Feature Selection for Electrical Brain Activity Classification in Newborns in Case of Painful Events
DOI:
https://doi.org/10.64915/RADAP.2025.102.%25pKeywords:
electroencephalography, pain markers, newborns, machine learning , feature selection, classification, classification accuracy, biosignal analysisAbstract
The understanding of pain mechanisms in infants is critically important because newborns lack verbal communication abilities to report their pain experiences. This study focuses on analyzing electrical brain activity features in time and time-frequency domains using electroencephalographic (EEG) signals collected during clinically required noxious stimuli in newborns. Different feature extraction techniques are explored by applying a combined feature selection approach with forward feature selection and statistical measures involved. Six machine learning algorithms, namely Logistic Regression, Linear Discriminant, K-Nearest Neighbors, Support Vector Machines, Random Forest, and Gaussian Naive Bayes, were used and compared with the purpose of painful events recognition in newborns. Two binary classification tasks were considered: the first task was to distinguish between EEG signals before painful stimulus and after it (painless and painful state of the patient) and the second task was to distinguish between EEG signals on the background of the painful event (heel lance for blood sampling in neonates) and signals without painful events (audio stimulation).
In the task of EEG signals classification into pre- and post-painful stimulus segments, the support vector machines classifier showed the best accuracy estimate of 93.5% with the pre-painful EEG segments classification accuracy of 100% and post-painful segment classification accuracy of 86.9%. In the task of distinguishing between EEG signals containing painful events as heel lance and signals without painful events, the linear discriminant algorithm showed the best accuracy estimate of 84% with 76.9% correctly determined EEG segments containing painful events and 91.6% correctly determined EEG segments without painful events. Results demonstrate the potential of using features that focus on spectral power in alpha, beta, and gamma frequency bands and machine learning techniques for advancing pain detection in neonates.
References
References
1. Witt, N., Coynor, S., Edwards, C., Bradshaw, H. (2016). A Guide to Pain Assessment and Management in the Neonate. Curr Emerg Hosp Med Rep, Vol. 4, pp. 1-10. PMID: 27073748; PMCID: PMC4819510. doi: 10.1007/s40138-016-0089-y.
2. Norman, E., Rosén, I., Vanhatalo, S. et al. (2008). Electroencephalographic Response to Procedural Pain in Healthy Term Newborn Infants. Pediatr Res, Vol. 64, pp. 429–434. doi: 10.1203/PDR.0b013e3181825487.
3. Van der Vaart, M., Hartley, C., Baxter, L., Mellado, G. S. et al. (2022). Premature infants display discriminable behavioral, physiological, and brain responses to noxious and non-noxious stimuli. Cereb Cortex, Vol. 32, Iss. 17, pp. 3799-3815, PMID: 34958675; PMCID: PMC9433423. doi: 10.1093/cercor/bhab449. Erratum in: Cereb Cortex, Vol. 32, Iss. 9, 2056. doi: 10.1093/cercor/bhac138.
4. Talebi, S., Frounchi, J., Tazehkand, B. M. (2022). A Novel Channel Selection Approach for Human Neonate’s Pain EEG Data Analysis. Research Square. doi: 10.21203/rs.3.rs-2390234/v1.
5. Thomas, K. R., Sudhakaran, P., Emerson, S., Rahul, R, Kurian, S. M. (2021). Automatic Neonatal Pain Detection for Pediatrics using CNN. International journal of engineering research & technology (IJERT) ICCIDT, Vol. 09, Iss. 07. doi: 10.17577/IJERTCONV9IS07005.
6. Jones, L., Laudiano-Dray, M., Whitehead, K. et al. (2018). EEG, behavioural and physiological recordings following a painful procedure in human neonates. Sci Data, Vol. 5, 180248. doi: 10.1038/sdata.2018.248.
7. Tiemann, L., Hohn, V. D., Ta Dinh, S. et al. (2018). Distinct patterns of brain activity mediate perceptual and motor and autonomic responses to noxious stimuli. Nat Commun, Vol. 9, 4487. doi: 10.1038/s41467-018-06875-x.
8. Bajaj, N., Carrion, J. R., Bellotti, F., Berta, R., De Gloria, A. (2020). Automatic and tunable algorithm for EEG artifact removal using wavelet decomposition with applications in predictive modeling during auditory tasks. Biomedical Signal Processing and Control, Vol. 55, 101624. doi: 10.1016/j.bspc.2019.101624.
9. Xiang, J., Maue, E., Fan, Y., Qi, L., Mangano, F. T., et al. (2020). Kurtosis and skewness of high-frequency brain signals are altered in paediatric epilepsy. Brain Commun, Vol. 2, Iss. 1, fcaa036. doi: 10.1093/braincomms/fcaa036.
