Bayesian multistate modelling of incomplete chronic disease burden data

Abstract

AbstractThe ‘multistate lifetable’ is a widely used model for the long-term health impacts of public health interventions. It requires estimates of the incidence, case fatality, and sometimes also remission rates, for multiple diseases by age and gender. The case fatality is the rate of death from a disease for people with a disease, and is commonly not observed directly. Instead, we often observe the mortality in the general population. Similarly, we might know the disease prevalence, but not the incidence. This paper presents Bayesian continuous-time multistate models for estimating transition rates between disease states based on incomplete data. It unifies and extends two previous methods, by using a formal statistical model, with more efficient computational algorithms. This allows rates for different ages, areas, and time periods to be related in more flexible ways, and allows models to be formally checked and compared. The methods are made more widely usable through an R package. The models are used to estimate case fatality for multiple diseases in the city regions of England, based on incidence, prevalence, and mortality data from the Global Burden of Disease study. The estimates can be used to inform health impact models relating to those diseases and areas.