Show simple item record

dc.contributor.authorScavuzzo, Carlos Matias
dc.contributor.authorScavuzzo, Juan Manuel
dc.contributor.authorCampero, Micaela Natalia
dc.contributor.authorAnegagrie, Melaku 
dc.contributor.authorAmor Aramendía, Aranzazu 
dc.contributor.authorBenito, Agustin 
dc.contributor.authorPeriago, Victoria
dc.date.accessioned2022-05-23T12:37:19Z
dc.date.available2022-05-23T12:37:19Z
dc.date.issued2022-02-03
dc.identifier.citationInfect Dis Model. 2022 Feb 3;7(1):262-276.es_ES
dc.identifier.issn2468-0427es_ES
dc.identifier.urihttp://hdl.handle.net/20.500.12105/14462
dc.description.abstractIn the field of landscape epidemiology, the contribution of machine learning (ML) to modeling of epidemiological risk scenarios presents itself as a good alternative. This study aims to break with the "black box" paradigm that underlies the application of automatic learning techniques by using SHAP to determine the contribution of each variable in ML models applied to geospatial health, using the prevalence of hookworms, intestinal parasites, in Ethiopia, where they are widely distributed; the country bears the third-highest burden of hookworm in Sub-Saharan Africa. XGBoost software was used, a very popular ML model, to fit and analyze the data. The Python SHAP library was used to understand the importance in the trained model, of the variables for predictions. The description of the contribution of these variables on a particular prediction was obtained, using different types of plot methods. The results show that the ML models are superior to the classical statistical models; not only demonstrating similar results but also explaining, by using the SHAP package, the influence and interactions between the variables in the generated models. This analysis provides information to help understand the epidemiological problem presented and provides a tool for similar studies.es_ES
dc.description.sponsorshipThis study was funded by Fundación Mundo Sano and Instituto de Salud Carlos III. The funders had no roles in the design of the study or collection, analysis and interpretation of the data. C.M.S. and M.N.C. had a PhD scholarship from Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET).es_ES
dc.language.isoenges_ES
dc.publisherElsevier es_ES
dc.relation.isversionofPublisher's versiones_ES
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectEthiopiaes_ES
dc.subjectHookwormes_ES
dc.subjectMachine learninges_ES
dc.subjectRemote sensinges_ES
dc.subjectShapes_ES
dc.subjectShapleyes_ES
dc.titleFeature importance: Opening a soil-transmitted helminth machine learning model via SHAPes_ES
dc.typeArtículoes_ES
dc.rights.licenseAttribution-NonCommercial-NoDerivatives 4.0 Internacional*
dc.identifier.pubmedID35224316es_ES
dc.format.volume7es_ES
dc.format.number1es_ES
dc.format.page262-276es_ES
dc.identifier.doi10.1016/j.idm.2022.01.004es_ES
dc.contributor.funderInstituto de Salud Carlos III es_ES
dc.contributor.funderFundación Mundo Sanoes_ES
dc.description.peerreviewedes_ES
dc.relation.publisherversionhttps://doi.org/10.1016/j.idm.2022.01.004es_ES
dc.identifier.journalInfectious Disease Modellinges_ES
dc.repisalud.centroISCIII::Centro Nacional de Medicina Tropicales_ES
dc.repisalud.institucionISCIIIes_ES
dc.rights.accessRightsinfo:eu-repo/semantics/openAccesses_ES


Files in this item

Acceso Abierto
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivatives 4.0 Internacional
This item is licensed under a: Attribution-NonCommercial-NoDerivatives 4.0 Internacional