Abstract
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.
Highlights
IntroductionConcussion injuries present a public health challenge that impacts many different professional and amateur sports [1], military training and deployment [2,3], and large pediatric [4], elderly [5], and civilian [6] populations
Phybrata Power (Eo + eyes closed (Ec))/two for the baseline and concussion populations are (i) Baseline: sample size = 83, Mean = 0.355, standard deviation (SD) = 0.104; (ii) Concussion: sample size = 92, Mean = 1.348, SD = 0.955. Based on this effect size, the present study cohort should allow a predictive power greater than 0.90 using an α value of 0.05. This high expected predictive power, together with the consistent performance observed throughout machine learning (ML) training, testing, and validation, indicate that the present results present a valid assessment of the classification performance of the ML models that we investigated in combination with the phybrata sensor data
We investigated the performance of four ML models (SVM, Random Forest Classifier (RF), XGB, convolutional neural network (CNN)) used to refine the neurophysiological impairment assessment capabilities of phybrata wearable sensors, utilizing data from a previously studied concussion patient cohort
Summary
Concussion injuries present a public health challenge that impacts many different professional and amateur sports [1], military training and deployment [2,3], and large pediatric [4], elderly [5], and civilian [6] populations. A concussion can lead to disruptions that are widespread throughout the brain [1,7]. Patients can suffer from impairments to multiple physiological systems in their bodies [7], including the central nervous system (CNS; brain and spinal cord), peripheral nervous system (PNS; somatic, autonomic), sensory systems (visual, vestibular, somatosensory), neurovascular system, and musculoskeletal system. If not properly diagnosed and treated, these impairments can persist for months or years and negatively impact many aspects of the patient’s health. Extensive studies over the past decade have established the link between repetitive head impacts and long-term degenerative decline such as chronic traumatic encephalopathy (CTE) [8]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
