Robust prediction of individual personality from brain functional connectome

Abstract

Neuroimaging studies have linked inter-individual variability in the brain to individualized personality traits. However, only one or several aspects of personality have been effectively predicted based on brain imaging features. The objective of this study was to construct a reliable prediction model of personality in a large sample by using connectome-based predictive modeling (CPM), a recently developed machine learning approach. High-quality resting-state functional magnetic resonance imaging data of 810 healthy young participants from the Human Connectome Project dataset were used to construct large-scale brain networks. Personality traits of the five-factor model (FFM) were assessed by the NEO Five Factor Inventory. We found that CPM successfully and reliably predicted all the FFM personality factors (agreeableness, openness, conscientiousness and neuroticism) other than extraversion in novel individuals. At the neural level, we found that the personality-associated functional networks mainly included brain regions within default mode, frontoparietal executive control, visual and cerebellar systems. Although different feature selection thresholds and parcellation strategies did not significantly influence the prediction results, some findings lost significance after controlling for confounds including age, gender, intelligence and head motion. Our finding of robust personality prediction from an individual's unique functional connectome may help advance the translation of 'brain connectivity fingerprinting' into real-world personality psychological settings.

Keywords: five-factor model; functional connectome; personality; predictive models; resting-state fMRI.

Fig. 1

CPM of agreeableness. (A, B) Scatter plots showing the correspondence between actual (x-axis) and predicted (y-axis) agreeableness values generated using CPM based on the positive and negative networks. (C, D) High-degree nodes (degree ≥6, larger spheres indicate nodes with higher degree) and their connections in the positive and negative networks. (E, F) Polar plots illustrating the 20 highest degree nodes summarized by overlap with canonical neural networks in the positive and negative networks.

Fig. 2

CPM of openness. (A, B) Scatter plots showing the correspondence between actual (x-axis) and predicted (y-axis) openness values generated using CPM based on the positive and negative networks. (C, D) High-degree nodes (degree ≥4, larger spheres indicate nodes with higher degree) and their connections in the positive and negative networks. (E, F) Polar plots illustrating the 20 highest degree nodes summarized by overlap with canonical neural networks in the positive and negative networks.

Fig. 3

CPM of conscientiousness. (A, B) Scatter plots showing the correspondence between actual (x-axis) and predicted (y-axis) conscientiousness values generated using CPM based on the positive and negative networks. (C, D) High-degree nodes (degree ≥4, larger spheres indicate nodes with higher degree) and their connections in the positive and negative networks. (E, F) Polar plots illustrating the 20 highest degree nodes summarized by overlap with canonical neural networks in the positive and negative networks.

Fig. 4

CPM of neuroticism. (A, B) Scatter plots showing the correspondence between actual (x-axis) and predicted (y-axis) neuroticism values generated using CPM based on the positive and negative networks. (C, D) High-degree nodes (degree ≥4, larger spheres indicate nodes with higher degree) and their connections in the positive and negative networks. (E, F) Polar plots illustrating the 20 highest degree nodes summarized by overlap with canonical neural networks in the positive and negative networks.

Fig. 5

CPM of extraversion. (A, B) Scatter plots showing the correspondence between actual (x-axis) and predicted (y-axis) extraversion values generated using CPM based on the positive and negative networks. (C, D) High-degree nodes (degree ≥4, larger spheres indicate nodes with higher degree) and their connections in the positive and negative networks. (E, F) Polar plots illustrating the 20 highest degree nodes summarized by overlap with canonical neural networks in the positive and negative networks.