Electroencephalography-Based Pain Detection Using Kernel Spectral Connectivity Network with Preserved Spatio-Frequency Interpretability

Chronic pain leads to not only physical discomfort but also psychological challenges, such as depression and anxiety, which contribute to a substantial healthcare burden. Pain detection and assessment remains a challenge due to its subjective nature. Current clinical methods may be inaccurate or unf...

Full description

Saved in:
Bibliographic Details
Main Authors: Santiago Buitrago-Osorio, Julian Gil-González, Andrés Marino Álvarez-Meza, David Cardenas-Peña, Alvaro Orozco-Gutierrez
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/9/4804
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850278553739853824
author Santiago Buitrago-Osorio
Julian Gil-González
Andrés Marino Álvarez-Meza
David Cardenas-Peña
Alvaro Orozco-Gutierrez
author_facet Santiago Buitrago-Osorio
Julian Gil-González
Andrés Marino Álvarez-Meza
David Cardenas-Peña
Alvaro Orozco-Gutierrez
author_sort Santiago Buitrago-Osorio
collection DOAJ
description Chronic pain leads to not only physical discomfort but also psychological challenges, such as depression and anxiety, which contribute to a substantial healthcare burden. Pain detection and assessment remains a challenge due to its subjective nature. Current clinical methods may be inaccurate or unfeasible for non-verbal patients. Consequently, Electroencephalography (EEG) has emerged as a promising non-invasive tool for pain detection. However, EEG-based pain detection faces challenges such as noise, volume conduction effects, and high inter-subject variability. Deep learning (DL) models have shown potential in overcoming these challenges by extracting nonlinear and discriminative patterns. Despite advancements, these models often require a subject-dependent approach and lack of interpretability. To address these limitations, we propose a threefold DL-based framework for coding EEG-based pain detection patterns. (i) We employ the Kernel Cross-Spectral Gaussian Functional Connectivity Network (KCS-FCnet) to code pairwise channel dependencies for pain detection. (ii) Furthermore, we introduce a frequency-based strategy for class activation mapping to visualize pertinent pain EEG features, thereby enhancing visual interpretability through spatio-frequency patterns. (iii) Further, to account for subject variability, we conduct cross-subject analysis and grouping, clustering individuals based on similar pain detection performance, functional connectivity patterns, sex, and age. We evaluate our model using the Brain Mediators of Pain dataset and demonstrate its robustness through subject-dependent and cross-subject generalization tasks for pain detection on non-verbal patients.
format Article
id doaj-art-37f4472cd89044758341a2024ce71a56
institution OA Journals
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-37f4472cd89044758341a2024ce71a562025-08-20T01:49:27ZengMDPI AGApplied Sciences2076-34172025-04-01159480410.3390/app15094804Electroencephalography-Based Pain Detection Using Kernel Spectral Connectivity Network with Preserved Spatio-Frequency InterpretabilitySantiago Buitrago-Osorio0Julian Gil-González1Andrés Marino Álvarez-Meza2David Cardenas-Peña3Alvaro Orozco-Gutierrez4Signal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, ColombiaAutomatics Research Group, Universidad Tecnológica de Pereira (UTP), Pereira 660003, ColombiaSignal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, ColombiaAutomatics Research Group, Universidad Tecnológica de Pereira (UTP), Pereira 660003, ColombiaAutomatics Research Group, Universidad Tecnológica de Pereira (UTP), Pereira 660003, ColombiaChronic pain leads to not only physical discomfort but also psychological challenges, such as depression and anxiety, which contribute to a substantial healthcare burden. Pain detection and assessment remains a challenge due to its subjective nature. Current clinical methods may be inaccurate or unfeasible for non-verbal patients. Consequently, Electroencephalography (EEG) has emerged as a promising non-invasive tool for pain detection. However, EEG-based pain detection faces challenges such as noise, volume conduction effects, and high inter-subject variability. Deep learning (DL) models have shown potential in overcoming these challenges by extracting nonlinear and discriminative patterns. Despite advancements, these models often require a subject-dependent approach and lack of interpretability. To address these limitations, we propose a threefold DL-based framework for coding EEG-based pain detection patterns. (i) We employ the Kernel Cross-Spectral Gaussian Functional Connectivity Network (KCS-FCnet) to code pairwise channel dependencies for pain detection. (ii) Furthermore, we introduce a frequency-based strategy for class activation mapping to visualize pertinent pain EEG features, thereby enhancing visual interpretability through spatio-frequency patterns. (iii) Further, to account for subject variability, we conduct cross-subject analysis and grouping, clustering individuals based on similar pain detection performance, functional connectivity patterns, sex, and age. We evaluate our model using the Brain Mediators of Pain dataset and demonstrate its robustness through subject-dependent and cross-subject generalization tasks for pain detection on non-verbal patients.https://www.mdpi.com/2076-3417/15/9/4804pain detectionEEGneural networkskernel methodsinterpretabilitycross-subject analysis
spellingShingle Santiago Buitrago-Osorio
Julian Gil-González
Andrés Marino Álvarez-Meza
David Cardenas-Peña
Alvaro Orozco-Gutierrez
Electroencephalography-Based Pain Detection Using Kernel Spectral Connectivity Network with Preserved Spatio-Frequency Interpretability
Applied Sciences
pain detection
EEG
neural networks
kernel methods
interpretability
cross-subject analysis
title Electroencephalography-Based Pain Detection Using Kernel Spectral Connectivity Network with Preserved Spatio-Frequency Interpretability
title_full Electroencephalography-Based Pain Detection Using Kernel Spectral Connectivity Network with Preserved Spatio-Frequency Interpretability
title_fullStr Electroencephalography-Based Pain Detection Using Kernel Spectral Connectivity Network with Preserved Spatio-Frequency Interpretability
title_full_unstemmed Electroencephalography-Based Pain Detection Using Kernel Spectral Connectivity Network with Preserved Spatio-Frequency Interpretability
title_short Electroencephalography-Based Pain Detection Using Kernel Spectral Connectivity Network with Preserved Spatio-Frequency Interpretability
title_sort electroencephalography based pain detection using kernel spectral connectivity network with preserved spatio frequency interpretability
topic pain detection
EEG
neural networks
kernel methods
interpretability
cross-subject analysis
url https://www.mdpi.com/2076-3417/15/9/4804
work_keys_str_mv AT santiagobuitragoosorio electroencephalographybasedpaindetectionusingkernelspectralconnectivitynetworkwithpreservedspatiofrequencyinterpretability
AT juliangilgonzalez electroencephalographybasedpaindetectionusingkernelspectralconnectivitynetworkwithpreservedspatiofrequencyinterpretability
AT andresmarinoalvarezmeza electroencephalographybasedpaindetectionusingkernelspectralconnectivitynetworkwithpreservedspatiofrequencyinterpretability
AT davidcardenaspena electroencephalographybasedpaindetectionusingkernelspectralconnectivitynetworkwithpreservedspatiofrequencyinterpretability
AT alvaroorozcogutierrez electroencephalographybasedpaindetectionusingkernelspectralconnectivitynetworkwithpreservedspatiofrequencyinterpretability