Introduction

Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in children and adults characterized by inattention, excess activity, and impulsive behavior.

Electroencephalography (EEG) is widely used for diagnosing ADHD since 1938 [ 1 ]. The features extracted from EEG for ADHD classification or markers are as follows: absolute and relative power [ 2 ], theta/beta ratio [ 3 - 9 ], nonlinear features such as fractal dimension, Lyapunov exponent, entropy [ 10 - 13 ], event-related potentials features [ 14 , 15 ], and connectivity features [ 16 , 17 ].

EEG connectivity is a highly effective method to investigate synchronization between EEG channels, categorized into functional, nonlinear, effective, and information-based methods. Functional connectivity applies cross-correlation and coherence while effective connectivity uses Granger causality and partial directed coherence. Nonlinear connectivity measures are phase synchronization and generalized synchronization [ 18 ]. EEG functional connectivity has been a marker in developmental brain disorders, such as ADHD [ 19 - 22 ], and EEG coherence and weighted phase lag index are two examples of connectivity measures applied for separating ADHD and normal patients [ 23 - 26 ]. Ahmadlou et al. [ 27 ] used synchronization likelihood as a connectivity measure in combination with wavelet decomposition. EEG connectivity is also used for investigating and diagnosing other neurological disorders, such as Alzheimer’s disease [ 28 , 29 ], epilepsy [ 30 , 31 ], Parkinson’s disease [ 32 ], and autism [ 33 - 35 ].

Machine learning approaches have been widely applied in classifying medical diseases and disorders such as ADHD in the last two decades such as multilayer perceptron [ 12 ] and support vector machines [ 13 ].

Chen et al. [ 36 ] used convolutional neural networks (CNNs) in combination with a visualization technique to indicate personalized spatial-frequency differences between EEG signals of ADHD and normal children with an accuracy of 90.29%. In the other work, Chen et al. [ 17 ] used mutual information as a synchronization measure and rearranged it in a connectivity matrix in which some channels were repeated to ensure that adjacent channels were correctly stored in the matrix using a convolutional neural network with an accuracy of 94.67% on the test data as well. Moghaddari et al. [ 37 ] also used convolutional neural networks to classify ADHD and normal children. Considering multichannel EEG as an image, Moghaddari et al. decomposed EEG signals to its frequency sub-bands to make an RGB image and used it as CNN input. They also achieved an average accuracy of 98.48%. Ahmadi et al. [ 38 ] used a convolutional neural network with different bands and spatial filtering kernels and reported 99.46% accuracy for classifying ADHD and normal children.

This study aims to introduce CNN models with connectivity features extracted from EEG signals for classifying ADHD and normal children.

Material and Methods

In this experimental study, EEG data were used for ADHD/control children, which is available online [ 39 ].

Data Acquisition

The data was collected from 121 healthy and ADHD subjects (males and females) aged 7-12 years old. The experienced psychiatrist confirmed the disorder of the ADHD group, including 61 children by a diagnostic and statistical manual of mental disorders, fourth edition (DSM-IV) criteria. The control group consisted of 60 healthy children without any history of psychiatric disorders.

EEG signals were recorded based on 10-20 standards using 19 channels (Fz, Cz, Pz, C3, T3, C4, T4, Fp1, Fp2, F3, F4, F7, F8, P3, P4, T5, T6, O1, O2) with a sampling rate of 128 Hz. The reference electrodes were located on earlobes.

Based on the protocol description, participants were asked to count a set of comic strip pictures shown on a screen during EEG recording. The number of pictures in each image was randomly selected between 5 and 16. After child response, the next image was displayed immediately with a variety of the time duration of EEG recordings based on the average response speed [ 39 ].

