{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["13(1)"],"submitter":["de Paiva BBM"],"pubmed_abstract":["The majority of early prediction scores and methods to predict COVID-19 mortality are bound by methodological flaws and technological limitations (e.g., the use of a single prediction model). Our aim is to provide a thorough comparative study that tackles those methodological issues, considering multiple techniques to build mortality prediction models, including modern machine learning (neural) algorithms and traditional statistical techniques, as well as meta-learning (ensemble) approaches. This study used a dataset from a multicenter cohort of 10,897 adult Brazilian COVID-19 patients, admitted from March/2020 to November/2021, including patients [median age 60 (interquartile range 48-71), 46% women]. We also proposed new original population-based meta-features that have not been devised "],"journal":["Scientific reports"],"pagination":["3463"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9975879"],"repository":["biostudies-literature"],"pubmed_title":["Potential and limitations of machine meta-learning (ensemble) methods for predicting COVID-19 mortality in a large inhospital Brazilian dataset."],"pmcid":["PMC9975879"],"pubmed_authors":["de Paiva BBM","Souza-Silva MVR","Farace BL","Cimini CCR","Silveira DV","Guimaraes HC","Bartolazzi F","Ponce D","Ziegelmann PK","Chatkin JM","Floriani MA","de Paula de Sordi MA","de Carvalho RLR","Carneiro M","de Deus Sousa L","Ramos LEF","de Andrade CMV","Goncalves MA","da Cunha Severino Sampaio N","Menezes RM","Guimaraes-Junior MH","Assaf PL","Rugolo JM","Batista JDL","Oliveira TF","de Almeida Cenci EP","Guimaraes SMM","Lucas FB","Bastos GAN","Vietta GG","de Freitas Martins Vieira A","Ribeiro YCNMB","de Alvarenga JC","Zandona LB","Bezerra AFB","Pereira PD","de Oliveira Jorge A","Paraiso PG","Costa JHSM","de Godoy MF","Fereguetti TO","Pires MC","de Oliveira Maurilio A","Ramires YC","Araujo SF","di Sabatino Santos Guimaraes J","Nogueira MCA","de Souza Viana L","de Oliveira NR","Nascimento GF","Silva RT","Martins KPMP","da Silva CTCA","Moreira LB","Ruschel KB","Grizende GMS","Gomes IM","de Morais JDP","Manenti ERF","Menezes LSM","Finger RG","Duani H","Senger R","Schwarzbold AV","Tupinambas JT","de Freitas R","Aranha FG","Assis LA","Pereira EC","de Oliveira LS","Rodrigues FD","Sales TLS","Pinheiro LS","Marques LM","Gomes VMR","Nunes AGS","Vianna HR","Noal HC","Valacio RA","Botoni FA","de Lima Martelli PJ","Anschau F","Ferreira MAP","Raposo MC","de Souza Cabral MA","de Figueiredo MP","de Moura Costa AS","Kopittke L","Marcolino MS","Kurtz T","Lima MCPB","Scotton ALBA","de Oliveira TC","de Oliveira LMC","Francisco SC","Lutkmeier R","Bicalho MAC","Diniz THO"],"additional_accession":[]},"is_claimable":false,"name":"Potential and limitations of machine meta-learning (ensemble) methods for predicting COVID-19 mortality in a large inhospital Brazilian dataset.","description":"The majority of early prediction scores and methods to predict COVID-19 mortality are bound by methodological flaws and technological limitations (e.g., the use of a single prediction model). Our aim is to provide a thorough comparative study that tackles those methodological issues, considering multiple techniques to build mortality prediction models, including modern machine learning (neural) algorithms and traditional statistical techniques, as well as meta-learning (ensemble) approaches. This study used a dataset from a multicenter cohort of 10,897 adult Brazilian COVID-19 patients, admitted from March/2020 to November/2021, including patients [median age 60 (interquartile range 48-71), 46% women]. We also proposed new original population-based meta-features that have not been devised ","dates":{"release":"2023-01-01T00:00:00Z","publication":"2023 Mar","modification":"2025-04-22T10:04:30.55Z","creation":"2025-04-05T23:23:39.677Z"},"accession":"S-EPMC9975879","cross_references":{"pubmed":["36859446"],"doi":["10.1038/s41598-023-28579-z"]}}