Search

The study objective was to apply machine learning methodologies to identify predictors of remission in a longitudinal sample of 296 adults with a primary diagnosis of obsessive compulsive disorder (OCD). Random Forests is an ensemble machine learning algorithm that has been successfully applied to large-scale data analysis across vast biomedical disciplines, though rarely in psychiatric research or for application to longitudinal data. When provided with 795 raw and composite scores primarily from baseline measures, Random Forest regression prediction explained 50.8% (5000-run average, 95% bootstrap confidence interval [CI]: 50.3–51.3%) of the variance in proportion of time spent remitted. Machine performance improved when only the most predictive 24 items were used in a reduced analysis. Consistently high-ranked predictors of longitudinal remission included Yale–Brown Obsessive Compulsive Scale (Y-BOCS) items, NEO items and subscale scores, Y-BOCS symptom checklist cleaning/washing compulsion score, and several self-report items from social adjustment scales. Random Forest classification was able to distinguish participants according to binary remission outcomes with an error rate of 24.6% (95% bootstrap CI: 22.9–26.2%). Our results suggest that clinically-useful prediction of remission may not require an extensive battery of measures. Rather, a small set of assessment items may efficiently distinguish high- and lower-risk patients and inform clinical decision-making. Copyright © 2015 John Wiley & Sons, Ltd.

Research has identified three personality subtypes in adults with eating disorders (EDs): a high-functioning, an undercontrolled, and an overcontrolled group. The current study investigated whether similar personality prototypes exist in adolescents with EDs, and whether these personality prototypes show relationships to external correlates indicative of diagnostic validity. Methods: Experienced clinicians from an adolescent practice-research network provided data on ED symptoms, DSM-IV comorbidity, personality pathology, and family and developmental history for 120 adolescent patients with EDs. Results: Consistent with the findings from the adult literature, three types of personality pathology emerged in adolescents: High functioning/Perfectionistic, Emotionally Dysregulated, and Avoidant/Depressed. The High-functioning prototype showed negative associations with comorbidity and positive associations with treatment response. The Emotionally Dysregulated prototype was specifically associated with externalizing Axis I and Cluster B Axis II disorders, poor school functioning, and adverse events in childhood. The Avoidant/Depressed prototype showed specific associations with internalizing Axis I and Clusters A Axis II disorders, poor peer relationships, poor maternal relationships, and internalizing disorders in first-degree relatives. Conclusions: These data support the presence of at least three diagnostically meaningful personality prototypes in adolescents with EDs, similar to those found previously in adults. Diagnosis of adolescents with EDs may be usefully supplemented by the assessment of personality style.