Impact of Feature Selection Techniques on the Performance of Machine Learning Models for Depression Detection Using EEG Data
Major depressive disorder (MDD) poses a significant challenge in mental healthcare due to difficulties in accurate diagnosis and timely identification. This study explores the potential of machine learning models trained on EEG-based features for depression detection. Six models and six feature sele...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/22/10532 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846154498105409536 |
|---|---|
| author | Marwa Hassan Naima Kaabouch |
| author_facet | Marwa Hassan Naima Kaabouch |
| author_sort | Marwa Hassan |
| collection | DOAJ |
| description | Major depressive disorder (MDD) poses a significant challenge in mental healthcare due to difficulties in accurate diagnosis and timely identification. This study explores the potential of machine learning models trained on EEG-based features for depression detection. Six models and six feature selection techniques were compared, highlighting the crucial role of feature selection in enhancing classifier performance. This study investigates the six feature selection methods: Elastic Net, Mutual Information (MI), Chi-Square, Forward Feature Selection with Stochastic Gradient Descent (FFS-SGD), Support Vector Machine-based Recursive Feature Elimination (SVM-RFE), and Minimal-Redundancy-Maximal-Relevance (mRMR). These methods were combined with six diverse classifiers: Logistic Regression, Support Vector Machine (SVM), Random Forest, Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Light Gradient Boosting Machine (LightGBM). The results demonstrate the substantial impact of feature selection on model performance. SVM-RFE with SVM achieved the highest accuracy (93.54%) and F1 score (95.29%), followed by Logistic Regression with an accuracy of 92.86% and F1 score of 94.84%. Elastic Net also delivered strong results, with SVM and Logistic Regression both achieving 90.47% accuracy. Other feature selection methods yielded lower performance, emphasizing the importance of selecting appropriate feature selection and machine learning algorithms. These findings suggest that careful selection and application of feature selection techniques can significantly enhance the accuracy of EEG-based depression detection. |
| format | Article |
| id | doaj-art-cbc37c7d137b4e92be28ae42a8e11152 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-cbc37c7d137b4e92be28ae42a8e111522024-11-26T17:49:08ZengMDPI AGApplied Sciences2076-34172024-11-0114221053210.3390/app142210532Impact of Feature Selection Techniques on the Performance of Machine Learning Models for Depression Detection Using EEG DataMarwa Hassan0Naima Kaabouch1Artificial Intelligence Research (AIR) Center, University of North Dakota, Grand Forks, ND 58202, USAArtificial Intelligence Research (AIR) Center, University of North Dakota, Grand Forks, ND 58202, USAMajor depressive disorder (MDD) poses a significant challenge in mental healthcare due to difficulties in accurate diagnosis and timely identification. This study explores the potential of machine learning models trained on EEG-based features for depression detection. Six models and six feature selection techniques were compared, highlighting the crucial role of feature selection in enhancing classifier performance. This study investigates the six feature selection methods: Elastic Net, Mutual Information (MI), Chi-Square, Forward Feature Selection with Stochastic Gradient Descent (FFS-SGD), Support Vector Machine-based Recursive Feature Elimination (SVM-RFE), and Minimal-Redundancy-Maximal-Relevance (mRMR). These methods were combined with six diverse classifiers: Logistic Regression, Support Vector Machine (SVM), Random Forest, Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Light Gradient Boosting Machine (LightGBM). The results demonstrate the substantial impact of feature selection on model performance. SVM-RFE with SVM achieved the highest accuracy (93.54%) and F1 score (95.29%), followed by Logistic Regression with an accuracy of 92.86% and F1 score of 94.84%. Elastic Net also delivered strong results, with SVM and Logistic Regression both achieving 90.47% accuracy. Other feature selection methods yielded lower performance, emphasizing the importance of selecting appropriate feature selection and machine learning algorithms. These findings suggest that careful selection and application of feature selection techniques can significantly enhance the accuracy of EEG-based depression detection.https://www.mdpi.com/2076-3417/14/22/10532depression detectionfeature selectionmachine learningElectroencephalography (EEG)major depressive disorder (MDD) |
| spellingShingle | Marwa Hassan Naima Kaabouch Impact of Feature Selection Techniques on the Performance of Machine Learning Models for Depression Detection Using EEG Data Applied Sciences depression detection feature selection machine learning Electroencephalography (EEG) major depressive disorder (MDD) |
| title | Impact of Feature Selection Techniques on the Performance of Machine Learning Models for Depression Detection Using EEG Data |
| title_full | Impact of Feature Selection Techniques on the Performance of Machine Learning Models for Depression Detection Using EEG Data |
| title_fullStr | Impact of Feature Selection Techniques on the Performance of Machine Learning Models for Depression Detection Using EEG Data |
| title_full_unstemmed | Impact of Feature Selection Techniques on the Performance of Machine Learning Models for Depression Detection Using EEG Data |
| title_short | Impact of Feature Selection Techniques on the Performance of Machine Learning Models for Depression Detection Using EEG Data |
| title_sort | impact of feature selection techniques on the performance of machine learning models for depression detection using eeg data |
| topic | depression detection feature selection machine learning Electroencephalography (EEG) major depressive disorder (MDD) |
| url | https://www.mdpi.com/2076-3417/14/22/10532 |
| work_keys_str_mv | AT marwahassan impactoffeatureselectiontechniquesontheperformanceofmachinelearningmodelsfordepressiondetectionusingeegdata AT naimakaabouch impactoffeatureselectiontechniquesontheperformanceofmachinelearningmodelsfordepressiondetectionusingeegdata |