Objective: To assess the utility of a head-mounted wearable inertial motion unit (IMU)-based sensor and 3 proposed measures of postural sway to detect outliers in athletic populations at risk of balance impairments. Methods: Descriptive statistics are used to define a normative reference range of postural sway (eyes open and eyes closed) in a cross-sectional sample of 347 college students using a wireless head-mounted IMU-based sensor. Three measures of postural sway were derived: linear sway power, eyes closed vs eyes open sway power ratio (Ec/Eo ratio), and weight-bearing asymmetry (L-R ratio), and confidence intervals for these measures were calculated. Questionnaires were used to identify potentially confounding state variables. A prospective study of postural sway changes in 47 professional, college, and high school athletes was then carried out in on-field settings to provide estimates of session-to-session variability and the influence of routine physical activity on sway measures. Finally, pre-post-injury changes in sway are measured for a participant who was diagnosed with a concussion. Results: Despite the heterogenous population and sampling environments, well-defined confidence intervals were established for all 3 sway measures. Men demonstrated significantly greater sway than women. Two state variables significantly increased sway: the use of nicotine and prescription medications. In the athletes, session-to-session variability and changes due to routine physical activity remained well within 95% confidence intervals defined by the cross-sectional sample for all 3 sway measures. The increase in sway power following a diagnosed concussion was more than an order of magnitude greater than the increases due to session-to-session variability, physical activity, or other participant state variables. Conclusion: The proposed postural sway measures and head-mounted wearable sensor demonstrate analytic utility for on-field detection of abnormal sway that could be potentially useful when making remove-from-activity and return-to-activity decisions for athletes at risk of impact-induced balance impairments.
Concussion injuries remain a significant public health challenge. A significant unmet clinical need remains for tools that allow related physiological impairments and longer-term health risks to be identified earlier, better quantified, and more easily monitored over time. We address this challenge by combining a head-mounted wearable inertial motion unit (IMU)-based physiological vibration acceleration (“phybrata”) sensor and several candidate machine learning (ML) models. The performance of this solution is assessed for both binary classification of concussion patients and multiclass predictions of specific concussion-related neurophysiological impairments. Results are compared with previously reported approaches to ML-based concussion diagnostics. Using phybrata data from a previously reported concussion study population, four different machine learning models (Support Vector Machine, Random Forest Classifier, Extreme Gradient Boost, and Convolutional Neural Network) are first investigated for binary classification of the test population as healthy vs. concussion (Use Case 1). Results are compared for two different data preprocessing pipelines, Time-Series Averaging (TSA) and Non-Time-Series Feature Extraction (NTS). Next, the three best-performing NTS models are compared in terms of their multiclass prediction performance for specific concussion-related impairments: vestibular, neurological, both (Use Case 2). For Use Case 1, the NTS model approach outperformed the TSA approach, with the two best algorithms achieving an F1 score of 0.94. For Use Case 2, the NTS Random Forest model achieved the best performance in the testing set, with an F1 score of 0.90, and identified a wider range of relevant phybrata signal features that contributed to impairment classification compared with manual feature inspection and statistical data analysis. The overall classification performance achieved in the present work exceeds previously reported approaches to ML-based concussion diagnostics using other data sources and ML models. This study also demonstrates the first combination of a wearable IMU-based sensor and ML model that enables both binary classification of concussion patients and multiclass predictions of specific concussion-related neurophysiological impairments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.