Bayesian Optimization of Machine Learning Classification of Resting-State EEG Microstates in Schizophrenia: A Proof-of-Concept Preliminary Study Based on Secondary Analysis
Resting-state electroencephalography (EEG) microstates reflect sub-second, quasi-stable states of brain activity. Several studies have reported alterations of microstate features in patients with schizophrenia (SZ). Based on these findings, it has been suggested that microstates may represent neurop...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Brain Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3425/12/11/1497 |
| _version_ | 1797468943727722496 |
|---|---|
| author | Ahmadreza Keihani Seyed Saman Sajadi Mahsa Hasani Fabio Ferrarelli |
| author_facet | Ahmadreza Keihani Seyed Saman Sajadi Mahsa Hasani Fabio Ferrarelli |
| author_sort | Ahmadreza Keihani |
| collection | DOAJ |
| description | Resting-state electroencephalography (EEG) microstates reflect sub-second, quasi-stable states of brain activity. Several studies have reported alterations of microstate features in patients with schizophrenia (SZ). Based on these findings, it has been suggested that microstates may represent neurophysiological biomarkers for the classification of SZ. To explore this possibility, machine learning approaches can be employed. Bayesian optimization is a machine learning approach that selects the best-fitted machine learning model with tuned hyperparameters from existing models to improve the classification. In this proof-of-concept preliminary study based on secondary analysis, 20 microstate features were extracted from 14 SZ patients and 14 healthy controls’ EEG signals. These parameters were then ranked as predictors based on their importance, and an optimized machine learning approach was applied to evaluate the performance of the classification. SZ patients had altered microstate features compared to healthy controls. Furthermore, Bayesian optimization outperformed conventional multivariate analyses and showed the highest accuracy (90.93%), AUC (0.90), sensitivity (91.37%), and specificity (90.48%), with reliable results using just six microstate predictors. Altogether, in this proof-of-concept study, we showed that machine learning with Bayesian optimization can be utilized to characterize EEG microstate alterations and contribute to the classification of SZ patients. |
| first_indexed | 2024-03-09T19:14:27Z |
| format | Article |
| id | doaj.art-a92da78c487e44d797cb5cf2f45ce8db |
| institution | Directory Open Access Journal |
| issn | 2076-3425 |
| language | English |
| last_indexed | 2024-03-09T19:14:27Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Brain Sciences |
| spelling | doaj.art-a92da78c487e44d797cb5cf2f45ce8db2023-11-24T03:56:54ZengMDPI AGBrain Sciences2076-34252022-11-011211149710.3390/brainsci12111497Bayesian Optimization of Machine Learning Classification of Resting-State EEG Microstates in Schizophrenia: A Proof-of-Concept Preliminary Study Based on Secondary AnalysisAhmadreza Keihani0Seyed Saman Sajadi1Mahsa Hasani2Fabio Ferrarelli3Department of Psychiatry, University of Pittsburgh, Pittsburgh, PA 15213, USADepartment of Medical Physics & Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Tehran 1416634793, IranInstitute of Medical Science and Technology, Shahid Beheshti University, Tehran 1985717443, IranDepartment of Psychiatry, University of Pittsburgh, Pittsburgh, PA 15213, USAResting-state electroencephalography (EEG) microstates reflect sub-second, quasi-stable states of brain activity. Several studies have reported alterations of microstate features in patients with schizophrenia (SZ). Based on these findings, it has been suggested that microstates may represent neurophysiological biomarkers for the classification of SZ. To explore this possibility, machine learning approaches can be employed. Bayesian optimization is a machine learning approach that selects the best-fitted machine learning model with tuned hyperparameters from existing models to improve the classification. In this proof-of-concept preliminary study based on secondary analysis, 20 microstate features were extracted from 14 SZ patients and 14 healthy controls’ EEG signals. These parameters were then ranked as predictors based on their importance, and an optimized machine learning approach was applied to evaluate the performance of the classification. SZ patients had altered microstate features compared to healthy controls. Furthermore, Bayesian optimization outperformed conventional multivariate analyses and showed the highest accuracy (90.93%), AUC (0.90), sensitivity (91.37%), and specificity (90.48%), with reliable results using just six microstate predictors. Altogether, in this proof-of-concept study, we showed that machine learning with Bayesian optimization can be utilized to characterize EEG microstate alterations and contribute to the classification of SZ patients.https://www.mdpi.com/2076-3425/12/11/1497microstate analysisschizophreniaoptimized machine learningmicrostate map correlationresting-state EEG |
| spellingShingle | Ahmadreza Keihani Seyed Saman Sajadi Mahsa Hasani Fabio Ferrarelli Bayesian Optimization of Machine Learning Classification of Resting-State EEG Microstates in Schizophrenia: A Proof-of-Concept Preliminary Study Based on Secondary Analysis Brain Sciences microstate analysis schizophrenia optimized machine learning microstate map correlation resting-state EEG |
| title | Bayesian Optimization of Machine Learning Classification of Resting-State EEG Microstates in Schizophrenia: A Proof-of-Concept Preliminary Study Based on Secondary Analysis |
| title_full | Bayesian Optimization of Machine Learning Classification of Resting-State EEG Microstates in Schizophrenia: A Proof-of-Concept Preliminary Study Based on Secondary Analysis |
| title_fullStr | Bayesian Optimization of Machine Learning Classification of Resting-State EEG Microstates in Schizophrenia: A Proof-of-Concept Preliminary Study Based on Secondary Analysis |
| title_full_unstemmed | Bayesian Optimization of Machine Learning Classification of Resting-State EEG Microstates in Schizophrenia: A Proof-of-Concept Preliminary Study Based on Secondary Analysis |
| title_short | Bayesian Optimization of Machine Learning Classification of Resting-State EEG Microstates in Schizophrenia: A Proof-of-Concept Preliminary Study Based on Secondary Analysis |
| title_sort | bayesian optimization of machine learning classification of resting state eeg microstates in schizophrenia a proof of concept preliminary study based on secondary analysis |
| topic | microstate analysis schizophrenia optimized machine learning microstate map correlation resting-state EEG |
| url | https://www.mdpi.com/2076-3425/12/11/1497 |
| work_keys_str_mv | AT ahmadrezakeihani bayesianoptimizationofmachinelearningclassificationofrestingstateeegmicrostatesinschizophreniaaproofofconceptpreliminarystudybasedonsecondaryanalysis AT seyedsamansajadi bayesianoptimizationofmachinelearningclassificationofrestingstateeegmicrostatesinschizophreniaaproofofconceptpreliminarystudybasedonsecondaryanalysis AT mahsahasani bayesianoptimizationofmachinelearningclassificationofrestingstateeegmicrostatesinschizophreniaaproofofconceptpreliminarystudybasedonsecondaryanalysis AT fabioferrarelli bayesianoptimizationofmachinelearningclassificationofrestingstateeegmicrostatesinschizophreniaaproofofconceptpreliminarystudybasedonsecondaryanalysis |