IntroductionExisting estimates of contraceptive use in Tanzania rely on cross-sectional or retrospective study designs. This study used a 2-year, retrospective, month-by-month calendar of contraceptive utilization among women aged 15–49 years.MethodsWe estimated the median duration of contraceptive use, factors associated with use, and contraceptive discontinuation rates in sexually active women, using life tables and Cox proportional hazard model.ResultsA total of 5416 women contributed to the analysis in the study. Of the 5416 women, 942 (17%) had never had sex, 410 (7.6%) had no sexual partner in the last year. Among the 5416 women, 4064 were sexually active during the period, 814 (21.1%) were pregnant or amenorrheic, 610 (15.0%) were using contraception, and 1203 (29.6%) did not want to get pregnant but were not using contraception. In the 1813 women who wanted to avoid pregnancy, contraceptive use was lower among women over 35 years compared to younger ones (OR = 0.28, 95%CI: 0.19, 0.41), and in HIV positive women (OR = 0.89, 95%CI: 0.60–1.32). On the other hand, use was higher among women who were married/living together compared to unmarried ones (OR = 2.23, 95% CI: 1.54, 3.23). Using a 2-year retrospective contraceptive calendar, 1054 women reported contraceptive use, 15.8% discontinued within 6 months and 30.5% discontinued within 12 months. Higher rates of contraceptive discontinuation were observed among women who used pills (OR = 1.86, 95%CI: 1.25, 2.77) or injections (OR = 2.04, 95%CI: 1.59, 2.61) compared to those who used implants.ConclusionContraceptive use was significantly associated with age, education and parity, but not with HIV status. HIV status, number of living children and education are not statistically associated with discontinuation of contraceptive use Pills and injections had the highest rates of discontinuation. Wider choice and greater accessibility of long-acting contraceptive methods with better effectiveness and convenience may serve women better. Furthermore, special efforts may be needed to remove barriers to contraceptive use amongst younger women.

We introduce a nonparametric estimator of the conditional survival function in the mixture cure model for right‐censored data when cure status is partially known. The estimator is developed for the setting of a single continuous covariate but it can be extended to multiple covariates. It extends the estimator of Beran, which ignores cure status information. We obtain an almost sure representation, from which the strong consistency and asymptotic normality of the estimator are derived. Asymptotic expressions of the bias and variance demonstrate a reduction in the variance with respect to Beran's estimator. A simulation study shows that, if the bandwidth parameter is suitably chosen, our estimator performs better than others for an ample range of covariate values. A bootstrap bandwidth selector is proposed. Finally, the proposed estimator is applied to a real dataset studying survival of sarcoma patients.

Cure models are a class of time-to-event models where a proportion of individuals will never experience the event of interest. The lifetimes of these so-called cured individuals are always censored. It is usually assumed that one never knows which censored observation is cured and which is uncured, so the cure status is unknown for censored times. In this paper, we develop a method to estimate the probability of cure in the mixture cure model when some censored individuals are known to be cured. A cure probability estimator that incorporates the cure status information is introduced. This estimator is shown to be strongly consistent and asymptotically normally distributed. Two alternative estimators are also presented. The first one considers a competing risks approach with two types of competing events, the event of interest and the cure. The second alternative estimator is based on the fact that the probability of cure can be written as the conditional mean of the cure status. Hence, nonparametric regression methods can be applied to estimate this conditional mean. However, the cure status remains unknown for some censored individuals. Consequently, the application of regression methods in this context requires handling missing data in the response variable (cure status). Simulations are performed to evaluate the finite sample performance of the estimators, and we apply them to the analysis of two datasets related to survival of breast cancer patients and length of hospital stay of COVID-19 patients requiring intensive care.

Unsupervised statistical analysis of unstructured data has gained wide acceptance especially in natural language processing and text mining domains. Topic modelling with Latent Dirichlet Allocation is one such statistical tool that has been successfully applied to synthesize collections of legal, biomedical documents and journalistic topics. We applied a novel two-stage topic modelling approach and illustrated the methodology with data from a collection of published abstracts from the University of Nairobi, Kenya. In the first stage, topic modelling with Latent Dirichlet Allocation was applied to derive the per-document topic probabilities. To more succinctly present the topics, in the second stage, hierarchical clustering with Hellinger distance was applied to derive the final clusters of topics. The analysis showed that dominant research themes in the university include: HIV and malaria research, research on agricultural and veterinary services as well as cross-cutting themes in humanities and social sciences. Further, the use of hierarchical clustering in the second stage reduces the discovered latent topics to clusters of homogeneous topics.

We examined the HIV care cascade in a community-based cohort study in Kisesa, Magu, Tanzania. We analyzed the proportion achieving each stage of the cascade -Seroconversion, Awareness of HIV status, Enrollment in Care and Antiretroviral therapy (ART) initiation-and estimated the median and interquartile range for the time for progression to the next stage. Modified Poisson regression was used to estimate prevalence risk ratios for enrollment in care and initiation of ART.From 2006 to 2017, 175 HIV-seroconverters were identified. 140(80%) knew their HIV status, of whom 97(69.3%) were enrolled in HIV care, and 87(49.7%) had initiated ART. Time from seroconversion to awareness of HIV status was 731.3 [475.5-1345.8] days. Time from awareness to enrollment was 7[0-64] days, and from enrollment to ART initiation was 19 days. There were no demographic differences in enrollment in care or ART initiation. Efforts have been focusing on shortening time from seroconversion to diagnosis, mostly by increasing the number of testing clinics available.We recommend increased systematic testing to reduce time from seroconversion to awareness of status, and by doing so speed up enrollment into care. Interventions that increase enrollment are likely to have the most impact in achieving UNAIDS targets.