An Automated Classification of Pathological Gait Using Unobtrusive Sensing Technology

Abstract

This paper integrates an unobtrusive and affordable sensing technology with machine learning methods to discriminate between healthy and pathological gait patterns as a result of stroke or acquired brain injury. A feature analysis is used to identify the role of each body part in separating pathological patterns from healthy patterns. Gait features, including the orientations of the hips and spine (trunk), shoulders and neck (upper limb), knees and ankles (lower limb), are calculated during walking based on Kinect skeletal tracking sequences. Sequences of these features during three types of walking conditions were examined: 1) walking at self-pace (WSP); 2) walking at distracted (WD); and 3) walking at fast pace (WFP). Two machine learning approaches, an instance-based discriminative classifier ( -nearest neighbor) and a dynamical generative classifier (using Gaussian Process Latent Variable Model), are examined to distinguish between healthy and pathological gaits. Nested cross validation is implemented to evaluate the performance of the two classifiers using three metrics: F1-score, macro-averaged error, and micro-averaged error. The discriminative model outperforms the generative model in terms of the F1-score (discriminative: WSP> 0.95, WD > 0.96, and WFP > 0.95 and generative: WSP > 0.87, WD > 0.85, and WFP > 0.68) and macro-averaged error (discriminative: WSP < 0.08, WD < 0.1, and WFP < 0.09 and generative: WSP < 0.11, WD < 0.12, and WFP < 0.14). The dynamical generative model on the other hand obtains better micro-averaged error (discriminative: WSP < 0.37, WD < 0.3, and WFP < 0.35 and generative: WSP < 0.15, WD < 0.2, and WFP < 0.2). The high-dimensional gait features are divided into five subsets: lower limb, upper limb, trunk, velocity, and acceleration. An instance-based feature analysis method (ReliefF) is used to assign weights to each subset of features according to its discriminatory power. The feature analysis establishes the most informative features (upper limb, lower limb, and trunk) for identifying pathological gait.

Machine Learning in Orthopedics: A Literature Review

“…In terms of gait patterns, recognition for gaits classification into healthy and pathological (Dolatabadi et al, 2017 ), an instance-based discriminative kNN was compared to a dynamical generative model like the Gaussian Process Latent Variable Model (GPLVM). Gait features acquired from kinetic skeletal tracking were divided into self pace (WSP), dual task (WD), and fast pace (WFP) and were used to train the two predictors by letting them observe single or multiple gait sequences of different kinds.…”

Convolutional neural network in upper limb functional motion analysis after stroke

“…The system requires installation in the laboratory and is therefore not mobile. The presented method in the future should be checked on data obtained from low-cost motion capture systems based on inertial sensors (Held et al, 2018;Pérez et al, 2010) or depth cameras (Chakraborty et al, 2020;Dolatabadi, Taati & Mihailidis, 2017;Bei et al, 2018).…”

Automatic Detection of Compensation During Robotic Stroke Rehabilitation Therapy

“…Compared to the other approaches, marker-free vision-based methods are more unobtrusive, convenient, economical, and adaptable [12] , [13] . Marker-free methods also demonstrated sufficient accuracy and precision for many common clinical imaging applications [13] – [19] .…”