The proposed method

The proposed method is described as follows: 1) data were preprocessed to remove noise and artifacts from EEG signals. Since deep CNNs usually use big data to train models, they were augmented to make big data and split it into train and test sets; in addition, the functional connectivity measure was calculated for all data epochs. The functional connectivity measures were arranged in four-dimensional (4D) and six-dimensional (6D) tensors according to their scalar or image nature. 4D connectivity and 6D scalogram tensors were given to the convolutional neural network as input.

Two different CNN architectures were used for 4D and 6D connectivity tensors; the train and validation sets were used for training the model and checking the model performance. 5-fold cross-validation was used to report the evaluation metrics of the model.

Data preprocessing and augmentation

EEG signals were bandpass filtered between 1 and 40 Hz using a 6^th order Butterworth filter. Then EEG signals were segmented into 2-second epochs with an overlap of 1s and those with amplitude exceeding 150 mv were removed due to motion artifacts. Independent component analysis (ICA) was used to minimize eye-blink artifacts [ 40 ]. Further, each epoch was considered as a sample to make big data; 7460 and 5561epochs of ADHD children and normal children were extracted.

A 5×5 channel location matrix was defined with all 19 channels to consider adjacent channels in a convolutional scheme. Figure 1 shows how the channels are located in the matrix; for example, the elements located at positions (3,4) and (4,5) represent C4 and P8 channels, respectively.

Figure 1. The proposed two-dimensional channel location matrixes.

Connectivity Measures and Tensors

In this study, two methods were used for measuring functional connectivity between EEG signals: synchronization likelihood (SL) and wavelet coherence (WC). SL is a nonlinear method between two signals calculated based on the distance of each point of the first signal from its nearest neighbors and the replacement of nearest neighbors by the equal time closest neighbors of the second signal. Based on chaos theory two signals are represented in embedding space [ 41 ].

Wavelet coherence is a linear method for coherence estimation between two signals considering non-stationarity by using wavelet transform, known as scalogram [ 42 ]. WC represents a two-dimensional (2D) map as a function of time and frequency as shown in Figure 2.

Figure 2. A sample of wavelet coherence between two electroencephalography channels

Functional connectivity should be measured between each two EEG channels, represented as a 2D matrix. In this work, the connectivity values were rearranged in a 4D tensor based on the described 2D channel location matrix. Hence a 2D by 2D (5×5×5×5) tensor is composed to represent the functional connectivity as a connectivity tensor. For example, the element located at the position (3,4,5) of the 4D connectivity tensor represents the functional connectivity value between C4 and P8 channels. A schematic stacked view of the 4D connectivity tensor is shown in Figure 3.

Figure 3. Block diagram of connectivity tensors construction; a) 4D connectivity tensor for synchronization likelihood (SL) and b) 6D connectivity tensor for wavelet coherence (WC).

Wavelet coherence represents functional connectivity between two channels as a 2D image with the connectivity matrix 6D for WC. To understand better this 6D tensor, the 4D connectivity tensor whose elements are 2D WC images individually was considered.

CNN Architecture

The convolutional neural network is a powerful tool for image classification with the main layers of a CNN, including convolutional, pooling, fully connected, and softmax layers. The convolutional layer extracts features from its input by using a kernel. During CNN training, the kernel coefficients are adjusted in a way to yield the minimum error and the pooling layer commonly comes after the convolutional layer(s) to reduce dimensionality and keep the best features. The fully connected layer flattens the output of its previous layer and feeds it to a common neural layer for predicting the classification output. Finally, the softmax layer generates the predicted class. In this study, for better representation of connectivity between nearby channels, CNNs were used, i.e. the inputs come in 4D and 6D for SL and WC connectivity measures, respectively. An architecture of 4D and 6D was used for the architecture of the CNNs. Tables 1 and 2 show the architecture of the proposed 4D and 6D CNNs, respectively. The input, convolutional, and pooling layers are 4D or 6D, while the fully connected layer flattens its input as common and processes in 1D.

