Are factors that predict conversion to psychosis associated with initial transition to a high risk state? An adolescent brain cognitive development study analysis.

OBJECTIVE: Previous work suggests that cognitive and environmental risk factors may predict conversion to psychosis in individuals at clinical high risk (CHRs) for the disorder. Less clear, however, is whether these same factors are also associated with the initial emergence of the high risk state in individuals who do not meet current threshold criteria for being considered high risk. METHOD: Here, using data from the Adolescent Brain Cognitive Development (ABCD) study, we examined associations between factors previously demonstrated to predict conversion to psychosis in CHRs with transition to a "high risk" state, here defined as having a distress score between 2 and 5 on any unusual thought content question in the Prodromal Questionnaire-Brief Child version. Of a sample of 5237 children (ages 11-12) studied at baseline, 470 transitioned to the high-risk state the following year. A logistic regression model was evaluated using age, cognition, negative and traumatic experiences, decline in school performance, and family history of psychosis as predictors. RESULTS: The overall model was significant (χ2 = 100.89, R2 = 0.042, p < .001). Significant predictors included number of negative life events, decline in school performance, number of trauma types, and verbal learning task performance. CONCLUSIONS: These results suggest that factors that predict conversion in CHR teenagers are also associated with initial emergence of a "high-risk" state in preadolescents. Limitations regarding the degree to which model factors and outcome in this study parallel those used in previous work involving psychosis risk in older teenagers are discussed.

Applications of Transductive Spectral Clustering Methods in a Military Medical Concussion Database.

Traumatic brain injury (TBI) is one of the most common forms of neurotrauma that has affected more than 250,000 military service members over the last decade alone. While in battle, service members who experience TBI are at significant risk for the development of normal TBI symptoms, as well as risk for the development of psychological disorders such as Post-Traumatic Stress Disorder (PTSD). As such, these service members often require intense bouts of medication and therapy in order to resume full return-to-duty status. The primary aim of this study is to identify the relationship between the administration of specific medications and reductions in symptomology such as headaches, dizziness, or light-headedness. Service members diagnosed with mTBI and seen at the Concussion Restoration Care Center (CRCC) in Afghanistan were analyzed according to prescribed medications and symptomology. Here, we demonstrate that in such situations with sparse labels and small feature sets, classic analytic techniques such as logistic regression, support vector machines, naïve Bayes, random forest, decision trees, and k-nearest neighbor are not well suited for the prediction of outcomes. We attribute our findings to several issues inherent to this problem setting and discuss several advantages of spectral graph methods.