A data-driven approach for neonatal mortality rate forecasting

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorUniv Taubate UNITAU-
Autor(es): dc.creatorRodriguez, Elen-
Autor(es): dc.creatorRodriguez, Elias-
Autor(es): dc.creatorNascimento, Luiz-
Autor(es): dc.creatorSilva, Aneirson da-
Autor(es): dc.creatorMarins, Fernando-
Autor(es): dc.creatorShakhovska, N.-
Autor(es): dc.creatorChretien, S.-
Autor(es): dc.creatorIzonin, I-
Autor(es): dc.creatorCampos, J.-
Data de aceite: dc.date.accessioned2025-08-21T21:05:12Z-
Data de disponibilização: dc.date.available2025-08-21T21:05:12Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2021-12-31-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/300196-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/300196-
Descrição: dc.descriptionNeonatal mortality is an important public health problem that reflects the development of a country, as well as the quality of care provided to the newborn. This article presents the development and comparison of classical models and machine learning models for time series forecasting, applied to the forecast of monthly neonatal mortality rates in the metropolitan region of Paraiba River Valley and North Coast - Sao Paulo State - Brazil. The database used comprised the monthly rates from January 2000 to December 2020. The models compared were Seasonal Autoregressive Integrated Moving Average, random forest, support vector machine (SVM), light gradient boosting machine, categorical boosting (CatBoost), gradient boosting (GB), extreme gradient boosting, and multilayer perceptron. The best parameters and hyperparameters of the models tested were adjusted through an exhaustive computational search. The results showed that the CatBoost, SVM, and GB models presented the lowest values in the error metrics evaluated, and the SVM model presented better precision. The forecasts of the SVM model showed a behavior very close to the actual rates, which was confirmed by the application of the paired t-test. These results corroborate that time series forecasting models can significantly contribute as a decision support tool for public health problems.-
Descrição: dc.descriptionCoordination for the Improvement of Higher Education Personnel-
Descrição: dc.descriptionNational Council for Scientific and Technological Development-
Descrição: dc.descriptionSao Paulo State Univ UNESP, Ave Dr Ariberto Pereira Cunha 33, BR-12516410 Guaratingueta, SP, Brazil-
Descrição: dc.descriptionUniv Taubate UNITAU, Estr Municipal Dr Jose Luiz Cembranelli 5-000, BR-1208101 Taubate, SP, Brazil-
Descrição: dc.descriptionSao Paulo State Univ UNESP, Ave Dr Ariberto Pereira Cunha 33, BR-12516410 Guaratingueta, SP, Brazil-
Descrição: dc.descriptionCoordination for the Improvement of Higher Education Personnel: CAPES - 001-
Descrição: dc.descriptionNational Council for Scientific and Technological Development: CNPq -304197/2021-1-
Descrição: dc.descriptionNational Council for Scientific and Technological Development: CNPq 303090/2021-9-
Formato: dc.format13-
Idioma: dc.languageen-
Publicador: dc.publisherRwth Aachen-
Relação: dc.relation5th International Conference On Informatics & Data-driven Medicine, Iddm 2022-
???dc.source???: dc.sourceWeb of Science-
Palavras-chave: dc.subjectNeonatal mortality-
Palavras-chave: dc.subjecttime series analysis-
Palavras-chave: dc.subjectforecasting-
Palavras-chave: dc.subjectdata-driven models-
Palavras-chave: dc.subjectmachine learning-
Título: dc.titleA data-driven approach for neonatal mortality rate forecasting-
Tipo de arquivo: dc.typeaula digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.