Researchers have developed an AI program that can assist physicians in performing a quantitative analysis when diagnosing Parkinson’s disease.
As human populations continue to age due to improved medical care, there is an impending ‘Parkinson’s disease pandemic’ where numbers of individuals suffering this age-related neurodegenerative disease threaten to overwhelm healthcare systems. There is a need to distinguish between Parkinson’s and other diseases which have similar motor symptoms.
Assistant Professor Andrey Somov at the Skolkovo Institute of Science and Technology and colleagues developed a machine learning algorithm to analyse video recordings of patients performing certain tasks.
“As part of the research process, we had the opportunity to closely interact with doctors and medical personnel, who shared their ideas and experience. It was fascinating observing how two seemingly different disciplines came together to help people. We also had the opportunity to monitor all parts of the research, from designing the methodology to data analysis and machine learning,” Kovalenko said.
The advantages of the video analysis approach is that it is simple, objective, noninvasive, quick, inexpensive and versatile.
To develop the machine learning algorithm, the researchers recorded 83 patients with and without Parkinson’s performing 15 tasks that they had designed, such as filling a glass with water. These tasks were developed in a prior feasibility study using wearable sensors. The machine learning technology allows for objective analysis which picks up certain features of the disease which may not be visible to the naked eye.
Coauthor of the study Sklotech Assistant Professor Dmitry Dylov, and “Machine learning and computer vision methods we used in this research are already well established in a number of medical applications; they can be trusted, and the diagnostic exercises for Parkinson’s disease have been in development by neurologists for some time. What is truly new about this study is our quantitative ranking of these exercises according to their contribution to a precise and specific final diagnosis. This could only be achieved in collaboration between doctors, mathematicians and engineers.”
“This collaboration between doctors and scientists in data analysis allows for many important clinical nuances and details that help achieve the best results. We as doctors see great potential in this; apart from differential diagnosis, we need objective tools to assess motor fluctuation in patients with PD. These tools can provide a more personalized approach to therapy and help make decisions on neurosurgical interventions as well as assess the outcomes of surgery later,” noted coauthor of the paper, neurologist Ekaterina Bril.
Source: News-Medical.Net
Journal information: Kovalenko, E., et al. (2021) Distinguishing Between Parkinson’s Disease and Essential Tremor Through Video Analytics Using Machine Learning: a Pilot Study. IEEE Sensors.doi.org/10.1109/JSEN.2020.3035240.