biostudies-literatureWichmann RMMicrosoftNational Council for Scientific and Technological Development (CNPq)1022https://www.ebi.ac.uk/biostudies/studies/S-EPMC9849836biostudies-literatureUnknown13(1)Machine learning algorithms are being increasingly used in healthcare settings but their generalizability between different regions is still unknown. This study aims to identify the strategy that maximizes the predictive performance of identifying the risk of death by COVID-19 in different regions of a large and unequal country. This is a multicenter cohort study with data collected from patients with a positive RT-PCR test for COVID-19 from March to August 2020 (n = 8477) in 18 hospitals, covering all five Brazilian regions. Of all patients with a positive RT-PCR test during the period, 2356 (28%) died. Eight different strategies were used for training and evaluating the performance of three popular machine learning algorithms (extreme gradient boosting, lightGBM, and catboost). The stratScientific reportsImproving the performance of machine learning algorithms for health outcomes predictions in multicentric cohorts.PMC9849836Microsoft AI for Health COVID-19 GrantGrant Number 402626/2020-6de Oliveira LPMimica MJde Castro Rodrigues HWichmann RMRocha HALde Macedo TTSSilva DLEBatista SRDos Santos Andrade LSDos Reis JCBde Maria Felix Mde Almeida Araujo MEIACOV-BR NetworkCiconelle ACMChiavegatto Filho ADPAnschau FNuno VLEArnoni MVJunior RMMde Lima RFda Penha RVNunes SFNunes BPFernandes FTde Brito AMESde Oliveira Cavalcante LVianna RBNasi LAVicente RNfalseImproving the performance of machine learning algorithms for health outcomes predictions in multicentric cohorts.Machine learning algorithms are being increasingly used in healthcare settings but their generalizability between different regions is still unknown. This study aims to identify the strategy that maximizes the predictive performance of identifying the risk of death by COVID-19 in different regions of a large and unequal country. This is a multicenter cohort study with data collected from patients with a positive RT-PCR test for COVID-19 from March to August 2020 (n = 8477) in 18 hospitals, covering all five Brazilian regions. Of all patients with a positive RT-PCR test during the period, 2356 (28%) died. Eight different strategies were used for training and evaluating the performance of three popular machine learning algorithms (extreme gradient boosting, lightGBM, and catboost). The strat2023-01-01T00:00:00Z2023 Jan2025-04-04T14:27:20.208Z2025-04-04T14:27:20.208ZS-EPMC98498363665818110.1038/s41598-022-26467-6