Brain functional connectome-based prediction of individual decision impulsivity

Area of Science:

• Neuroscience
• Cognitive Neuroscience
• Neuroimaging

Background:

• Identifying neural correlates of decision impulsivity is challenging due to inconsistent findings from previous studies.
• Limitations include small sample sizes, variable image quality, and methodological differences.

Purpose of the Study:

• To develop a reliable predictive model of the decision impulsivity-brain relationship using connectome-based predictive modeling (CPM).
• To leverage a large sample and high-quality resting-state functional MRI data for robust analysis.

Main Methods:

• Utilized resting-state functional MRI data from 809 healthy young participants (Human Connectome Project).
• Constructed whole-brain functional connectomes to serve as 'neural fingerprints'.
• Applied CPM with leave-one-out cross-validation to predict individual decision impulsivity (delay discounting scores).

Main Results:

• CPM successfully and reliably predicted individual decision impulsivity scores in novel participants.
• Prediction accuracy remained stable across different feature selection thresholds, parcellation strategies, and cross-validation approaches.
• Decision impulsivity was associated with functional networks including default-mode, subcortical, somato-motor, dorsal attention, and visual systems.

Conclusions:

• Decision impulsivity arises from integrated connections across multiple intrinsic brain networks.
• Findings enhance understanding of the neural mechanisms underlying decision impulsivity.
• Presents a potential pathway for translating neuroimaging findings into real-world economic decision-making applications.