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

IF 2.1 4区医学 Q3 HEALTH CARE SCIENCES & SERVICES

Journal of evaluation in clinical practice Pub Date : 2024-10-23 DOI:10.1111/jep.14206

Yang Yang, Xingyu Wan, Ning Zhang, Zhengyang Wu, Rong Qiu, Jing Yuan, Yinyin Xie

{"title":"Analysis and modelling of global online public interest in multiple other infectious diseases due to the COVID-19 pandemic.","authors":"Yang Yang, Xingyu Wan, Ning Zhang, Zhengyang Wu, Rong Qiu, Jing Yuan, Yinyin Xie","doi":"10.1111/jep.14206","DOIUrl":null,"url":null,"abstract":"Rationale: Previous research has demonstrated the applicability of Google Trends in predicting infectious diseases.Aims and objectives: This 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.Method: Google 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.Results: Our 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.Conclusions: Our study highlights the potential application value of Google Trends and large pre-trained models for infectious disease prediction.","PeriodicalId":15997,"journal":{"name":"Journal of evaluation in clinical practice","volume":" ","pages":""},"PeriodicalIF":2.1000,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of evaluation in clinical practice","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/jep.14206","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"HEALTH CARE SCIENCES & SERVICES","Score":null,"Total":0}

引用次数: 0

Abstract

Rationale: Previous research has demonstrated the applicability of Google Trends in predicting infectious diseases.

Aims and objectives: This 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.

Method: Google 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.

Results: Our 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.

Conclusions: Our study highlights the potential application value of Google Trends and large pre-trained models for infectious disease prediction.

查看原文本刊更多论文

分析和模拟 COVID-19 大流行引起的全球公众对其他多种传染病的在线兴趣。

理论依据：以前的研究已经证明了谷歌趋势在预测传染病方面的适用性：本研究旨在通过谷歌趋势数据分析 COVID-19 爆发前后公众对其他传染病的兴趣，并通过时间序列模型预测这些趋势：本研究获得了 12 种常见传染病的 Google Trends 数据，时间跨度为 2018 年 2 月 1 日至 2023 年 5 月 5 日。然后利用 ARIMA、TimeGPT、XGBoost 和 LSTM 算法建立时间序列预测模型：我们的研究表明，在大流行爆发初期，公众对大多数传染病的兴趣明显降低，而在大流行结束后，这种兴趣又有所回升，这与报告的疾病发病率相吻合。此外，我们的预测模型显示出良好的准确性，其中 TimeGPT 显示出独特的优势：我们的研究凸显了谷歌趋势和大型预训练模型在传染病预测方面的潜在应用价值。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of evaluation in clinical practice 医学-卫生保健

CiteScore

4.80

自引率

4.20%

发文量

143

审稿时长

3-8 weeks

期刊介绍： The Journal of Evaluation in Clinical Practice aims to promote the evaluation and development of clinical practice across medicine, nursing and the allied health professions. All aspects of health services research and public health policy analysis and debate are of interest to the Journal whether studied from a population-based or individual patient-centred perspective. Of particular interest to the Journal are submissions on all aspects of clinical effectiveness and efficiency including evidence-based medicine, clinical practice guidelines, clinical decision making, clinical services organisation, implementation and delivery, health economic evaluation, health process and outcome measurement and new or improved methods (conceptual and statistical) for systematic inquiry into clinical practice. Papers may take a classical quantitative or qualitative approach to investigation (or may utilise both techniques) or may take the form of learned essays, structured/systematic reviews and critiques.