fNIRS Classification of Adults With ADHD Enhanced by Feature Selection
Adult attention deficit hyperactivity disorder (ADHD), a prevalent psychiatric disorder, significantly impacts social, academic, and occupational functioning. However, it has been relatively less prioritized compared to childhood ADHD. This study employed a functional near-infrared spectroscopy (fNI...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10813598/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841555823542665216 |
|---|---|
| author | Minyeong Hong Suh-Yeon Dong Roger S. McIntyre Soon-Kiat Chiang Roger Ho |
| author_facet | Minyeong Hong Suh-Yeon Dong Roger S. McIntyre Soon-Kiat Chiang Roger Ho |
| author_sort | Minyeong Hong |
| collection | DOAJ |
| description | Adult attention deficit hyperactivity disorder (ADHD), a prevalent psychiatric disorder, significantly impacts social, academic, and occupational functioning. However, it has been relatively less prioritized compared to childhood ADHD. This study employed a functional near-infrared spectroscopy (fNIRS) during verbal fluency tasks in conjunction with machine learning (ML) techniques to differentiate between healthy controls (N =75) and ADHD individuals (N =120). Efficient feature selection in high-dimensional fNIRS datasets is crucial for improving accuracy. To address this, we propose a hybrid feature selection method that combines a wrapper-based and embedded approach, termed Bayesian-Tuned Ridge RFECV (BTR-RFECV). The proposed method facilitated streamlined feature selection and hyperparameter tuning in high-dimensional data, thereby reducing the number of features while enhancing accuracy. HbO features from the combined frontal and temporal regions were key, with the models achieving precision (89.89%), recall (89.74%), F-1 score (89.66%), accuracy (89.74%), MCC (78.36%), and GDR (88.45%). The outcomes of this study highlight the promising potential of combining fNIRS with ML as diagnostic tools in clinical settings, offering a pathway to significantly reduce manual intervention. |
| format | Article |
| id | doaj-art-476bc2f845814ab8ad9488c6fbea2977 |
| institution | Kabale University |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-476bc2f845814ab8ad9488c6fbea29772025-01-08T00:00:11ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102025-01-013322023110.1109/TNSRE.2024.352212110813598fNIRS Classification of Adults With ADHD Enhanced by Feature SelectionMinyeong Hong0https://orcid.org/0009-0007-4845-0501Suh-Yeon Dong1https://orcid.org/0000-0002-2960-7303Roger S. McIntyre2https://orcid.org/0000-0003-3123-4937Soon-Kiat Chiang3Roger Ho4Department of Information Technology Engineering, Sookmyung Women’s University, Seoul, South KoreaDivision of Artificial Intelligence Engineering, Sookmyung Women’s University, Seoul, South KoreaDepartment of Psychiatry, University of Toronto, Toronto, CanadaInstitute for Health Innovation and Technology (iHealthtech), National University of Singapore, Queenstown, SingaporeiHealthtech, National University of Singapore, Queenstown, SingaporeAdult attention deficit hyperactivity disorder (ADHD), a prevalent psychiatric disorder, significantly impacts social, academic, and occupational functioning. However, it has been relatively less prioritized compared to childhood ADHD. This study employed a functional near-infrared spectroscopy (fNIRS) during verbal fluency tasks in conjunction with machine learning (ML) techniques to differentiate between healthy controls (N =75) and ADHD individuals (N =120). Efficient feature selection in high-dimensional fNIRS datasets is crucial for improving accuracy. To address this, we propose a hybrid feature selection method that combines a wrapper-based and embedded approach, termed Bayesian-Tuned Ridge RFECV (BTR-RFECV). The proposed method facilitated streamlined feature selection and hyperparameter tuning in high-dimensional data, thereby reducing the number of features while enhancing accuracy. HbO features from the combined frontal and temporal regions were key, with the models achieving precision (89.89%), recall (89.74%), F-1 score (89.66%), accuracy (89.74%), MCC (78.36%), and GDR (88.45%). The outcomes of this study highlight the promising potential of combining fNIRS with ML as diagnostic tools in clinical settings, offering a pathway to significantly reduce manual intervention.https://ieeexplore.ieee.org/document/10813598/Verbal fluency taskfunctional near- infrared spectroscopyattention-deficit/hyperactivity disordermachine learningfeature selection |
| spellingShingle | Minyeong Hong Suh-Yeon Dong Roger S. McIntyre Soon-Kiat Chiang Roger Ho fNIRS Classification of Adults With ADHD Enhanced by Feature Selection IEEE Transactions on Neural Systems and Rehabilitation Engineering Verbal fluency task functional near- infrared spectroscopy attention-deficit/hyperactivity disorder machine learning feature selection |
| title | fNIRS Classification of Adults With ADHD Enhanced by Feature Selection |
| title_full | fNIRS Classification of Adults With ADHD Enhanced by Feature Selection |
| title_fullStr | fNIRS Classification of Adults With ADHD Enhanced by Feature Selection |
| title_full_unstemmed | fNIRS Classification of Adults With ADHD Enhanced by Feature Selection |
| title_short | fNIRS Classification of Adults With ADHD Enhanced by Feature Selection |
| title_sort | fnirs classification of adults with adhd enhanced by feature selection |
| topic | Verbal fluency task functional near- infrared spectroscopy attention-deficit/hyperactivity disorder machine learning feature selection |
| url | https://ieeexplore.ieee.org/document/10813598/ |
| work_keys_str_mv | AT minyeonghong fnirsclassificationofadultswithadhdenhancedbyfeatureselection AT suhyeondong fnirsclassificationofadultswithadhdenhancedbyfeatureselection AT rogersmcintyre fnirsclassificationofadultswithadhdenhancedbyfeatureselection AT soonkiatchiang fnirsclassificationofadultswithadhdenhancedbyfeatureselection AT rogerho fnirsclassificationofadultswithadhdenhancedbyfeatureselection |