Abstract
Leveraging consumer technology such as smartphone and smartwatch devices to objectively assess people with multiple sclerosis (PwMS) remotely could capture unique aspects of disease progression. This study explores the feasibility of assessing PwMS and Healthy Control's (HC) physical function by characterising gait-related features, which can be modelled using machine learning (ML) techniques to correctly distinguish subgroups of PwMS from healthy controls. A total of 97 subjects (24HC subjects, 52 mildly disabled (PwMSmild, EDSS [0-3]) and 21 moderately disabled (PwMSmod, EDSS [3.5-5.5]) contributed data which was recorded from a Two-Minute Walk Test (2MWT) performed out-of-clinic and daily over a 24-week period. Signal-based features relating to movement were extracted from sensors in smartphone and smartwatch devices. A large number of features (n = 156) showed fair-to-strong (R 0.3) correlations with clinical outcomes. LASSO feature selection was applied to select and rank subsets of features used for dichotomous classification between subject groups, which were compared using Logistic Regression (LR), Support Vector Machines (SVM) and Random Forest (RF) models. Classifications of subject types were compared using data obtained from smartphone, smartwatch and the fusion of features from both devices. Models built on smartphone features alone achieved the highest classification performance, indicating that accurate and remote measurement of the ambulatory characteristics of HC and PwMS can be achieved with only one device. It was observed however that smartphone-based performance was affected by inconsistent placement location (running belt versus pocket). Results show that PwMSmod could be distinguished from HC subjects (Acc. 82.2 ± 2.9%, Sen. 80.1 ± 3.9%, Spec. 87.2 ± 4.2%, F 1 84.3 ± 3.8), and PwMSmild (Acc. 82.3 ± 1.9%, Sen. 71.6 ± 4.2%, Spec. 87.0 ± 3.2%, F 1 75.1 ± 2.2) using an SVM classifier with a Radial Basis Function (RBF). PwMSmild were shown to exhibit HC-like behaviour and were thus less distinguishable from HC (Acc. 66.4 ± 4.5%, Sen. 67.5 ± 5.7%, Spec. 60.3 ± 6.7%, F 1 58.6 ± 5.8). Finally, it was observed that subjects in this study demonstrated low intra- and high inter-subject variability which was representative of subject-specific gait characteristics.
Highlights
M ULTIPLE Sclerosis (MS) is a progressive neurodegenerative disease that is typically diagnosed in young adults, causing varied and unpredictable physical and mental disability and neurological deterioration over time [1]
It was observed that the ratio of total (AUC) spectral energy in the gait domain (0.5–3 Hz) to higher frequency “noise” energy per subject was lower in PwMSmod than in HC or PwMSmild smartphone tests (Fig. 3(a), p < 0.001)
This study further focused on subjects who exhibit clinically moderate disease symptoms, within the gait domain (PwMSmod, Expanded Disability Status Scale (EDSS) [3.5–5.5])
Summary
M ULTIPLE Sclerosis (MS) is a progressive neurodegenerative disease that is typically diagnosed in young adults, causing varied and unpredictable physical and mental disability and neurological deterioration over time [1]. The Timed 25-Foot Walk (T25FW), developed as part of the Multiple Sclerosis Functional Composite score [10], [11], and the Two-Minute Walk Test (2MWT) are used to assess physical gait function and fatigue in PwMS. The 2MWT outcome is typically reported as distance travelled [12], [13]. These clinically administered measures have a number of limitations, such as: low intra- and inter-rater reliability [14], in addition to an infrequent
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
