Forecasting influenza-like illness trends in Cameroon using Google Search Data

Abstract Although acute respiratory infections are a leading cause of mortality in sub-Saharan Africa, surveillance of diseases such as influenza is mostly neglected. Evaluating the usefulness of influenza-like illness (ILI) surveillance systems and developing approaches for forecasting future trend...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Elaine O. Nsoesie, Olubusola Oladeji, Aristide S. Abah Abah, Martial L. Ndeffo-Mbah
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/3d1886dd45a94c51b80ae51b89506a3b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3d1886dd45a94c51b80ae51b89506a3b
record_format	dspace
spelling	oai:doaj.org-article:3d1886dd45a94c51b80ae51b89506a3b2021-12-02T11:45:04ZForecasting influenza-like illness trends in Cameroon using Google Search Data10.1038/s41598-021-85987-92045-2322https://doaj.org/article/3d1886dd45a94c51b80ae51b89506a3b2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-85987-9https://doaj.org/toc/2045-2322Abstract Although acute respiratory infections are a leading cause of mortality in sub-Saharan Africa, surveillance of diseases such as influenza is mostly neglected. Evaluating the usefulness of influenza-like illness (ILI) surveillance systems and developing approaches for forecasting future trends is important for pandemic preparedness. We applied and compared a range of robust statistical and machine learning models including random forest (RF) regression, support vector machines (SVM) regression, multivariable linear regression and ARIMA models to forecast 2012 to 2018 trends of reported ILI cases in Cameroon, using Google searches for influenza symptoms, treatments, natural or traditional remedies as well as, infectious diseases with a high burden (i.e., AIDS, malaria, tuberculosis). The R2 and RMSE (Root Mean Squared Error) were statistically similar across most of the methods, however, RF and SVM had the highest average R2 (0.78 and 0.88, respectively) for predicting ILI per 100,000 persons at the country level. This study demonstrates the need for developing contextualized approaches when using digital data for disease surveillance and the usefulness of search data for monitoring ILI in sub-Saharan African countries.Elaine O. NsoesieOlubusola OladejiAristide S. Abah AbahMartial L. Ndeffo-MbahNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Elaine O. Nsoesie Olubusola Oladeji Aristide S. Abah Abah Martial L. Ndeffo-Mbah Forecasting influenza-like illness trends in Cameroon using Google Search Data
description	Abstract Although acute respiratory infections are a leading cause of mortality in sub-Saharan Africa, surveillance of diseases such as influenza is mostly neglected. Evaluating the usefulness of influenza-like illness (ILI) surveillance systems and developing approaches for forecasting future trends is important for pandemic preparedness. We applied and compared a range of robust statistical and machine learning models including random forest (RF) regression, support vector machines (SVM) regression, multivariable linear regression and ARIMA models to forecast 2012 to 2018 trends of reported ILI cases in Cameroon, using Google searches for influenza symptoms, treatments, natural or traditional remedies as well as, infectious diseases with a high burden (i.e., AIDS, malaria, tuberculosis). The R2 and RMSE (Root Mean Squared Error) were statistically similar across most of the methods, however, RF and SVM had the highest average R2 (0.78 and 0.88, respectively) for predicting ILI per 100,000 persons at the country level. This study demonstrates the need for developing contextualized approaches when using digital data for disease surveillance and the usefulness of search data for monitoring ILI in sub-Saharan African countries.
format	article
author	Elaine O. Nsoesie Olubusola Oladeji Aristide S. Abah Abah Martial L. Ndeffo-Mbah
author_facet	Elaine O. Nsoesie Olubusola Oladeji Aristide S. Abah Abah Martial L. Ndeffo-Mbah
author_sort	Elaine O. Nsoesie
title	Forecasting influenza-like illness trends in Cameroon using Google Search Data
title_short	Forecasting influenza-like illness trends in Cameroon using Google Search Data
title_full	Forecasting influenza-like illness trends in Cameroon using Google Search Data
title_fullStr	Forecasting influenza-like illness trends in Cameroon using Google Search Data
title_full_unstemmed	Forecasting influenza-like illness trends in Cameroon using Google Search Data
title_sort	forecasting influenza-like illness trends in cameroon using google search data
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/3d1886dd45a94c51b80ae51b89506a3b
work_keys_str_mv	AT elaineonsoesie forecastinginfluenzalikeillnesstrendsincameroonusinggooglesearchdata AT olubusolaoladeji forecastinginfluenzalikeillnesstrendsincameroonusinggooglesearchdata AT aristidesabahabah forecastinginfluenzalikeillnesstrendsincameroonusinggooglesearchdata AT martiallndeffombah forecastinginfluenzalikeillnesstrendsincameroonusinggooglesearchdata
_version_	1718395275497701376

Forecasting influenza-like illness trends in Cameroon using Google Search Data

Ejemplares similares