Detection of Typical Compensatory Movements during Autonomously Performed Exercises Preventing Low Back Pain (LBP)

Abstract

With the growing number of people seeking medical advice due to low back pain (LBP), individualised physiotherapeutic rehabilitation is becoming increasingly relevant. Thirty volunteers were asked to perform three typical LBP rehabilitation exercises (Prone-Rocking, Bird-Dog and Rowing) in two categories: clinically prescribed exercise (CPE) and typical compensatory movement (TCM). Three inertial sensors were used to detect the movement of the back during exercise performance and thus generate a dataset that is used to develop an algorithm that detects typical compensatory movements in autonomously performed LBP exercises. The best feature combinations out of 50 derived features displaying the highest capacity to differentiate between CPE and TCM in each exercise were determined. For classifying exercise movements as CPE or TCM, a binary decision tree was trained with the best performing features. The results showed that the trained classifier is able to distinguish CPE from TCM in Bird-Dog, Prone-Rocking and Rowing with up to 97.7% (Head Sensor, one feature), 98.9% (Upper back Sensor, one feature) and 80.5% (Upper back Sensor, two features) using only one sensor. Thus, as a proof-of-concept, the introduced classification models can be used to detect typical compensatory movements in autonomously performed LBP exercises.

Ipsilateral versus contralateral static endurance- balance abilities among healthy college students

“… 1 , 2 , 3 , 4 Quadruped bird dog (QBD) and side bridge exercises are popular core exercises commonly used for the prevention and treatment of spine disorders and improvement of athletic performance. 5 , 6 , 7 , 8 This type of exercise typically focuses on engaging and strengthening core muscles for improved stability and endurance. 8 , 9 Exercises are easy and convenient, activate the trunk stability muscles, and are effectively used in clinical settings.…”

Online detection of compensatory strategies in human movement with supervised classification: a pilot study

“…The acquired dataset of motions is used to train a machine learning model, which can be used afterwards for classifying observed motions at test time. Previous works have explored a variety of machine-learning architectures and models for this task, ranging from decision-trees (Sellmann et al, 2022) and non-parametric methods, such as k-Nearest Neighbor classification (Cai et al, 2019) and Support Vector Machine classifiers (Taati et al, 2012;Zhi et al, 2017) to parametric deep learning methods, such as a Multi-layer Perceptron (MLP) (Lin et al, 2021) or recurrent neural networks with Long Short-Term Memory (LSTM networks) (Zhi et al, 2017). A wide range of measurements including kinematics (Taati et al, 2012;Zhi et al, 2017;Sellmann et al, 2022), applied forces (Cai et al, 2019), and muscle activity (Ma et al, 2019) have been used as an input for these data -driven classifiers.…”