Classifying Idiopathic Rapid Eye Movement Sleep Behavior Disorder, Controls, and Mild Parkinson's Disease Using Gait Parameters

• Published in: Movement disorders Vol. 37; no. 4; pp. 842 - 846
• Main Authors: Cochen De Cock, Valérie, Dotov, Dobromir, Lacombe, Sandy, Picot, Marie Christine, Galtier, Florence, Driss, Valérie, Giovanni, Castelnovo, Geny, Christian, Abril, Beatriz, Damm, Loic, Janaqi, Stefan
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.04.2022; Wiley Subscription Services, Inc; Wiley
• Subjects: Behavior disorders; Computer Science; conversion; Eye movements; Gait; gait parameters; Humans; idiopathic REM sleep behavior disorder; iRBD; Life Sciences; machine learning classification; Mathematical models; Movement disorders; Neurodegenerative diseases; Parkinson Disease - complications; Parkinson Disease - diagnosis; Parkinson's disease; Probability learning; REM sleep; REM Sleep Behavior Disorder - complications; REM Sleep Behavior Disorder - diagnosis; Santé publique et épidémiologie; Sleep disorders; Synucleinopathies; idiopathic REM sleep behavior disorder; Parkinson's disease; iRBD; machine learning classification; gait parameters; conversion
• ISSN: 0885-3185; 1531-8257; 1531-8257
• DOI: 10.1002/mds.28894

ABSTRACT Background Subtle gait changes associated with idiopathic rapid eye movement sleep behavior disorder (iRBD) could allow early detection of subjects with future synucleinopathies. Objective The aim of this study was to create a multiclass model, using statistical learning from probability distribution of gait parameters, to distinguish between patients with iRBD, healthy control subjects (HCs), and patients with Parkinson's disease (PD). Methods Gait parameters were collected in 21 participants with iRBD, 21 with PD, and 21 HCs, matched for age, sex, and education level. Lasso sparse linear regression explored gait features able to classify the three groups. Results The final model classified iRBD from HCs and from patients with PD equally well, with 95% accuracy, 100% sensitivity, and 90% specificity. Conclusions Gait parameters and a pretrained statistical model can robustly distinguish participants with iRBD from HCs and patients with PD. This could be used to screen subjects with future synucleinopathies in the general population and to identify a conversion threshold to PD. © 2022 International Parkinson and Movement Disorder Society