Results

The proposed high dimensional convolutional neural networks were evaluated using 5-fold cross-validation. For this purpose, epochs were split into 5 subsets that in each fold, 4 subsets were used to train the model and the remaining subset was used for evaluation. Moreover, 20% of training data was kept for evaluation during training to prevent overfitting. The confusion matrix of 5 folds and the average for the proposed 4D and 6D CNNs are shown in Figures 4 and 5, respectively. On average, 4D CNN could truly predict 98.81% of ADHD epochs and 98.24% of normal epochs, while 6D CNN can truly predict 99.25% of ADHD epochs and 98.31% of normal epochs.

In supervised learning, accuracy is a fine metric to evaluate the model. Since the number of epochs in ADHD and control classes was not the same, F1_score, recall, and precision metrics were also used and defined according to the number of true positives (TP), i.e. the number of epochs associated truly with the ADHD group by the model, true negatives (TN), i.e. the number of epoch associated truly to the control group by the model, false positives (FP), i.e. the number of epochs associated wrongly to the ADHD group by the model, and false negatives (FN), i.e. the number of epochs associated wrongly to the control group by the model as below:

$\mathrm{Accuracy}=(\mathrm{TP}+\mathrm{TN})/(\mathrm{TP}+\mathrm{FP}+\mathrm{TN}+\mathrm{FN})$

$\mathrm{Precision}=\mathrm{TP}/(\mathrm{TP}+\mathrm{FP})$

$\mathrm{Recall}=\mathrm{TP}/(\mathrm{TP}+\mathrm{FN})$

$\mathrm{F1\_score}=\frac{(2\times recall\times precision)}{(recall+precision+recall)}$

Figure 4. Confusion matrices for 5-fold cross-validation of four-dimensional convolutional neural network classifier. Each confusion matrix shows true positive, true negative, false positive, and false negative of each fold with an average of 5 folds.

Figure 5. Confusion matrices for evaluation of six-dimensional convolutional neural network classifier. Each confusion matrix shows true positive, true negative, false positive, and false negative of each fold and the average of 5 folds.

Table 3 shows the described metrics for epoch-based classification.

Subject-based classification

The high-dimensional neural network was evaluated to classify each subject. For this purpose, all 2-second epochs of each subject were considered and the class of each subject for each of 5 trained models was determined by the most repetitive class. The final class for each subject was determined by the most voted class by the 5 trained models. Table 4 represents the results for subject-based classification.

Discussion

In this study, a novel CNN approach was proposed for classifying ADHD and normal children. Based on the importance of nearby channels in functional connectivity measures, a channel location matrix was designed and functional connectivity measures were arranged in 4D and 6D tensors, depending on their scalar or 2D image nature. The architectures designed for convolutional neural networks are capable of getting 4D or 6D tensors as input and setting the weights in the kernel of convolutional layers and fully connected layers to achieve minimum error. 13021 2-second epochs of EEG signals were extracted to make connectivity tensors and feed them to the proposed models. 5-fold cross-validation was utilized to assess the proposed models.

Kernels in convolutional layers of CNNs consider adjacent elements for processing. Moreover, adjacency among EEG channels plays an important role in connectivity analysis. Thus, considering adjacency among EEG channels is important before feeding connectivity measures to CNN. Since EEG electrodes are placed on the surface head, adjacency among EEG channels can be better represented in 2D (the described channel location matrix) rather than 1D. Hence, the connectivity measures could have higher dimensions, i.e. four-dimensional for scalar connectivity measures and six-dimensional for 2D connectivity measures. In comparison with arranging EEG channels in 1D and making a 2D connectivity matrix [ 17 ], connectivity tensors with higher dimensions to feed CNN can reach higher accuracy.

Table 5 shows comparing the proposed methods with similar previous works using EEG to diagnose ADHD. Moreover, in the current study, the dataset consists of 121 subjects, including 60 healthy and 61 ADHD children, which is significantly larger than mostly those used in other works. The accuracy of subject-based classification in the proposed method is 99.17%, comparable with other works.

