Skip navigation
Universidade de Brasília
Por favor, use este identificador para citar o enlazar este ítem: http://repositorio.unb.br/handle/10482/54910
Ficheros en este ítem:
Fichero Tamaño Formato  
ARTIGO_AssessmentofMachineLearning.pdf1,75 MBAdobe PDFVisualizar/Abrir
Registro completo de metadatos
Campo DC Valor Lengua/Idioma
dc.contributor.authorSilva, Jéssica Aparecidapt_BR
dc.contributor.authorBloch, Katia Vergettipt_BR
dc.contributor.authorSzklo, Moysespt_BR
dc.contributor.authorDeusdará, Rodolfopt_BR
dc.date.accessioned2026-06-18T12:27:57Z-
dc.date.available2026-06-18T12:27:57Z-
dc.date.issued2026-3-15pt_BR
dc.identifier.citationSILVA, Jéssica Aparecida et al. Assessment of machine learning model performance for clinical prediction of insulin resistance in the study of cardiovascular risk in adolescents—ERICA. Journal of Clinical Medicine, [S.l.], v. 15, n. 6, p. 2224, 2026. DOI: https://doi.org/10.3390/jcm15062224. Disponível em: https://www.mdpi.com/2077-0383/15/6/2224. Acesso em: 18 jun.2026.pt_BR
dc.identifier.urihttps://doi.org/10.3390/jcm15062224pt_BR
dc.identifier.urihttp://repositorio.unb.br/handle/10482/54910-
dc.language.isoeng-
dc.publisherMDPIpt_BR
dc.rightsAcesso Abertopt_BR
dc.titleAssessment of machine learning model performance for clinical prediction of insulin resistance in the study of cardiovascular risk in adolescents - ERICApt_BR
dc.typeArtigopt_BR
dc.subject.keywordInsulina-
dc.subject.keywordDiabetes-
dc.subject.keywordSaúde-
dc.rights.licenseLicensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.-
dc.identifier.doihttps://doi.org/10.3390/jcm15062224pt_BR
dc.description.abstract1Background: Insulin resistance is defined as reduced tissue responsiveness to insulin-mediated glucose actions. Gold standard methods like hyperinsulinemic-euglycemic clamp and hyperglycemic clamps are costly and rarely used in large epidemiological studies. The aim was to evaluate the best performing machine learning algorithm for insulin resistance predictions in Brazilian adolescents. Methods: We used data from 37,454 Brazilian adolescents from 12 to 17 years, sampled from the Study of Cardiovascular Risk Factors in Adolescents (2013–2014). Covariates included other cardiovascular risk factors. We evaluate seven machine learning models stratifying the subset by sex. The performance of the models was assessed by area under the curve (AUC), calibration curves and decision curve analysis (DCA). Finally, we adopted the SHAP approach to assess the importance of each variable to the best performing ML model. Results: The Logistic Regression model presented the best AUC value (AUC = 0.8 for boys and girls). The best performing ML models had higher calibration in girls than in boys. The DCA curves showed prevalence of almost equal values for girls and for boys. The most important clinical predictors for both sexes were waist circumference, triglycerides and age. Conclusions: Logistic Regression proved to be the best clinical prediction model comparable to complex models. Further studies are needed in more diverse populations.pt_BR
dc.abstract-
dc.identifier.orcidhttps://orcid.org/0000-0002-6992-3159pt_BR
dc.identifier.orcidhttps://orcid.org/0000-0002-1343-3265pt_BR
dc.contributor.affiliationUniversity of Brasília, Postgraduate Program in Medical Sciences, Faculty of Medicinept_BR
dc.contributor.affiliationUniversity of Rio de Janeiro, Institute for Studies in Public Healthpt_BR
dc.contributor.affiliationDepartment of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimorept_BR
dc.contributor.affiliationUniversity of Brasília, Postgraduate Program in Medical Sciencespt_BR
dc.contributor.affiliationUniversity of Brasília, Faculty of Medicinept_BR
dc.contributor.affiliationNational Institute of Science and Technology for Health Technology Assessment (IATS)pt_BR
dc.contributor.affiliationUniversity of Brasília, Laboratory of Epidemiology, Faculty of Medicinept_BR
dc.contributor.affiliationInstitute for Health Assessment and Translation for Chronic and Neglected Diseases of High Relevance (IATS-CARE), Belo Horizontept_BR
dc.description.unidadeFaculdade de Medicina (FM)-
dc.description.ppgPrograma de Pós-Graduação em Ciências Médicas-
Aparece en las colecciones: Artigos publicados em periódicos e afins

Mostrar el registro sencillo del ítem " class="statisticsLink btn btn-primary" href="/handle/10482/54910/statistics">



Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.