ADHD ve Sağlıklı Bireylerin Tanısında Boyut Azaltan Zamansal Karakteristik Özellik Çıkarma Yaklaşımı ve 1D-CNN

Yıl 2023, , 349 - 359, 27.10.2023

Kutlucan Görür

https://doi.org/10.46387/bjesr.1336892

Öz

EEG sinyalleri, bir çocukluk nörogelişimsel bozukluğu olan ADHD/ Attention Deficit Hyperactivity Disorder (Dikkat Eksikliği Hiperaktivite Bozukluğu) ile ilgili kritik bilgileri ayıklamak için güvenilir bir şekilde kullanılabilir. ADHD'nin erken tespiti, bu bozukluğun gelişimini azaltmak ve uzun vadeli etkisini azaltmak için önemlidir. Bu çalışmanın amacı, katılımcıların ekran üzerindeki rakamları takip etmeleri istenirken toplanan Elektroensefalografi (EEG) sinyallerinden, t-SNE tekniği ile zaman alanında özellik çıkarıldıktan sonra, RNN (Recurrent Neural Network) derin öğrenme modelleri ile ADHD ve sağlıklı bireyleri ayıran yüksek bir tahmin başarısına sahip bir çalışma-çerçevesi tanımlamaktır. Çalışmaya 15 ADHD hastası ve 15 sağlıklı kontrol bireyi dahil edilmiştir. 15’er kişiden oluşan veri setleri (ACC: ≤100% ve AUC: 1), 10’ar kişiden oluşan veri setlerinden (ACC: ≥94.23% ve AUC: 1) daha başarılı sonuçlar ürettiğini göstermiştir. t-SNE, yüksek boyutlu özellik görselleştirme veri gösterim tekniği olarak kullanıldığında da her iki grubun da önemli ölçüde ayırt edilebildiğini ortaya koymuştur. Bulgular, ADHD'nin erken teşhisinde ve objektif tanısında yardımcı olacağı düşünülmektedir.

Anahtar Kelimeler

ADHD, t-SNE Özellik Çıkarma, Derin Öğrenme, Hastalık Teşhisi

Low Dimensionality Temporal Characteristic Feature Extraction Approach and 1D-CNN for Diagnosing ADHD and Healthy Individuals

Öz

EEGs (Electroencephalography) can be reliably used to extract critical information about ADHD/Attention Deficit Hyperactivity Disorder, a childhood neurodevelopmental disorder. Early detection of ADHD is important to reduce the development of this disorder and lessen its long-term impact. This study aims to achieve a high prediction success framework that distinguishes ADHD and healthy individuals with RNN (Recurrent Neural Network) models, after extracting the features with the t-SNE technique from the EEGs. It is to define a high-success framework that has 15 ADHD patients and 15 healthy controls included in the study. Datasets comprising 15 people (ACC: ≤100% and AUC: 1) have shown more successful results than datasets comprising 10 people (ACC: ≥94.23% and AUC: 1). Both groups were significantly distinguishable when t-SNE was used as a high-dimensional feature visualization data display technique. The findings are thought to be helpful in the early and objective diagnosis of ADHD.

