Header

UZH-Logo

Maintenance Infos

Predictive neurofunctional markers of attention-deficit/hyperactivity disorder based on pattern classification of temporal processing


Hart, Heledd; Marquand, Andre F; Smith, Anna; Cubillo, Ana; Simmons, Andrew; Brammer, Michael; Rubia, Katya (2014). Predictive neurofunctional markers of attention-deficit/hyperactivity disorder based on pattern classification of temporal processing. Journal of the American Academy of Child and Adolescent Psychiatry, 53(5):569-578.e1.

Abstract

Objective

Attention-deficit/hyperactivity disorder (ADHD) is currently diagnosed on the basis of subjective measures, despite evidence for multi-systemic structural and neurofunctional deficits. A consistently observed neurofunctional deficit is in fine-temporal discrimination (TD). The aim of this proof-of-concept study was to examine the feasibility of distinguishing patients with ADHD from controls using multivariate pattern recognition analyses of functional magnetic resonance imaging (fMRI) data of TD.

Method

A total of 20 medication-naive adolescent male patients with ADHD and 20 age-matched healthy controls underwent fMRI while performing a TD task. The fMRI data were analyzed with Gaussian process classifiers to predict individual ADHD diagnosis based on brain activation patterns.

Results

The pattern of brain activation correctly classified up to 80% of patients and 70% of controls, achieving an overall classification accuracy of 75%. The distributed activation networks with the highest delineation between patients and controls corresponded to a distributed network of brain regions involved in TD and typically compromised in ADHD, including inferior and dorsolateral prefrontal, insula, and parietal cortices, and the basal ganglia, anterior cingulate, and cerebellum. These regions overlapped with areas of reduced activation in patients with ADHD relative to controls in a univariate analysis, suggesting that these are dysfunctional regions.

Conclusions

We show evidence that pattern recognition analyses combined with fMRI using a disorder-sensitive task such as timing have potential in providing objective diagnostic neuroimaging biomarkers of ADHD.

Abstract

Objective

Attention-deficit/hyperactivity disorder (ADHD) is currently diagnosed on the basis of subjective measures, despite evidence for multi-systemic structural and neurofunctional deficits. A consistently observed neurofunctional deficit is in fine-temporal discrimination (TD). The aim of this proof-of-concept study was to examine the feasibility of distinguishing patients with ADHD from controls using multivariate pattern recognition analyses of functional magnetic resonance imaging (fMRI) data of TD.

Method

A total of 20 medication-naive adolescent male patients with ADHD and 20 age-matched healthy controls underwent fMRI while performing a TD task. The fMRI data were analyzed with Gaussian process classifiers to predict individual ADHD diagnosis based on brain activation patterns.

Results

The pattern of brain activation correctly classified up to 80% of patients and 70% of controls, achieving an overall classification accuracy of 75%. The distributed activation networks with the highest delineation between patients and controls corresponded to a distributed network of brain regions involved in TD and typically compromised in ADHD, including inferior and dorsolateral prefrontal, insula, and parietal cortices, and the basal ganglia, anterior cingulate, and cerebellum. These regions overlapped with areas of reduced activation in patients with ADHD relative to controls in a univariate analysis, suggesting that these are dysfunctional regions.

Conclusions

We show evidence that pattern recognition analyses combined with fMRI using a disorder-sensitive task such as timing have potential in providing objective diagnostic neuroimaging biomarkers of ADHD.

Statistics

Citations

11 citations in Web of Science®
11 citations in Scopus®
Google Scholar™

Altmetrics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Economics
Dewey Decimal Classification:330 Economics
Language:English
Date:May 2014
Deposited On:10 Nov 2014 11:38
Last Modified:08 Dec 2017 08:03
Publisher:Elsevier
ISSN:0890-8567
Publisher DOI:https://doi.org/10.1016/j.jaac.2013.12.024

Download

Full text not available from this repository.
View at publisher