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

BACKGROUND: Changes in gait characteristics have been reported in people with chronic neck pain (CNP). RESEARCH QUESTION: Can we classify people with and without CNP by training machine learning models with Inertial Measurement Units (IMU)-based gait kinematic data? METHODS: 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. RESULTS: 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. SIGNIFICANCE: 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.

Kinematic biomarkers of chronic neck pain measured during gait: A data-driven classification approach.

People with chronic neck pain (CNP) often present with altered gait kinematics. This paper investigates, combines, and compares the kinematic features from linear and nonlinear walking trajectories to design supervised machine learning models which differentiate asymptomatic individuals from those with CNP. For this, 126 features were extracted from seven body segments of 20 asymptomatic subjects and 20 individuals with non-specific CNP. Neighbourhood Component Analysis (NCA) was used to identify body segments and the corresponding significant features which have the maximum discriminative power for conducting classification. We assessed the efficacy of NCA combined with K- Nearest Neighbour (K-NN), Support Vector Machine and Linear Discriminant Analysis. By applying NCA, all classifiers increased their performance for both linear and nonlinear walking trajectories. Notably, features selected by NCA which magnify the classification power of the computational model were solely from the head, trunk and pelvis kinematics. Our results revealed that the nonlinear trajectory provides the best classification performance through the NCA-K-NN algorithms with an accuracy of 90%, specificity of 100% and sensitivity of 83.3%. The selected features by NCA are introduced as key biomarkers of gait kinematics for classifying non-specific CNP. This paper provides insight into changes in gait kinematics which are present in people with non-specific CNP which can be exploited for classification purposes. The result highlights the importance of curvilinear gait kinematic features which potentially could be utilized in future research to predict recurrent episodes of neck pain.

Wearable multichannel haptic device for encoding proprioception in the upper limb.

OBJECTIVE: We present the design, implementation, and evaluation of a wearable multichannel haptic system. The device is a wireless closed-loop armband driven by surface electromyography (EMG) and provides sensory feedback encoding proprioception. The study is motivated by restoring proprioception information in upper limb prostheses. APPROACH: The armband comprises eight vibrotactile actuators that generate distributed patterns of mechanical waves around the limb to stimulate perception and to transfer proportional information on the arm motion. An experimental study was conducted to assess: the sensory threshold in eight locations around the forearm, the user adaptation to the sensation provided by the device, the user performance in discriminating multiple stimulation levels, and the device performance in coding proprioception using four spatial patterns of stimulation. Eight able-bodied individuals performed reaching tasks by controlling a cursor with an EMG interface in a virtual environment. Vibrotactile patterns were tested with and without visual information on the cursor position with the addition of a random rotation of the reference control system to disturb the natural control and proprioception. MAIN RESULTS: The sensation threshold depended on the actuator position and increased over time. The maximum resolution for stimuli discrimination was four. Using this resolution, four patterns of vibrotactile activation with different spatial and magnitude properties were generated to evaluate their performance in enhancing proprioception. The optimal vibration pattern varied among the participants. When the feedback was used in closed-loop control with the EMG interface, the task success rate, completion time, execution efficiency, and average target-cursor distance improved for the optimal stimulation pattern compared to the condition without visual or haptic information on the cursor position. SIGNIFICANCE: The results indicate that the vibrotactile device enhanced the participants' perceptual ability, suggesting that the proposed closed-loop system has the potential to code proprioception and enhance user performance in the presence of perceptual perturbation.