A0785
Title: Latent random partition model: An application to childhood co-morbidity
Authors: Maria De Iorio - National University of Singapore (Singapore) [presenting]
Abstract: Asthma, hypertension and obesity are three of the most common chronic diseases worldwide, with known presence of comorbid pathophysiological mechanisms. Such data are collected from different sources and are usually analysed separately, neglecting the shared information among subjects, underlining the need for a more comprehensive statistical approach. A novel Bayesian nonparametric model is developed for the joint analysis of biomarkers of different types related to obesity (longitudinal data), history of asthma (panel count data) and symptoms of hypertension (multi-state process). In particular, the random partitions of the subjects are modelled in each dataset independently and conditionally on an underlying partition structure. The proposed strategy allows for the sharing of information among the clustering structures within the different datasets, thus providing more robust inference. Random partitions of different datasets are marginally dependent, with dependence learnt from the data. The model allows for the inclusion of mixed-type covariates, aiding the identification of risk factors affecting the evolution of the diseases. A tailored MCMC algorithm is developed. The model is demonstrated in an application from the Singaporean birth cohort GUSTO.
