Deep Learning Convolutional Neural Networks Discriminate Adult ADHD From Healthy Individuals on the Basis of Event-Related Spectral EEG

Abstract

Attention deficit hyperactivity disorder (ADHD) is a heterogeneous neurodevelopmental disorder that affects 5% of the pediatric and adult population worldwide. The diagnosis remains essentially clinical, based on history and exam, with no available biomarkers. In this paper, we describe a convolutional neural network (CNN) with a four-layer architecture combining filtering and pooling, which we train using stacked multi-channel EEG time-frequency decompositions (spectrograms) of electroencephalography data (EEG), particularly of event-related potentials (ERP) from ADHD patients (n = 20) and healthy controls (n = 20) collected during the Flanker Task, with 2800 samples for each group. We treat the data as in audio or image classification approaches, where deep networks have proven successful by exploiting invariances and compositional features in the data. The model reaches a classification accuracy of 88% ± 1.12%, outperforming the Recurrent Neural Network and the Shallow Neural Network used for comparison, and with the key advantage, compared with other machine learning approaches, of avoiding the need for manual selection of EEG spectral or channel features. The event-related spectrograms also provide greater accuracy compared to resting state EEG spectrograms. Finally, through the use of feature visualization techniques such as DeepDream, we show that the main features exciting the CNN nodes are a decreased power in the alpha band and an increased power in the delta-theta band around 100 ms for ADHD patients compared to healthy controls, suggestive of attentional and inhibition deficits, which have been previously suggested as pathophyisiological signatures of ADHD. While confirmation with larger clinical samples is necessary, these results suggest that deep networks may provide a useful tool for the analysis of EEG dynamics even from relatively small datasets, highlighting the potential of this methodology to develop biomarkers of practical clinical utility.

Graph Theory Analysis of Microstates in Attention-Deficit Hyperactivity Disorder

“…The Frequency of Occurrence, Duration Time, and Transition Probabilities from microstates were calculated using the Microstate EEGlab Toolbox (Poulsen et al, 2018). The most recent works involving the use of machine learning to identify ADHD use deep learning techniques with EEG signals (Vahid et al, 2019;Dubreuil-Vall et al, 2020).The work of Vahid et al (2019) was the first study showing that deep learning methods applied to EEG data are capable to dissociate between patients with ADHD and healthy controls with accuracy up to 86%. In their work was used EEGNet model as a deep learning architecture.…”

“…(Ahmadi et al, 2014;Ghanizadeh, 2011), complicating the diagnosis. Therefore, a biomarker can be of great value to reduce the inherent uncertainty of clinical diagnosis (Dubreuil-Vall et al, 2020;Vahid et al, 2019). In recent years, several studies have been carried out to assess the usefulness of neurophysiological (electroencephalography -EEG) and functional image data to assist in the process of diagnosing ADHD (Vahid et al, 2019;Dubreuil-Vall et al, 2020).…”

Artificial Intelligence in Translational Medicine

“…Based on the results presented by the authors, the computational tool can correctly categorize ADHD patients, showing an accuracy value of 88%, outperforming other models such as RNN and other ML models previously reported. Although the data are interesting and promising, studies considering a more consistent number of participants are highly desirable [273].…”

Artificial Intelligence in Translational Medicine

“…Based on the results presented by the authors the computational tool can correctly categorize ADHD patients, showing an accuracy value of 88%, outperforming other models such as RNN and other ML models previously reported. Although the data are interesting and promising, studies considering a more consistent number of participants is highly desirable [262].…”