Search research articles

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Neurobiological subtypes in alcohol use disorder and their phenotypic and clinical profiles.

Molecular psychiatry·2026

Same author

Altered resting state EEG microstate dynamics in acute concussion in adolescents.

Scientific reports·2026

Same author

GLP-1 Receptor Agonist Medications: Interactions With Addiction Neurocircuitry.

Biological psychiatry·2026

Same author

Environmental, Health, and Psychological Factors Predict Alcohol Sipping in Childhood: A Machine Learning Analysis of the ABCD Study.

JAACAP open·2025

Same author

Subtypes of cocaine use disorder and their neurobehavioral profiles.

Translational psychiatry·2025

Same author

Contrast-Based Artifact Removal Enables Microstate Analysis in Ambulatory EEG.

IEEE transactions on bio-medical engineering·2025

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Nov 2, 2025

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

Recurrent neural network-based acute concussion classifier using raw resting state EEG data.

Karun Thanjavur¹, Arif Babul², Brandon Foran³

¹Department of Physics and Astronomy, University of Victoria, Victoria, BC, V8P 5C2, Canada. karun@uvic.ca.

Scientific Reports

|June 12, 2021

Summary

A new deep learning model uses raw EEG data to accurately detect concussions in adolescent athletes. This breakthrough offers a potential objective, easy-to-use tool for diagnosing sports-related brain injuries.

More Related Videos

Objectively Assessing Sports Concussion Utilizing Visual Evoked Potentials

Objectively Assessing Sports Concussion Utilizing Visual Evoked Potentials

Published on: April 27, 2021

A Neuroscientific Approach to the Examination of Concussions in Student-Athletes

A Neuroscientific Approach to the Examination of Concussions in Student-Athletes

Published on: December 8, 2014

Related Experiment Videos

Last Updated: Nov 2, 2025

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

Objectively Assessing Sports Concussion Utilizing Visual Evoked Potentials

Objectively Assessing Sports Concussion Utilizing Visual Evoked Potentials

Published on: April 27, 2021

A Neuroscientific Approach to the Examination of Concussions in Student-Athletes

A Neuroscientific Approach to the Examination of Concussions in Student-Athletes

Published on: December 8, 2014

Area of Science:

Neuroscience
Medical Technology
Artificial Intelligence

Background:

Concussion is a prevalent global health issue, particularly affecting children and adolescents.
Current concussion diagnosis lacks objective, brain-based methods, posing challenges for athletes' management and recovery.
Repeated concussions increase the risk of long-term neurological and mental health issues.

Purpose of the Study:

To develop an objective, brain-based method for diagnosing acute concussions in adolescent athletes.
To introduce a deep learning model capable of classifying concussions using resting-state electroencephalography (EEG) data.
To address the need for a clinically-accepted, automated concussion detection system.

Main Methods:

A deep learning long short-term memory (LSTM) recurrent neural network was employed.
The model utilized short, resting-state EEG samples (90 seconds) from adolescent athletes.
Data from 27 concussed and 35 non-concussed male adolescent athletes were used for training and validation.

Main Results:

The LSTM classifier achieved over 90% accuracy in distinguishing between concussed and non-concussed athletes.
An Area Under the ROC Curve (ROC/AUC) of 0.971 was obtained, indicating high diagnostic performance.
The model successfully used raw, unfiltered EEG data without artifact removal or feature extraction.

Conclusions:

This study presents the first high-performing concussion classifier based solely on easily acquired, resting-state raw EEG data.
The developed classifier shows significant promise for creating an objective, user-friendly, and automated system for individual concussion diagnosis.
This approach could revolutionize concussion management by providing timely and accurate brain-based assessments.