Bayesian consensus clustering for multivariate longitudinal data

In clinical and epidemiological studies, there is a growing interest in studying the heterogeneity among patients based on longitudinal characteristics to identify subtypes of the study population. Compared to clustering a single longitudinal marker, simultaneously clustering multiple longitudinal markers allow additional information to be incorporated into the clustering process, which reveals co-existing longitudinal patterns and generates deeper biological insight. In the current study, we propose a Bayesian consensus clustering (BCC) model for multivariate longitudinal data. Instead of arriving at a single overall clustering, the proposed model allows each marker to follow marker-specific local clustering and these local clusterings are aggregated to find a global (consensus) clustering. To estimate the posterior distribution of model parameters, a Gibbs sampling algorithm is proposed. We apply our proposed model to the primary biliary cirrhosis study to identify patient subtypes that may be associated with their prognosis. We also perform simulation studies to compare the clustering performance between the proposed model and existing models under several scenarios. The results demonstrate that the proposed BCC model serves as a useful tool for clustering multivariate longitudinal data.     

Living with the financial consequences of cancer: A life course perspective

Abstract

Purpose

Financial hardship can be a major cause of distress among persons with cancer, resulting in chronic stress and impacting physical and emotional health. This paper provides an analysis of the lived experience of cancer patients’ financial hardship from diagnosis to post-treatment.     

South African abortion attitudes from 2007-2016: the roles of religiosity and attitudes toward sexuality and gender equality

ABSTRACT

Abortion is legal in South Africa, but negative abortion attitudes remain common and are poorly understood. We used nationally representative South African Social Attitudes Survey data to analyze abortion attitudes in the case of fetal anomaly and in the case of poverty from 2007 to 2016 (n = 20,711; ages = 16+). We measured correlations between abortion attitudes and these important predictors: religiosity, attitudes about premarital sex, attitudes about preferential hiring and promotion of women, and attitudes toward family gender roles. Abortion acceptability for poverty increased over time (b = 0.05, p < .001), but not for fetal anomaly (b = ?0.008, p = .284). Highly religious South Africans reported lower abortion acceptability in both cases (Odds Ratio (OR)_anomaly = 0.85, p = .015; OR_poverty = 0.84, p = .02). Premarital sex acceptability strongly and positively predicted abortion acceptability (OR_anomaly = 2.63, p < .001; OR_poverty = 2.46, p < .001). Attitudes about preferential hiring and promotion of women were not associated with abortion attitudes, but favorable attitudes about working mothers were positively associated with abortion acceptability for fetal anomaly ((OR_anomaly = 1.09, p = .01; OR_poverty = 1.02, p = .641)). Results suggest negative abortion attitudes remain common in South Africa and are closely tied to religiosity, traditional ideologies about sexuality, and gender role expectations about motherhood.