Comparison of ARIMA and Random Forest time series models for prediction of avian influenza H5N1 outbreaks

Michael J. Kane, Natalie Price, Matthew Scotch, Peter Rabinowitz

Research output: Contribution to journalArticle

70 Citations (Scopus)

Abstract

Background: Time series models can play an important role in disease prediction. Incidence data can be used to predict the future occurrence of disease events. Developments in modeling approaches provide an opportunity to compare different time series models for predictive power. Results: We applied ARIMA and Random Forest time series models to incidence data of outbreaks of highly pathogenic avian influenza (H5N1) in Egypt, available through the online EMPRES-I system. We found that the Random Forest model outperformed the ARIMA model in predictive ability. Furthermore, we found that the Random Forest model is effective for predicting outbreaks of H5N1 in Egypt. Conclusions: Random Forest time series modeling provides enhanced predictive ability over existing time series models for the prediction of infectious disease outbreaks. This result, along with those showing the concordance between bird and human outbreaks (Rabinowitz et al. 2012), provides a new approach to predicting these dangerous outbreaks in bird populations based on existing, freely available data. Our analysis uncovers the time-series structure of outbreak severity for highly pathogenic avain influenza (H5N1) in Egypt.

Original languageEnglish (US)
Article number276
JournalBMC Bioinformatics
Volume15
Issue number1
DOIs
StatePublished - Aug 13 2014

Fingerprint

ARIMA
Influenza in Birds
Random Forest
Influenza
Time Series Models
Disease Outbreaks
Time series
Egypt
Prediction
Incidence
ARIMA Models
Time Series Modelling
Birds
Concordance
Infectious Diseases
Predict
Human Influenza
Forests
Modeling
Model

ASJC Scopus subject areas

  • Applied Mathematics
  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications

Cite this

Comparison of ARIMA and Random Forest time series models for prediction of avian influenza H5N1 outbreaks. / Kane, Michael J.; Price, Natalie; Scotch, Matthew; Rabinowitz, Peter.

In: BMC Bioinformatics, Vol. 15, No. 1, 276, 13.08.2014.

Research output: Contribution to journalArticle

@article{4a7c9cdd5a6640298fc3171025884651,
title = "Comparison of ARIMA and Random Forest time series models for prediction of avian influenza H5N1 outbreaks",
abstract = "Background: Time series models can play an important role in disease prediction. Incidence data can be used to predict the future occurrence of disease events. Developments in modeling approaches provide an opportunity to compare different time series models for predictive power. Results: We applied ARIMA and Random Forest time series models to incidence data of outbreaks of highly pathogenic avian influenza (H5N1) in Egypt, available through the online EMPRES-I system. We found that the Random Forest model outperformed the ARIMA model in predictive ability. Furthermore, we found that the Random Forest model is effective for predicting outbreaks of H5N1 in Egypt. Conclusions: Random Forest time series modeling provides enhanced predictive ability over existing time series models for the prediction of infectious disease outbreaks. This result, along with those showing the concordance between bird and human outbreaks (Rabinowitz et al. 2012), provides a new approach to predicting these dangerous outbreaks in bird populations based on existing, freely available data. Our analysis uncovers the time-series structure of outbreak severity for highly pathogenic avain influenza (H5N1) in Egypt.",
author = "Kane, {Michael J.} and Natalie Price and Matthew Scotch and Peter Rabinowitz",
year = "2014",
month = "8",
day = "13",
doi = "10.1186/1471-2105-15-276",
language = "English (US)",
volume = "15",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Comparison of ARIMA and Random Forest time series models for prediction of avian influenza H5N1 outbreaks

AU - Kane, Michael J.

AU - Price, Natalie

AU - Scotch, Matthew

AU - Rabinowitz, Peter

PY - 2014/8/13

Y1 - 2014/8/13

N2 - Background: Time series models can play an important role in disease prediction. Incidence data can be used to predict the future occurrence of disease events. Developments in modeling approaches provide an opportunity to compare different time series models for predictive power. Results: We applied ARIMA and Random Forest time series models to incidence data of outbreaks of highly pathogenic avian influenza (H5N1) in Egypt, available through the online EMPRES-I system. We found that the Random Forest model outperformed the ARIMA model in predictive ability. Furthermore, we found that the Random Forest model is effective for predicting outbreaks of H5N1 in Egypt. Conclusions: Random Forest time series modeling provides enhanced predictive ability over existing time series models for the prediction of infectious disease outbreaks. This result, along with those showing the concordance between bird and human outbreaks (Rabinowitz et al. 2012), provides a new approach to predicting these dangerous outbreaks in bird populations based on existing, freely available data. Our analysis uncovers the time-series structure of outbreak severity for highly pathogenic avain influenza (H5N1) in Egypt.

AB - Background: Time series models can play an important role in disease prediction. Incidence data can be used to predict the future occurrence of disease events. Developments in modeling approaches provide an opportunity to compare different time series models for predictive power. Results: We applied ARIMA and Random Forest time series models to incidence data of outbreaks of highly pathogenic avian influenza (H5N1) in Egypt, available through the online EMPRES-I system. We found that the Random Forest model outperformed the ARIMA model in predictive ability. Furthermore, we found that the Random Forest model is effective for predicting outbreaks of H5N1 in Egypt. Conclusions: Random Forest time series modeling provides enhanced predictive ability over existing time series models for the prediction of infectious disease outbreaks. This result, along with those showing the concordance between bird and human outbreaks (Rabinowitz et al. 2012), provides a new approach to predicting these dangerous outbreaks in bird populations based on existing, freely available data. Our analysis uncovers the time-series structure of outbreak severity for highly pathogenic avain influenza (H5N1) in Egypt.

UR - http://www.scopus.com/inward/record.url?scp=84906828147&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906828147&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-15-276

DO - 10.1186/1471-2105-15-276

M3 - Article

C2 - 25123979

AN - SCOPUS:84906828147

VL - 15

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - 1

M1 - 276

ER -