Using perceptive computing in multiple sclerosis - the Short Maximum Speed Walk test

Abstract

Background: We investigated the applicability and feasibility of perceptive computing assisted gait analysis in multiple sclerosis (MS) patients using Microsoft Kinect™. To detect the maximum walking speed and the degree of spatial sway, we established a computerized and observer-independent measure, which we named Short Maximum Speed Walk (SMSW), and compared it to established clinical measures of gait disability in MS, namely the Expanded Disability Status Scale (EDSS) and the Timed 25-Foot Walk (T25FW).

Methods: Cross-sectional study of 22 MS patients (age mean ± SD 43 ± 9 years, 13 female) and 22 age and gender matched healthy control subjects (HC) (age 37 ± 11 years, 13 female). The disability level of each MS patient was graded using the EDSS (median 3.0, range 0.0-6.0). All subjects then performed the SMSW and the Timed 25-Foot Walk (T25FW). The SMSW comprised five gait parameters, which together assessed average walking speed and gait stability in different dimensions (left/right, up/down and 3D deviation).

Results: SMSW average walking speed was slower in MS patients (1.6 ± 0.3 m/sec) than in HC (1.8 ± 0.4 m/sec) (p = 0.005) and correlated well with EDSS (Spearman's Rho 0.676, p < 0.001). Furthermore, SMSW revealed higher left/right deviation in MS patients compared to HC. SMSW showed high recognition quality and retest-reliability (covariance 0.13 m/sec, ICC 0.965, p < 0.001). There was a significant correlation between SMSW average walking speed and T25FW (Pearson's R = -0.447, p = 0.042).

Conclusion: Our data suggest that ambulation tests using Microsoft Kinect™ are feasible, well tolerated and can detect clinical gait disturbances in patients with MS. The retest-reliability was on par with the T25FW.

Figure 1

System setup. A) Schematic system setup (view from above): The Kinect sensor (K) was positioned 140 cm above ground, angled -9° towards the floor. Starting (S) about 2 metres in front of the beam path (light blue area), subjects walked with maximum speed towards the Kinect camera (red arrow). Recording started and stopped automatically as sensors detected the subjects entering and leaving the detection zone (dark blue area). B) Sample screenshot of a healthy subject during the test with skeleton projection (green lines). The hip-centre joint (marked as red dot) was used as the data source for analysis. C) Sample data from single healthy subject after normalization. At the position of the red arrow a measurement frame was removed due to a detected calibration jump.

Figure 2

Test outcome differences. Box plots of test outcome measurements (red = MS patients, grey = healthy subjects). Significance levels from t-tests: *** = p < 0.001; ** = p < 0.01; * = p < 0.05.

Figure 3

SMSW in comparison with the T25FW. Measuring agreement of gait speed detection of MS patients (red dots) and healthy subjects (grey triangles) with standard T25FW and SMSW. To be able to directly compare SMSW and T25FW in a Bland-Altman analysis, the SMSW time equivalent of walking 25-feet at the detected average speed was calculated. A) Results are plotted against each other. The solid line represents an R² of 0.392 from a linear regression analysis; the long dashed lines are 95% confidence intervals to the mean. The short-dashed line represents the theoretical test equality (T25FW = SMSW). B) Bland-Altman plot comparison between T25FW and SMSW average speed. B) The difference of the mean is -0.4 sec (solid line). Long dashed lines are 2x standard deviation.