Enhancing syndromic surveillance for fallen dairy cattle: modelling and detecting mortality peaks at different administrative levels

Amanda Fernández-Fontelo, Pedro Puig, Germán Caceres, Luis Romero, Crawford W. Revie, Javier Sanchez, Fernanda C. Dórea, Anna Alba

Research output: Contribution to journalConference Contribution

Abstract

The automated collection of non-specific data from livestock combined with current techniques of data mining and time series analyses facilitate the development of veterinary syndromic surveillance. This type of approach may enhance traditional surveillance of animal diseases. An example involves the continuous analysis of fallen cattle data, which are registered at farm level. However, further research is needed to incorporate such monitoring processes within an early warning system. This study presents a process aimed at 1) fitting automatically the parameters of the classical AutoRegressive Integrated Moving Average models (ARIMA) including patterns of trend and seasonality aggregated at different spatial levels, 2) predicting the mortality at n-ahead period; and 3) detecting mortality peaks. The application of this work is illustrated in the context of fallen dairy cattle data sets from two regions of Spain. The mortality levels registered by week are modelled at county, province and region levels between 2006 and 2013. Using these models the mortality is predicted between January 2014 and June 2015. Values of mortality that are out of the predicted confidence limits are identified as mortality peaks. The causes of such mortality peaks in some affected farms are assessed using data from expert's reports held by associated insurance companies This work compares patterns of fallen dairy cattle in populations with disparate management and environmental conditions with the aim of illustrating a novel approach to obtain information from mortality data at different administrative levels.
LanguageEnglish
Pages15-26
Number of pages13
JournalEpidemiologie et Sante Animale
Volume2017-72
Publication statusPublished - 24 Mar 2017

Fingerprint

Dairies
Farms
dairy cattle
Mortality
monitoring
Process monitoring
Alarm systems
Insurance
Data mining
Time series
Animals
process monitoring
early warning systems
farms
Animal Diseases
Data Mining
Industry
insurance
animal diseases
Livestock

Keywords

  • dairy cattle
  • syndromic surveillance
  • hierarchical time series
  • ARIMA models
  • Spain

Cite this

Fernández-Fontelo, Amanda ; Puig, Pedro ; Caceres, Germán ; Romero, Luis ; Revie, Crawford W. ; Sanchez, Javier ; Dórea, Fernanda C. ; Alba, Anna. / Enhancing syndromic surveillance for fallen dairy cattle : modelling and detecting mortality peaks at different administrative levels. In: Epidemiologie et Sante Animale. 2017 ; Vol. 2017-72. pp. 15-26.
@article{fe8da5e0193d4839904584db2e8b9bf5,
title = "Enhancing syndromic surveillance for fallen dairy cattle: modelling and detecting mortality peaks at different administrative levels",
abstract = "The automated collection of non-specific data from livestock combined with current techniques of data mining and time series analyses facilitate the development of veterinary syndromic surveillance. This type of approach may enhance traditional surveillance of animal diseases. An example involves the continuous analysis of fallen cattle data, which are registered at farm level. However, further research is needed to incorporate such monitoring processes within an early warning system. This study presents a process aimed at 1) fitting automatically the parameters of the classical AutoRegressive Integrated Moving Average models (ARIMA) including patterns of trend and seasonality aggregated at different spatial levels, 2) predicting the mortality at n-ahead period; and 3) detecting mortality peaks. The application of this work is illustrated in the context of fallen dairy cattle data sets from two regions of Spain. The mortality levels registered by week are modelled at county, province and region levels between 2006 and 2013. Using these models the mortality is predicted between January 2014 and June 2015. Values of mortality that are out of the predicted confidence limits are identified as mortality peaks. The causes of such mortality peaks in some affected farms are assessed using data from expert's reports held by associated insurance companies This work compares patterns of fallen dairy cattle in populations with disparate management and environmental conditions with the aim of illustrating a novel approach to obtain information from mortality data at different administrative levels.",
keywords = "dairy cattle, syndromic surveillance, hierarchical time series, ARIMA models, Spain",
author = "Amanda Fern{\'a}ndez-Fontelo and Pedro Puig and Germ{\'a}n Caceres and Luis Romero and Revie, {Crawford W.} and Javier Sanchez and D{\'o}rea, {Fernanda C.} and Anna Alba",
year = "2017",
month = "3",
day = "24",
language = "English",
volume = "2017-72",
pages = "15--26",
journal = "Epidemiologie et Sante Animale",
issn = "0754-2186",

}

Fernández-Fontelo, A, Puig, P, Caceres, G, Romero, L, Revie, CW, Sanchez, J, Dórea, FC & Alba, A 2017, 'Enhancing syndromic surveillance for fallen dairy cattle: modelling and detecting mortality peaks at different administrative levels' Epidemiologie et Sante Animale, vol. 2017-72, pp. 15-26.

