Towards realtime spatiotemporal prediction of district level meningitis incidence in sub-Saharan Africa

Michelle C. Stanton, and Lydiane Agier, Benjamin M. Taylor, Peter J. Diggle

Research output: Contribution to journalArticle

Abstract

Within an area of sub-Saharan Africa termed 'the meningitis belt', meningococcal meningitis epidemics are a major public health concern. The epidemic control strategy that is currently utilized is reactive, such that a vaccination programme is initiated in a district once a predefined weekly incidence threshold has been exceeded. We report progress towards the development of an early warning system based on statistical modelling of district level weekly incidence data. Four modelling approaches are considered and their forecasting performances are compared by using weekly epidemiological data from Niger for the period 1986-2007. We conclude that the models under consideration are advantageous in different situations. The three-state Markov model described in which observed incidence is categorized according to policy-defined thresholds gives the most reliable short-term forecasts, whereas the dynamic linear model proposed, using log-transformed weekly incidence as the response variable, gives more reliable predictions of annual epidemics.

Original languageEnglish (US)
Pages (from-to)661-678
Number of pages18
JournalJournal of the Royal Statistical Society. Series A: Statistics in Society
Volume177
Issue number3
DOIs
StatePublished - 2014
Externally publishedYes

Fingerprint

Incidence
incidence
district
Real-time
Prediction
Dynamic Linear Models
early warning system
Early Warning
Vaccination
Niger
Statistical Modeling
Public Health
vaccination
linear model
Markov Model
Annual
Forecast
Control Strategy
Forecasting
public health

Keywords

  • Dynamic generalized linear models
  • Epidemic control
  • Markov chain
  • Meningitis belt
  • Meningococcal meningitis

ASJC Scopus subject areas

  • Statistics and Probability
  • Economics and Econometrics
  • Social Sciences (miscellaneous)
  • Statistics, Probability and Uncertainty

Cite this

Towards realtime spatiotemporal prediction of district level meningitis incidence in sub-Saharan Africa. / Stanton, Michelle C.; Agier, and Lydiane; Taylor, Benjamin M.; Diggle, Peter J.

In: Journal of the Royal Statistical Society. Series A: Statistics in Society, Vol. 177, No. 3, 2014, p. 661-678.

Research output: Contribution to journalArticle

Stanton, Michelle C. ; Agier, and Lydiane ; Taylor, Benjamin M. ; Diggle, Peter J. / Towards realtime spatiotemporal prediction of district level meningitis incidence in sub-Saharan Africa. In: Journal of the Royal Statistical Society. Series A: Statistics in Society. 2014 ; Vol. 177, No. 3. pp. 661-678.
@article{b3cf21987d294de09263f58f1c551423,
title = "Towards realtime spatiotemporal prediction of district level meningitis incidence in sub-Saharan Africa",
abstract = "Within an area of sub-Saharan Africa termed 'the meningitis belt', meningococcal meningitis epidemics are a major public health concern. The epidemic control strategy that is currently utilized is reactive, such that a vaccination programme is initiated in a district once a predefined weekly incidence threshold has been exceeded. We report progress towards the development of an early warning system based on statistical modelling of district level weekly incidence data. Four modelling approaches are considered and their forecasting performances are compared by using weekly epidemiological data from Niger for the period 1986-2007. We conclude that the models under consideration are advantageous in different situations. The three-state Markov model described in which observed incidence is categorized according to policy-defined thresholds gives the most reliable short-term forecasts, whereas the dynamic linear model proposed, using log-transformed weekly incidence as the response variable, gives more reliable predictions of annual epidemics.",
keywords = "Dynamic generalized linear models, Epidemic control, Markov chain, Meningitis belt, Meningococcal meningitis",
author = "Stanton, {Michelle C.} and Agier, {and Lydiane} and Taylor, {Benjamin M.} and Diggle, {Peter J.}",
year = "2014",
doi = "10.1111/rssa.12033",
language = "English (US)",
volume = "177",
pages = "661--678",
journal = "Journal of the Royal Statistical Society. Series A: Statistics in Society",
issn = "0964-1998",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Towards realtime spatiotemporal prediction of district level meningitis incidence in sub-Saharan Africa

AU - Stanton, Michelle C.

AU - Agier, and Lydiane

AU - Taylor, Benjamin M.

AU - Diggle, Peter J.

PY - 2014

Y1 - 2014

N2 - Within an area of sub-Saharan Africa termed 'the meningitis belt', meningococcal meningitis epidemics are a major public health concern. The epidemic control strategy that is currently utilized is reactive, such that a vaccination programme is initiated in a district once a predefined weekly incidence threshold has been exceeded. We report progress towards the development of an early warning system based on statistical modelling of district level weekly incidence data. Four modelling approaches are considered and their forecasting performances are compared by using weekly epidemiological data from Niger for the period 1986-2007. We conclude that the models under consideration are advantageous in different situations. The three-state Markov model described in which observed incidence is categorized according to policy-defined thresholds gives the most reliable short-term forecasts, whereas the dynamic linear model proposed, using log-transformed weekly incidence as the response variable, gives more reliable predictions of annual epidemics.

AB - Within an area of sub-Saharan Africa termed 'the meningitis belt', meningococcal meningitis epidemics are a major public health concern. The epidemic control strategy that is currently utilized is reactive, such that a vaccination programme is initiated in a district once a predefined weekly incidence threshold has been exceeded. We report progress towards the development of an early warning system based on statistical modelling of district level weekly incidence data. Four modelling approaches are considered and their forecasting performances are compared by using weekly epidemiological data from Niger for the period 1986-2007. We conclude that the models under consideration are advantageous in different situations. The three-state Markov model described in which observed incidence is categorized according to policy-defined thresholds gives the most reliable short-term forecasts, whereas the dynamic linear model proposed, using log-transformed weekly incidence as the response variable, gives more reliable predictions of annual epidemics.

KW - Dynamic generalized linear models

KW - Epidemic control

KW - Markov chain

KW - Meningitis belt

KW - Meningococcal meningitis

UR - http://www.scopus.com/inward/record.url?scp=84901275790&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901275790&partnerID=8YFLogxK

U2 - 10.1111/rssa.12033

DO - 10.1111/rssa.12033

M3 - Article

VL - 177

SP - 661

EP - 678

JO - Journal of the Royal Statistical Society. Series A: Statistics in Society

JF - Journal of the Royal Statistical Society. Series A: Statistics in Society

SN - 0964-1998

IS - 3

ER -