BackgroundThere are numerous event-related potential (ERP) studies in relation to attention-deficit hyperactivity disorder (ADHD), and a substantial number of ERP correlates of the disorder have been identified. However, most of the studies are limited to group differences in children. Independent component analysis (ICA) separates a set of mixed event-related potentials into a corresponding set of statistically independent source signals, which are likely to represent different functional processes. Using a support vector machine (SVM), a classification method originating from machine learning, this study aimed at investigating the use of such independent ERP components in differentiating adult ADHD patients from non-clinical controls by selecting a most informative feature set. A second aim was to validate the predictive power of the SVM classifier by means of an independent ADHD sample recruited at a different laboratory.MethodsTwo groups of age-matched adults (75 ADHD, 75 controls) performed a visual two stimulus go/no-go task. ERP responses were decomposed into independent components, and a selected set of independent ERP component features was used for SVM classification.ResultsUsing a 10-fold cross-validation approach, classification accuracy was 91%. Predictive power of the SVM classifier was verified on the basis of the independent ADHD sample (17 ADHD patients), resulting in a classification accuracy of 94%. The latency and amplitude measures which in combination differentiated best between ADHD patients and non-clinical subjects primarily originated from independent components associated with inhibitory and other executive operations.ConclusionsThis study shows that ERPs can substantially contribute to the diagnosis of ADHD when combined with up-to-date methods.

This study investigated whether treatment naïve adults with Attention Deficit Hyperactivity Disorder (ADHD; n = 33; 19 female) differed from healthy controls (n = 31; 17 female) in behavioral performance, event-related potential (ERP) indices of preparatory attention (CueP3 and late CNV), and reactive response control (Go P3, NoGo N2, and NoGo P3) derived from a visual cued Go/NoGo task. On several critical measures, Cue P3, late CNV, and NoGo N2, there were no significant differences between the groups. This indicated normal preparatory processes and conflict monitoring in ADHD patients. However, the patients had attenuated Go P3 and NoGoP3 amplitudes relative to controls, suggesting reduced allocation of attentional resources to processes involved in response control. The patients also had a higher rate of Go signal omission errors, but no other performance decrements compared with controls. Reduced Go P3 and NoGo P3 amplitudes were associated with poorer task performance, particularly in the ADHD group. Notably, the ERPs were not associated with self-reported mood or anxiety. The results provide electrophysiological evidence for reduced effortful engagement of attentional resources to both Go and NoGo signals when reactive response control is needed. The absence of group differences in ERP components indexing proactive control points to impairments in specific aspects of cognitive processes in an untreated adult ADHD cohort. The associations between ERPs and task performance provided additional support for the altered electrophysiological responses.

The study demonstrates the need to interpret BRIEF-A results within a broad differential diagnostic context, where measures of psychological distress are included in addition to neuropsychological tests. Uncertainty about the appropriateness of U.S. normative data in non-U.S. countries adds to the need for interpretive caution. (JINS, 2016, 22, 682-694).