Using a simple eye exam combined with powerful machine learning technologymedical artificial intelligence(AI) one could detect Parkinson's early. This is according to research presented at the annual meeting of the Radiological Society of North America (RSNA). Parkinson's disease is a progressive disorder of the central nervous system that affects millions of people worldwide. Diagnosis is usually based on symptoms such as tremors, muscle stiffness and balance problems. However, this approach has significant limitations.
New technology can detect Parkinson's disease
The problem with traditional methods is that patients usually only get treatment after a long period of progressionSymptoms of Parkinson'sdevelop with a significant violation of dopamine brain neurons. This means that medicine diagnoses patients late in the course of the disease. The progression of the disease is characterized by the decay of nerve cells. This thins the walls of the retina, the layer of tissue that lines the back of the eyeball. The disease also affects the microscopic blood vessels or microvessels of the retina.
However, these insights provide an opportunity to harness the power of AI. This allows images of the eyes to be examined for signs of Parkinson's disease. The researchers used a type of AI called a support vector machine (SVM), which has existed since 1989. With the help ofImages of the fundus of patients' eyeswith Parkinson's disease and controls, they trained the SVM to recognize clues and signs of the disease in the images.
The results showed that the machine learning networks can detect Parkinson's and classify the disease based on the retinal vasculature. The main features are smaller blood vessels. The proposed methods further support the idea that changes in brain physiology can be observed in the eye. The most important result of this study was that a basic image of the eye could be diagnosed in the case of a brain disease. This differs from traditional approaches in which researchers look at different brain images to find a problem with the brain. The research team found that these traditional imaging techniques using MRI, CT and nuclear medicine techniques can be very expensive. In contrast, the new approach uses basic photography with equipment commonly available in eye clinics. Thus, an image is easily available. Such retinal images can even be captured by a smartphone with a special lens.
Medical perspectives
So there is hope that medicine could detect more cases of Parkinson's earlier in the future. Additionally, this can help better understand the disease and find a cure and a way to slow its progression. “It is just a simple image of the eye that can be taken in less than a minute,” say the authorsof the study. The approach could also have applications in identifying other diseases. This is especially true when the structure of the brain is affected, such as in Alzheimer's disease and multiple sclerosis.
