We investigated the overall test-retest reliability and other psychometric properties of a self-report version of the Liebowitz Social Anxiety Scale (LSAS) translated into Hebrew. We also evaluated the utility of three new subscales that were identified by nonparametric analysis (multidimensional scaling; MDS). Two hundred and seven patients who sought treatment for social anxiety or panic disorder were evaluated. All patients completed the self-administered version of the LSAS. A subsample completed the LSAS a second time prior to the beginning of treatment. The results indicate that the self-report format of the LSAS translated into Hebrew demonstrates high test-retest reliability, internal consistency, and discriminant validity. Additionally, some evidence for convergent and divergent validity was noted, and treatment sensitivity was high. MDS analysis followed by the investigation of common underlying facets for items related in two-dimensional space identified three subgroups: 1) the Group Performance/Interaction ("Group") subscale that consists of group performance and group interaction items; 2) the Dyadic Interaction ("Dyadic") subscale that consists of Dyadic interaction items; and 3) the Public Activities ("Public") subscale that consists of individual activities carried out in public. The three new subscales identified by MDS appear to provide clinically relevant information that relates to both demographic and treatment outcome variables and warrant further study.

Background Currently, postpartum depression (PPD) screening is mainly based on self‐report symptom‐based assessment, with lack of an objective, integrative tool which identifies women at increased risk, before the emergent of PPD. We developed and validated a machine learning‐based PPD prediction model utilizing electronic health record (EHR) data, and identified novel PPD predictors. Methods A nationwide longitudinal cohort that included 214,359 births between January 2008 and December 2015, divided into model training and validation sets, was constructed utilizing Israel largest health maintenance organization's EHR‐database. PPD was defined as new diagnosis of a depressive episode or antidepressant prescription within the first year postpartum. A gradient‐boosted decision tree algorithm was applied to EHR‐derived sociodemographic, clinical, and obstetric features. Results Among the birth cohort, 1.9% (n = 4104) met the case definition of new‐onset PPD. In the validation set, the prediction model achieved an area under the curve (AUC) of 0.712 (95% confidence interval, 0.690–0.733), with a sensitivity of 0.349 and a specificity of 0.905 at the 90th percentile risk threshold, identifying PPDs at a rate more than three times higher than the overall set (positive and negative predictive values were 0.074 and 0.985, respectively). The model's strongest predictors included both well‐recognized (e.g., past depression) and less‐recognized (differing patterns of blood tests) PPD risk factors. Conclusions Machine learning‐based models incorporating EHR‐derived predictors, could augment symptom‐based screening practice by identifying the high‐risk population at greatest need for preventive intervention, before development of PPD.

No abstract