An integer-valued time series model for multivariate surveillance

TL;DR

This paper introduces a multivariate integer-valued autoregressive model for public health surveillance data, capturing serial and cross correlations, overdispersion, and covariates, with applications to outbreak detection.

Contribution

It proposes a novel multivariate integer-valued autoregressive model that addresses both serial and cross correlations in surveillance data, including overdispersion and covariates, with a natural endemic-epidemic decomposition.

Findings

Model effectively detects disease outbreaks.

Applied successfully to Athens 2004 Olympic surveillance data.

Captures complex correlation structures in multivariate counts.

Abstract

In recent days different types of surveillance data are becoming available for public health reasons. In most cases several variables are monitored and events of different types are reported. As the amount of surveillance data increases, statistical methods that can effectively address multivariate surveillance scenarios are demanded. Even though research activity in this field is increasing rapidly in recent years, only a few approaches have simultaneously addressed the integer-valued property of the data and its correlation (both time correlation and cross correlation) structure. In this paper, we suggest a multivariate integer-valued autoregressive model that allows for both serial and cross correlation between the series and can easily accommodate overdispersion and covariate information. Moreover, its structure implies a natural decomposition into an endemic and an epidemic component, a common distinction in dynamic models for infectious disease counts. Detection of disease outbreaks is achieved through the comparison of surveillance data with one-step-ahead predictions obtained after fitting the suggested model to a set of clean historical data. The performance of the suggested model is illustrated on a trivariate series of syndromic surveillance data collected during Athens 2004 Olympic Games.