Ensemble learning techniques reveals multidimensional EEG feature alterations in pediatric schizophrenia
Schizophrenia (SCZ) is a severe mental disorder that impairs brain function and daily life, while its early and objective diagnosis remains a major clinical challenge due to the reliance on subjective assessments. This study aims to develop a machine learning-based framework for the auxiliary diagno...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Human Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2025.1530291/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849393335508140032 |
|---|---|
| author | Ying Mao Ying Mao Fang Wang Shan Wang Zhaowei Wang Gang Li Xuchen Qi Xuchen Qi Yu Sun Yu Sun |
| author_facet | Ying Mao Ying Mao Fang Wang Shan Wang Zhaowei Wang Gang Li Xuchen Qi Xuchen Qi Yu Sun Yu Sun |
| author_sort | Ying Mao |
| collection | DOAJ |
| description | Schizophrenia (SCZ) is a severe mental disorder that impairs brain function and daily life, while its early and objective diagnosis remains a major clinical challenge due to the reliance on subjective assessments. This study aims to develop a machine learning-based framework for the auxiliary diagnosis of SCZ using multi-dimensional electroencephalogram (EEG) features and to investigate the underlying neural alterations. Resting-state EEG data were obtained from 45 male patients with pediatric SCZ and 39 age-and gender-matched healthy controls. Three types of EEG features (relative power (RP), fuzzy entropy (FuzEn), and functional connectivity (FC)) were extracted under various time window lengths and fed into four ensemble learning models. A data-driven feature selection approach (Recursive Feature Elimination) was applied to identify the most informative features, resulting in 212 most discriminative features (48 RP, 40 FuzEn, and 124 FC) out of the initial 760. Leveraging the selected features, the Categorical Boosting model achieved the highest classification accuracy of 99.60% at the 4-s window. Further analysis of the discriminative features revealed that the altered EEG characteristics were mainly in the alpha, beta, and gamma bands. Particularly, altered FCs exhibited a fronto-increase-parieto-decrease pattern mainly in the right hemisphere along with spectral-dependent RP alterations and a universally reduced FuzEn in the pediatric SCZ group. In summary, this study not only showcases the potential of advanced ensemble learning algorithms in precisely identifying pediatric SCZ, but also provides new insights into the altered brain functions in pediatric SCZ patients, which may benefit the future development of automatic diagnosis systems. |
| format | Article |
| id | doaj-art-931cde600a82433aaa079f084ce0a09b |
| institution | Kabale University |
| issn | 1662-5161 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Human Neuroscience |
| spelling | doaj-art-931cde600a82433aaa079f084ce0a09b2025-08-20T03:40:26ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612025-08-011910.3389/fnhum.2025.15302911530291Ensemble learning techniques reveals multidimensional EEG feature alterations in pediatric schizophreniaYing Mao0Ying Mao1Fang Wang2Shan Wang3Zhaowei Wang4Gang Li5Xuchen Qi6Xuchen Qi7Yu Sun8Yu Sun9Department of Special Examination, Shaoxing People’s Hospital, Shaoxing, ChinaSchool of Medicine, Shaoxing University, Shaoxing, ChinaDepartment of Special Examination, Shaoxing People’s Hospital, Shaoxing, ChinaDepartment of Special Examination, Shaoxing People’s Hospital, Shaoxing, ChinaDepartment of Neurology, Shaoxing People’s Hospital, Shaoxing, ChinaCollege of Mathematic Medicine, Zhejiang Normal University, Jinhua, ChinaSchool of Medicine, Shaoxing University, Shaoxing, ChinaDepartment of Neurosurgery, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaDepartment of Rehabilitation, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaKey Laboratory for Biomedical Engineering of Ministry of Education of China, Zhejiang University, Hangzhou, ChinaSchizophrenia (SCZ) is a severe mental disorder that impairs brain function and daily life, while its early and objective diagnosis remains a