Prediction of influenza-like illness based on the improved artificial tree algorithm and artificial neural network

Sci Rep. 2018 Mar 20;8(1):4895. doi: 10.1038/s41598-018-23075-1.

Abstract

Because influenza is a contagious respiratory illness that seriously threatens public health, accurate real-time prediction of influenza outbreaks may help save lives. In this paper, we use the Twitter data set and the United States Centers for Disease Control's influenza-like illness (ILI) data set to predict a nearly real-time regional unweighted percentage ILI in the United States by use of an artificial neural network optimized by the improved artificial tree algorithm. The results show that the proposed method is an efficient approach to real-time prediction.

Publication types

  • Research Support, Non-U.S. Gov't
  • Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

  • Algorithms
  • Centers for Disease Control and Prevention, U.S.
  • Computational Biology
  • Computer Simulation*
  • Datasets as Topic
  • Disease Outbreaks
  • Humans
  • Influenza, Human / epidemiology*
  • Neural Networks, Computer*
  • Prevalence
  • Public Health
  • United States / epidemiology