Conclusion

In this paper, two architectures are presented for high dimensional convolutional networks to classify ADHD and normal children using EEG connectivity. The proposed methods use 4D and 6D connectivity tensors as convolutional neural network input, with a CNN architecture designed for better adjacent channels connectivity. Both of the proposed 4D and 6D CNNs could classify ADHD and normal children with 100% recall, 98.39% precision, and 99.17% accuracy, i.e. the proposed classifiers can successfully diagnose ADHD, and discriminate the ADHD and normal children significantly. In the future, we would study neural source-space methods in combination with the proposed method.

Authors’ Contribution

All authors contributed to this paper: M. Mafi wrote the article, gathered the images and the related literature, and analyzed the results. Also, M. Mafi and Shokoufeh Radfar supervised his research. Sh. Radfar clinically contributed to this study. All the authors read, modified, and approved the final version of the manuscript.

Ethical Approval

The Ethics Committee of Baqiyatallah University of Medical Sciences approved the protocol of the study (Ethic cod: IR.BMSU.REC.1399.458).

Informed consent

We have the consent of participants in preparing our article.

Conflict of Interest

None

References

1. Jasper HH, Solomon P, Bradley C. Electroencephalographic analyses of behavior problem children. Am J Psychiat. 1938; 95(3):641-58. DOI
2. Magee CA, Clarke AR, Barry RJ, McCarthy R, Selikowitz M. Examining the diagnostic utility of EEG power measures in children with attention deficit/hyperactivity disorder. Clin Neurophysiol. 2005; 116(5):1033-40. DOI | PubMed
3. Monastra VJ, Lubar JF, Linden M. The development of a quantitative electroencephalographic scanning process for attention deficit-hyperactivity disorder: reliability and validity studies. Neuropsychology. 2001; 15(1):136-44. DOI | PubMed
4. Snyder SM, Quintana H, Sexson SB, Knott P, Haque AF, Reynolds DA. Blinded, multi-center validation of EEG and rating scales in identifying ADHD within a clinical sample. Psychiatry Res. 2008; 159(3):346-58. DOI | PubMed
5. Ogrim G, Kropotov J, Hestad K. The quantitative EEG theta/beta ratio in attention deficit/hyperactivity disorder and normal controls: sensitivity, specificity, and behavioral correlates. Psychiatry Res. 2012; 198(3):482-8. DOI | PubMed
6. Liechti MD, Valko L, Müller UC, Döhnert M, et al. Diagnostic value of resting electroencephalogram in attention-deficit/hyperactivity disorder across the lifespan. Brain Topogr. 2013; 26(1):135-51. DOI | PubMed
7. Loo SK, Cho A, Hale TS, McGough J, McCracken J, Smalley SL. Characterization of the theta to beta ratio in ADHD: identifying potential sources of heterogeneity. J Atten Disord. 2013; 17(5):384-92. DOI | PubMed
8. Barry RJ, Clarke AR, Johnstone SJ, McCarthy R, Selikowitz M. Electroencephalogram theta/beta ratio and arousal in attention-deficit/hyperactivity disorder: evidence of independent processes. Biol Psychiatry. 2009; 66(4):398-401. DOI | PubMed
9. Williams LM, Hermens DF, Thein T, Clark CR, et al. Using brain-based cognitive measures to support clinical decisions in ADHD. Pediatr Neurol. 2010; 42(2):118-26. DOI | PubMed
10. Ghassemi F, Hassan_Moradi M, Tehrani-Doost M, Abootalebi V. Using non-linear features of EEG for ADHD/normal participants’ classification. Procedia Soc. 2012; 32:148-52. DOI
