Artificial Intelligence Predicts AMD Progression

Our rapid paced world continues to deliver some startling advancements within many facets of technology. When it comes to medical applications, this tech is surpassing antiquated practices and ushering in a whole new way to approach the human body. Enter artificial intelligence (AI), which is the ability for a computer to solve human problems on many levels. New evidence shows how AI might be applied to age-related macular degeneration (AMD) for early predictions that could help slow progression.

A Hard Nut to Crack

As researchers and doctors search for more significant disease slowing remedies and potentially a cure for AMD it is still an incurable disease that afflicts millions. From the elderly to middle-aged individuals some believe this disease is on the brink of epidemic proportions as it runs rampant through almost every demographic ultimately leading to vision loss. In fact, it is one of the top causes of blindness worldwide today.

According to the American Academy of Ophthalmology,

“Nearly 2.1 million Americans age 50 and older have late AMD, the stage that can lead to severe vision impairment. In 2010, 9.1 million Americans had early AMD. By age 80, one in ten Americans has late AMD, which is more common in women than in men.”

The Future of Thinking

In an early paper by Dr. István S. N. Berkeley of The University of Louisiana at Lafayette, AI was described as,

“Artificial Intelligence is the study of man-made computational devices and systems which can be made to act in a manner which we would be inclined to call intelligent. The birth of the field can be traced back to the early 1950s. Arguably, the first significant event in the history of AI was the publication of a paper entitled “Computing Machinery and Intelligence” by the British Mathematician Alan Turing.”

Since the inception of computers thinking for humans, all sorts of applications have been invented with many used regularly today. One example of mainstream AI use are the voice activated devices such as Amazon Echo and Google Home. These are standing, continuous internet Wi-Fi connected microphone/speaker gadgets that can simply be asked a question without touching them. They quickly respond as if an all-knowing robot were standing beside you.

Now, using AI in the lab has shown promise in detecting specific ophthalmological biomarkers that humans are unable to determine on their own. It is the beginning, and in some cases the continuation, of AI medical applications.

All in the Algorithm

Before you envision robots taking over the earth, consider the fact that AI for AMD utilizes complex algorithms that can be deciphered in a fraction of the time that a human can do it. This assistance is key to advancing research that might have taken years to construct.

In a pilot study presented at the Association for Research in Vision and Ophthalmology annual meeting, the largest eye and vision research organization in the world, it was shown that, according to a report by News Medical Life Sciences,

“By pinpointing the moment of transition from early/intermediate to late AMD, the researchers state that machine learning will substantially contribute to the development of new therapeutics that target slowing AMD progression.”

The algorithms or specifically developed ‘recipes’ show the precise steps AMD may be heading in each individual. By monitoring these steps and applying them to various levels found in each case of AMD, researchers and doctors can determine a better course of treatment that may considerably slow down the disease. These algorithms may predict when early onset or intermediate AMD will develop into severe symptoms enabling patients to also prepare accordingly.

Drusen Regression Determined

Lipids (fatty acids) and protein deposits which develop on the retina have been one of the major indicators of AMD. Through optical coherence tomography (OCT) when these lipid/proteins begin to regress, known as individual drusen regression, it is a clear sign of the development of late stage or severe AMD.

Until now, researchers were only able to detect this regression when, basically, it was too late and vision loss had occurred. With AI, computer algorithms are being constructed to predict up to twelve months before the regression transpires.

Dr. Hrvoje Bogunovic, Senior Postdoc at Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology, Medical University of Vienna, comments on these findings,

“[The algorithm] would support ophthalmologists in estimating patients’ risk of developing severe AMD needed for patient counseling and would allow to adjust their screening schedule according to their risk,” he continues, “Once validated it could serve as a clinical decision support, ie as another objective ‘pair of eyes’ that will look at the OCT images and their changes with time,”

The Inner Workings

In the beginning, AI applications do not work on their own. Obviously, human interaction is essential before AI calculations can fly into the stratosphere beyond the speed humans are capable of.

With AMD and many other visual challenges, diagnosis is relegated to using high-def camera enhanced portable imaging instruments. These images are essential to determining the degree of affliction, however it is shown that a combination of this data plugged into an AI algorithm enhancer can go beyond in-office diagnosis.

Deep convolution neural networks (CNN) are the main contributors to AI learning. These are a combination of thousands of images that can  be rapidly deciphered to deliver future advancement information for not only AMD but other eye diseases as well.

A Sun Yat-Sen University news release describes this application when used for cataracts,

“This platform simulates the human brain, learns and analyzes vast congenital cataract images, and improves itself by continuous feedback. After embedding of the program into cloud-based platform, diagnosis, risk evaluation, and treatment strategy of congenital cataract could be obtained by simply uploading ocular images of patients.”

The inner workings of this AI algorithm are just the beginning of being able to amass scientific information, evaluation, and diagnosis in the blink of an eye. When it comes to age-related macular degeneration, cataracts, glaucoma and many other vision challenges AI tech could significantly change the treatment protocol.

Artificial intelligence may be a dubious technology to embrace, yet whether you like it or not it is being implemented into daily life. Some of it may revolve around convenience and entertainment but this is one example of how AI is affecting lives in pain relieving, disease fighting and possibly life saving ways.