Anahtar Kelimeler

ADHD, t-SNE Feature Extraction, Deep Learning, Diagnostic

Kaynakça

• M. Maniruzzaman, M.A.M. Hasan, N. Asai, and J. Shin “Optimal Channels and Features Selection Based ADHD Detection From EEG Signal Using Statistical and Machine Learning Techniques,” IEEE Access, vol. 11, pp. 33570–33583, 2023.
• G. Hámori et al. “Adolescent ADHD and electrophysiological reward responsiveness: A machine learning approach to evaluate classification accuracy and prognosis,” Psychiatry Res., vol. 323, p. 115139, 2023.
• A. Alim and M.H. Imtiaz “Automatic Identification of Children with ADHD from EEG Brain Waves,” Signals, vol. 4, no. 1, pp. 193–205, Feb. 2023
• S.K. Khare and U.R. Acharya “An explainable and interpretable model for attention deficit hyperactivity disorder in children using EEG signals,” Comput. Biol. Med., vol. 155, p. 106676, Mar. 2023
• Y.S. Liu, B. Cao, and P.R. Chokka “Screening for Adulthood ADHD and Comorbidities in a Tertiary Mental Health Center Using EarlyDetect: A Machine Learning-Based Pilot Study,” J. Atten. Disord., vol. 27, no. 3, pp. 324–331, Feb. 2023
• C.-C. Chen, E.H.-K. Wu, Y.-Q. Chen, H.-J. Tsai, C.-R. Chung, and S.-C. Yeh “Neuronal Correlates of Task Irrelevant Distractions Enhance the Detection of Attention Deficit/Hyperactivity Disorder,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 31, pp. 1302–1310, 2023
• O. Karabiber Cura, S. Kocaaslan Atli, and A. Akan “Attention deficit hyperactivity disorder recognition based on intrinsic time-scale decomposition of EEG signals,” Biomed. Signal Process. Control, vol. 81, p. 104512, Mar. 2023
• R.C. Joy et al. “Detection and Classification of ADHD from EEG Signals Using Tunable Q-Factor Wavelet Transform,” J. Sensors, vol. 2022, pp. 1–17, 2022.
• H. Deng et al. “Systematic bibliometric and visualized analysis of research hotspots and trends in attention-deficit hyperactivity disorder neuroimaging,” Front. Neurosci., vol. 17, 2023.
• A. Khaleghi, P.M. Birgani, M.F. Fooladi, and M.R. Mohammadi “Applicable features of electroencephalogram for ADHD diagnosis,” Res. Biomed. Eng., vol. 36, no. 1, pp. 1–11, 2020.
• M. Altınkaynak et al., “Diagnosis of Attention Deficit Hyperactivity Disorder with combined time and frequency features,” Biocybern. Biomed. Eng., vol. 40, no. 3, pp. 927–937, Jul. 2020.
• M. Svantesson, H. Olausson, A. Eklund, and M. Thordstein “Get a New Perspective on EEG: Convolutional Neural Network Encoders for Parametric t-SNE,” Brain Sci., vol. 13, no. 3, p. 453, 2023.
• S. Hwang, K. Hong, G. Son, and H. Byun “Learning CNN features from DE features for EEG-based emotion recognition,” Pattern Anal. Appl., vol. 23, no. 3, pp. 1323–1335, 2020.
• O.P. Idowu, A.E. Ilesanmi, X. Li, O W. Samuel, P. Fang, and G. Li “An integrated deep learning model for motor intention recognition of multi-class EEG Signals in upper limb amputees,” Comput. Methods Programs Biomed., vol. 206, p. 106121, 2021.
• J. Xu, H. Zheng, J. Wang, D. Li, and X. Fang “Recognition of EEG Signal Motor Imagery Intention Based on Deep Multi-View Feature Learning,” Sensors, vol. 20, no. 12, p. 3496, 2020.
• T. Nishimoto, H. Higashi, H. Morioka, and S. Ishii “EEG-based personal identification method using unsupervised feature extraction and its robustness against intra-subject variability,” J. Neural Eng., vol. 17, no. 2, p. 026007, 2020.
• Z. Wang, Y. Wang, J. Zhang, C. Hu, Z. Yin, and Y. Song “Spatial-Temporal Feature Fusion Neural Network for EEG-Based Emotion Recognition,” IEEE Trans. Instrum. Meas., vol. 71, pp. 1–12, 2022.
