The light-sensitive layer found at the back of a person's eyes contains more than just cells that detect shadows and light — it also contains information about the health of a person's entire body. And now, artificial intelligence can glean this information from a single snapshot, new research suggests.

The new AI algorithm, which analyzes images of this light-sensitive layer of the eye, called the retina, could one day provide on the spot diagnoses of various ailments from diabetes to autoimmune and neurodegenerative diseases, the researchers claim.

The AI algorithm was presented by Dr. Ursula Schmidt-Erfurth, the director of the ophthalmology department at the Medical University of Vienna, earlier this month at a scientific meeting in Vienna. Research on the algorithm was published Dec. 8 in the journal Ophthalmology.

Schmidt-Erfurth's research focuses on using AI to detect signs of various diseases in the images of the retina. [‘Eye’ Can’t Look: 9 Eyeball Injuries That Will Make You Squirm]

"From a simple color photo of the retina, you can tell how old the person is, what gender are they, what is their smoking history, their blood sugar level and blood pressure," Schmidt-Erfurth said. "But we can also use an image from an optical coherence tomography scanner and that gives us much more detail."

Optical coherence tomography (OCT) is a technique commonly used in ophthalmology that takes 3D images of the retina and allows the doctor to examine in detail what is happening in each layer of the light-sensitive tissue. Artificial intelligence, however, can do this much more precisely and much faster, Schmidt-Erfurth told Live Science.

In the presentation, Schmidt-Erfurth showed how such an AI algorithm could accurately spot signs of diabetes in the retina. Patients with diabetes frequently develop a condition called macular edema, which is essentially accumulation of fluid in the macula, a layer of the retina responsible for sharp central vision. If left untreated, the macular edema can cause permanent damage and vision loss.

"The algorithm gives you precise information about how much fluid is there, which the image by itself does not provide," Schmidt-Erfurth said. Doctors could assess how well macular edema treatments are working by looking at these fluid levels — a decrease in fluid over time would show that the treatment is effective, she added.

The same algorithm could also detect the earliest signs of age-relatedmacular degeneration (ARMD) and even predict how the disease will progress, Schmidt-Erfurth said.

ARMD is the most common cause of vision impairment in elderly people, according to Schmidt-Erfuhrt. About 60 percent of people older than 50 years show early symptoms, Schmidt-Erfurth said. However, only 15 percent of these cases eventually progress to the advanced stages of the disease. Similar to the diabetes-related macular edema, ARMD leads to a blurring of central vision. The person gradually stops being able to distinguish details and may even struggle to recognize faces.

"With this technology, we can predict the risk" of a person progressing to more serious stages, Schmidt-Erfurth said. "By training the algorithm on large data sets of previous patients, we can identify patients that are at risk to develop the disease in comparison to other patients, which will never develop the advanced disease."

The high-risk individuals would then receive early treatment, which could potentially help them maintain their eyesight into old age.

The biggest advantage of the technology, Schmidt-Erfurth said, is the fact that it doesn’t require a specialist to interpret the results.

"Artificial intelligence will make therapy available to millions of people who until now are not diagnosed," she said. "It's very easy, you don't even need to go to see an eye doctor."

Schmidt-Erfurth's earlier technology is already approved for commercial use in Europe and has been deployed in five hospitals across the continent. It uses AI to detect signs of diabetic retinopathy, a condition in which the blood vessels in the retina break down, from 2D color photographs of the eye.