Sampriti Roy, University of Calcutta
Parkinson’s disease is a neurodegenerative disorder occurring when nerve cells, or neurons, in an area of the brain that controls movement become impaired and/or die. It is a progressive disorder of the central nervous system that affects millions of people worldwide. However, even after being such a wide-spread disease, there are significant limitations in the methods of diagnosis that are typically based on symptoms like tremors and impaired balance. Since symptoms only develop after prolonged progression of the disease with a significant injury to dopamine brain neurons, by the time the diagnosis is confirmed, it is often too late in the course of the disease. However, a recent study may be a turning point in Parkinson’s disease treatment.
The fact that the disease affects microscopic blood vessels of the retina and that the disease progression can be characterized by nerve cell decay that thins the walls of the retina has presented an opportunity for advancement in the treatment of the disease. This is seen as an opportunity to leverage artificial intelligence (AI) to examine images of the eyes for Parkinson’s. In the new study, with lead author Maximillian Diaz (the University of Florida in Gainesville), the researchers are seen deploying a type of AI called support vector machine (SVM) learning. By using pictures of the back of the eye from both the control participants and those affected with Parkinson’s disease, SVM is trained to detect signs on the images suggestive of the disease.
The results of the study indicate that the machine learning networks can classify Parkinson’s disease based on the vasculature of the retina, with principle features being smaller blood vessels. According to Diaz, the most significant part of this study is the fact that a brain disease was able to be identified with a basic picture of the eye. This approach, requiring just a simple picture of the eye, may also have applications in identifying other diseases that affect the structure of the brain, such as multiple sclerosis and Alzheimer’s.
The study holds major significance concerning affordability. Traditional approaches to diagnosing brain diseases include several costly imaging approaches including MRIs, nuclear medicine techniques and CT scans. The new approach will be using basic photography with equipment commonly available in eye clinics and images can even be captured by a smartphone with a special lens.
With the discovery of methods that promote relatively easier and accessible means of diagnosis, researchers hope to make yearly screenings of Parkinson’s a reality. This is said to be helpful to them in gaining a better understanding of the disease, finding a way to slow the progression of the disease and advance towards a particularly ambitious goal – curing it.
Also read: Turbinmicin- A New Fighter
- The Corrosion Prediction from the Corrosion Product Performance
- Nitrogen Resilience in Waterlogged Soybean plants
- Cell Senescence in Type II Diabetes: Therapeutic Potential
- Transgene-Free Canker-Resistant Citrus sinensis with Cas12/RNP
- AI Literacy in Early Childhood Education: Challenges and Opportunities
One thought on “An eye exam with AI to achieve early Parkinson’s detection?”