Development of an early-warning system for high-risk patients for suicide attempt using deep learning and electronic health records.

Suicide is the tenth leading cause of death in the United States (US). An early-warning system (EWS) for suicide attempt could prove valuable for identifying those at risk of suicide attempts, and analyzing the contribution of repeated attempts to the risk of eventual death by suicide. In this study we sought to develop an EWS for high-risk suicide attempt patients through the development of a population-based risk stratification surveillance system. Advanced machine-learning algorithms and deep neural networks were utilized to build models with the data from electronic health records (EHRs). A final risk score was calculated for each individual and calibrated to indicate the probability of a suicide attempt in the following 1-year time period. Risk scores were subjected to individual-level analysis in order to aid in the interpretation of the results for health-care providers managing the at-risk cohorts. The 1-year suicide attempt risk model attained an area under the curve (AUC ROC) of 0.792 and 0.769 in the retrospective and prospective cohorts, respectively. The suicide attempt rate in the "very high risk" category was 60 times greater than the population baseline when tested in the prospective cohorts. Mental health disorders including depression, bipolar disorders and anxiety, along with substance abuse, impulse control disorders, clinical utilization indicators, and socioeconomic determinants were recognized as significant features associated with incident suicide attempt.

Evaluation of Risk Factors for Antipsychotic Polypharmacy in Inpatient Psychiatry Units of a Community Hospital: A Retrospective Analysis.

Antipsychotic polypharmacy (APP) is a common practice while treating severe mental illness but the benefits of APP over antipsychotic monotherapy is controversial. This is a retrospective analysis comparing risk factors for people on APP and those on non-APP in inpatient psychiatry units. Two years data with 72 people in non-APP group and 82 people in APP group were analyzed quantitatively. The diagnoses of schizoaffective disorder (OR 11.5), schizophrenia (OR 4.65) and depression (OR 0.31), and history of > 2 psychiatric admissions (OR 3.2) and > 2 psychiatric emergency visits (OR 2.87) in 2 years were studied as potential risk factors for APP. Similarly, history of violence (OR 1.7) and history of substance abuse (OR 0.51) were also studied. Schizophrenia spectrum disorder, higher number of psychiatric hospitalizations, and psychiatric emergency visits were positively associated while depression and substance abuse were negatively associated with APP in our study.