Monitoring Count Time Series in R: Aberration Detection in Public Health Surveillance

TL;DR

This paper introduces the R package surveillance for automatic detection of anomalies in public health time series, utilizing advanced statistical models and monitoring techniques to improve outbreak detection accuracy.

Contribution

It extends existing methods like the Farrington algorithm with new modeling approaches, including spline and Bayesian models, and addresses categorical data and overdispersion in surveillance.

Findings

Enhanced visualization and modeling tools for surveillance data

Implementation of Bayesian and spline-based extensions of Farrington algorithm

Practical integration of surveillance methods into public health workflows

Abstract

Public health surveillance aims at lessening disease burden, e.g., in case of infectious diseases by timely recognizing emerging outbreaks. Seen from a statistical perspective, this implies the use of appropriate methods for monitoring time series of aggregated case reports. This paper presents the tools for such automatic aberration detection offered by the R package surveillance. We introduce the functionality for the visualization, modelling and monitoring of surveillance time series. With respect to modelling we focus on univariate time series modelling based on generalized linear models (GLMs), multivariate GLMs, generalized additive models and generalized additive models for location, shape and scale. This ranges from illustrating implementational improvements and extensions of the well-known Farrington algorithm, e.g, by spline-modelling or by treating it in a Bayesian context. Furthermore, we look at categorical time series and address overdispersion using beta-binomial or Dirichlet-Multinomial modelling. With respect to monitoring we consider detectors based on either a Shewhart-like single timepoint comparison between the observed count and the predictive distribution or by likelihood-ratio based cumulative sum methods. Finally, we illustrate how surveillance can support aberration detection in practice by integrating it into the monitoring workflow of a public health institution. Altogether, the present article shows how well surveillance can support automatic aberration detection in a public health surveillance context.