Abstract
BackgroundMost studies of epidemic detection focus on their start and rarely on the whole signal or the end of the epidemic. In some cases, it may be necessary to retrospectively identify outbreak signals from surveillance data. Our study aims at evaluating the ability of change point analysis (CPA) methods to locate the whole disease outbreak signal. We will compare our approach with the results coming from experts’ signal inspections, considered as the gold standard method.MethodsWe simulated 840 time series, each of which includes an epidemic-free baseline (7 options) and a type of epidemic (4 options). We tested the ability of 4 CPA methods (Max-likelihood, Kruskall-Wallis, Kernel, Bayesian) methods and expert inspection to identify the simulated outbreaks. We evaluated the performances using metrics including delay, accuracy, bias, sensitivity, specificity and Bayesian probability of correct classification (PCC).ResultsA minimum of 15 h was required for experts for analyzing the 840 curves and a maximum of 25 min for a CPA algorithm. The Kernel algorithm was the most effective overall in terms of accuracy, bias and global decision (PCC = 0.904), compared to PCC of 0.848 for human expert review.ConclusionsFor the aim of retrospectively identifying the start and end of a disease outbreak, in the absence of human resources available to do this work, we recommend using the Kernel change point model. And in case of experts’ availability, we also suggest to supplement the Human expertise with a CPA, especially when the signal noise difference is below 0.Electronic supplementary materialThe online version of this article (doi:10.1186/s12911-016-0271-x) contains supplementary material, which is available to authorized users.
Highlights
The US Centers for Disease Control and Prevention (CDC) define an epidemic as "the occurrence of more cases of disease than expected in a given area or among a specific group of people over a particular period of time"[1]
Our study aims at evaluating the ability of change point analysis (CPA) methods to identify the beginning and ending dates of a disease outbreak from weekly counts
Change point analysis Epidemics as state changes in surveillance series Following several authors [15,16,17,18,19], we consider that the weekly count of an infectious disease is a time series resulting from a model combining two endemic and epidemic components
Summary
The US Centers for Disease Control and Prevention (CDC) define an epidemic as "the occurrence of more cases of disease than expected in a given area or among a specific group of people over a particular period of time"[1]. Human signal inspection Historically, identifying a whole outbreak signal in surveillance data has relied more on human judgment, for example through review by a committee of experts [12], than on signal processing as for the prospective detection of outbreak starts. This visual inspection of the time series is still considered by many authors as the gold standard approach. Considering a time series {x1, x2,..., xn} measured with an index of time τ ∈ {1, 2,...,n}, a change point is a time index where a structure change occurs in data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
