Modified smartphone detects early signs of diabetes-induced blindness

One of the disastrous effects of diabetes is the harm it can cause to the retina, with this degeneration of blood vessels in the eye now the leading cause of new blindness in working-age adults. An international team of scientists has developed technology that could pick up this so-called diabetic retinopathy in its early stages, using a standard smartphone as the basis for a low-cost diagnostic method that could greatly improve care in developing regions.

Diabetic retinopathy is said to affect between 40 and 45 percent of American diabetics, according to the National Eye Institute, with the condition characterized by leaky vessels that displace healthy ones and feed unwanted fluids into the retina, the photosensitive layer of the eye. Robbed of vital oxygen and nutrients, the retina then begins to deteriorate, which can lead to the partial loss of vision or total blindness.

“If such a retinopathy is recognized and treated in time, vision loss can often be prevented,” says Dr. Maximilian Wintergerst from the Department of Ophthalmology at the University Hospital Bonn. “An important aspect of therapy is better control of the diabetes; in addition, it is also possible to treat the undersupplied retina with laser light before further problems occur.”

Wintergerst and his colleagues from University Hospital Bonn teamed up with researchers from the Sankara Eye Hospital in Bangalaore, India, to explore how diabetic retinopathy could be diagnosed earlier in developing countries, where health systems are often not equipped to screen widely for the condition.

Like many researchers pursuing low-cost solutions for medical diagnostics, the team turned to the modern smartphone. The researchers experimented with four different approaches designed to leverage the device’s built-in camera to image the retina, and found that one using a special adapter produced the clearest view.

“The best result in our test was achieved by an adapter with an additional lens that is attached to the smartphone,” Wintergerst says. “It allowed almost 80 percent of eyes with any retinal changes to be detected, even in the early stages. Advanced damage could even be diagnosed 100 percent of the time.”

The technique works by imaging the back of the eye and documenting changes to the retina, with trained optometrists able to perform the examinations in one or two minutes on average. The fact that it involves a smartphone, however, could open up some interesting possibilities according to the team.

“This means that the examination can also be enabled by trained laypersons,” says Dr. Robert Finger from the University Hospital Bonn. “The images are then sent via the internet to the ophthalmologist for diagnosis.”

The team is now working on an app that could facilitate this type of remote health care. The app would store encrypted files of the patient’s images and the results of the doctor’s analysis, but with further work, the team hopes that artificial intelligence could be used to detect pathological changes that are indicative of diabetic retinopathy as an automatic first step.

The research was published in the journal Ophthalmology.

Source: University of Bonn

Source of Article