major clinical challenge due to the reliance on subjective assessments. This study aims to develop a machine learning-based framework for the auxiliary diagnosis of SCZ using multi-dimensional electroencephalogram (EEG) features and to investigate the underlying neural alterations. Resting-state EEG data were obtained from 45 male patients with pediatric SCZ and 39 age-and gender-matched healthy controls. Three types of EEG features (relative power (RP), fuzzy entropy (FuzEn), and functional connectivity (FC)) were extracted under various time window lengths and fed into four ensemble learning models. A data-driven feature selection approach (Recursive Feature Elimination) was applied to identify the most informative features, resulting in 212 most discriminative features (48 RP, 40 FuzEn, and 124 FC) out of the initial 760. Leveraging the selected features, the Categorical Boosting model achieved the highest classification accuracy of 99.60% at the 4-s window. Further analysis of the discriminative features revealed that the altered EEG characteristics were mainly in the alpha, beta, and gamma bands. Particularly, altered FCs exhibited a fronto-increase-parieto-decrease pattern mainly in the right hemisphere along with spectral-dependent RP alterations and a universally reduced FuzEn in the pediatric SCZ group. In summary, this study not only showcases the potential of advanced ensemble learning algorithms in precisely identifying pediatric SCZ, but also provides new insights into the altered brain functions in pediatric SCZ patients, which may benefit the future development of automatic diagnosis systems.https://www.frontiersin.org/articles/10.3389/fnhum.2025.1530291/fullpediatric schizophreniaelectroencephalogramensemble learningfeature selectionbrain function |
| spellingShingle | Ying Mao Ying Mao Fang Wang Shan Wang Zhaowei Wang Gang Li Xuchen Qi Xuchen Qi Yu Sun Yu Sun Ensemble learning techniques reveals multidimensional EEG feature alterations in pediatric schizophrenia Frontiers in Human Neuroscience pediatric schizophrenia electroencephalogram ensemble learning feature selection brain function |
| title | Ensemble learning techniques reveals multidimensional EEG feature alterations in pediatric schizophrenia |
| title_full | Ensemble learning techniques reveals multidimensional EEG feature alterations in pediatric schizophrenia |
| title_fullStr | Ensemble learning techniques reveals multidimensional EEG feature alterations in pediatric schizophrenia |
| title_full_unstemmed | Ensemble learning techniques reveals multidimensional EEG feature alterations in pediatric schizophrenia |
| title_short | Ensemble learning techniques reveals multidimensional EEG feature alterations in pediatric schizophrenia |
| title_sort | ensemble learning techniques reveals multidimensional eeg feature alterations in pediatric schizophrenia |
| topic | pediatric schizophrenia electroencephalogram ensemble learning feature selection brain function |
| url | https://www.frontiersin.org/articles/10.3389/fnhum.2025.1530291/full |
| work_keys_str_mv | AT yingmao ensemblelearningtechniquesrevealsmultidimensionaleegfeaturealterationsinpediatricschizophrenia AT yingmao ensemblelearningtechniquesrevealsmultidimensionaleegfeaturealterationsinpediatricschizophrenia AT fangwang ensemblelearningtechniquesrevealsmultidimensionaleegfeaturealterationsinpediatricschizophrenia AT shanwang ensemblelearningtechniquesrevealsmultidimensionaleegfeaturealterationsinpediatricschizophrenia AT zhaoweiwang ensemblelearningtechniquesrevealsmultidimensionaleegfeaturealterationsinpediatricschizophrenia AT gangli ensemblelearningtechniquesrevealsmultidimensionaleegfeaturealterationsinpediatricschizophrenia AT xuchenqi ensemblelearningtechniquesrevealsmultidimensionaleegfeaturealterationsinpediatricschizophrenia AT xuchenqi ensemblelearningtechniquesrevealsmultidimensionaleegfeaturealterationsinpediatricschizophrenia AT yusun ensemblelearningtechniquesrevealsmultidimensionaleegfeaturealterationsinpediatricschizophrenia AT yusun ensemblelearningtechniquesrevealsmultidimensionaleegfeaturealterationsinpediatricschizophrenia |