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

Real-Time Pain Assessment from Electrodermal Activity Using Deep Learning.

Sensors (Basel, Switzerland)·2026
Same author

Assessing Locomotive Syndrome Through Instrumented Five-Time Sit-to-Stand Test and Machine Learning.

Sensors (Basel, Switzerland)·2024
Same author

Diagnosis of Schizophrenia Using EEG Sensor Data: A Novel Approach with Automated Log Energy-Based Empirical Wavelet Reconstruction and Cepstral Features.

Sensors (Basel, Switzerland)·2024
Same author

Multilevel Pain Assessment with Functional Near-Infrared Spectroscopy: Evaluating Δ<i>HBO</i><sub>2</sub> and Δ<i>HHB</i> Measures for Comprehensive Analysis.

Sensors (Basel, Switzerland)·2024
Same author

Experimental Exploration of Multilevel Human Pain Assessment Using Blood Volume Pulse (BVP) Signals.

Sensors (Basel, Switzerland)·2023
Same author

A systematic review of neurophysiological sensing for the assessment of acute pain.

NPJ digital medicine·2023

Related Experiment Video

Updated: May 28, 2026

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers
08:33

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers

Published on: January 5, 2024

Connectivity-Based Pain Recognition from fNIRS: Parsimonious Subject-Independent Classification.

Mohammadreza Safari1, Maryam Ghahramani1, Raul Fernandez Rojas1

  • 1BioSIS (Biosensing & Intelligent Systems) Lab, Centre for Intelligent Computing and Systems, University of Canberra, Bruce, ACT 2617, Australia.

Sensors (Basel, Switzerland)
|May 27, 2026
PubMed
Summary
This summary is machine-generated.

Functional near-infrared spectroscopy (fNIRS) shows promise for objective pain assessment. A new subject-independent framework using fNIRS connectivity features achieved 69.6% accuracy in classifying pain levels, highlighting potential for clinical monitoring.

Keywords:
fNIRSfeature selectionfunctional and effective connectivityleave-one-subject-outmachine learningmodel parsimonypain assessment

More Related Videos

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

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Related Experiment Videos

Last Updated: May 28, 2026

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers
08:33

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers

Published on: January 5, 2024

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

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Medical Technology

Background:

  • Accurate pain assessment is difficult due to subjectivity and reliance on self-report or observation.
  • Functional near-infrared spectroscopy (fNIRS) offers a non-invasive method to study brain activity by measuring cortical hemodynamics.
  • fNIRS shows potential for developing objective pain assessment tools.

Purpose of the Study:

  • To propose and evaluate a subject-independent framework for pain state modeling using fNIRS-derived connectivity features.
  • To investigate the effectiveness of various connectivity measures (correlation, partial correlation, coherence, Granger causality) for pain assessment.
  • To determine an optimal feature set size for reliable pain classification.

Main Methods:

  • Utilized the AI4PAIN dataset with 65 participants and 24 fNIRS channels.
  • Extracted functional and effective connectivity features from hemodynamic signals (HbO2, HHb, HbT).
  • Employed leave-one-subject-out cross-validation for a three-class classification task (No Pain, Low Pain, High Pain).
  • Applied mutual-information-based feature selection to identify a reduced, optimal feature set.

Main Results:

  • A reduced feature set of 700 connectivity features achieved performance comparable to the full set (1380 features).
  • The framework achieved a best accuracy of 69.6%, with HHb signals yielding the highest accuracy.
  • High Pain instances were detectable with approximately 50% recall using the optimized feature set.

Conclusions:

  • Connectivity-based, subject-independent pain assessment using fNIRS is feasible.
  • fNIRS holds significant potential for objective and reliable clinical pain monitoring.
  • Granger causality connections were predominantly selected, indicating stable patterns in pain processing.