MSMilan2023 (The 9th Joint ECTRIMS-ACTRIMS Meeting)

ePoster session Information:

ePoster Session: ePoster #P1253

Title: Six precise gait measures, captured with body-worn inertial sensors during a 6-minute walk test, discriminate Multiple Sclerosis from healthy controls while gait speed does not

Abstract:

Background: Gait deficits are common in Multiple Sclerosis (MS) but poorly captured by stopwatch-timed tests or rating scales. Body-worn inertial sensors can detect gait abnormalities in people with MS who have normal walking speed but the most discriminative measures of gait for MS are unknown. 

Objective: This study aimed to determine the best combination of gait measures to discriminate MS from healthy control (HC) subjects.  

Methods: We used two datasets: Study I as a training dataset, and Study II as a validation dataset to test the generalizability of the proposed model.  Study I recruited 10 MS and 12 HC, and Study II recruited 9 MS and 7 HC. Participants completed the 6-minute walk test at their fastest speed by walking back-and-forth along a 20-m straight walkway (Study I) or a 15-m straight walkway (Study II). Subjects wore inertial sensors (Opals) attached to both feet, sternum, and lumbar regions, and 36 gait measures were extracted. LASSO (5-fold, cross-validated least absolute shrinkage and selection operator) was applied as a feature-selection method.  

Results: From 36 gait measures, LASSO selected 6 measures from the training dataset: stride time, double-support time standard deviation, turn duration, number of turns, elevation at mid-swing, and toe-out angle standard deviation. The model applied to the validation dataset resulted in AUC=0.92 (sensitivity=0.89, specificity=1).  

Conclusions: The best combination of gait measures for accurate classification of MS from HC gait during the 6-minute walk test did not include gait speed. Digital gait measures show promise for endpoints in clinical trials. 

Authors:

• Vrutangkumar Shah – Director, Data Science and Biostatistics, Precision Motion at Clario
• Kristen Sowalsky, Ph.D., D.C. – VP, Medical and Scientific Affairs at Clario
• Fay Horak – Chief Scientist at Clario

This ePoster will be displayed on ePoster screens within the congress centre, as well as on the congress platform and the app during the congress. It will not be presented at a specific session. In addition, all ePosters will be remain available on the congress platform and congress app until 3 months after the congress.