Classification Model to Discriminate People with and without Pain in the Lower Back and Lower Limb using Symmetry Data

Classification Model to Discriminate People with and without Pain in the Lower Back and Lower Limb using Symmetry Data

Background Multiple factors are associated with lower back and lower limb (LB & LL) pain, such as impaired muscle strength, balance, endurance, and motor control, and altered movement patterns. Symmetry of motion, strength and balance are goals for rehabilitation in patients with LB & LL pain. When classifying patients before or during on- and offline assessment, it is necessary that an easy to use functional test be available for clinicians. Purpose To establish a classification tree model for discriminating people with and without LB & LL pain during walking using symmetry values from side plank endurance test, hip abductor strength test, one-leg standing time tests and walking tests. Study design Cross-sectional study Methods A total of 100 subjects with and without LB & LL pain during walking participated. We measured the side plank endurance time, hip abductor strength and one-leg standing time with eyes open and closed, and the sagittal and frontal head angles at comfortable and fast walking speeds using a wearable wireless earbud sensor and calculated the symmetry index (SI) for each test. Classification and regression tree analysis with 10-fold cross validation was used to develop the classification model. Results The classification tree had 83% accuracy for discriminating people with and without LB & LL pain during walking. The most important factor for classification was the SI of the one-leg standing time with eyes closed; the second-most important factor was the SI of the frontal head angle during fast walking. Conclusions The present classification model can differentiate people with and without LB & LL pain during walking based on symmetry data acquired during functional tests, such as one-leg standing time with the eyes closed and fast walking test using the wearable device. Based on the present results, clinicians can classify patients before and during on- and offline assessments using cutoff values of the SI of the one-leg standing test with eyes closed of 63.88%, and of frontal head motion during a fast-walking test of 63.31%.