• M. Sun, W. Cui, S. Yu, H. Han, B. Hu, and Y. Li “A Dual-Branch Dynamic Graph Convolution Based Adaptive TransFormer Feature Fusion Network for EEG Emotion Recognition,” IEEE Trans. Affect. Comput., vol. 13, no. 4, pp. 2218–2228, 2022.
• “EEG DATA FOR ADHD / CONTROL CHILDREN.” https://ieee-dataport.org/open-access/eeg-data-adhd-control-children.
• “Recurrence Plot.” https://www.mathworks.com/matlabcentral/fileexchange/58246-tool-box-of-recurrence-plot-and-recurrence quantification-analysis.
• H. W. Loh et al. “Deep neural network technique for automated detection of ADHD and CD using ECG signal,” Comput. Methods Programs Biomed., vol. 241, p. 107775, 2023.
• Ö. Kasim and M. Tosun “Biometric Authentication from Photic Stimulated EEG Records,” Appl. Artif. Intell., vol. 35, no. 15, pp. 1407–1419, 2021
• R. Du, S. Zhu, H. Ni, T. Mao, J. Li, and R. Wei “Valence-arousal classification of emotion evoked by Chinese ancient-style music using 1D-CNN-BiLSTM model on EEG signals for college students,” Multimed. Tools Appl., vol. 82, no. 10, pp. 15439–15456, 2023.
• S. Shanmugam and S. Dharmar “A CNN-LSTM hybrid network for automatic seizure detection in EEG signals,” Neural Comput. Appl., vol. 35, no. 28, pp. 20605–20617, 2023.
• K. Gorur and B. Eraslan “The single-channel dry electrode SSVEP-based biometric approach: data augmentation techniques against overfitting for RNN-based deep models,” Phys. Eng. Sci. Med., vol. 45, no. 4, pp. 1219–1240, 2022.
• I. Ozer, C.K. Ozer, A.C. Karaca, K. Gorur, I. Kocak, and O. Cetin “Species-level microfossil identification for globotruncana genus using hybrid deep learning algorithms from the scratch via a low-cost light microscope imaging,” Multimed. Tools Appl., vol. 82, no. 9, pp. 13689–13718, 2023.
• “Time Domain Analysis.” https://www.quora.com/What-are-the-advantages-and-disadvantages-of-frequency-domain-analysis-compared-to-time-domain-analysis.
• “Functional Connectivity.” https://www.mathworks.com/matlabcentral/fileexchange/48576-circulargraph.
• “Brain Mapping.” https://www.mathworks.com/matlabcentral/fileexchange/72729-topographic-eeg-meg-plot.
• K. Rubia et al. “Functional connectivity changes associated with fMRI neurofeedback of right inferior frontal cortex in adolescents with ADHD,” Neuroimage, vol. 188, pp. 43–58, 2019.
• G. Leisman and R. Melillo “Front and center: Maturational dysregulation of frontal lobe functional neuroanatomic connections in attention deficit hyperactivity disorder,” Front. Neuroanat., vol. 16, 2022.
• A.F.T. Arnsten “The Emerging Neurobiology of Attention Deficit Hyperactivity Disorder: The Key Role of the Prefrontal Association Cortex,” J. Pediatr., vol. 154, no. 5, pp. I-S43, 2009.
• L. Dubreuil-Vall, G. Ruffini, and J. A. Camprodon “Deep Learning Convolutional Neural Networks Discriminate Adult ADHD From Healthy Individuals on the Basis of Event-Related Spectral EEG,” Front. Neurosci., vol. 14, Apr. 2020
• A. Parashar, N. Kalra, J. Singh, and R. Kumar Goyal, “Machine Learning Based Framework for Classification of Children with ADHD and Healthy Controls,” Intell. Autom. Soft Comput., vol. 28, no. 3, pp. 669–682, 2021.
• A. Ekhlasi, A. Motie Nasrabadi, and M. Mohammadi, “Classification of the Children with ADHD and Healthy Children Based on the Directed Phase Transfer Entropy of EEG Signals,” Front. Biomed. Technol., 2021.
• M. Maniruzzaman, J. Shin, M. Al Mehedi Hasan, and A. Yasumura “Efficient Feature Selection and Machine Learning Based ADHD Detection Using EEG Signal,” Comput. Mater. Contin., vol. 72, no. 3, pp. 5179–5195, 2022.
• D. Wang, D. Hong, and Q. Wu “Attention Deficit Hyperactivity Disorder Classification Based on Deep Learning,” IEEE/ACM Trans. Comput. Biol. Bioinforma., vol. 20, no. 2, pp. 1581–1586, 2023.