RESUMO
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.
Assuntos
Aprendizado de Máquina , Redes Neurais de Computação , Algoritmos , Humanos , Monitorização Fisiológica , Máquina de Vetores de SuporteRESUMO
OBJECTIVE: To assess the utility of a head-mounted wearable inertial motion unit (IMU)-based physiological vibration acceleration ("phybrata") sensor to support the clinical diagnosis of concussion, classify and quantify specific concussion-induced physiological system impairments and sensory reweighting, and track individual patient recovery trajectories. METHODS: Data were analyzed from 175 patients over a 12-month period at three clinical sites. Comprehensive clinical concussion assessments were first completed for all patients, followed by testing with the phybrata sensor. Phybrata time series data and spatial scatter plots, eyes open (Eo) and eyes closed (Ec) phybrata powers, average power (Eo+Ec)/2, Ec/Eo phybrata power ratio, time-resolved phybrata spectral density (TRPSD) distributions, and receiver operating characteristic (ROC) curves are compared for individuals with no objective impairments and those clinically diagnosed with concussions and accompanying vestibular impairment, other neurological impairment, or both vestibular and neurological impairments. Finally, pre- and post-injury phybrata case report results are presented for a participant who was diagnosed with a concussion and subsequently monitored during treatment, rehabilitation, and return-to-activity clearance. RESULTS: Phybrata data demonstrate distinct features and patterns for individuals with no discernable clinical impairments, diagnosed vestibular pathology, and diagnosed neurological pathology. ROC curves indicate that the average power (Eo+Ec)/2 may be utilized to support clinical diagnosis of concussion, while Eo and Ec/Eo may be utilized as independent measures to confirm accompanying neurological and vestibular impairments, respectively. All 3 measures demonstrate area under the curve (AUC), sensitivity, and specificity above 90% for their respective diagnoses. Phybrata spectral analyses demonstrate utility for quantifying the severity of concussion-induced physiological impairments, sensory reweighting, and subsequent monitoring of improvements throughout treatment and rehabilitation. CONCLUSION: Phybrata testing assists with objective concussion diagnosis and provides an important adjunct to standard concussion assessment tools by objectively ascertaining neurological and vestibular impairments, guiding targeted rehabilitation strategies, monitoring recovery, and assisting with return-to-sport/work/learn decision-making.
RESUMO
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.