Generalisation of EEG-Based Pain Biomarker Classification for Predicting Central Neuropathic Pain in Subacute Spinal Cord Injury
<b>Background:</b> The objective was to test the generalisability of electroencephalography (EEG) markers of future pain using two independent datasets. <b>Methods:</b> Datasets, A [N = 20] and B [N = 35], were collected from participants with subacute spinal cord injury who...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Biomedicines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9059/13/1/213 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589020459171840 |
|---|---|
| author | Keri Anderson Sebastian Stein Ho Suen Mariel Purcell Maurizio Belci Euan McCaughey Ronali McLean Aye Khine Aleksandra Vuckovic |
| author_facet | Keri Anderson Sebastian Stein Ho Suen Mariel Purcell Maurizio Belci Euan McCaughey Ronali McLean Aye Khine Aleksandra Vuckovic |
| author_sort | Keri Anderson |
| collection | DOAJ |
| description | <b>Background:</b> The objective was to test the generalisability of electroencephalography (EEG) markers of future pain using two independent datasets. <b>Methods:</b> Datasets, A [N = 20] and B [N = 35], were collected from participants with subacute spinal cord injury who did not have neuropathic pain at the time of recording. In both datasets, some participants developed pain within six months, (PDP) will others did not (PNP). EEG features were extracted based on either band power or Higuchi fractal dimension (HFD). Three levels of generalisability were tested: (1) classification PDP vs. PNP in datasets A and B separately; (2) classification between groups in datasets A and B together; and (3) classification where one dataset (A or B) was used for training and testing, and the other for validation. A novel normalisation method was applied to HFD features. <b>Results:</b> Training and testing of individual datasets achieved classification accuracies of >80% using either feature set, and classification of joint datasets (A and B) achieved a maximum accuracy of 86.4% (HFD, support vector machine (SVM)). With normalisation and feature reduction (principal components), the validation accuracy was 66.6%. <b>Conclusions:</b> An SVM classifier with HFD features showed the best robustness, and normalisation improved the accuracy of predicting future neuropathic pain well above the chance level. |
| format | Article |
| id | doaj-art-fcbb6c25333a484485b0394c6a6f7e35 |
| institution | Kabale University |
| issn | 2227-9059 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomedicines |
| spelling | doaj-art-fcbb6c25333a484485b0394c6a6f7e352025-01-24T13:24:25ZengMDPI AGBiomedicines2227-90592025-01-0113121310.3390/biomedicines13010213Generalisation of EEG-Based Pain Biomarker Classification for Predicting Central Neuropathic Pain in Subacute Spinal Cord InjuryKeri Anderson0Sebastian Stein1Ho Suen2Mariel Purcell3Maurizio Belci4Euan McCaughey5Ronali McLean6Aye Khine7Aleksandra Vuckovic8Biomedical Engineering Division, James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UKSchool of Computing Science, University of Glasgow, Glasgow G12 8QQ, UKBiomedical Engineering Division, James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UKQueen Elizabeth National Spinal Injuries Unit, Queen Elizabeth University Hospital, Glasgow G51 4TF, UKStoke Mandeville Spinal Injuries Centre, Stoke Mandeville Hospital, Aylesbury HP21 8AL, UKQueen Elizabeth National Spinal Injuries Unit, Queen Elizabeth University Hospital, Glasgow G51 4TF, UKQueen Elizabeth National Spinal Injuries Unit, Queen Elizabeth University Hospital, Glasgow G51 4TF, UKStoke Mandeville Spinal Injuries Centre, Stoke Mandeville Hospital, Aylesbury HP21 8AL, UKBiomedical Engineering Division, James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK<b>Background:</b> The objective was to test the generalisability of electroencephalography (EEG) markers of future pain using two independent datasets. <b>Methods:</b> Datasets, A [N = 20] and B [N = 35], were collected from participants with subacute spinal cord injury who did not have neuropathic pain at the time of recording. In both datasets, some participants developed pain within six months, (PDP) will others did not (PNP). EEG features were extracted based on either band power or Higuchi fractal dimension (HFD). Three levels of generalisability were tested: (1) classification PDP vs. PNP in datasets A and B separately; (2) classification between groups in datasets A and B together; and (3) classification where one dataset (A or B) was used for training and testing, and the other for validation. A novel normalisation method was applied to HFD features. <b>Results:</b> Training and testing of individual datasets achieved classification accuracies of >80% using either feature set, and classification of joint datasets (A and B) achieved a maximum accuracy of 86.4% (HFD, support vector machine (SVM)). With normalisation and feature reduction (principal components), the validation accuracy was 66.6%. <b>Conclusions:</b> An SVM classifier with HFD features showed the best robustness, and normalisation improved the accuracy of predicting future neuropathic pain well above the chance level.https://www.mdpi.com/2227-9059/13/1/213EEGcentral neuropathic painspinal cord injurybiomarkersmachine learning |
| spellingShingle | Keri Anderson Sebastian Stein Ho Suen Mariel Purcell Maurizio Belci Euan McCaughey Ronali McLean Aye Khine Aleksandra Vuckovic Generalisation of EEG-Based Pain Biomarker Classification for Predicting Central Neuropathic Pain in Subacute Spinal Cord Injury Biomedicines EEG central neuropathic pain spinal cord injury biomarkers machine learning |
| title | Generalisation of EEG-Based Pain Biomarker Classification for Predicting Central Neuropathic Pain in Subacute Spinal Cord Injury |
| title_full | Generalisation of EEG-Based Pain Biomarker Classification for Predicting Central Neuropathic Pain in Subacute Spinal Cord Injury |
| title_fullStr | Generalisation of EEG-Based Pain Biomarker Classification for Predicting Central Neuropathic Pain in Subacute Spinal Cord Injury |
| title_full_unstemmed | Generalisation of EEG-Based Pain Biomarker Classification for Predicting Central Neuropathic Pain in Subacute Spinal Cord Injury |
| title_short | Generalisation of EEG-Based Pain Biomarker Classification for Predicting Central Neuropathic Pain in Subacute Spinal Cord Injury |
| title_sort | generalisation of eeg based pain biomarker classification for predicting central neuropathic pain in subacute spinal cord injury |
| topic | EEG central neuropathic pain spinal cord injury biomarkers machine learning |
| url | https://www.mdpi.com/2227-9059/13/1/213 |
| work_keys_str_mv | AT kerianderson generalisationofeegbasedpainbiomarkerclassificationforpredictingcentralneuropathicpaininsubacutespinalcordinjury AT sebastianstein generalisationofeegbasedpainbiomarkerclassificationforpredictingcentralneuropathicpaininsubacutespinalcordinjury AT hosuen generalisationofeegbasedpainbiomarkerclassificationforpredictingcentralneuropathicpaininsubacutespinalcordinjury AT marielpurcell generalisationofeegbasedpainbiomarkerclassificationforpredictingcentralneuropathicpaininsubacutespinalcordinjury AT mauriziobelci generalisationofeegbasedpainbiomarkerclassificationforpredictingcentralneuropathicpaininsubacutespinalcordinjury AT euanmccaughey generalisationofeegbasedpainbiomarkerclassificationforpredictingcentralneuropathicpaininsubacutespinalcordinjury AT ronalimclean generalisationofeegbasedpainbiomarkerclassificationforpredictingcentralneuropathicpaininsubacutespinalcordinjury AT ayekhine generalisationofeegbasedpainbiomarkerclassificationforpredictingcentralneuropathicpaininsubacutespinalcordinjury AT aleksandravuckovic generalisationofeegbasedpainbiomarkerclassificationforpredictingcentralneuropathicpaininsubacutespinalcordinjury |