Using a Motion Sensor to Categorize Nonspecific Low Back Pain Patients: A Machine Learning Approach.

Masoud Abdollahi,Sajad Ashouri,Nasibeh Azadeh-Fard,Kinda Khalaf,Mohsen Abedi,Mohamad Parnianpour,Ehsan Rashedi

doi:10.3390/s20123600

Abstract

Nonspecific low back pain (NSLBP) constitutes a critical health challenge that impacts millions of people worldwide with devastating health and socioeconomic consequences. In today’s clinical settings, practitioners continue to follow conventional guidelines to categorize NSLBP patients based on subjective approaches, such as the STarT Back Screening Tool (SBST). This study aimed to develop a sensor-based machine learning model to classify NSLBP patients into different subgroups according to quantitative kinematic data, i.e., trunk motion and balance-related measures, in conjunction with STarT output. Specifically, inertial measurement units (IMU) were attached to the trunks of ninety-four patients while they performed repetitive trunk flexion/extension movements on a balance board at self-selected pace. Machine learning algorithms (support vector machine (SVM) and multi-layer perceptron (MLP)) were implemented for model development, and SBST results were used as ground truth. The results demonstrated that kinematic data could successfully be used to categorize patients into two main groups: high vs. low-medium risk. Accuracy levels of ~75% and 60% were achieved for SVM and MLP, respectively. Additionally, among a range of variables detailed herein, time-scaled IMU signals yielded the highest accuracy levels (i.e., ~75%). Our findings support the improvement and use of wearable systems in developing diagnostic and prognostic tools for various healthcare applications. This can facilitate development of an improved, cost-effective quantitative NSLBP assessment tool in clinical and home settings towards effective personalized rehabilitation.

Highlights

Considered as the most common cause of disability, as well as the most widespread musculoskeletal disorder worldwide, low back pain (LBP) remains a tremendous health and socioeconomic challenge of pandemic proportions [1,2]
Since we found no other existing studies which classified nonspecific low back pain (NSLBP) patients, we used machine-learning-based models developed for other forms of clinical decision making for comparison [52,53,54]
This study explored the capability of using a simple cost-effective motion-capture sensor, in conjunction with STarT—the current gold standard clinical assessment NSLBP questionnaire—as a potential quantitative decision-making tool in clinical settings and telemedicine/rehabilitation applications

Summary

Introduction

Considered as the most common cause of disability, as well as the most widespread musculoskeletal disorder worldwide, low back pain (LBP) remains a tremendous health and socioeconomic challenge of pandemic proportions [1,2]. It is estimated that around 84% of the global adult population will experience LBP at least once during their lifetimes, where every second, up to 33% adults, or one in every three people, suffer an LBP episode [3,4,5]. In both developed and developing countries, Sensors 2020, 20, 3600; doi:10.3390/s20123600 www.mdpi.com/journal/sensors. LBP has been identified as the fourth-most frequent condition warranting a visit to a physician, the fifth-most common reason for hospitalization, and the third-most frequent cause for surgery [4,6]. Researchers confirm that there is no “one-size-fits-all” management approach for NSLBP patients, given the elusive etiology, complexity, and trigger heterogeneity among sufferers [8,9]

Objectives

Methods

Results

Discussion

Conclusion