BSI

BSI
Creating Generational Legacies

Monday, April 16, 2018

AI device for diabetic eye problems approved by FDA


IDx-DR can diagnose diabetic retinopathy, the most common cause of vision loss among the more than 30 million Americans living with diabetes  
The US Food and Drug Administration has approved an artificial intelligence diagnostic device that doesn’t need a specialized doctor to interpret the results. The software program, called IDx-DR, detects a form of eye disease called diabetic retinopathy by looking at photos of the retina.

Diabetic retinopathy (although rare)  is the most common vision complication for more than 30 million Americans living  with diabetes 

Photos are taken by a retinal camera of the patient’s retina are uploaded to IDx-DR  and an algorithm analyzes the images to determine whether the patient has the disease , where too much blood sugar damages the blood vessels in the back of the eye. 

In one clinical trial that used more than 900 images, IDx-DR correctly detected retinopathy about 87 percent of the time, and could correctly identify those who didn’t have the disease about 90 percent of the time. 

The software is unique because it’s autonomous and there’s “not a specialist looking over the shoulder of [this] algorithm,”

 IDx-DR founder Michael Abràmoff told Science News. “It makes the clinical decision on its own.” This means that the technology can be used by a nurse or doctor who’s not an eye specialist, making diagnosis more accessible. 

The benefit..... over 30 million patients wouldn’t need to wait for an eye specialist to be available to get a diagnosis...

There will always be a need for a specialist to check and be responsible when the diagnosis is wrong - but that specialist can be a technician that can check lots - creating other jobs 

Now that the FDA has cleared IDx-DR, it might lead the way to a new slew of autonomous diagnostic tests and the trade-offs they bring. Such as Googles  DeepMind which is using  AI to spot eye disease


No comments:

Post a Comment