Phybrata Sensors and Machine Learning for Enhanced Neurophysiological Diagnosis and Treatment

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...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Alex J. Hope, Utkarsh Vashisth, Matthew J. Parker, Andreas B. Ralston, Joshua M. Roper, John D. Ralston
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	machine learning wearable sensor concussion physiological impairment vestibular neurological Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/a7ac4205b47a4d319ee59edca5b02e47
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a7ac4205b47a4d319ee59edca5b02e47
record_format	dspace
spelling	oai:doaj.org-article:a7ac4205b47a4d319ee59edca5b02e472021-11-11T19:20:20ZPhybrata Sensors and Machine Learning for Enhanced Neurophysiological Diagnosis and Treatment10.3390/s212174171424-8220https://doaj.org/article/a7ac4205b47a4d319ee59edca5b02e472021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7417https://doaj.org/toc/1424-8220Concussion 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.Alex J. HopeUtkarsh VashisthMatthew J. ParkerAndreas B. RalstonJoshua M. RoperJohn D. RalstonMDPI AGarticlemachine learningwearable sensorconcussionphysiological impairmentvestibularneurologicalChemical technologyTP1-1185ENSensors, Vol 21, Iss 7417, p 7417 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	machine learning wearable sensor concussion physiological impairment vestibular neurological Chemical technology TP1-1185
spellingShingle	machine learning wearable sensor concussion physiological impairment vestibular neurological Chemical technology TP1-1185 Alex J. Hope Utkarsh Vashisth Matthew J. Parker Andreas B. Ralston Joshua M. Roper John D. Ralston Phybrata Sensors and Machine Learning for Enhanced Neurophysiological Diagnosis and Treatment
description	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.
format	article
author	Alex J. Hope Utkarsh Vashisth Matthew J. Parker Andreas B. Ralston Joshua M. Roper John D. Ralston
author_facet	Alex J. Hope Utkarsh Vashisth Matthew J. Parker Andreas B. Ralston Joshua M. Roper John D. Ralston
author_sort	Alex J. Hope
title	Phybrata Sensors and Machine Learning for Enhanced Neurophysiological Diagnosis and Treatment
title_short	Phybrata Sensors and Machine Learning for Enhanced Neurophysiological Diagnosis and Treatment
title_full	Phybrata Sensors and Machine Learning for Enhanced Neurophysiological Diagnosis and Treatment
title_fullStr	Phybrata Sensors and Machine Learning for Enhanced Neurophysiological Diagnosis and Treatment
title_full_unstemmed	Phybrata Sensors and Machine Learning for Enhanced Neurophysiological Diagnosis and Treatment
title_sort	phybrata sensors and machine learning for enhanced neurophysiological diagnosis and treatment
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/a7ac4205b47a4d319ee59edca5b02e47
work_keys_str_mv	AT alexjhope phybratasensorsandmachinelearningforenhancedneurophysiologicaldiagnosisandtreatment AT utkarshvashisth phybratasensorsandmachinelearningforenhancedneurophysiologicaldiagnosisandtreatment AT matthewjparker phybratasensorsandmachinelearningforenhancedneurophysiologicaldiagnosisandtreatment AT andreasbralston phybratasensorsandmachinelearningforenhancedneurophysiologicaldiagnosisandtreatment AT joshuamroper phybratasensorsandmachinelearningforenhancedneurophysiologicaldiagnosisandtreatment AT johndralston phybratasensorsandmachinelearningforenhancedneurophysiologicaldiagnosisandtreatment
_version_	1718431543185113088

Phybrata Sensors and Machine Learning for Enhanced Neurophysiological Diagnosis and Treatment

Ejemplares similares