External validation of binary machine learning models for pain intensity perception classification from EEG in healthy individuals
Abstract Discrimination of pain intensity using machine learning (ML) and electroencephalography (EEG) has significant potential for clinical applications, especially in scenarios where self-report is unsuitable. However, existing research is limited due to a lack of external validation (assessing p...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-27298-1 |
| _version_ | 1797958667338776576 |
|---|---|
| author | Tyler Mari Oda Asgard Jessica Henderson Danielle Hewitt Christopher Brown Andrej Stancak Nicholas Fallon |
| author_facet | Tyler Mari Oda Asgard Jessica Henderson Danielle Hewitt Christopher Brown Andrej Stancak Nicholas Fallon |
| author_sort | Tyler Mari |
| collection | DOAJ |
| description | Abstract Discrimination of pain intensity using machine learning (ML) and electroencephalography (EEG) has significant potential for clinical applications, especially in scenarios where self-report is unsuitable. However, existing research is limited due to a lack of external validation (assessing performance using novel data). We aimed for the first external validation study for pain intensity classification with EEG. Pneumatic pressure stimuli were delivered to the fingernail bed at high and low pain intensities during two independent EEG experiments with healthy participants. Study one (n = 25) was utilised for training and cross-validation. Study two (n = 15) was used for external validation one (identical stimulation parameters to study one) and external validation two (new stimulation parameters). Time–frequency features of peri-stimulus EEG were computed on a single-trial basis for all electrodes. ML training and analysis were performed on a subset of features, identified through feature selection, which were distributed across scalp electrodes and included frontal, central, and parietal regions. Results demonstrated that ML models outperformed chance. The Random Forest (RF) achieved the greatest accuracies of 73.18, 68.32 and 60.42% for cross-validation, external validation one and two, respectively. Importantly, this research is the first to externally validate ML and EEG for the classification of intensity during experimental pain, demonstrating promising performance which generalises to novel samples and paradigms. These findings offer the most rigorous estimates of ML’s clinical potential for pain classification. |
| first_indexed | 2024-04-11T00:22:13Z |
| format | Article |
| id | doaj.art-ae5e5a6b290f4ad49f1b9b3b025296e1 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-11T00:22:13Z |
| publishDate | 2023-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-ae5e5a6b290f4ad49f1b9b3b025296e12023-01-08T12:12:55ZengNature PortfolioScientific Reports2045-23222023-01-0113111310.1038/s41598-022-27298-1External validation of binary machine learning models for pain intensity perception classification from EEG in healthy individualsTyler Mari0Oda Asgard1Jessica Henderson2Danielle Hewitt3Christopher Brown4Andrej Stancak5Nicholas Fallon6Department of Psychology, Institute of Population Health, University of LiverpoolDepartment of Psychology, Institute of Population Health, University of LiverpoolDepartment of Psychology, Institute of Population Health, University of LiverpoolDepartment of Psychology, Institute of Population Health, University of LiverpoolDepartment of Psychology, Institute of Population Health, University of LiverpoolDepartment of Psychology, Institute of Population Health, University of LiverpoolDepartment of Psychology, Institute of Population Health, University of LiverpoolAbstract Discrimination of pain intensity using machine learning (ML) and electroencephalography (EEG) has significant potential for clinical applications, especially in scenarios where self-report is unsuitable. However, existing research is limited due to a lack of external validation (assessing performance using novel data). We aimed for the first external validation study for pain intensity classification with EEG. Pneumatic pressure stimuli were delivered to the fingernail bed at high and low pain intensities during two independent EEG experiments with healthy participants. Study one (n = 25) was utilised for training and cross-validation. Study two (n = 15) was used for external validation one (identical stimulation parameters to study one) and external validation two (new stimulation parameters). Time–frequency features of peri-stimulus EEG were computed on a single-trial basis for all electrodes. ML training and analysis were performed on a subset of features, identified through feature selection, which were distributed across scalp electrodes and included frontal, central, and parietal regions. Results demonstrated that ML models outperformed chance. The Random Forest (RF) achieved the greatest accuracies of 73.18, 68.32 and 60.42% for cross-validation, external validation one and two, respectively. Importantly, this research is the first to externally validate ML and EEG for the classification of intensity during experimental pain, demonstrating promising performance which generalises to novel samples and paradigms. These findings offer the most rigorous estimates of ML’s clinical potential for pain classification.https://doi.org/10.1038/s41598-022-27298-1 |
| spellingShingle | Tyler Mari Oda Asgard Jessica Henderson Danielle Hewitt Christopher Brown Andrej Stancak Nicholas Fallon External validation of binary machine learning models for pain intensity perception classification from EEG in healthy individuals Scientific Reports |
| title | External validation of binary machine learning models for pain intensity perception classification from EEG in healthy individuals |
| title_full | External validation of binary machine learning models for pain intensity perception classification from EEG in healthy individuals |
| title_fullStr | External validation of binary machine learning models for pain intensity perception classification from EEG in healthy individuals |
| title_full_unstemmed | External validation of binary machine learning models for pain intensity perception classification from EEG in healthy individuals |
| title_short | External validation of binary machine learning models for pain intensity perception classification from EEG in healthy individuals |
| title_sort | external validation of binary machine learning models for pain intensity perception classification from eeg in healthy individuals |
| url | https://doi.org/10.1038/s41598-022-27298-1 |
| work_keys_str_mv | AT tylermari externalvalidationofbinarymachinelearningmodelsforpainintensityperceptionclassificationfromeeginhealthyindividuals AT odaasgard externalvalidationofbinarymachinelearningmodelsforpainintensityperceptionclassificationfromeeginhealthyindividuals AT jessicahenderson externalvalidationofbinarymachinelearningmodelsforpainintensityperceptionclassificationfromeeginhealthyindividuals AT daniellehewitt externalvalidationofbinarymachinelearningmodelsforpainintensityperceptionclassificationfromeeginhealthyindividuals AT christopherbrown externalvalidationofbinarymachinelearningmodelsforpainintensityperceptionclassificationfromeeginhealthyindividuals AT andrejstancak externalvalidationofbinarymachinelearningmodelsforpainintensityperceptionclassificationfromeeginhealthyindividuals AT nicholasfallon externalvalidationofbinarymachinelearningmodelsforpainintensityperceptionclassificationfromeeginhealthyindividuals |