Journal of depression & anxiety最新文献

Background: Reliable prediction of clinical progression over time can improve the outcomes of depression. Little work has been done integrating various risk factors for depression, to determine the combinations of factors with the greatest utility for identifying which individuals are at the greatest risk.

Materials and methods: This study demonstrates that data-driven Machine Learning (ML) methods such as Random Effects/Expectation Maximization (RE-EM) trees and Mixed Effects Random Forest (MERF) can be applied to reliably identify variables that have the greatest utility for classifying subgroups at greatest risk for depression. 185 young adults completed measures of depression risk, including rumination, worry, negative cognitive styles, cognitive and coping flexibilities and negative life events, along with symptoms of depression. We trained RE-EM trees and MERF algorithms and compared them to traditional Linear Mixed Models (LMMs) predicting depressive symptoms prospectively and concurrently with cross-validation.

Results: Our results indicated that the RE-EM tree and MERF methods model complex interactions, identify subgroups of individuals and predict depression severity comparable to LMM. Further, machine learning models determined that brooding, negative life events, negative cognitive styles, and perceived control were the most relevant predictors of future depression levels.

Conclusion: Random effects machine learning models have the potential for high clinical utility and can be leveraged for interventions to reduce vulnerability to depression.

Background: The increasing rate of comorbid posttraumatic stress and depressive symptoms among young adults presents a unique symptom presentation and challenges to treatment. The current study examined psychosocial barriers--external locus of control-- and facilitators-- social support-- in the posttraumatic stress and depressive symptoms association.

Methods: The current cross-sectional study was conducted among 701 Jamaican university participants, ages 18-30 years. Participants completed self-report measures of general demographic information as well as target variables which include the CES-D-10, Sense of control (external and internal locus of control), Short screening scale for DSM-IV posttraumatic stress disorder and social support measures.

Results: Majority of the sample was female (76.2%; n=534); and slightly more than half of the sample self-identified as Black/African ancestry (59.7%). External locus of control (LOC) partially mediated the relationship between posttraumatic stress and depressive symptoms, external locus of control (LOC) had a greater mediation magnitude than social support in the posttraumatic stress-depressive symptoms association (Indirect Effect=0.133, 95% CI-0.075-0.211). In post-hoc analyses women appeared more highly traumatized than their male counterparts (14.3%, χ² =8.032, p=0.005). The sub-sample of highly traumatized individuals reported higher levels of depression, posttraumatic stress symptoms, external LOC, and lower levels of social support and internal LOC than did individuals with lower levels of trauma.

Conclusion: Contrary to previous research, our findings indicate that external LOC partially mediated the relationship between posttraumatic stress and depressive symptoms among a Jamaica university sample more so than social support. These findings therefore suggest that psychosocial treatments should consider locus of control focused interventions or skill building for young adults who suffer from posttraumatic stress and depressive symptoms.