Prediction of depressive symptoms severity based on sleep quality, anxiety, and gray matter volume: a generalizable machine learning approach across three datasets.

Background: Depressive symptoms are rising in the general population, but their associated factors are unclear. Although the link between sleep disturbances and depressive symptoms severity (DSS) is reported, the predictive role of sleep on DSS and the impact of anxiety and the brain on their relationship remained obscure.

Methods: Using three population-based datasets (N = 1813), we trained the machine learning models in the primary dataset (N = 1101) to assess the predictive role of sleep quality, anxiety problems, and brain structural (and functional) measurements on DSS, then we tested our models' performance in two independent datasets (N = 378, N = 334) to test the generalizability of our findings.

Insomnia and post-traumatic stress disorder: A meta-analysis on interrelated association (n = 57,618) and prevalence (n = 573,665).

Posttraumatic stress disorder (PTSD) is a common mental disorder, which is strongly associated with insomnia, yet their epidemiological overlap is poorly understood. To determine the convergent quantitative magnitude of their relationship, PubMed, EMBASE, Scopus, Web of Science, PubPsych, and PsycINFO were searched to identify studies that either reported the correlation or frequency of insomnia symptoms in PTSD and posttraumatic stress symptoms (PTSS), or both. Out of 3714 records, 75 studies met selection criteria and aggregate effect size (ES) estimates were generated for the correlations (K=44, comprising 57,618 subjects) and frequencies (K=33, comprising 573,665 subjects with PTSD/PTSS) of insomnia symptoms in PTSD/PTSS.