Optimal Channels and Features Selection Based ADHD Detection From EEG Signal Using Statistical and Machine Learning Techniques
Attention deficit hyperactivity disorder (ADHD) is one of the major psychiatric and neurodevelopment disorders worldwide. Electroencephalography (EEG) signal-based approach is very important for the early detection and classification of children with ADHD. However, diagnosing children with ADHD usin...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10091501/ |
_version_ | 1827969721180356608 |
---|---|
author | Md. Maniruzzaman Md. Al Mehedi Hasan Nobuyoshi Asai Jungpil Shin |
author_facet | Md. Maniruzzaman Md. Al Mehedi Hasan Nobuyoshi Asai Jungpil Shin |
author_sort | Md. Maniruzzaman |
collection | DOAJ |
description | Attention deficit hyperactivity disorder (ADHD) is one of the major psychiatric and neurodevelopment disorders worldwide. Electroencephalography (EEG) signal-based approach is very important for the early detection and classification of children with ADHD. However, diagnosing children with ADHD using full EEG channels with all features may lead to computational complexity and overfitting problems. To solve these problems, machine learning (ML)-based ADHD detection was designed by identifying optimal channels and its significant features. In this work, support vector machine and t-test based, two separate approaches were devised to select optimal channels individually and then proposed a hybrid channel selection approach by combining these two channel selection methods in order to select the optimal channels. After that, LASSO logistic regression-based model was used to select the important features from the selected channels. Finally, six ML-based classifiers, like Gaussian process classification (GPC), random forest, k-nearest neighbors, multilayer perceptron, decision tree, and logistic regression were applied for the detection of children with ADHD and evaluated their performances using accuracy and area under the curve (AUC). This study utilized a total of one hundred twenty-one children, with sixty-one children with ADHD, aged 7-12 years, and had nineteen channels. Ten different channels were selected by SVM based and an independent t-test-based approach separately and six overlapping channels were identified from both channel selection methods. Then, we selected twenty-eight features from selected six channels using LASSO. Using only six channels and twenty-eight features, GP-based classifier achieved an accuracy rate of 97.53% and AUC of 0.999. This is an improvement of 3% over previously developed techniques published in the literature. This study illustrated that LASSO with GP-based system performed outstanding performance in distinguishing children with ADHD from healthy children. This proposed system will be helpful to doctors and physicians in order to detect children with ADHD at an early stage and take the necessary steps for the patients to access appropriate healthcare services, receive effective treatment, and be more conscious of maintaining their lives. |
first_indexed | 2024-04-09T18:43:07Z |
format | Article |
id | doaj.art-a94b569d133944eb9ea46adbcf383db4 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-09T18:43:07Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-a94b569d133944eb9ea46adbcf383db42023-04-10T23:00:58ZengIEEEIEEE Access2169-35362023-01-0111335703358310.1109/ACCESS.2023.326426610091501Optimal Channels and Features Selection Based ADHD Detection From EEG Signal Using Statistical and Machine Learning TechniquesMd. Maniruzzaman0https://orcid.org/0000-0001-6151-8071Md. Al Mehedi Hasan1https://orcid.org/0000-0003-2966-7055Nobuyoshi Asai2https://orcid.org/0000-0002-8832-0521Jungpil Shin3https://orcid.org/0000-0002-7476-2468School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, JapanDepartment of Computer Science and Engineering, Rajshahi University of Engineering and Technology, Rajshahi, BangladeshSchool of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, JapanSchool of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, JapanAttention deficit hyperactivity disorder (ADHD) is one of the major psychiatric and neurodevelopment disorders worldwide. Electroencephalography (EEG) signal-based approach is very important for the early detection and classification of children with ADHD. However, diagnosing children with ADHD using full EEG channels with all features may lead to computational complexity and overfitting problems. To solve these problems, machine learning (ML)-based ADHD detection was designed by identifying optimal channels and its significant features. In this work, support vector machine and t-test based, two separate approaches were devised to select optimal channels individually and then proposed a hybrid channel selection approach by combining these two channel selection methods in order to select the optimal channels. After that, LASSO logistic regression-based model was used to select the important features from the selected channels. Finally, six ML-based classifiers, like Gaussian process classification (GPC), random forest, k-nearest neighbors, multilayer perceptron, decision tree, and logistic regression were applied for the detection of children with ADHD and evaluated their performances using accuracy and area under the curve (AUC). This study utilized a total of one hundred twenty-one children, with sixty-one children with ADHD, aged 7-12 years, and had nineteen channels. Ten different channels were selected by SVM based and an independent t-test-based approach separately and six overlapping channels were identified from both channel selection methods. Then, we selected twenty-eight features from selected six channels using LASSO. Using only six channels and twenty-eight features, GP-based classifier achieved an accuracy rate of 97.53% and AUC of 0.999. This is an improvement of 3% over previously developed techniques published in the literature. This study illustrated that LASSO with GP-based system performed outstanding performance in distinguishing children with ADHD from healthy children. This proposed system will be helpful to doctors and physicians in order to detect children with ADHD at an early stage and take the necessary steps for the patients to access appropriate healthcare services, receive effective treatment, and be more conscious of maintaining their lives.https://ieeexplore.ieee.org/document/10091501/Attention deficit hyperactivity disorderelectroencephalographychannel selectiont-testfeature selectionmachine learning |
spellingShingle | Md. Maniruzzaman Md. Al Mehedi Hasan Nobuyoshi Asai Jungpil Shin Optimal Channels and Features Selection Based ADHD Detection From EEG Signal Using Statistical and Machine Learning Techniques IEEE Access Attention deficit hyperactivity disorder electroencephalography channel selection t-test feature selection machine learning |
title | Optimal Channels and Features Selection Based ADHD Detection From EEG Signal Using Statistical and Machine Learning Techniques |
title_full | Optimal Channels and Features Selection Based ADHD Detection From EEG Signal Using Statistical and Machine Learning Techniques |
title_fullStr | Optimal Channels and Features Selection Based ADHD Detection From EEG Signal Using Statistical and Machine Learning Techniques |
title_full_unstemmed | Optimal Channels and Features Selection Based ADHD Detection From EEG Signal Using Statistical and Machine Learning Techniques |
title_short | Optimal Channels and Features Selection Based ADHD Detection From EEG Signal Using Statistical and Machine Learning Techniques |
title_sort | optimal channels and features selection based adhd detection from eeg signal using statistical and machine learning techniques |
topic | Attention deficit hyperactivity disorder electroencephalography channel selection t-test feature selection machine learning |
url | https://ieeexplore.ieee.org/document/10091501/ |
work_keys_str_mv | AT mdmaniruzzaman optimalchannelsandfeaturesselectionbasedadhddetectionfromeegsignalusingstatisticalandmachinelearningtechniques AT mdalmehedihasan optimalchannelsandfeaturesselectionbasedadhddetectionfromeegsignalusingstatisticalandmachinelearningtechniques AT nobuyoshiasai optimalchannelsandfeaturesselectionbasedadhddetectionfromeegsignalusingstatisticalandmachinelearningtechniques AT jungpilshin optimalchannelsandfeaturesselectionbasedadhddetectionfromeegsignalusingstatisticalandmachinelearningtechniques |