Individual level prediction of emerging suicide events in the pharmacologic treatment of bipolar disorder

BackgroundPatients with bipolar disorder have a high lifetime risk of suicide. Predicting, preventing and managing suicidal behavior are major goals in clinical practice. Changes in suicidal thoughts and behavior are common in the course of treatment of bipolar disorder.MethodsUsing a dataset from a randomized clinical trial of bipolar disorder treatment (N=98), we tested predictors of future suicidal behavior identified through a review of literature and applied marginal variable selection and machine learning methods. The performance of the models was assessed using the optimism-adjusted C statistic.ResultsNumber of prior hospitalizations, number of prior suicide attempts, current employment status and Hamilton Depression Scale were identified as predictors and a simple logistic regression model was constructed. This model was compared with a model incorporating interactions with treatment group assignment, and more complex variable selection methods (LASSO and Survival Trees). The best performing models had average optimism-adjusted C-statistics of 0.67 (main effects only) and 0.69 (Survival Trees). Incorporating medication group did not improve prediction performance of the models.ConclusionsThese results suggest that models with a few predictors may yield a clinically meaningful way to stratify risk of emerging suicide events in patients who are undergoing pharmacologic treatment for bipolar disorder.Significance StatementThis study aims to find out whether suicide events that occur during the pharmacological treatment of bipolar disorder, a severe psychiatric disorder that is highly associated with suicide behavior, can be predicted. Using existing methods, we developed and compared several predictive models. We showed that these models performed similarly to predictive models of other outcomes, such as treatment efficacy, in unipolar and bipolar depression. This suggests that suicide events during bipolar disorder may be a feasible target for individualized interventions in the future.

The Lynched Earth

Focusing first on Welty’s “A Worn Path” then Morrison’s Home, this chapter discusses the authors’ treatment of landscape, which reverberates with lingering touches of racialized violence and trauma, and identifies how black characters read and decode its various evocations. The characters’ ability to recognize trees as signposts of the lynched black male body demonstrates a political consciousness necessary for their survival. Trees in these works figure as totems of death and destruction and as potent life-forces, pointing expectantly toward survival and regeneration. Shifting from figurative burial to affirmative acts of intrusion and trespass, these texts’ protagonists defy the forces of immobilization and the stereotypical images of southern black women depicted in earlier pastoral formations. Ultimately, this chapter argues that Welty and Morrison reorient the apocalyptic visioning of the antipastoral by bending the arc toward resilience and resurrection, permitting their terrain to appear mutably as bleak and beautiful, frightening and futurist.

The probability of exitfrom registered unemployment, based on the example of Szczecin

The aim of the paper is to determine the influence of sex, age and education on the probability of exit from the registered unemployment in Szczecin. For the purposes of the study, the authors employed the survival analysis method, where they used survival trees built on the basis of the Kaplan-Meier estimators and adopted the statistic of the log-rank test as the splitting criterion. The research analysed the two most frequent reasons for deregistration, namely starting a job and the unemployed person’s failure to meet the conditions for being registered as unemployed. In addition, the study extracted subgroups of persons whom it took shortest and longestto start a job or deregister froma labour office. The analysis was based on the microdata from the Powiat Labour Office in Szczecin concerning persons who registered as unemployed in 2013 and were moni-tored until the end of 2014. The calculations were made in the R computer programme, using the partykit package and the ctree function. The research demonstrated that the probability of deregistration from the unemployment register because of finding a job depends solely on the age and education of the unemployed person, while the probability of getting removed from the unemployment register –on the two former determinants plus sex.

Survival forests under test: Impact of the proportional hazards assumption on prognostic and predictive forests for amyotrophic lateral sclerosis survival

We investigate the effect of the proportional hazards assumption on prognostic and predictive models of the survival time of patients suffering from amyotrophic lateral sclerosis. We theoretically compare the underlying model formulations of several variants of survival forests and implementations thereof, including random forests for survival, conditional inference forests, Ranger, and survival forests with L1 splitting, with two novel variants, namely distributional and transformation survival forests. Theoretical considerations explain the low power of log-rank-based splitting in detecting patterns in non-proportional hazards situations in survival trees and corresponding forests. This limitation can potentially be overcome by the alternative split procedures suggested herein. We empirically investigated this effect using simulation experiments and a re-analysis of the Pooled Resource Open-Access ALS Clinical Trials database of amyotrophic lateral sclerosis survival, giving special emphasis to both prognostic and predictive models.