Background: Suicide prevention is a public health priority, but risk factors for suicide after medical hospitalization remain understudied. This problem is critical for women, for whom suicide rates in the United States are disproportionately increasing. Objective: To differentiate the risk of suicide attempt and self-harm following general medical hospitalization among women with depression, bipolar disorder, and chronic psychosis. Methods: We developed a machine learning algorithm that identified risk factors of suicide attempt and self-harm after general hospitalization using electronic health record data from 1628 women in the University of California Los Angeles Integrated Clinical and Research Data Repository. To assess replicability, we applied the algorithm to a larger sample of 140,848 women in the New York City Clinical Data Research Network. Results: The classification tree algorithm identified risk groups in University of California Los Angeles Integrated Clinical and Research Data Repository (area under the curve 0.73, sensitivity 73.4, specificity 84.1, accuracy 0.84), and predictor combinations characterizing key risk groups were replicated in New York City Clinical Data Research Network (area under the curve 0.71, sensitivity 83.3, specificity 82.2, and accuracy 0.84). Predictors included medical comorbidity, history of pregnancy-related mental illness, age, and history of suicide-related behavior. Women with antecedent medical illness and history of pregnancy-related mental illness were at high risk (6.9%–17.2% readmitted for suicide-related behavior), as were women below 55 years old without antecedent medical illness (4.0%–7.5% readmitted). Conclusions: Prevention of suicide attempt and self-harm among women following acute medical illness may be improved by screening for sex-specific predictors including perinatal mental health history.

Objective: To investigate predictors of psychiatric hospital readmission of children and adolescents, a systematic review and meta-analysis was conducted.Methods: Following PRISMA statement guidelines, a systematic literature search of articles published between 1997 and 2018 was conducted in PubMed/MEDLINE, Google Scholar, and PsycINFO for original peer-reviewed articles investigating predictors of psychiatric hospital readmission among youths (,18 years old). Effect sizes were extracted and combined by using random-effects meta-analysis. Covariates were investigated with meta-regression and subgroup analyses.Results: Thirty-three studies met inclusion criteria, containing information on 83,361 children and adolescents, of which raw counts of readmitted vs. non-readmitted youths were available for 76,219. Of these youths, 13.2% (N=10,076) were readmitted. The mean6SD study followup was 15.9615.0 months, and time to readmission was 13.1612.8 months. Readmission was associated with, but not limited to, suicidal ideation at index hospitalization (pooled odds ratio [OR pooled ]=2.35, 95% confidence interval [CI]=1.64-3.37), psychotic disorders (OR pooled =1.87, 95% CI=1.53-2.28), prior hospitalization (OR pooled =2.51, 95% CI=1.76-3.57), and discharge to residential treatment (OR pooled =1.84, 95% CI=1.07-3.16). There was evidence of moderate study bias. Prior investigations were methodologically and substantively heterogeneous, particularly for measurement of family-level factors.

Medication nonadherence among youth with SMI is highly prevalent. Children and adolescents with more severe illness and higher comorbidity burden are at greater risk for nonadherence. Positive interpersonal care processes and adherence to nonpharmacological treatment may be protective. These findings inform development of a risk profile for nonadherence among youth with SMI. Future prospective research is needed to address the shortcomings in the existing literature and inform interventions to improve adherence.

An unprecedented amount of clinical information is now available via electronic health records (EHRs). These massive data sets have stimulated opportunities to adapt computational approaches to track and identify target areas for quality improvement in mental health care. In this column, three key areas of EHR data science are described: EHR phenotyping, natural language processing, and predictive modeling. For each of these computational approaches, case examples are provided to illustrate their role in mental health services research. Together, adaptation of these methods underscores the need for standardization and transparency while recognizing the opportunities and challenges ahead.