Neural network will detect the signs of Parkinson's disease before the onset of symptoms

Russian scientists have presented an innovative approach to the early diagnosis of Parkinson's disease using advanced neural networks. The project, developed by young specialists from Sechenov University, is aimed at detecting the disease at the preclinical stage, that is, while the symptoms have not yet occurred, which can significantly increase the effectiveness of treatment and improve the quality of life of patients.

From a different test: how Russian scientists are changing breast cancer treatment

The country has registered the first domestic test system for the selection of targeted treatment

Currently, the standard diagnosis is based on clinical signs such as tremor, stiffness, and slowness of movement, followed by confirmation by neuroimaging. The new method suggests using electroencephalography (EEG), which has not previously been used for these purposes. It is based on an analysis of the electrical activity of the brain in patients with Parkinson's disease.

"There are scientific publications by Russian and foreign researchers devoted to the peculiarities of the electrical activity of the brain on electroencephalography of patients with Parkinson's disease and their comparison with the EEG of healthy people. We set ourselves the task of finding out whether it is possible to differentiate this data using a neural network. As it turned out, this is quite realistic," Ekaterina Vakhromeeva, the author of the project, a graduate of the Master's degree in Information Systems and Technologies at Sechenov University, told Izvestia.

The study used anonymized EEG data from an open foreign source. The neural network was trained on a sample of data marked up by a neurologist. Subsequent testing showed that the model is able to detect frequency abnormalities of electroencephalograms with an accuracy of 97%, which makes it possible to identify patients with Parkinson's disease at an early stage.

Read more in the exclusive Izvestia article:

Scientific model: neural network will detect early signs of Parkinson's disease by EEG