Optimal channel and feature selection for automatic prediction of functional brain age of preterm infant based on EEG
IntroductionApproximately 15 million premature infants are born each year, many of whom face risks of neurological impairments. Accurate assessment of brain maturity is crucial for timely intervention and treatment planning. Electroencephalography (EEG) is a noninvasive method commonly used for this...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2025.1517141/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583700503592960 |
|---|---|
| author | Ling Li Jiahui Li Hui Wu Yanping Zhao Qinmei Liu Hairong Zhang Wei Xu |
| author_facet | Ling Li Jiahui Li Hui Wu Yanping Zhao Qinmei Liu Hairong Zhang Wei Xu |
| author_sort | Ling Li |
| collection | DOAJ |
| description | IntroductionApproximately 15 million premature infants are born each year, many of whom face risks of neurological impairments. Accurate assessment of brain maturity is crucial for timely intervention and treatment planning. Electroencephalography (EEG) is a noninvasive method commonly used for this purpose. However, using all channels and features for brain maturity assessment can lead to high computational burden and overfitting, which can decrease the performance of the prediction system.MethodsIn this study, we propose an automatic prediction framework based on EEG to predict functional brain age (FBA) for assessing brain maturity in preterm infants. To optimize channel selection, we combine Binary Particle Swarm Optimization (BPSO) with Forward Addition (FA) and Backward Elimination (BE) methods. For feature selection, we combine the Pearson Correlation Coefficient (PCC), Recursive Feature Elimination (RFE), and Support Vector Regression (SVR) model.ResultsThe proposed framework achieved a prediction accuracy of 76.71% within ±1 week and 94.52% within ±2 weeks. Effective channel and feature selection significantly improved model performance while reducing computational costs.DiscussionThese results demonstrate that optimizing channel and feature selection can enhance the performance of FBA prediction in preterm infants, offering a more efficient and accurate tool for brain maturity assessment. |
| format | Article |
| id | doaj-art-1e612c9aedcd4a3685aa27a2dea37293 |
| institution | Kabale University |
| issn | 1662-453X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj-art-1e612c9aedcd4a3685aa27a2dea372932025-01-28T06:41:24ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2025-01-011910.3389/fnins.2025.15171411517141Optimal channel and feature selection for automatic prediction of functional brain age of preterm infant based on EEGLing Li0Jiahui Li1Hui Wu2Yanping Zhao3Qinmei Liu4Hairong Zhang5Wei Xu6College of Communication Engineering, Jilin University, Changchun, Jilin, ChinaCollege of Communication Engineering, Jilin University, Changchun, Jilin, ChinaDepartment of Neonatology, The First Hospital of Jilin University, Changchun, Jilin, ChinaCollege of Communication Engineering, Jilin University, Changchun, Jilin, ChinaDepartment of Neonatology, The First Hospital of Jilin University, Changchun, Jilin, ChinaCollege of Communication Engineering, Jilin University, Changchun, Jilin, ChinaDepartment of Neonatology, The First Hospital of Jilin University, Changchun, Jilin, ChinaIntroductionApproximately 15 million premature infants are born each year, many of whom face risks of neurological impairments. Accurate assessment of brain maturity is crucial for timely intervention and treatment planning. Electroencephalography (EEG) is a noninvasive method commonly used for this purpose. However, using all channels and features for brain maturity assessment can lead to high computational burden and overfitting, which can decrease the performance of the prediction system.MethodsIn this study, we propose an automatic prediction framework based on EEG to predict functional brain age (FBA) for assessing brain maturity in preterm infants. To optimize channel selection, we combine Binary Particle Swarm Optimization (BPSO) with Forward Addition (FA) and Backward Elimination (BE) methods. For feature selection, we combine the Pearson Correlation Coefficient (PCC), Recursive Feature Elimination (RFE), and Support Vector Regression (SVR) model.ResultsThe proposed framework achieved a prediction accuracy of 76.71% within ±1 week and 94.52% within ±2 weeks. Effective channel and feature selection significantly improved model performance while reducing computational costs.DiscussionThese results demonstrate that optimizing channel and feature selection can enhance the performance of FBA prediction in preterm infants, offering a more efficient and accurate tool for brain maturity assessment.https://www.frontiersin.org/articles/10.3389/fnins.2025.1517141/fullpreterm infantsfunctional brain ageEEGchannel selectionfeature selectionSVR |
| spellingShingle | Ling Li Jiahui Li Hui Wu Yanping Zhao Qinmei Liu Hairong Zhang Wei Xu Optimal channel and feature selection for automatic prediction of functional brain age of preterm infant based on EEG Frontiers in Neuroscience preterm infants functional brain age EEG channel selection feature selection SVR |
| title | Optimal channel and feature selection for automatic prediction of functional brain age of preterm infant based on EEG |
| title_full | Optimal channel and feature selection for automatic prediction of functional brain age of preterm infant based on EEG |
| title_fullStr | Optimal channel and feature selection for automatic prediction of functional brain age of preterm infant based on EEG |
| title_full_unstemmed | Optimal channel and feature selection for automatic prediction of functional brain age of preterm infant based on EEG |
| title_short | Optimal channel and feature selection for automatic prediction of functional brain age of preterm infant based on EEG |
| title_sort | optimal channel and feature selection for automatic prediction of functional brain age of preterm infant based on eeg |
| topic | preterm infants functional brain age EEG channel selection feature selection SVR |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2025.1517141/full |
| work_keys_str_mv | AT lingli optimalchannelandfeatureselectionforautomaticpredictionoffunctionalbrainageofpreterminfantbasedoneeg AT jiahuili optimalchannelandfeatureselectionforautomaticpredictionoffunctionalbrainageofpreterminfantbasedoneeg AT huiwu optimalchannelandfeatureselectionforautomaticpredictionoffunctionalbrainageofpreterminfantbasedoneeg AT yanpingzhao optimalchannelandfeatureselectionforautomaticpredictionoffunctionalbrainageofpreterminfantbasedoneeg AT qinmeiliu optimalchannelandfeatureselectionforautomaticpredictionoffunctionalbrainageofpreterminfantbasedoneeg AT hairongzhang optimalchannelandfeatureselectionforautomaticpredictionoffunctionalbrainageofpreterminfantbasedoneeg AT weixu optimalchannelandfeatureselectionforautomaticpredictionoffunctionalbrainageofpreterminfantbasedoneeg |