A Spatio-Temporal Multivariate Shared Component Model with an Application in Iran Cancer Data

TL;DR

This paper introduces a novel spatio-temporal multivariate shared component model that jointly analyzes multiple diseases over space and time, providing detailed insights into regional and temporal variations in disease risks.

Contribution

The paper proposes a new model that combines shared components with spatio-temporal analysis for multiple diseases, allowing for joint inference and detailed variation analysis.

Findings

Identified regional and temporal variations in cancer risks in Iran.

Demonstrated the model's ability to analyze multiple diseases simultaneously.

Showed how shared components influence individual disease risk estimates.

Abstract

Among the proposals for joint disease mapping, the shared component model has become more popular. Another recent advance to strengthen inference of disease data has been the extension of purely spatial models to include time and space-time interaction. Such analyses have additional benefits over purely spatial models. However, only a few proposed spatio-temporal models could address analysing multiple diseases jointly. In the proposed model, each component is shared by different subsets of diseases, spatial and temporal trends are considered for each component, and the relative weight of these trends for each component for each relevant disease can be estimated. We present an application of the proposed method on incidence rates of seven prevalent cancers in Iran. The effect of the shared components on the individual cancer types can be identified. Regional and temporal variation in relative risks is shown. We present a model which combines the benefits of shared-components with spatio-temporal techniques for multivariate data. We show, how the model allows to analyse geographical and temporal variation among diseases beyond previous approaches.