Enhanced classification of tinnitus patients using EEG microstates and deep learning techniques
Abstract This study aims to deepen the understanding and classification of tinnitus through a comprehensive analysis of EEG signals utilizing innovative microstate analysis techniques and cutting-edge machine learning approaches. EEG data were collected from two datasets: a primary dataset with 36 p...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-01129-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850190507449253888 |
|---|---|
| author | Zahra Raeisi Abolfazl Sodagartojgi Fahimeh Sharafkhani Amirsadegh Roshanzamir Hossein Najafzadeh Omid Bashiri Alireza Golkarieh |
| author_facet | Zahra Raeisi Abolfazl Sodagartojgi Fahimeh Sharafkhani Amirsadegh Roshanzamir Hossein Najafzadeh Omid Bashiri Alireza Golkarieh |
| author_sort | Zahra Raeisi |
| collection | DOAJ |
| description | Abstract This study aims to deepen the understanding and classification of tinnitus through a comprehensive analysis of EEG signals utilizing innovative microstate analysis techniques and cutting-edge machine learning approaches. EEG data were collected from two datasets: a primary dataset with 36 participants (16 healthy, 20 tinnitus) and a public dataset with 37 participants (15 healthy, 22 tinnitus). Signals were decomposed into five frequency bands (delta, theta, alpha, beta, gamma) using Daubechies 4 wavelet at five decomposition levels. Microstate features (Duration, Occurrence, Mean Global Field Power, and Coverage) were extracted across four microstate configurations (4-state to 7-state) under both eyes-closed and eyes-open conditions. Classification was performed using SVM, Decision Tree, Random Forest, and Deep Neural Networks. Additionally, pre-trained models (VGG16, ResNet50, Xception) were used with a novel feature-to-image transformation approach for validation. Analysis revealed significant alterations in beta band microstates, with microstate A showing increased duration (+ 7.8% to + 11.2%) and microstate B showing decreased duration (− 9.0% to − 13.8%) in tinnitus patients. Occurrence rates were markedly elevated (~ 28–29% higher) in the tinnitus group. Transition probability analysis identified distinctive patterns between groups, with the most pronounced differences observed in gamma band (6-state configuration) during eyes-closed condition (healthy: F → B = 0.143; tinnitus: C → D = 0.153) and beta band (7-state configuration) also during eyes-closed condition (healthy: E → A = 0.091; tinnitus: C → E = 0.082). In the eyes-open condition, gamma band with 7 microstates showed substantial differences in transition patterns (healthy: E → A = 0.149; tinnitus: C → G = 0.157). Classification performance was exceptional, with DNN achieving 100% accuracy in the gamma frequency band during eyes-open condition with 5-state configuration. Frequency band analysis demonstrated that gamma band performed best for open eyes (99.89% accuracy) and beta band excelled for closed eyes (96.46% accuracy). Validation with pre-trained models showed ResNet50 with SVM classifier using 6-state configurations provided optimal discrimination (100% accuracy). EEG microstate dynamics in beta and gamma bands serve as reliable markers for distinguishing tinnitus patients. These findings provide insights into tinnitus-related neural alterations and highlight microstate analysis as a potential objective diagnostic tool for guiding personalized neuromodulation therapies. |
| format | Article |
| id | doaj-art-aeb5e87ddd3544d38f66b3989f7e6126 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-aeb5e87ddd3544d38f66b3989f7e61262025-08-20T02:15:16ZengNature PortfolioScientific Reports2045-23222025-05-0115112810.1038/s41598-025-01129-5Enhanced classification of tinnitus patients using EEG microstates and deep learning techniquesZahra Raeisi0Abolfazl Sodagartojgi1Fahimeh Sharafkhani2Amirsadegh Roshanzamir3Hossein Najafzadeh4Omid Bashiri5Alireza Golkarieh6Department of Computer Science, University of Fairleigh Dickinson, Vancouver CampusDepartment of Statistics, Rutgers UniversityEngineering Management and Systems Engineering Department, Missouri University of Science and TechnologyDepartment of Information Systems and Management, University of South FloridaDepartment of Medical Bioengineering, Faculty of Advanced Medical Sciences, Tabriz University of Medical SciencesDepartment of Kinesiology and Nutrition Sciences, University of Nevada, Las VegasPhD Student in Computer Science and Informatics, Department of Computer Science and Engineering, Oakland