Joint modelling of association networks and longitudinal biomarkers: an application to child obesity

TL;DR

This paper introduces a Bayesian joint modelling approach for analyzing growth and metabolic data in children to identify pathways linked to obesity, enabling risk subgroup detection and pathway exploration.

Contribution

It presents a novel non-parametric Bayesian framework that jointly models longitudinal biomarkers and association networks, incorporating clustering and risk factors.

Findings

Identified key metabolic pathways associated with child obesity.

Demonstrated the method on Singapore cohort data.

Revealed risk sub-groups with distinct metabolic profiles.

Abstract

The prevalence of chronic non-communicable diseases such as obesity has noticeably increased in the last decade. The study of these diseases in early life is of paramount importance in determining their course in adult life and in supporting clinical interventions. Recently, attention has been drawn on approaches that study the alteration of metabolic pathways in obese children. In this work, we propose a novel joint modelling approach for the analysis of growth biomarkers and metabolite concentrations, to unveil metabolic pathways related to child obesity. Within a Bayesian framework, we flexibly model the temporal evolution of growth trajectories and metabolic associations through the specification of a joint non-parametric random effect distribution which also allows for clustering of the subjects, thus identifying risk sub-groups. Growth profiles as well as patterns of metabolic associations determine the clustering structure. Inclusion of risk factors is straightforward through the specification of a regression term. We demonstrate the proposed approach on data from the Growing Up in Singapore Towards healthy Outcomes (GUSTO) cohort study, based in Singapore. Posterior inference is obtained via a tailored MCMC algorithm, accommodating a nonparametric prior with mixed support. Our analysis has identified potential key pathways in obese children that allows for exploration of possible molecular mechanisms associated with child obesity.