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

Area of Science:

• Neuroimaging
• Psychiatry
• Computational Neuroscience

Background:

• Attention-deficit/hyperactivity disorder (ADHD) diagnosis relies on subjective measures.
• Evidence suggests underlying structural and neurofunctional deficits in ADHD.
• Fine-temporal discrimination (TD) deficits are a consistent neurofunctional finding in ADHD.

Purpose of the Study:

• To assess the feasibility of using multivariate pattern recognition with fMRI data to differentiate individuals with ADHD from controls.
• To explore brain activation patterns during a TD task for diagnostic potential.

Main Methods:

• Functional magnetic resonance imaging (fMRI) was used in 20 medication-naive adolescent males with ADHD and 20 age-matched healthy controls.
• Participants performed a fine-temporal discrimination (TD) task during fMRI scanning.
• Gaussian process classifiers analyzed fMRI data to predict ADHD diagnosis based on brain activation patterns.

Main Results:

• The pattern recognition analysis achieved an overall classification accuracy of 75%.
• Classification correctly identified 80% of ADHD patients and 70% of controls.
• Key differentiating brain regions included prefrontal, parietal, insula, basal ganglia, anterior cingulate, and cerebellum, areas known to be affected in ADHD.

Conclusions:

• Multivariate pattern recognition analysis of fMRI data shows promise for objective ADHD diagnosis.
• Combining fMRI with tasks sensitive to ADHD-related deficits, like TD, may yield valuable neuroimaging biomarkers.
• This approach could lead to more objective diagnostic tools for ADHD.