January 1, 2020Open Access

Self-Management of Low Back Pain Using Neural Network

Q: What is the clinical evidence from this study?

Study design: Other. Population: Low back pain (n=33). Intervention: Wearable sensor-based activity recognition using feedforward artificial neural network. Primary outcome: Activity classification accuracy (Weighted Average F-Measure).

Key Result

A feedforward artificial neural network using wearable tri-axial accelerometer data classified nine daily activities with a weighted average F-measure of 0.824 to aid in low back pain self-management.

Structured PICO

Population

33 participants performing 9 daily activities (6 ambulatory and 3 sedentary) for approximately 3 minutes each, recorded using wrist and thigh accelerometers.

Intervention

Activity monitoring and classification using a feedforward Artificial Neural Network based on tri-axial accelerometer data.

Outcome

Activity classification accuracy (distinguishing between 9 common daily activities)

A feedforward artificial neural network using wrist and thigh accelerometer data can effectively classify nine daily activities to aid in the self-management of low back pain.

Abstract

Low back pain (LBP) is a morbid condition that has afflicted several citizens in Europe. It has negatively impacted the European economy due to several man-days lost, with bed rest and forced inactivity being the usual LBP care and management steps. Direct models, which incorporate various regression analyses, have been executed for the investigation of this premise due to the simplicity of translation. However, such straight models fail to completely consider the impact of association brought about by a mix of nonlinear connections and autonomous factors.In this paper, we discuss a system that aids decision-making regarding the best-suited support system for LBP, allowing the individual to avail of reinforcement and improvement in its self-management. These activities are monitored with the help of a wearable sensor that helps in their detection and their classification as those that soothe or aggravate LBP and hence, should or should not be performed. This system helps the patients set their own boundaries and milestones with respect to suitable activities. This system also does windowing and feature extraction. The present study is an empirical and comparative analysis of the most suitable activities that patients suffering from low back pain can select. The evaluation shows that the system can distinguish between nine common daily activities effectively and helps self-monitor these activities for the effi- cient management of LBP.

Mark Helpful

Bookmark

Relay

View Full Paper

Mark Helpful

Bookmark

Relay

View Full Paper

Cite This Study

Sharma et al. (Wed,) conducted a other in Low back pain (n=33). Wearable sensor-based activity recognition using feedforward artificial neural network was evaluated on Activity classification accuracy (Weighted Average F-Measure). A feedforward artificial neural network using wearable tri-axial accelerometer data classified nine daily activities with a weighted average F-measure of 0.824 to aid in low back pain self-management.

synapsesocial.com/papers/6a1c7391973ffece4bc3d65a https://doi.org/https://doi.org/10.32604/cmc.2020.012251

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: