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.

Levetiracetam for treatment of premenstrual dysphoric disorder: a pilot, open-label study.

Kindling and impaired electroencephalophysiology have been suggested to play a role in the pathophysiology of premenstrual dysphoric disorder (PMDD). Levetiracetam is a novel antiepileptic drug which has shown strong anti-kindling activity in animal models of epilepsy. In this preliminary prospective study we examined the safety and efficacy of levetiracetam for the treatment of PMDD. One hundred twenty-three potential patients were prospectively screened to enroll seven patients into the open-label treatment phase of the study. PMDD was diagnosed per DSM-IV-TR criteria and two consecutive months of prospective ratings of Daily Record of Severity of Problems (DRSP). The Mini International Neuropsychiatric Interview (MINI) was used to exclude any co-morbid conditions. Levetiracetam was started at 250 mg qhs at the end of the first week of the follicular phase. Dosage was gradually increased up to 1,500 mg bid as tolerated or clinically effective. The treatment phase lasted 4 months. Response to treatment was evaluated by Clinical Global Impression (CGI) and DRSP scores. Six out of seven patients experienced a considerable decrease in their DRSP scores with levetiracetam, starting from the first treatment cycle. One patient dropped out of the study due to lack of efficacy after one cycle. Medication was fairly well tolerated. Improvements in food cravings and premenstrual headaches were also noted as unexpected benefits. Anticonvulsant medications, specifically levetiracetam, could be effective in the treatment of PMDD. Future double-blind, placebo controlled, randomized studies are warranted and should include larger number of patients.