One of the main features of bipolar disorder is repletion of relapse overtime. Many studies have focused on time-to-first relapse using the most popular Cox proportional hazard model which discards subsequent information on recurrent relapses. The aim of this study was to identify some risk factors of time-to-recurrent relapses in bipolar disorder inpatients by using appropriate recurrent event model. Data on 206 inpatients, available at Amanuel mental specialized hospital, were collected by reviewing the medical records from September 11, 2013 to March 12, 2019. Different extended cox proportional hazard models including AG, PWP-TT, PWP-GT and semiparametric shared gamma frailty models were used. R package FrailtyEM package used to fit semi-parametric shared gamma frailty models through EM algorithm. The mean age of the patients was 33.33 years. Within the study time, a total of 418 inpatient admissions (relapses) were registered for 206 inpatients. Among these admissions, about 49.3% of the patients had first relapse and 50.7% of the patients had more than one relapses. The likelihood test results indicated that the appropriate model is the gap-time based semi-parametric shared gamma frailty model and the important risk factors that have effect on time since the end of the most recent relapse to the start of the next relapses are marital status, substance abuse, employment status and residence. Recurrent relapse may be reduced by giving more intensive forms of treatment and creating awareness on each risk factor.
For large observational studies lacking a control group (unlike randomized controlled trials, RCT), propensity scores (PS) are often the method of choice to account for pre-treatment confounding in baseline characteristics, and thereby avoid substantial bias in treatment estimation. A vast majority of PS techniques focus on average treatment effect estimation, without any clear consensus on how to account for confounders, especially in a multiple treatment setting. Furthermore, for time-to event outcomes, the analytical framework is further complicated in presence of high censoring rates (sometimes, due to non-susceptibility of study units to a disease), imbalance between treatment groups, and clustered nature of the data (where, survival outcomes appear in groups). Motivated by a right-censored kidney transplantation dataset derived from the United Network of Organ Sharing (UNOS), we investigate and compare two recent promising PS procedures, (a) the generalized boosted model (GBM), and (b) the covariate-balancing propensity score (CBPS), in an attempt to decouple the causal effects of treatments (here, study subgroups, such as hepatitis C virus (HCV) positive/negative donors, and positive/negative recipients) on time to death of kidney recipients due to kidney failure, post transplantation. For estimation, we employ a 2-step procedure which addresses various complexities observed in the UNOS database within a unified paradigm. First, to adjust for the large number of confounders on the multiple sub-groups, we fit multinomial PS models via procedures (a) and (b). In the next stage, the estimated PS is incorporated into the likelihood of a semi-parametric cure rate Cox proportional hazard frailty model via inverse probability of treatment weighting, adjusted for multi-center clustering and excess censoring, Our data analysis reveals a more informative and superior performance of the full model in terms of treatment effect estimation, over sub-models that relaxes the various features of the event time dataset.