Borderline Personality Traits Are Not Correlated With Brain Structure in Two Large Samples

BACKGROUND: Borderline personality disorder is associated with severe psychiatric presentations and has been linked to variability in brain structure. Dimensional models of borderline personality traits (BPTs) have become influential; however, associations between BPTs and brain structure remain poorly understood. METHODS: We tested whether BPTs are associated with regional cortical thickness, cortical surface area, and subcortical volumes (n = 152 brain structure metrics) in data from the Duke Neurogenetics Study (n = 1299) and Human Connectome Project (n = 1099). Positive control analyses tested whether BPTs are associated with related behaviors (e.g., suicidal thoughts and behaviors, psychiatric diagnoses) and experiences (e.g., adverse childhood experiences). RESULTS: While BPTs were robustly associated with all positive control measures, they were not significantly associated with any brain structure metrics in the Duke Neurogenetics Study or Human Connectome Project, or in a meta-analysis of both samples. The strongest findings from the meta-analysis showed a positive association between BPTs and volumes of the left ventral diencephalon and thalamus (p values < .005 uncorrected, p values > .1 false discovery rate-corrected). Contrasting high and low BPT decile groups (n = 552) revealed no false discovery rate-significant associations with brain structure. CONCLUSIONS: We find replicable evidence that BPTs are not associated with brain structure despite being correlated with independent behavioral measures. Prior reports linking brain morphology to borderline personality disorder may be driven by factors other than traits (e.g., severe presentations, comorbid conditions, severe childhood adversity, or medication) or reflect false positives. The etiology or consequences of BPTs may not be attributable to brain structure measured via magnetic resonance imaging. Future studies of BPTs will require much larger sample sizes to detect these very small effects.