biostudies-literatureUnknown13(1)de Paiva BBMThe 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 Scientific reports3463https://www.ebi.ac.uk/biostudies/studies/S-EPMC9975879biostudies-literaturePotential and limitations of machine meta-learning (ensemble) methods for predicting COVID-19 mortality in a large inhospital Brazilian dataset.PMC9975879de Paiva BBMSouza-Silva MVRFarace BLCimini CCRSilveira DVGuimaraes HCBartolazzi FPonce DZiegelmann PKChatkin JMFloriani MAde Paula de Sordi MAde Carvalho RLRCarneiro Mde Deus Sousa LRamos LEFde Andrade CMVGoncalves MAda Cunha Severino Sampaio NMenezes RMGuimaraes-Junior MHAssaf PLRugolo JMBatista JDLOliveira TFde Almeida Cenci EPGuimaraes SMMLucas FBBastos GANVietta GGde Freitas Martins Vieira ARibeiro YCNMBde Alvarenga JCZandona LBBezerra AFBPereira PDde Oliveira Jorge AParaiso PGCosta JHSMde Godoy MFFereguetti TOPires MCde Oliveira Maurilio ARamires YCAraujo SFdi Sabatino Santos Guimaraes JNogueira MCAde Souza Viana Lde Oliveira NRNascimento GFSilva RTMartins KPMPda Silva CTCAMoreira LBRuschel KBGrizende GMSGomes IMde Morais JDPManenti ERFMenezes LSMFinger RGDuani HSenger RSchwarzbold AVTupinambas JTde Freitas RAranha FGAssis LAPereira ECde Oliveira LSRodrigues FDSales TLSPinheiro LSMarques LMGomes VMRNunes AGSVianna HRNoal HCValacio RABotoni FAde Lima Martelli PJAnschau FFerreira MAPRaposo MCde Souza Cabral MAde Figueiredo MPde Moura Costa ASKopittke LMarcolino MSKurtz TLima MCPBScotton ALBAde Oliveira TCde Oliveira LMCFrancisco SCLutkmeier RBicalho MACDiniz THOfalsePotential and limitations of machine meta-learning (ensemble) methods for predicting COVID-19 mortality in a large inhospital Brazilian dataset.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 2023-01-01T00:00:00Z2023 Mar2025-04-22T10:04:30.55Z2025-04-05T23:23:39.677ZS-EPMC99758793685944610.1038/s41598-023-28579-z