11. Sadatnezhad K, Boostani R, Ghanizadeh A. Classification of BMD and ADHD patients using their EEG signals. Expert Syst Appl. 2011; 38(3):1956-63. DOI
12. Mohammadi MR, Khaleghi A, Nasrabadi AM, et al. EEG classification of ADHD and normal children using non-linear features and neural network. Biomed Eng Lett. 2016; 6(2):66-73. DOI
13. Tor HT, Ooi CP, Lim-Ashworth NS, Wei JKE, et al. Automated detection of conduct disorder and attention deficit hyperactivity disorder using decomposition and nonlinear techniques with EEG signals. Comput Methods Programs Biomed. 2021; 200:105941. DOI | PubMed
14. Mueller A, Candrian G, Grane VA, Kropotov JD, et al. Discriminating between ADHD adults and controls using independent ERP components and a support vector machine: a validation study. Nonlinear Biomed Phys. 2011; 5:5. Publisher Full Text | DOI | PubMed
15. Nazhvani AD, Boostani R, Afrasiabi S, Sadatnezhad K. Classification of ADHD and BMD patients using visual evoked potential. Clin Neurol Neurosurg. 2013; 115(11):2329-35. DOI | PubMed
16. Ahmadlou M, Adeli H. Wavelet-synchronization methodology: a new approach for EEG-based diagnosis of ADHD. Clin EEG Neurosci. 2010; 41(1):1-10. DOI | PubMed
17. Chen H, Song Y, Li X. A deep learning framework for identifying children with ADHD using an EEG-based brain network. Neurocomputing. 2019; 356:83-96. DOI
18. Sakkalis V, Doru Giurc Neanu C, Xanthopoulos P, Zervakis ME, Tsiaras V, et al. Assessment of linear and nonlinear synchronization measures for analyzing EEG in a mild epileptic paradigm. IEEE Trans Inf Technol Biomed. 2009; 13(4):433-41. DOI | PubMed
19. Murias M, Swanson JM, Srinivasan R. Functional connectivity of frontal cortex in healthy and ADHD children reflected in EEG coherence. Cereb Cortex. 2007; 17(8):1788-99. Publisher Full Text | DOI | PubMed
20. Castellanos FX, Aoki Y. Intrinsic Functional Connectivity in Attention-Deficit/Hyperactivity Disorder: A Science in Development. Biol Psychiatry Cogn Neurosci Neuroimaging. 2016; 1(3):253-61. Publisher Full Text | DOI | PubMed
21. Debnath R, Miller NV, Morales S, Seddio KR, Fox NA. Investigating brain electrical activity and functional connectivity in adolescents with clinically elevated levels of ADHD symptoms in alpha frequency band. Brain Res. 2021; 1750:147142. Publisher Full Text | DOI | PubMed
22. Furlong S, Cohen JR, Hopfinger J, Snyder J, Robertson MM, Sheridan MA. Resting-state EEG Connectivity in Young Children with ADHD. J Clin Child Adolesc Psychol. 2021; 50(6):746-62. Publisher Full Text | DOI | PubMed
23. Clarke AR, Barry RJ, McCarthy R, Selikowitz M, et al. Coherence in children with Attention-Deficit/Hyperactivity Disorder and excess beta activity in their EEG. Clin Neurophysiol. 2007; 118(7):1472-9. DOI | PubMed
24. Dupuy FE, Clarke AR, Barry RJ, McCarthy R, Selikowitz M. EEG coherence in girls with attention-deficit/hyperactivity disorder: stimulant effects in good responders. Int J Psychophysiol. 2008; 70(3):151-7. DOI | PubMed
25. Michelini G, Jurgiel J, Bakolis I, Cheung CH, Asherson P, et al. Atypical functional connectivity in adolescents and adults with persistent and remitted ADHD during a cognitive control task. Transl psychiat. 2019; 9(1):1-15. DOI
