Search research articles

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

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

Exploring the Effects of tACS Duration on Resting-State EEG: An Exploratory Within-Subject Study in Healthy Volunteers.

Journal of medical systems·2026

Same author

Melanopic equivalent daylight illuminance of 2 lx maintains and restores physiological and neurophysiological circadian rhythms in rats.

Scientific reports·2026

Same author

SleepPACNet: new convolutional neural network considering phase-amplitude coupling for automatic sleep stage classification using single-channel electroencephalogram.

Scientific reports·2026

Same author

Prediction of treatment responsiveness to home-based transcranial photobiomodulation (tPBM) intervention for cognitive decline using fNIRS concurrently recorded during tPBM.

Frontiers in aging neuroscience·2026

Same author

Deep Convolutional Neural Network-Based Detection of Gait Abnormalities in Parkinson's Disease Using Fewer Plantar Sensors in a Smart Insole.

Biosensors·2026

Same author

Altered resting-state sensorimotor network in patients with obsessive-compulsive disorder: An EEG study.

Journal of affective disorders·2026

Search research articles

Related Experiment Video

Updated: Mar 17, 2026

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization

Published on: September 20, 2024

Machine-learning-based diagnosis of schizophrenia using combined sensor-level and source-level EEG features.

Miseon Shim¹, Han-Jeong Hwang², Do-Won Kim³

¹Department of Biomedical Engineering, Hanyang University, Seoul, South Korea.

Schizophrenia Research

|July 19, 2016

Summary

This study combined sensor-level and source-level electroencephalography (EEG) features for improved machine learning-based diagnosis of schizophrenia. Combining both feature types significantly enhanced classification accuracy in distinguishing patients from healthy controls.

Keywords:

Computer-aided diagnosis Event-related potential (ERP)Machine learning Schizophrenia Source-level features

More Related Videos

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Related Experiment Videos

Last Updated: Mar 17, 2026

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization

Published on: September 20, 2024

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Area of Science:

Neuroscience
Computational Psychiatry
Biomedical Engineering

Background:

Schizophrenia diagnosis often relies on clinical observation, lacking objective biomarkers.
Machine learning (ML) applied to electroencephalography (EEG) shows promise for objective schizophrenia diagnosis.
Previous studies primarily utilized sensor-level EEG features, potentially overlooking valuable source-level information.

Purpose of the Study:

To investigate the diagnostic utility of combining sensor-level and source-level EEG features for schizophrenia classification.
To compare classification accuracy using only sensor-level features versus a combination of sensor-level and source-level features.
To identify specific brain regions associated with schizophrenia using EEG biomarkers.

Main Methods:

EEG data were collected from 34 patients with schizophrenia and 34 healthy controls during an auditory oddball task.
Both sensor-level (e.g., ERP peak amplitude, power spectrum) and source-level EEG features were extracted.
Machine learning models were employed to classify schizophrenia patients and healthy controls using the extracted features.

Main Results:

Classification accuracy was significantly higher when combining source-level and sensor-level EEG features compared to using sensor-level features alone.
Sensor-level features were predominantly identified in the frontal brain areas.
Source-level features were mainly extracted from the temporal areas, aligning with known neuropathology in schizophrenia.

Conclusions:

The integration of source-level and sensor-level EEG features offers a more accurate approach for computer-aided diagnosis of schizophrenia.
The identified brain regions (frontal and temporal) highlight key areas for future research in schizophrenia pathophysiology.
This combined feature approach represents a promising advancement for objective diagnostic tools in psychiatry.