Distinct personality profiles associated with disease risk and diagnostic status in eating disorders.

BACKGROUND: Personality traits have been associated with eating disorders (EDs) and comorbidities. However, it is unclear which personality profiles are premorbid risk rather than diagnostic markers. METHODS: We explored associations between personality and ED-related mental health symptoms using canonical correlation analyses. We investigated personality risk profiles in a longitudinal sample, associating personality at age 14 with onset of mental health symptoms at ages 16 or 19. Diagnostic markers were identified in a sample of young adults with anorexia nervosa (AN, n = 58) or bulimia nervosa (BN, n = 63) and healthy controls (n = 47). RESULTS: Two significant premorbid risk profiles were identified, successively explaining 7.93 % and 5.60 % of shared variance (Rc2). The first combined neuroticism (canonical loading, rs = 0.68), openness (rs = 0.32), impulsivity (rs = 0.29), and conscientiousness (rs = 0.27), with future onset of anxiety symptoms (rs = 0.87) and dieting (rs = 0.58). The other, combined lower agreeableness (rs = -0.60) and lower anxiety sensitivity (rs = -0.47), with future deliberate self-harm (rs = 0.76) and purging (rs = 0.55). Personality profiles associated with "core psychopathology" in both AN (Rc2 = 80.56 %) and BN diagnoses (Rc2 = 64.38 %) comprised hopelessness (rs = 0.95, 0.87) and neuroticism (rs = 0.93, 0.94). For BN, this profile also included impulsivity (rs = 0.60). Additionally, extraversion (rs = 0.41) was associated with lower depressive risk in BN. LIMITATIONS: The samples were not ethnically diverse. The clinical cohort included only females. There was non-random attrition in the longitudinal sample. CONCLUSIONS: The results suggest neuroticism and impulsivity as risk and diagnostic markers for EDs, with neuroticism and hopelessness as shared diagnostic markers. They may inform the design of more personalised prevention and intervention strategies.

Machine learning models for diagnosis and risk prediction in eating disorders, depression, and alcohol use disorder.

This study uses machine learning models to uncover diagnostic and risk prediction markers for eating disorders (EDs), major depressive disorder (MDD), and alcohol use disorder (AUD). Utilizing case-control samples (ages 18-25 years) and a longitudinal population-based sample (n=1,851), the models, incorporating diverse data domains, achieved high accuracy in classifying EDs, MDD, and AUD from healthy controls. The area under the receiver operating characteristic curves (AUC-ROC [95% CI]) reached 0.92 [0.86-0.97] for AN and 0.91 [0.85-0.96] for BN, without relying on body mass index as a predictor. The classification accuracies for MDD (0.91 [0.88-0.94]) and AUD (0.80 [0.74-0.85]) were also high. Each data domain emerged as accurate classifiers individually, with personality distinguishing AN, BN, and their controls with AUC-ROCs ranging from 0.77 to 0.89. The models demonstrated high transdiagnostic potential, as those trained for EDs were also accurate in classifying AUD and MDD from healthy controls, and vice versa (AUC-ROCs, 0.75-0.93). Shared predictors, such as neuroticism, hopelessness, and symptoms of attention-deficit/hyperactivity disorder, were identified as reliable classifiers. For risk prediction in the longitudinal population sample, the models exhibited moderate performance (AUC-ROCs, 0.64-0.71), highlighting the potential of combining multi-domain data for precise diagnostic and risk prediction applications in psychiatry.