AI That Can Analyze Your Eyes Like a Specialist Just Got Approved by the FDA

IDx-DR is a software program that can detect a certain type of eye disease from photos of a human retina, and it was just approved by the US Food and Drug Administration (FDA).

This is a huge win for artificial intelligence (AI) and MedTech development: this is the first time the FDA has approved an AI-powered diagnostic device that doesn’t require a doctor to interpret the results.

Augmented Image Analysis

Diabetic retinopathy is an eye disease in which an excess of blood sugar damages blood vessels located in the back of the eye. It’s the most common vision malady for people afflicted with diabetes, with about 200,000 new cases occurring per year.

After photos of a patient’s retina are taken with a special retinal camera, IDx-DR’s algorithm verifies that the picture quality is good enough to use for analysis. Once confirmed, the algorithm can then determine if the patient has diabetic retinopathy or not. In a clinical trial involving more than 900 photos, IDx-DR was able to correctly detect the disease 87% of the time. It could also correctly tell if a person didn’t have the disease 90% of the time.

Seeing What a Specialist Can

IDx-DR is autonomous, or as Michael Abràmoff says, there’s “not a specialist looking over the shoulder of [this] algorithm. It makes the clinical decision on its own.” Abràmoff is the founder of IDx, the company behind the autonomous AI image analyzer. Contrary to the usual startup, IDx-DR was not developed in New York City, San Francisco, or some other popular tech hub. IDx is based in Coralville, Iowa.

Because of this new FDA-approved algorithm, diagnosis will be more accessible. Medical workers who are not eye specialists will be able to utilize the technology to reach informed conclusions. This, in turn, means that patients won’t need to see an eye specialist to get answers.

IDx-DR joins a new wave of algorithms being used to diagnose diseases. We’ve previously covered how Google wants to deduce your medical outcome when you’re admitted to a hospital. The tech titan is also working on identifying eye disease with its DeepMind AI. Algorithms are also being used to help with diagnosing chronic obstructive pulmonary disease, heart disease, and lung cancer.

AI is quickly becoming an integral part of medical science. But if that means smarter methodologies and better health outcomes, I don’t think anyone’s complaining.