UniversityAbstract This study aims to deepen the understanding and classification of tinnitus through a comprehensive analysis of EEG signals utilizing innovative microstate analysis techniques and cutting-edge machine learning approaches. EEG data were collected from two datasets: a primary dataset with 36 participants (16 healthy, 20 tinnitus) and a public dataset with 37 participants (15 healthy, 22 tinnitus). Signals were decomposed into five frequency bands (delta, theta, alpha, beta, gamma) using Daubechies 4 wavelet at five decomposition levels. Microstate features (Duration, Occurrence, Mean Global Field Power, and Coverage) were extracted across four microstate configurations (4-state to 7-state) under both eyes-closed and eyes-open conditions. Classification was performed using SVM, Decision Tree, Random Forest, and Deep Neural Networks. Additionally, pre-trained models (VGG16, ResNet50, Xception) were used with a novel feature-to-image transformation approach for validation. Analysis revealed significant alterations in beta band microstates, with microstate A showing increased duration (+ 7.8% to + 11.2%) and microstate B showing decreased duration (− 9.0% to − 13.8%) in tinnitus patients. Occurrence rates were markedly elevated (~ 28–29% higher) in the tinnitus group. Transition probability analysis identified distinctive patterns between groups, with the most pronounced differences observed in gamma band (6-state configuration) during eyes-closed condition (healthy: F → B = 0.143; tinnitus: C → D = 0.153) and beta band (7-state configuration) also during eyes-closed condition (healthy: E → A = 0.091; tinnitus: C → E = 0.082). In the eyes-open condition, gamma band with 7 microstates showed substantial differences in transition patterns (healthy: E → A = 0.149; tinnitus: C → G = 0.157). Classification performance was exceptional, with DNN achieving 100% accuracy in the gamma frequency band during eyes-open condition with 5-state configuration. Frequency band analysis demonstrated that gamma band performed best for open eyes (99.89% accuracy) and beta band excelled for closed eyes (96.46% accuracy). Validation with pre-trained models showed ResNet50 with SVM classifier using 6-state configurations provided optimal discrimination (100% accuracy). EEG microstate dynamics in beta and gamma bands serve as reliable markers for distinguishing tinnitus patients. These findings provide insights into tinnitus-related neural alterations and highlight microstate analysis as a potential objective diagnostic tool for guiding personalized neuromodulation therapies.https://doi.org/10.1038/s41598-025-01129-5TinnitusEEG microstatesDeep learningClassification |
| spellingShingle | Zahra Raeisi Abolfazl Sodagartojgi Fahimeh Sharafkhani Amirsadegh Roshanzamir Hossein Najafzadeh Omid Bashiri Alireza Golkarieh Enhanced classification of tinnitus patients using EEG microstates and deep learning techniques Scientific Reports Tinnitus EEG microstates Deep learning Classification |
| title | Enhanced classification of tinnitus patients using EEG microstates and deep learning techniques |
| title_full | Enhanced classification of tinnitus patients using EEG microstates and deep learning techniques |
| title_fullStr | Enhanced classification of tinnitus patients using EEG microstates and deep learning techniques |
| title_full_unstemmed | Enhanced classification of tinnitus patients using EEG microstates and deep learning techniques |
| title_short | Enhanced classification of tinnitus patients using EEG microstates and deep learning techniques |
| title_sort | enhanced classification of tinnitus patients using eeg microstates and deep learning techniques |
| topic | Tinnitus EEG microstates Deep learning Classification |
| url | https://doi.org/10.1038/s41598-025-01129-5 |
| work_keys_str_mv | AT zahraraeisi enhancedclassificationoftinnituspatientsusingeegmicrostatesanddeeplearningtechniques AT abolfazlsodagartojgi enhancedclassificationoftinnituspatientsusingeegmicrostatesanddeeplearningtechniques AT fahimehsharafkhani enhancedclassificationoftinnituspatientsusingeegmicrostatesanddeeplearningtechniques AT amirsadeghroshanzamir enhancedclassificationoftinnituspatientsusingeegmicrostatesanddeeplearningtechniques AT hosseinnajafzadeh enhancedclassificationoftinnituspatientsusingeegmicrostatesanddeeplearningtechniques AT omidbashiri enhancedclassificationoftinnituspatientsusingeegmicrostatesanddeeplearningtechniques AT alirezagolkarieh enhancedclassificationoftinnituspatientsusingeegmicrostatesanddeeplearningtechniques |