Hidden Markov model-based similarity measure (HMM-SM) for gait quality assessment of lower-limb prosthetic users using inertial sensor signals

Table 4 Correlations with functional measures

	GPS	HMM-SM upper	HMM-SM lower	HMM-SM pelvis	MDP upper	MDP lower	MDP pelvis	DTW upper	DTW lower	DTW pelvis	INI	MGS
PEQ-MS	0.106 (0.934)	0.051 (0.934)	0.081 (0.934)	0.08 (0.934)	0.161 (0.934)	0.126 (0.934)	0.177 (0.934)	0.177 (0.934)	0.274 (0.934)	0.123 (0.934)	0.027 (0.943)	0.113 (0.934)
LCI-5	−0.081 (0.934)	0.047 (0.934)	0.075 (0.934)	0.23 (0.934)	−0.066 (0.934)	−0.058 (0.934)	−0.172 (0.934)	−0.066 (0.934)	−0.04 (0.934)	−0.146 (0.934)	−0.45 (0.746)	−0.009 (0.967)

R-values provided with corresponding adjusted p-values in parentheses. Correlations with achieved significance threshold (alpha = 0.05) are bolded. None of the assessed correlations to functional measures were statistically significant in this study
GPS Gait Profile Score, HMM-SM hidden Markov model-based similarity measure, MDP Movement deviation profile, DTW Dynamic time warping, INI IMU-based Gait Normalcy Index, MGS Multifeature Gait Score, PEQ-MS Prosthetic Evaluation Questionnaire – Mobility Section, LCI-5 Locomotor Capabilities Index-5

ISSN: 1743-0003