Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Toward Multi-Dimensional Depression Assessment: EEG-Based Machine Learning and Neurophysiological Interpretation for Diagnosis, Severity, and Cognitive Decline.

Brain sciences·2026
Same author

A Hybrid CNN-SVM Approach for ECG-Based Multi-Class Differential Diagnosis of PTSD, Depression, and Panic Attack.

Biosensors·2026
Same author

Cognitive load in cyclists while navigating in traffic: Effects of static and dynamic route events on neural activity of cyclists measured by fNIRS.

PloS one·2025
Same author

Diffusion Model-Based Augmentation Using Asymmetric Attention Mechanisms for Cardiac MRI Images.

Diagnostics (Basel, Switzerland)·2025
Same author

SHAP-Based Identification of Potential Acoustic Biomarkers in Patients with Post-Thyroidectomy Voice Disorder.

Diagnostics (Basel, Switzerland)·2025
Same author

ECG Signal Analysis for Detection and Diagnosis of Post-Traumatic Stress Disorder: Leveraging Deep Learning and Machine Learning Techniques.

Diagnostics (Basel, Switzerland)·2025

Related Experiment Video

Updated: Jan 13, 2026

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

1.2K

Explainable AI for pain perception: subject-independent EEG decoding using DeepSHAP and CNNs.

Feyzi Alkım Aktaş1,2, Aykut Eken1,3, Osman Erogul1

  • 1Department of Biomedical Engineering, TOBB University of Economics and Technology, Ankara, Turkey.

Biomedical Physics & Engineering Express
|January 7, 2026
PubMed
Summary

This study uses explainable deep learning to decode pain levels from electroencephalography (EEG) signals with 95.85% accuracy. The method identifies specific brainwave patterns associated with different pain intensities, enabling objective pain monitoring.

Keywords:
BCIEEGLOSOdeep learningexplainable AImachine learningpain decoding

More Related Videos

Monitoring Acupuncture Effects on Human Brain by fMRI
09:55

Monitoring Acupuncture Effects on Human Brain by fMRI

Published on: April 8, 2010

15.9K
Multi-Modal Signals for Analyzing Pain Responses to Thermal and Electrical Stimuli
09:16

Multi-Modal Signals for Analyzing Pain Responses to Thermal and Electrical Stimuli

Published on: April 5, 2019

11.4K

Related Experiment Videos

Last Updated: Jan 13, 2026

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

1.2K
Monitoring Acupuncture Effects on Human Brain by fMRI
09:55

Monitoring Acupuncture Effects on Human Brain by fMRI

Published on: April 8, 2010

15.9K
Multi-Modal Signals for Analyzing Pain Responses to Thermal and Electrical Stimuli
09:16

Multi-Modal Signals for Analyzing Pain Responses to Thermal and Electrical Stimuli

Published on: April 5, 2019

11.4K

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Accurate pain assessment is crucial for patient care, especially for individuals with communication impairments.
  • Current pain monitoring methods often rely on subjective reporting, limiting their effectiveness in certain clinical populations.

Purpose of the Study:

  • To investigate the feasibility of decoding pain levels from electroencephalography (EEG) signals using explainable deep learning models.
  • To develop a subject-independent method for objective pain assessment.

Main Methods:

  • EEG data was collected from 50 subjects experiencing low and high pain stimuli.
  • A 1D convolutional neural network (CNN) was trained using leave-one-subject-out (LOSO) cross-validation for subject-independent classification.
  • DeepSHAP (SHapley Additive exPlanations) was employed to identify frequency-specific EEG features contributing to pain classification.

Main Results:

  • The CNN model achieved a high classification accuracy of 95.85%, surpassing traditional machine learning classifiers.
  • Explainability analysis revealed that increased beta band activity (14-15 Hz) correlated with high pain.
  • Alpha (11-12 Hz), theta, and delta band activities were associated with lower pain states.

Conclusions:

  • Explainable deep learning offers a promising approach for real-time, subject-independent pain decoding from EEG.
  • The findings support the integration of explainable artificial intelligence (XAI) techniques into EEG-based brain-computer interface (BCI) systems for objective pain monitoring.