A machine learning approach for the identification of kinematic biomarkers of chronic neck pain during single- and dual-task gait

• Published in: Gait & posture Vol. 96; pp. 81 - 86
• Main Authors: Jiménez-Grande, David, Farokh Atashzar, S., Devecchi, Valter, Martinez-Valdes, Eduardo, Falla, Deborah
• Format: Journal Article
• Language: English
• Published: England Elsevier B.V 01-07-2022
• Subjects: Biomarkers; Biomechanical Phenomena; Chronic neck pain; Chronic Pain - diagnosis; Gait; Gait kinematics; Humans; Machine Learning; Neck Pain - diagnosis; Walking; Wearable sensors; Biomarkers; Chronic neck pain; Wearable sensors; Machine learning; Gait kinematics
• ISSN: 0966-6362; 1879-2219
• DOI: 10.1016/j.gaitpost.2022.05.015

Changes in gait characteristics have been reported in people with chronic neck pain (CNP).
Can we classify people with and without CNP by training machine learning models with Inertial Measurement Units (IMU)-based gait kinematic data?
Eighteen asymptomatic individuals and 21 participants with CNP were recruited for the study and performed two gait trajectories, (1) linear walking with their head straight (single-task) and (2) linear walking with continuous head-rotation (dual-task). Kinematic data were recorded from three IMU sensors attached to the forehead, upper thoracic spine (T1), and lower thoracic spine (T12). Temporal and spectral features were extracted to generate the dataset for both single- and dual-task gait. To evaluate the most significant features and simultaneously reduce the dataset size, the Neighbourhood Component Analysis (NCA) method was utilized. Three supervised models were applied, including K-Nearest Neighbour, Support Vector Machine, and Linear Discriminant Analysis to test the performance of the most important temporal and spectral features.
The performance of all classifiers increased after the implementation of NCA. The best performance was achieved by NCA-Support Vector Machine with an accuracy of 86.85%, specificity of 83.30%, and sensitivity of 92.85% during the dual-task gait using only nine features.
The results present a data-driven approach and machine learning-based methods to identify test conditions and features from high-dimensional data obtained during gait for the classification of people with and without CNP.
•Machine learning was used to classify people with and without neck pain.•Classification was based on gait features for both single- and dual-task gait.•Results highlight the importance of gait frequency features for the classification.•Kinematic data extracted during dual-task gait emphasised group differences.