Robust outbreak surveillance of epidemics in Sweden
Statistical Research Unit, Department of Economics, University of Gothenburg, and Department of Occupational and Environmental Medicine, Sahlgrenska University Hospital, SE 40530, Gothenburg, Sweden. Statistics in Medicine
(Impact Factor: 1.83).
02/2009; 28(3):476-93. DOI: 10.1002/sim.3483
Outbreak detection is of interest in connection with several diseases and syndromes. The aim is to detect the progressive increase in the incidence as soon as possible after the onset of the outbreak. A semiparametric method is applied to Swedish data on tularaemia and influenza. The method is constructed to detect a change from a constant level to a monotonically increasing incidence. If seasonal effects are present, the residuals from a model incorporating these can be used. The properties of the method are evaluated by application to Swedish data on tularaemia and influenza and by simulations. The suggested method is compared with subjective judgments as well as with other algorithms. The conclusion is that the method works well. A user-friendly computer program is described.
Available from: Marianne Frisen
- "rveillance. The method is also available in the R package Surveillance, described in Höhle (2010) and available on CRAN, and the open JAVA package CASE described in Cakici et al. (2010). For the univariate surveillance of the influenza incidence in Sweden as a whole, the OutbreakP method was evaluated by Frisén and Andersson (2009) and Frisén, et al. (2009). We will now adapt this method for a multivariate situation."
[Show abstract] [Hide abstract]
ABSTRACT: Online monitoring is needed to detect outbreaks of diseases such as influenza. Surveillance is also needed for other kinds of outbreaks, in the sense of an increasing expected value after a constant period. Information on spatial location or other variables might be available and may be utilized. We adapted a robust method for outbreak detection to a multivariate case. The relation between the times of the onsets of the outbreaks at different locations (or some other variable) was used to determine the sufficient statistic for surveillance. The derived maximum-likelihood estimator of the outbreak regression was semi-parametric in the sense that the baseline and the slope were non-parametric while the distribution belonged to the one-parameter exponential family. The estimator was used in a generalized-likelihood ratio surveillance method. The method was evaluated with respect to robustness and efficiency in a simulation study and applied to spatial data for detection of influenza outbreaks in Sweden.
Available from: gupea.ub.gu.se
- "Bock et al. (2008) suggest a method for peak detection and apply it to Swedish data. Frisén and Andersson (2007) and Frisén et al. (2008) suggest a method for outbreak detection and apply it to Swedish influenza data. There is also some work on other related aspects of influenza in Sweden. "
[Show abstract] [Hide abstract]
ABSTRACT: Information about the spatial spread of epidemics can be useful for many purposes. The spatial aspect of Swedish influenza data was analyzed with the main aim of finding patterns that could be useful for statistical surveillance of the outbreak, i.e. for detecting an increase in incidence as soon as possible. In Sweden, two types of data are collected during the influenza season: laboratory diagnosed cases (LDI), collected by a number of laboratories, and cases of influenza-like illness (ILI), c... merollected by a number of selected physicians. Quality problems were found for both types of data but were most severe for ILI. No evidence for a geographical pattern was found. Instead, it was found that the influenza outbreak starts at about the same time in the major cities and then occurs in the rest of the country. The data were divided into two groups, a metropolitan group representing the major cities and a locality group representing the rest of the country. The properties of the metropolitan group and the locality group were studied and it was found that the time difference in the onset of the outbreak was about one week. Both parametric and nonparametric regression models were suggested.
Available from: univ-toulouse.fr
[Show abstract] [Hide abstract]
ABSTRACT: We address 2 challenges related to modelling of the time-varying exposures in survival analysis. Firstly, the exposure may have a cumulative or lagged effect, but often little is known about relative importance of exposures that occurred in different intervals in the past (Hauptmann et al (2000)). Secondly, the form of the dose-response relationship is typically unknown. We are unaware of methods allowing flexible modelling of both (i) weight functions for cumulative ef-fects modelling, and (ii) non-linear dose response curves. We estimate the weighed cumulative exposure (WCE) effect at time τ , as a function of the past exposure history, described by the time-dependent exposure intensity x(t), at 0 < t < τ : WCE(τ |x(t), t < τ) = w(τ − t) * s[x(t)], where w(τ − t) assigns importance weights to past exposures as the function of time elapsed since exposure, while s[x(t)] represents a smooth dose-response curve. The estimated WCE is then included as a time-dependent covariate in the Cox's proportional hazards model. Both w(τ − t) and s[x(t)] are modelled using cubic regression splines. Quasi-parametric likelihood ratio tests (Abrahamowicz and MacKenzie (2007)) are used for hypothesis testing. In simulations, we assess the accuracy of the estimated functions and tests. We apply the model to re-assess the relative importance of past blood pressure values in a cohort study of cardiovascular mortality. References  Hauptmann M, Wellmann J, Lubin JH et al (2000) Analysis of exposure-time-response rela-tionships using a spline weight function, Biometrics, Vol. 56, 1105-1108.  Abrahamowicz M and MacKenzie T (2007) Joint estimation of time-dependent and non-linear effects of continuous covariates on survival, Statistics in Medicine, Vol. 26, 392-408.
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.