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

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

doi:10.1186/1471-2105-15-276

Abstract

BackgroundTime 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.ResultsWe 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.ConclusionsRandom 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.

Highlights

Time series models can play an important role in disease prediction
Certain infectious diseases and disease events occur in a cyclic or rhythmic pattern related to climate or other factors that allows for modeling and prediction of future outbreaks
An example is the recent emergence of highly pathogenic avian influenza

Summary

Introduction

Time series models can play an important role in disease prediction. Incidence data can be used to predict the future occurrence of disease events. Certain infectious diseases and disease events occur in a cyclic or rhythmic pattern related to climate or other factors that allows for modeling and prediction of future outbreaks. By understanding when a future outbreak may occur, preventative steps can be taken to minimize its impact Examples of such preventive steps include vector control, public health messaging to avoid high-risk behaviors or areas, and raising clinician awareness for early diagnosis and treatment. For such prevention to take place, timely and accurate prediction of outbreaks is critical. An important application of new, improved predictive models should be related to the emergence of zoonotic disease

Methods

Results

Discussion

Conclusion