Analysis and modelling of global online public interest in multiple other infectious diseases due to the COVID-19 pandemic

被引：0

作者：

Yang, Yang ^{[1
,2
]}

Wan, Xingyu ^{[3
]}

Zhang, Ning ^{[1
,2
,4
]}

Wu, Zhengyang ^{[2
]}

Qiu, Rong ^{[5
]}

Yuan, Jing ^{[1
]}

Xie, Yinyin ^{[1
]}

机构：

[1] Anhui Med Univ, Coll Life Sci, Hefei 230032, Peoples R China

[2] Anhui Med Univ, Sch Clin Med 1, Hefei, Peoples R China

[3] Anhui Med Univ, Sch Clin Med 2, Hefei, Peoples R China

[4] Anhui Med Univ, Affiliated Hosp 1, Dept Obstet & Gynecol, Hefei, Peoples R China

[5] Anhui Med Univ, Sch Basic Med Sci, Hefei, Peoples R China

来源：

JOURNAL OF EVALUATION IN CLINICAL PRACTICE | 2024年

关键词：

ARIMA; COVID-19; infectious disease; Google Trends; time series models;

D O I：

10.1111/jep.14206

中图分类号：

R19 [保健组织与事业（卫生事业管理）];

学科分类号：

摘要：

RationalePrevious research has demonstrated the applicability of Google Trends in predicting infectious diseases.Aims and ObjectivesThis study aimed to analyze public interest in other infectious diseases before and after the outbreak of COVID-19 via Google Trends data and to predict these trends via time series models.MethodGoogle Trends data for 12 common infectious diseases were obtained in this study, covering the period from 1 February 2018 to 5 May 2023. The ARIMA, TimeGPT, XGBoost, and LSTM algorithms were then utilized to establish time series prediction models.ResultsOur study revealed a significant decrease in public interest in most infectious diseases at the beginning of the pandemic outbreak, followed by a rebound in the post-pandemic era, which is consistent with reported disease incidences. Furthermore, our prediction models demonstrated good accuracy, with TimeGPT showing unique advantages.ConclusionsOur study highlights the potential application value of Google Trends and large pre-trained models for infectious disease prediction.

引用

页数：6

共 14 条

[1] Modeling COVID-19 incidence with Google Trends [J].