Enhancing syndromic surveillance for fallen dairy cattle : modelling and detecting mortality peaks at different administrative levels. / Fernández-Fontelo, Amanda; Puig, Pedro; Caceres, Germán; Romero, Luis; Revie, Crawford W.; Sanchez, Javier; Dórea, Fernanda C.; Alba, Anna.

In: Epidemiologie et Sante Animale, Vol. 2017-72, 24.03.2017, p. 15-26.

Research output: Contribution to journalConference Contribution

TY - JOUR

T1 - Enhancing syndromic surveillance for fallen dairy cattle

T2 - Epidemiologie et Sante Animale

AU - Fernández-Fontelo, Amanda

AU - Puig, Pedro

AU - Caceres, Germán

AU - Romero, Luis

AU - Revie, Crawford W.

AU - Sanchez, Javier

AU - Dórea, Fernanda C.

AU - Alba, Anna

PY - 2017/3/24

Y1 - 2017/3/24

N2 - The automated collection of non-specific data from livestock combined with current techniques of data mining and time series analyses facilitate the development of veterinary syndromic surveillance. This type of approach may enhance traditional surveillance of animal diseases. An example involves the continuous analysis of fallen cattle data, which are registered at farm level. However, further research is needed to incorporate such monitoring processes within an early warning system. This study presents a process aimed at 1) fitting automatically the parameters of the classical AutoRegressive Integrated Moving Average models (ARIMA) including patterns of trend and seasonality aggregated at different spatial levels, 2) predicting the mortality at n-ahead period; and 3) detecting mortality peaks. The application of this work is illustrated in the context of fallen dairy cattle data sets from two regions of Spain. The mortality levels registered by week are modelled at county, province and region levels between 2006 and 2013. Using these models the mortality is predicted between January 2014 and June 2015. Values of mortality that are out of the predicted confidence limits are identified as mortality peaks. The causes of such mortality peaks in some affected farms are assessed using data from expert's reports held by associated insurance companies This work compares patterns of fallen dairy cattle in populations with disparate management and environmental conditions with the aim of illustrating a novel approach to obtain information from mortality data at different administrative levels.

AB - The automated collection of non-specific data from livestock combined with current techniques of data mining and time series analyses facilitate the development of veterinary syndromic surveillance. This type of approach may enhance traditional surveillance of animal diseases. An example involves the continuous analysis of fallen cattle data, which are registered at farm level. However, further research is needed to incorporate such monitoring processes within an early warning system. This study presents a process aimed at 1) fitting automatically the parameters of the classical AutoRegressive Integrated Moving Average models (ARIMA) including patterns of trend and seasonality aggregated at different spatial levels, 2) predicting the mortality at n-ahead period; and 3) detecting mortality peaks. The application of this work is illustrated in the context of fallen dairy cattle data sets from two regions of Spain. The mortality levels registered by week are modelled at county, province and region levels between 2006 and 2013. Using these models the mortality is predicted between January 2014 and June 2015. Values of mortality that are out of the predicted confidence limits are identified as mortality peaks. The causes of such mortality peaks in some affected farms are assessed using data from expert's reports held by associated insurance companies This work compares patterns of fallen dairy cattle in populations with disparate management and environmental conditions with the aim of illustrating a novel approach to obtain information from mortality data at different administrative levels.

KW - dairy cattle

KW - syndromic surveillance

KW - hierarchical time series

KW - ARIMA models

KW - Spain

M3 - Conference Contribution

VL - 2017-72

SP - 15

EP - 26

JO - Epidemiologie et Sante Animale

JF - Epidemiologie et Sante Animale

SN - 0754-2186

ER -