Predicting verbal and performance intelligence quotients from multimodal data in individuals with attention...

Area of Science:

• Neuroscience
• Neuroimaging
• Cognitive Psychology

Background:

• Understanding intelligence in neurological disorders is crucial.
• Limited research exists on intelligence-related brain alterations in atypical neurodevelopmental disorders like ADHD.

Purpose of the Study:

• To investigate the relationship between brain structure, function, and intellectual performance in ADHD patients.
• To identify specific brain features that predict intellectual abilities in ADHD.

Main Methods:

• Utilized resting-state functional and structural MRI data from 139 ADHD patients.
• Extracted brain features including fractional amplitude of low-frequency fluctuation, regional homogeneity, and gray/white matter volumes.
• Employed a two-layer feature-selection method with support vector regression and 10-fold cross-validation.

Main Results:

• Models demonstrated good predictive performance, with correlation coefficients >0.41 (p<0.05).
• Key predictive brain regions identified in the prefrontal, parietal, and temporal lobes, as well as cerebellar areas.
• Voxel-based brain features effectively predicted intellectual performance.

Conclusions:

• Brain imaging indicators can adequately predict intellectual performance in ADHD patients.
• Findings provide a foundation for future neuroimaging studies on ADHD and intelligence.