A novel data-driven methodology for influenza outbreak detection and prediction

Abstract Influenza is an infectious disease that leads to an estimated 5 million cases of severe illness and 650,000 respiratory deaths worldwide each year. The early detection and prediction of influenza outbreaks are crucial for efficient resource planning to save patient’s lives and healthcare co...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lin Du, Yan Pang
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/f58112c4b89a4e8da26ae1e74e05d5b2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f58112c4b89a4e8da26ae1e74e05d5b2
record_format	dspace
spelling	oai:doaj.org-article:f58112c4b89a4e8da26ae1e74e05d5b22021-12-02T16:07:03ZA novel data-driven methodology for influenza outbreak detection and prediction10.1038/s41598-021-92484-62045-2322https://doaj.org/article/f58112c4b89a4e8da26ae1e74e05d5b22021-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-92484-6https://doaj.org/toc/2045-2322Abstract Influenza is an infectious disease that leads to an estimated 5 million cases of severe illness and 650,000 respiratory deaths worldwide each year. The early detection and prediction of influenza outbreaks are crucial for efficient resource planning to save patient’s lives and healthcare costs. We propose a new data-driven methodology for influenza outbreak detection and prediction at very local levels. A doctor’s diagnostic dataset of influenza-like illness from more than 3000 clinics in Malaysia is used in this study because these diagnostic data are reliable and can be captured promptly. A new region index (RI) of the influenza outbreak is proposed based on the diagnostic dataset. By analysing the anomalies in the weekly RI value, potential outbreaks are identified using statistical methods. An ensemble learning method is developed to predict potential influenza outbreaks. Cross-validation is conducted to optimize the hyperparameters of the ensemble model. A testing data set is used to provide an unbiased evaluation of the model. The proposed methodology is shown to be sensitive and accurate at influenza outbreak prediction, with average of 75% recall, 74% precision, and 83% accuracy scores across five regions in Malaysia. The results are also validated by Google Flu Trends data, news reports, and surveillance data released by World Health Organization.Lin DuYan PangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-16 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Lin Du Yan Pang A novel data-driven methodology for influenza outbreak detection and prediction
description	Abstract Influenza is an infectious disease that leads to an estimated 5 million cases of severe illness and 650,000 respiratory deaths worldwide each year. The early detection and prediction of influenza outbreaks are crucial for efficient resource planning to save patient’s lives and healthcare costs. We propose a new data-driven methodology for influenza outbreak detection and prediction at very local levels. A doctor’s diagnostic dataset of influenza-like illness from more than 3000 clinics in Malaysia is used in this study because these diagnostic data are reliable and can be captured promptly. A new region index (RI) of the influenza outbreak is proposed based on the diagnostic dataset. By analysing the anomalies in the weekly RI value, potential outbreaks are identified using statistical methods. An ensemble learning method is developed to predict potential influenza outbreaks. Cross-validation is conducted to optimize the hyperparameters of the ensemble model. A testing data set is used to provide an unbiased evaluation of the model. The proposed methodology is shown to be sensitive and accurate at influenza outbreak prediction, with average of 75% recall, 74% precision, and 83% accuracy scores across five regions in Malaysia. The results are also validated by Google Flu Trends data, news reports, and surveillance data released by World Health Organization.
format	article
author	Lin Du Yan Pang
author_facet	Lin Du Yan Pang
author_sort	Lin Du
title	A novel data-driven methodology for influenza outbreak detection and prediction
title_short	A novel data-driven methodology for influenza outbreak detection and prediction
title_full	A novel data-driven methodology for influenza outbreak detection and prediction
title_fullStr	A novel data-driven methodology for influenza outbreak detection and prediction
title_full_unstemmed	A novel data-driven methodology for influenza outbreak detection and prediction
title_sort	novel data-driven methodology for influenza outbreak detection and prediction
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/f58112c4b89a4e8da26ae1e74e05d5b2
work_keys_str_mv	AT lindu anoveldatadrivenmethodologyforinfluenzaoutbreakdetectionandprediction AT yanpang anoveldatadrivenmethodologyforinfluenzaoutbreakdetectionandprediction AT lindu noveldatadrivenmethodologyforinfluenzaoutbreakdetectionandprediction AT yanpang noveldatadrivenmethodologyforinfluenzaoutbreakdetectionandprediction
_version_	1718384815779086336

A novel data-driven methodology for influenza outbreak detection and prediction

Ejemplares similares