Dataset Information

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.

SUBMITTER: Dubreuil-Vall L

PROVIDER: S-EPMC7160297 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Dubreuil-Vall Laura L Ruffini Giulio G Camprodon Joan A JA

Frontiers in neuroscience 20200409

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 electroencephalo ...[more]

PMID: 32327965

Similar Datasets

Project description:ObjectivesAlzheimer's disease (AD) is the most prevalent neurodegenerative disorder and the most common form of dementia in the elderly. Certain genes have been identified as important clinical risk factors for AD, and technological advances in genomic research, such as genome-wide association studies (GWAS), allow for analysis of polymorphisms and have been widely applied to studies of AD. However, shortcomings of GWAS include sensitivity to sample size and hereditary deletions, which result in low classification and predictive accuracy. Therefore, this paper proposes a novel deep-learning genomics approach and applies it to multitasking classification of AD progression, with the goal of identifying novel genetic biomarkers overlooked by traditional GWAS analysis.MethodsIn this study, we selected genotype data from 1461 subjects enrolled in the Alzheimer's Disease Neuroimaging Initiative, including 622 AD, 473 mild cognitive impairment (MCI), and 366 healthy control (HC) subjects. The proposed deep-learning genomics (DLG) approach consists of three steps: quality control, coding of single-nucleotide polymorphisms, and classification. The ResNet framework was used for the DLG model, and the results were compared with classifications by simple convolutional neural network structure. All data were randomly assigned to one training/validation group and one test group at a ratio of 9 : 1. And fivefold cross-validation was used.ResultsWe compared classification results from the DLG model to those from traditional GWAS analysis among the three groups. For the AD and HC groups, the accuracy, sensitivity, and specificity of classification were, respectively, 98.78 ± 1.50%, 98.39% ± 2.50%, and 99.44% ± 1.11% using the DLG model, while 71.38% ± 0.63%, 63.13% ± 2.87%, and 85.59% ± 6.66% using traditional GWAS. Similar results were obtained from the other two intergroup classifications.ConclusionThe DLG model can achieve higher accuracy and sensitivity when applied to progression of AD. More importantly, we discovered several novel genetic biomarkers of AD progression, including rs6311 and rs6313 in HTR2A, rs1354269 in NAV2, and rs690705 in RFC3. The roles of these novel loci in AD should be explored in future research.

Project description:BackgroundAttention-Deficit/Hyperactivity Disorder (ADHD) is a prevalent, complex disorder which is characterized by symptoms of inattention, hyperactivity, and impulsivity. Convergent evidence from neurobiological studies of ADHD identifies dysfunction in fronto-striatal-cerebellar circuitry as the source of behavioural deficits. Recent studies have shown that regions governing basic sensory processing, such as the somatosensory cortex, show abnormalities in those with ADHD suggesting that these processes may also be compromised.MethodsWe used event-related magnetoencephalography (MEG) to examine patterns of cortical rhythms in the primary (SI) and secondary (SII) somatosensory cortices in response to median nerve stimulation, in 9 adults with ADHD and 10 healthy controls. Stimuli were brief (0.2 ms) non-painful electrical pulses presented to the median nerve in two counterbalanced conditions: unpredictable and predictable stimulus presentation. We measured changes in strength, synchronicity, and frequency of cortical rhythms.ResultsHealthy comparison group showed strong event-related desynchrony and synchrony in SI and SII. By contrast, those with ADHD showed significantly weaker event-related desynchrony and event-related synchrony in the alpha (8-12 Hz) and beta (15-30 Hz) bands, respectively. This was most striking during random presentation of median nerve stimulation. Adults with ADHD showed significantly shorter duration of beta rebound in both SI and SII except for when the onset of the stimulus event could be predicted. In this case, the rhythmicity of SI (but not SII) in the ADHD group did not differ from that of controls.ConclusionOur findings suggest that somatosensory processing is altered in individuals with ADHD. MEG constitutes a promising approach to profiling patterns of neural activity during the processing of sensory input (e.g., detection of a tactile stimulus, stimulus predictability) and facilitating our understanding of how basic sensory processing may underlie and/or be influenced by more complex neural networks involved in higher order processing.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets