[ad_1]
An eye exam may be all that is needed to diagnose Parkinson’s disease, new research shows.
Using an advanced machine learning algorithm and fundus eye images, which depict the small blood vessels and more at the back of the eye, researchers are able to classify patients with Parkinson’s disease versus a control group. . “We found that the micro blood vessels decreased in both size and number in Parkinson’s patients,” Maximillian Diaz, a doctoral student at the University of Florida at Gainesville, told Medscape.
A simple eye examination can offer a way to diagnose Parkinson’s in the early stages of the disease’s progression.
Diaz said the test could be incorporated into a patient’s annual physical exam to look for not only Parkinson’s but other neurological diseases as well. A team in his lab is also evaluating whether the same technique can diagnose Alzheimer’s disease.
The beauty of this is that “the technique is simple,” he said. “What surprised us is that we can do this with fundus images, which can be taken in a clinical setting with a lens that attaches to the smartphone.”
“It’s affordable and portable and takes less than a minute,” he added.
Machine learning on fundus eye images
The researchers, under the direction of Ruogu Fang, PhD, director of the Smart Medical Informatics Learning and Evaluation Lab (SMILE) of the J. Crayton Pruitt Department of Biomedical Engineering, collected fundus images from 476 individuals of the same age and gender 238 diagnosed with Parkinson’s and 238 images from the control group. Another set of 100 images was collected from the University of Florida database using green color channels (UKB-Green and UF-UKB Green) and used to improve vessel segmentation. Of these, 28 were controls and 72 were Parkinson’s patients. The researchers added another 44 control images from the UK biobank to complete the second age- and gender-matched dataset.
“We used 80% of the images to develop the machine learning network,” Diaz said. Were the other 20% of the images, which were new to the algorithm, used to test it, to determine true or false, Parkinson’s or control?
“We were able to achieve 85 percent accuracy,” Diaz said Medscape Medical News. There are currently no biomarkers to diagnose Parkinson’s. The disease is only recognizable when 80% of the dopaminergic cells have already decayed. “Clinically, there’s no way to tell how long anyone has had it,” Diaz said. He hopes that by doing more research and testing ahead of time, with a longitudinal study of the images, a pattern can be found to better predict the disease.
Ocular vascularization reveals the disease
“This concept [studying eye vasculature] is generating a lot of interest right now, “said Anant Madabhushi, PhD, Case Western Reserve University, Cleveland, Ohio, Medscape Medical News. “The eye is the proverbial window on the soul and, in this case, it shows what is happening in the rest of the body”.
Madabhushi, who was not involved in Parkinson’s research, also worked with a team in Cleveland to see how vessels in the eye predict response to drug therapies in diabetic macular edema, including duration of treatment. “What we found is that the more twisted the vessels are, the more narrow they are and the less likely the person is to respond to therapy,” he said, adding that studying eye pathology makes a lot of sense. “The arrangement of the vessels in the eye is likely to have implications for all kinds of diseases.”
Since Parkinson’s disease has no biomarkers, this technology could be very helpful in diagnosis. “With specific quantitative measurements, we could have computational imaging biomarkers to predict Parkinson’s risk of onset and disease prognosis. That’s the real utility of this approach,” he said.
Diaz did not disclose any relevant financial relationships. Madabhushi partnered with Aiforia Inc and had research sponsored by AstraZeneca, Bristol-Myers Squibb, and Boehringer Ingleheim.
Radiological Society of North America (RSNA) Annual Meeting: Poster IN-1A-07. Presented on November 29, 2020.
Ingrid Hein is a freelance healthcare and technology journalist based in Hudson, Quebec.
.
[ad_2]
Source link
