Forecasting the Potential Number of Influenza-like Illness Cases by Fusing Internet Public Opinion

Yu-Chih Wei,Jianqiang Li,Wei-Chen Wu,Yan-Ling Ou

doi:10.3390/su14052803

Abstract

As influenza viruses mutate rapidly, a prediction model for potential outbreaks of influenza-like illnesses helps detect the spread of the illnesses in real time. In order to create a better prediction model, in this study, in addition to using the traditional hydrological and atmospheric data, features, such as popular search keywords on Google Trends, public holiday information, population density, air quality indices, and the numbers of COVID-19 confirmed cases, were also used to train the model in this research. Furthermore, Random Forest and XGBoost were combined and used in the proposed prediction model to increase the prediction accuracy. The training data used in this research were the historical data taken from 2016 to 2021. In our experiments, different combinations of features were tested. The results show that features, such as popular search keywords on Google Trends, the numbers of COVID-19 confirmed cases, and air quality indices can improve the outcome of the prediction model. The evaluation results showed that the error rate between the predicted results and the actual number of influenza-like cases form Week 15 to Week 18 fell to less than 5%. The outbreak of COVID-19 in Taiwan began in Week 19 and resulted in a sharp rise in the number of clinic or hospital visits by patients of influenza-like illnesses. After that, from Week 21 to Week 26, the error rate between the predicted and actual numbers of influenza-like cases in the later period dropped down to 13%. It can be confirmed from the actual experimental results in this research that the use of the ensemble learning prediction model proposed in this research can accurately predict the trend of influenza-like cases.

Highlights

Publisher’s Note: MDPI stays neutralThe COVID-19 pandemic broke out at the end of 2019
The ensemble learning model combining RandomForest and XGBoost was used as a predictive model, and the data of the week before Week 0 were used as the data of Week 0; the number of influenza-like cases for Week 1 was predicted
It was mentioned in the previous section that the three feature combinations with the smallest error rates were: Covid_noWD_df, GT_noWD_df, and AQI_noWD_df

Summary

Introduction

The COVID-19 pandemic broke out at the end of 2019. It has spread all over the world at lightning speed. Due to the convenience in public transport, viruses these days can be spread to every corner of the world these days [3,4]. An influenza-like illness means any illness caused by a virus with symptoms similar to those that are caused by influenza viruses (“flu”), including symptoms such as fever, respiratory symptoms, muscle pain, and fatigue, etc. If they are not diagnosed as influenza, they are called influenza-like illnesses. Prel et al [6] explored the effects of different climates on acute respiratory tract infections (ARI) and found that different with regard to jurisdictional claims in published maps and institutional affiliations

Methods

Results

Conclusion