Machine Learning Derived Lifting Techniques and Pain Self-Efficacy in People with Chronic Low Back Pain

Abstract

This paper proposes an innovative methodology for finding how many lifting techniques people with chronic low back pain (CLBP) can demonstrate with camera data collected from 115 participants. The system employs a feature extraction algorithm to calculate the knee, trunk and hip range of motion in the sagittal plane, Ward’s method, a combination of K-means and Ensemble clustering method for classification algorithm, and Bayesian neural network to validate the result of Ward’s method and the combination of K-means and Ensemble clustering method. The classification results and effect size show that Ward clustering is the optimal method where precision and recall percentages of all clusters are above 90, and the overall accuracy of the Bayesian Neural Network is 97.9%. The statistical analysis reported a significant difference in the range of motion of the knee, hip and trunk between each cluster, F (9, 1136) = 195.67, p < 0.0001. The results of this study suggest that there are four different lifting techniques in people with CLBP. Additionally, the results show that even though the clusters demonstrated similar pain levels, one of the clusters, which uses the least amount of trunk and the most knee movement, demonstrates the lowest pain self-efficacy.

Unsupervised machine learning for clustering forward head posture, protraction and retraction movement patterns based on craniocervical angle data in individuals with nonspecific neck pain

“…Selecting the optimal number of clusters for a given dataset is challenging. One common strategy for finding the optimal number of clusters is calculating the average silhouette score among the criteria used in the optimization process [ 22 ]. The silhouette method was used to determine the similarity within the cluster of each data point and the distance between other clusters [ 22 , 23 ].…”

“…One common strategy for finding the optimal number of clusters is calculating the average silhouette score among the criteria used in the optimization process [ 22 ]. The silhouette method was used to determine the similarity within the cluster of each data point and the distance between other clusters [ 22 , 23 ]. The silhouette scores range from 0 to 1, with higher scores indicating better cluster categorization and lower scores indicating poorer cluster categorization [ 23 ].…”

Regression-Based Machine Learning for Predicting Lifting Movement Pattern Change in People with Low Back Pain

“…Recent technological advancements, such as motion capture systems and machine learning algorithms, have shown great potential in objectively identifying and correcting movement patterns during lifting tasks or patient flow [ 7 , 8 ]. Motion capture systems can capture detailed movement data during lifting tasks, including joint angles and velocity.…”

“…There are two main applications of machine learning: classification and regression. Recent research has presented the potential of machine learning in clustering lifting movements in people with LBP and healthy people [ 7 ] or classifying thyroid disease [ 9 ]. Regression analysis is a commonly used statistical technique for modelling the associations among variables.…”

Wearable Sensors Applied in Movement Analysis

“…Moreover, machine learning identified that simple kinematic indicators were sensitive to low-back pain and therefore could gradually be used by clinicians in the assessment of CLBP patients. Machine learning can even go beyond binary classification in CLBP patients, as shown in [ 11 ]. From the video analysis of 115 CLBP participants lifting an 8 kg weight, Ward clustering suggests that there are four different lifting techniques in people with CLBP.…”