Severity of Parkinson’s disease can be Diagnosed by a New Tool

New tool using 3D images and artificial intelligence could allow healthcare personnel to diagnose different degrees of Parkinson's disease (PD) as developed by the University of Cordoba, in collaboration with the Nuclear Medicine Unit at the Hospital Reina Sofía. Parkinson's disease (PD) is a progressive neurodegenerative disorder that primarily affects movement due to loss of nerve cells – neurons that produce a chemical messenger (neurotransmitter) in the brain called dopamine (black substance). PD is characterized by the formation of inclusion proteins called Lewy bodies, triggered by the misfolding of a protein called alpha-synuclein in a part of the brain called the substantia nigra.

PD affects 7 million people worldwide as per the World Health Organization (WHO) data. The available diagnostic methods show only the presence of the disease.

However, the present study can specify the phase of the disease based on its severity using Artificial Intelligence and three-dimensional images of the area of the brain in which the neuronal degeneration is occurring.

The AI Algorithm in PD

The study team has analyzed, voxel by voxel (the equivalent of a 3D pixel), more than 500 photographs of the brains of people with symptoms compatible with the disease. The algorithm result predicts the severity of the disease, based on neuron damage.

In PD, there is a loss of density in the proteins responsible for transporting dopamine. Detecting the density of these proteins using the 3D images and ascertaining the places in the brain where they are found, which offers clues to the severity of the disease.

Advertisement

The process has also been validated through two different methodologies. The first of them uses classic ordinal classification techniques, while the second is based on "Convolutional Neural Networks" (CNN), a type of Artificial Intelligence model that is very effective with vision-related tasks such as image classification. Thus, the project "does not seek to substitute the assessments of specialized personnel, but rather to offer support for medical decision-making", says César Hervás, the AYRNA group's principal investigator. The study thereby states that this precise determination of the condition could help to manage the treatment strategies of the disease's condition.

Source-Medindia