November 24


How Artificial Intelligence Can Detect Diabetic Eye Disease

By Gabriela

November 24, 2021

If we happen to have diabetes, we’re at risk of developing diabetic retinopathy. If this condition does not get suitable treatment, then it may become severe and even cause blindness over time.

That’s why eye doctors advise anyone who is diabetic to check for this condition at least once a year.

And yes, this goes for those who haven’t had any known eye-related problems so far. Severe diabetic retinopathy can be present without any noticeable symptoms.

And what with the number of those with diabetes growing each year (and not just here in the U.S.) it would seem that artificial intelligence has a crucial part to play. To put it simply, it is a type of learning that one can ‘teach’ to a machine, like a computer.

In the modern age, AI (artificial intelligence) is used for handwriting recognition, facial recognition, and voice recognition, and this is just the tip of the iceberg! Healthcare leaders are looking for new ways of using AL to make the diagnosis and treatment of patients more efficient.

This can benefit the branch of medicine which has to do with the eyes, and ophthalmology because it can help in the more accurate identification of lesions and any other signs of diabetic retinopathy.

By using computers and AL in this way, there are significant improvements in inpatient care.

Why It’s So Beneficial

It makes sense, doesn’t it? If we have a machine that tells us what we need to do and what we don’t to prevent, improve, and treat our condition, that makes things easier for us as a patients. Not to mention it saves us a lot of time.

Otherwise, this process can be very bothersome and time-consuming. This puts a toll on ophthalmologists who have to go through so many eye photos (there are more than enough of those with diabetes, after all).

And it’s not like it’s just the United States which is faced with this problem.

This is precisely why AL is so useful: the analysis of images of one’s retina sounds so much simpler and fits in perfectly with the trend of telemedicine, which is already growing.

This could be even more beneficial for rural areas or developing countries. They usually send the eye images to other ophthalmologists, and once again, more time is needed for such backup diagnostics. The initial results from Al retinopathy studies are certainly promising.

And they will improve as time passes, becoming faster and better over time. This can only mean big ramifications and good news for the field of diabetes care.

This method of reading eye images using AL will most likely become predominant at larger institutions shortly. Let’s say, in the next 5 to 10 years.

And the reason it will take longer in other places is that there is such great variation concerning approaches to healthcare from state to state.

It’s no surprise that the medical community is particularly excited about this. It will offer patients the possibility to obtain proper diagnostics without having to travel to see a specialist in person.

Having Said All of This

There is currently one possible limitation to this technological method, and that is the quality of the images. Those tasked with analyzing the photos say about 10% of them are simply unreadable.

This could be due to several reasons. Reasons like a cataract or drug use block the proper view of a patient’s retina.

And, even though they may not have anything wrong with their eyes, as doctors find it impossible to say from just a blurry image, those individuals would still need to come in for an eye exam. And that can mean a bit of a downside.

Moreover, doctors want to make sure that patients realize that a photo of their retina analyzed by Al is by no means a replacement for a thorough eye exam. After all, other important parts of one’s eye health need to be tested. This is best done directly in an exam face-to-face.

Think of it this way. Simply because we’ve done a blood pressure check at our pharmacy, it doesn’t mean we don’t have to see our internist once a year. There is only so much technology can offer, and we still need people for many health issues.

Al is useful because it can help identify which patients need extra attention concerning their diabetic retinopathy, and which don’t. Predictions for the future are that, with more advanced technology, we can even take a ‘selfie’ using our cell phone for our retinal eye screening.

Bottom Line

Even though Al may prove useful in helping us deal with any potential diabetic retinopathy, we shouldn’t just rely on it. Rather, stick to the usual bits of advice. Eat healthily, don’t smoke, keep tight control over our blood glucose levels, and do some exercise.

And don’t skip out on our eye exams. Let’s end this with one more bit of good news. Nowadays some medications can prevent blindness caused by this condition in 95% of the cases! We hope this information was of some use to people.

Source: U.S. News


  • Gabriela

    Co-Founder & Editor-in-Chief of Diabetes Health Page, Fitness trainer and instructor has dedicated her career to educating and informing people for over 10 years. As one of the most passionate diabetes advocates, Gabi has worked tirelessly to ensure that those people receive the education and support they need to properly manage their diabetes and achieve their health, fitness and weight loss goals.

{"email":"Email address invalid","url":"Website address invalid","required":"Required field missing"}