10. Gladun, K. V. (2021). Higuchi Fractal Dimension as a Method for Assessing Response to Sound Stimuli in Patients with Diffuse Axonal Brain Injury. Sovrem Tekhnologii Med, Vol. 12, Iss. 4, pp. 63-70. doi: 10.17691/stm2020.12.4.08.
11. Yogarajan, G., Alsubaie, N., Rajasekaran, G., Revathi, T., Alqahtani, M. S., et al. (2023). EEG-based epileptic seizure detection using binary dragonfly algorithm and deep neural network. Sci Rep, Vol. 13, 17710. doi: 10.1038/s41598-023-44318-w.
12. Hjorth, B. (1970). EEG analysis based on time domain properties. Electroencephalog Clin Neurophysiol, Vol. 29, Iss. 3, pp. 306-310. doi: 10.1016/0013-4694(70)90143-4.
13. Lal, U., Chikkankod, A., Longo, L. (2023). Leveraging SVD Entropy and Explainable Machine Learning for Alzheimer’s and Frontotemporal Dementia Detection using EEG. TechRxiv. doi: 10.36227/techrxiv.23992554.v2.
14. Grigg, O. A., Farewell, V. T., Spiegelhalter, D. J. (2003). Use of risk-adjusted CUSUM and RSPRT charts for monitoring in medical contexts. Stat Methods Med Res, Vol. 12, Iss. 2, pp. 147-70. doi: 10.1177/096228020301200205.
15. Andrade, C. (2021). Z Scores, Standard Scores, and Composite Test Scores Explained. Indian J Psychol Med, Vol. 43, Iss. 6, pp. 555-557. doi: 10.1177/02537176211046525.
16. Mishra, P., Singh, U., Pandey, C. M., Mishra, P., Pandey, G. (2019). Application of student's t-test, analysis of variance, and covariance. Ann Card Anaesth, Vol. 22, Iss. 4, pp. 407-411. doi: 10.4103/aca.ACA_94_19. PMID: 31621677; PMCID: PMC6813708.
17. Abdulmohsin, H., Abdul, H., Hossen, A. (2021). A New Hybrid Feature Selection Method Using T-test and Fitness Function. Computers, Materials & Continua, Vol. 68, Iss. 3, pp. 3997-4016. doi: 10.32604/cmc.2021.014840.
18. Chen, W., Cai, Y., Li, A. et al. (2023). EEG feature selection method based on maximum information coefficient and quantum particle swarm. Sci Rep, Vol. 13, 14515. doi: 10.1038/s41598-023-41682-5.
19. Pan, C., Shi, C., Mu, H., Li, J., Gao, X. (2020). EEG-Based Emotion Recognition Using Logistic Regression with Gaussian Kernel and Laplacian Prior and Investigation of Critical Frequency Bands. Applied Sciences, Vol. 10, Iss. 5, 1619. doi: 10.3390/app10051619.
20. Fu, R., Tian, Y., Bao, T., Meng, Z., Shi, P. (2019). Improvement Motor Imagery EEG Classification Based on Regularized Linear Discriminant Analysis. J Med Syst, Vol. 43, Iss. 6, 169, doi: 10.1007/s10916-019-1270-0. PMID: 31062175.
21. Ginting, A. S., Simanjuntak, R. M., Lumbantoruan, N. and Sitanggang D. (2024). EEG Signal Classification using K-Nearest Neighbor Method to Measure Impulsivity Level. Jurnal Sisfokom, Vol. 13, Iss. 2, pp. 261-266. doi: 10.32736/sisfokom.v13i2.2154.
22. Himalyan, S., Gupta, V. (2022). Support Vector Machine-Based Epileptic Seizure Detection Using EEG Signals. Engineering Proceedings, Vol. 18, Iss. 1, 73. doi: 10.3390/ecsa-11-20506.
23. Edla, D., Mangalorekar, K., Dhavalikar, G., Dodia, S. (2018). Classification of EEG data for human mental state analysis using Random Forest Classifier. Procedia Computer Science, Vol. 132, pp. 1523-1532. doi: 10.1016/j.procs.2018.05.116.
24. Machado, J., Balbinot, A. (2014). Executed Movement Using EEG Signals through a Naive Bayes Classifier. Micromachines, Vol. 5, Iss. 4, pp. 1082-1105. doi: 10.3390/mi5041082.
25. Bigoni, C., Cadic-Melchior, A., Morishita, T., Hummel, F. C. (2023). Optimization of phase prediction for brain-state dependent stimulation: a grid-search approach. J Neural Eng, Vol. 20, Iss. 1. doi: 10.1088/1741-2552/acb1d8. PMID: 36626830.
26. Kaneko, H. (2022). Cross-validated permutation feature importance considering correlation between features. Analytical Science Advances, Vol. 3, Iss. 9-10, pp. 278–287. doi: 10.1002/ansa.202200018.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 В. Р. Бондарев, К. О. Іванько, А. О. Попов, Є. С. Карплюк, Н. С. Корогод
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