26. Kiiski H, Rueda-Delgado LM, Bennett M, Knight R, Rai L, et al. Functional EEG connectivity is a neuromarker for adult attention deficit hyperactivity disorder symptoms. Clin Neurophysiol. 2020; 131(1):330-42. DOI | PubMed
27. Ahmadlou M, Adeli H, Adeli A. Graph theoretical analysis of organization of functional brain networks in ADHD. Clin EEG Neurosci. 2012; 43(1):5-13. DOI | PubMed
28. Briels CT, Schoonhoven DN, Stam CJ, De Waal H, Scheltens P, Gouw AA. Reproducibility of EEG functional connectivity in Alzheimer’s disease. Alzheimers Res Ther. 2020; 12(1):68. Publisher Full Text | DOI | PubMed
29. Hata M, Kazui H, Tanaka T, Ishii R, Canuet L, et al. Functional connectivity assessed by resting state EEG correlates with cognitive decline of Alzheimer’s disease - An eLORETA study. Clin Neurophysiol. 2016; 127(2):1269-78. DOI | PubMed
30. Van Mierlo P, Papadopoulou M, Carrette E, Boon P, Vandenberghe S, et al. Functional brain connectivity from EEG in epilepsy: seizure prediction and epileptogenic focus localization. Prog Neurobiol. 2014; 121:19-35. DOI | PubMed
31. Van Mierlo P, Höller Y, Focke NK, Vulliemoz S. Network Perspectives on Epilepsy Using EEG/MEG Source Connectivity. Front Neurol. 2019; 10:721. Publisher Full Text | DOI | PubMed
32. Bočková M, Rektor I. Impairment of brain functions in Parkinson’s disease reflected by alterations in neural connectivity in EEG studies: a viewpoint. Clin Neurophysiol. 2019; 130(2):239-47. DOI
33. Peters JM, Taquet M, Vega C, Jeste SS, Fernández IS, et al. Brain functional networks in syndromic and non-syndromic autism: a graph theoretical study of EEG connectivity. BMC Med. 2013; 11:54. Publisher Full Text | DOI | PubMed
34. O’Reilly C, Lewis JD, Elsabbagh M. Is functional brain connectivity atypical in autism? A systematic review of EEG and MEG studies. PLoS One. 2017; 12(5):e0175870. Publisher Full Text | DOI | PubMed
35. Wang J, Wang X, Wang X, Zhang H, Zhou Y, Chen L, Li Y, Wu L. Increased EEG coherence in long-distance and short-distance connectivity in children with autism spectrum disorders. Brain Behav. 2020; 10(10):e01796. Publisher Full Text | DOI | PubMed
36. Chen H, Song Y, Li X. Use of deep learning to detect personalized spatial-frequency abnormalities in EEGs of children with ADHD. J Neural Eng. 2019; 16(6):066046. DOI | PubMed
37. Moghaddari M, Lighvan MZ, Danishvar S. Diagnose ADHD disorder in children using convolutional neural network based on continuous mental task EEG. Comput Methods Programs Biomed. 2020; 197:105738. DOI | PubMed
38. Ahmadi A, Kashefi M, Shahrokhi H, Nazari MA. Computer aided diagnosis system using deep convolutional neural networks for ADHD subtypes. Biomed Signal Proces. 2020; 63:102227. DOI
39. Nasrabadi AM, Allahverdy A, Samavati M, Mohammadi MR. EEG data for ADHD / Control children [Internet]. IEEE Dataport; 2020. DOI
40. Samavati M, Nasrabadi AM, Mohammadi MR. IEEE: Tehran, Iran; 2012. DOI
41. Stam CJ, Van Dijk B. Synchronization likelihood: an unbiased measure of generalized synchronization in multivariate data sets. Physica D: Nonlinear Phenomena. 2002; 163(3-4):236-51. DOI
42. Lachaux JP, Lutz A, Rudrauf D, Cosmelli D, Le Van Quyen M, et al. Estimating the time-course of coherence between single-trial brain signals: an introduction to wavelet coherence. Neurophysiol Clin. 2002; 32(3):157-74. DOI | PubMed