in a real-world clinical setting

In a 2017 U.S. clinical trial involving 900 subjects with diabetes, IDx-DR demonstrated 87% sensitivity and 90% specificity at detecting more than mild diabetic retinopathy (mtmDR) in fundus images.

Sensitivity

87%

Specificity

90%

Imageability

96%

More Data on IDx-DR