Objective Classification of Dynamic Balance Using a Single Wearable Sensor

Abstract

Abstract:The Y Balance Test (YBT) is one of the most commonly used dynamic balance assessments in clinical and research settings. This study sought to investigate the ability of a single lumbar inertial measurement unit (IMU) to discriminate between the three YBT reach directions, and between pre and post-fatigue balance performance during the YBT. Fifteen subjects (age: 23±4, weight: 67.5±8, height: 175±8, BMI: 22±2) were fitted with a lumbar IMU. Three YBTs were performed on the dominant leg at 0, 10 and 20 minutes. A modified Wingate fatiguing intervention was conducted to introduce a balance deficit. This was followed immediately by three post-fatigue YBTs. Features were extracted from the IMU, and used to train and evaluate the random-forest classifiers. Reach direction classification achieved an accuracy of 97.80%, sensitivity of 97.86±0.89% and specificity of 98.90±0.56%. "Normal" and "abnormal" balance performance, as influenced by fatigue, was classified with an accuracy of 61.90%-71.43%, sensitivity of 61.90%-69.04% and specificity of 61.90%-78.57% depending on which reach direction was chosen. These results demonstrate that a single lumbar IMU is capable of accurately distinguishing between the different YBT reach directions and can classify between pre and post-fatigue balance with moderate levels of accuracy.

A Wearable Sensor-Based Exercise Biofeedback System: Mixed Methods Evaluation of Formulift

“…These range from early stage rehabilitation exercises such as heel slides and straight leg raises [ 12 ] to more complex S&C exercises such as bodyweight squats [ 14 ], lunges [ 15 ], and single-leg squats [ 13 , 16 , 17 ]. More cost-effective and practical systems using a single body-worn IMU have also been shown to be effective in the analysis of exercise technique [ 13 , 15 , 18 , 19 ]. Such single IMU-based systems are considered preferential where they can provide equivalent exercise analysis quality to multiple IMU setups.…”

Investigating normal day to day variations of postural control in a healthy young population using Wii balance boards

“…This may be applied in clinical practice through long-term tracking of injury/ pathology risk, recovery and response to interventions. For example, fatigue has been shown to negatively influence PC performance [15,16], potentially increasing an individual's propensity to injury [17]. As such, longitudinal monitoring paradigms may be used to model an individual's 'normal' PC, with large alterations outside of an acceptable range aiding in the identification of those who may be at an increased risk of pathology.…”

Reliability, Validity and Utility of Inertial Sensor Systems for Postural Control Assessment in Sport Science and Medicine Applications: A Systematic Review

“…Twelve studies assessed discriminant validity in healthy cohorts, assessing the ability of inertial sensor systems to discriminate between known stance, visual, hearing, fatigue or taping conditions [25,28,32,41,[43][44][45][46][47][48][49][50].…”

“…Two studies investigated the ability of a lumbar mounted sensor to differentiate fatigue and nonfatigued dynamic PC performance during the YBT. Johnston et al [49] demonstrated that a machine learning approach can classify PC performance with 61.9 -71.4% accuracy, and differentiate YBT reach directions with 97.8% accuracy. Additionally, Johnston et al [45] reported significant differences between fatigued and non-fatigued performance, capturing alterations in balance not detected by the traditional measure, suggesting greater sensitivity.…”