Brain age prediction in generalized anxiety disorder using a convolutional neural network

Area of Science:

• Neuroimaging
• Psychiatry
• Aging Research

Background:

• Accelerated brain aging is linked to psychiatric disorders, with generalized anxiety disorder (GAD) showing potential aging markers.
• Previous research suggests a connection between GAD and accelerated brain aging, necessitating further investigation.

Purpose of the Study:

• To determine brain predicted age difference (PAD) in individuals with GAD compared to healthy controls (HC).
• To investigate group differences in PAD variability using voxel-wise structural MRI.
• To explore the relationship between GAD symptom severity and PAD.

Main Methods:

• Utilized a large dataset from the ENIGMA-Anxiety GAD Working Group (1595 GAD, 4552 HC).
• Employed a convolutional neural network model with four input modalities for brain age prediction.
• Calculated PAD by subtracting chronological age from predicted brain age.

Main Results:

• No significant evidence of accelerated brain aging in individuals with GAD compared to HC.
• Found significantly greater variability in PAD for individuals with GAD (Levene's test: W=442.98, p < 0.001).
• Exploratory analyses revealed a significant relationship between GAD symptom severity and PAD, independent of medication and comorbidities.

Conclusions:

• GAD is not associated with accelerated brain aging, contrary to some prior hypotheses.
• Increased heterogeneity in brain aging, indicated by PAD variability, is a key feature in GAD.
• Future research should consider the dimensional and heterogeneous nature of psychopathology in brain age studies.