Skip to Content


MDS makes every effort to publish accurate information on the website. "Google Translate" is provided as a free tool for visitors to read content in one's native language. Translations are not guaranteed to be 100% accurate. Neither MDS nor its employees assume liability for erroneous translations of website content.

International Parkinson and Movement Disorder Society
Main Content

Novel Application of Machine Learning Approaches Predicts Gait Dysfunction in Parkinson’s Disease

August 27, 2023

COPENHAGEN, DENMARK — A machine learning approach from diffusion tensor imaging (DTI) multi-spectral diffusion weighted imaging (DWI) showed prediction of gait dysfunction in PD according to a study released today at the International Congress of Parkinson’s Disease and Movement Disorders® in Copenhagen, Denmark. 

Several neuroimaging studies in Parkinson’s disease (PD) suggest an altered interplay between cortical and subcortical brain areas at a structural and functional level each that contributes to gait dysfunction in PD. 

This study used 7 different quantitative DTI measures from 43 PD patients along with UPDRS III, to develop a prediction model for gait dysfunction using different machine learning approaches and 60 template regions of interest (ROIs). The analysis concluded that the multilayer perceptron (MLP) machine learning approach with 5 hidden layers and Rectified Linear Unit (ReLU) activation performed best to predict gait dysfunction in PD with an area under the curve (AUC) of 0.78. 

Klaus Seppi, Director of the Department of Neurology at the Hospital Kufstein and Professor for Neurology with the focus on Movement Disorders of the Department of Neurology at the Medical University Innsbruck, responded to this study.

“Recent advances in MR methodology allowing quantitative evaluation of biochemical changes and macro- and microstructural alterations as well as analytic approaches including voxel-based analyses, machine-learning techniques and other post-processing algorithms have gained growing popularity in medical image analysis offering insights into the pathophysiology underlying key symptoms such as gait dysfunction in PD,” he said. “This study suggests that a machine learning approach of DTI analysis may have potential in predicting gait dysfunction in PD patients if confirmed by larger confirmative studies. Moreover, future studies have to explore if this pattern changes with disease progression.”

Full text of this abstract will be available at (Reference #297) after the embargo lifts August 27, 2023, 08:00 CEST. 

* * *  

About the 2023 MDS International Congress of Parkinson’s Disease and Movement Disorders®:  
The MDS International Congress is the premiere annual event to advance the clinical and scientific discipline of Movement Disorders, including Parkinson’s disease. Convening thousands of leading clinicians, scientists and other health professionals from around the globe, the International Congress will introduce more than 1,800 scientific abstracts and provide a forum for education and collaboration on latest research findings and state-of-the-art treatment options. 

About the International Parkinson and Movement Disorder Society: 
The International Parkinson and Movement Disorder Society® (MDS), an international society of more than 11,000 clinicians, scientists, and other healthcare professionals, is dedicated to improving patient care through education and research. For more information about MDS, visit

We use cookies to give you the best possible experience with our website. These cookies are also used to ensure we show you content that is relevant to you. If you continue without changing your settings, you are agreeing to our use of cookies to improve your user experience. You can click the cookie settings link on our website to change your cookie settings at any time. Note: The MDS site uses related multiple domains, including and This cookie policy only covers the primary and domain. Please refer to the MDS Privacy Policy for information on how to configure cookies for all other domains on the MDS site.
Cookie PolicyPrivacy Notice