Análise Estatística e Comparativa de Algoritmos de Machine Learning para Predição de Mortalidade em Unidades de Terapia Intensiva
##plugins.themes.bootstrap3.article.sidebar##
Publicado
Sep 21, 2026
##plugins.themes.bootstrap3.article.main##
Resumo
A predição de mortalidade em unidades de terapia intensiva (UTI) é um desafio crítico para a medicina. Este trabalho propõe a aplicação de algoritmos de Machine Learning para estimar o risco de óbito hospitalar, utilizando dados da base MIMIC-III processados com uma estratégia de interpolação inspirada no sistema MedLens. Foram avaliados cinco modelos supervisionados, com destaque para técnicas de ensemble como LightGBM e XGBoost. Diferentemente de abordagens anteriores, implementou-se um protocolo de validação rigoroso com 25 execuções independentes, seguido de testes de hipótese. Os resultados comprovaram a superioridade estatística do LightGBM, que atingiu acurácia média de 92,99% e F1-Score de 0,927. A aplicação do teste de Wilcoxon Signed-Rank confirmou ($p < 0,05$) que o desempenho do LightGBM é significativamente superior aos demais competidores, validando sua robustez como ferramenta de suporte à decisão clínica e otimização de recursos hospitalares.
Downloads
Não há dados estatísticos.
##plugins.themes.bootstrap3.article.details##
Como Citar
Aguiar, R., & Fagundes, R. (2026). Análise Estatística e Comparativa de Algoritmos de Machine Learning para Predição de Mortalidade em Unidades de Terapia Intensiva. Revista De Engenharia E Pesquisa Aplicada, 11(3), 83-91. https://doi.org/10.25286/repa.v11i3.3974
Seção
Edição Especial Ingenia
Referências
[1] HARUTYUNYAN, H.; KHACHATRIAN, H.; KALE, D. C.; VER STEEG, G.; GALSTYAN, A. Multitask learning and benchmarking with clinical time series data. Scientific Data, [S.l.], v. 6, n. 1, p. 96, 2019.
[2] WANG, J. et al. MedLens: Improve Mortality Prediction via Medical Signs Selecting and Regression. IEEE Journal of Biomedical and Health Informatics, [S.l.], v. 25, n. 2, p. 390–400, 2021.
[3] JOHNSON, A. E. W. et al. MIMIC-III, a freely accessible critical care database. Scientific Data, [S.l.], v. 3, n. 160035, 2016.
[4] CHEN, Tianqi; GUESTRIN, Carlos. XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016. p. 785–794.
[5] KE, Guolin et al. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In: Advances in Neural Information Processing Systems (NIPS 30). Long Beach, CA: Curran Associates, Inc., 2017. p. 3146–3154.
[6] FREUND, Yoav; SCHAPIRE, Robert E. A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. Journal of Computer and System Sciences, v. 55, n. 1, p. 119–139, 1997.
[7] CORTES, Corinna; VAPNIK, Vladimir. Support-vector networks. Machine Learning, v. 20, n. 3, p. 273–297, 1995.
[8] PLATT, John. Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods. In: Advances in Large Margin Classifiers. Cambridge, MA: MIT Press, 1999. p. 61–74.
[9] SAUNDERS, Craig; GAMMERAAN, Alexander; VOLKMER, Vovk. Ridge Regression Learning Algorithm in Dual Variables. In: Proceedings of the 15th International Conference on Machine Learning (ICML). San Francisco: Morgan Kaufmann, 1998. p. 515–521.
[10] HU, T. L. et al. Machine Learning-Based Predictions of Mortality and Readmission in Type 2 Diabetes Patients in the ICU. Applied Sciences, [S.l.], v. 14, n. 18, p. 8443, 2024.
[11] IM, S.; LEE, S. M. Development of mortality prediction model using electronic health record (EHR) data and machine learning algorithm in intensive care unit (ICU). Journal of the Korean Data Analysis Society, [S.l.], v. 25, n. 5, p. 1977–1994, 2023.
[12] JAIN, E.; SINGH, A. Optimizing Gradient Boosting Algorithms for Obesity Risk Prediction. In: IEEE INTERNATIONAL CONFERENCE ON CYBERNETICS AND COMPUTATIONAL INTELLIGENCE (CYBERCOM), 2024. Proceedings... [S.l.]: IEEE, 2024.
[13] MONTGOMERY, Douglas C. Design and Analysis of Experiments. 8. ed. New York: John Wiley & Sons, 2012.
[14] SCHMIDT, G. A.; HALL, J. B. Hypoxemia. In: HALL, J. B.; SCHMIDT, G. A.; KRESS, J. P. (Ed.). Principles of Critical Care. [S.l.]: McGraw-Hill Education, 2011. p. 144-154.
[2] WANG, J. et al. MedLens: Improve Mortality Prediction via Medical Signs Selecting and Regression. IEEE Journal of Biomedical and Health Informatics, [S.l.], v. 25, n. 2, p. 390–400, 2021.
[3] JOHNSON, A. E. W. et al. MIMIC-III, a freely accessible critical care database. Scientific Data, [S.l.], v. 3, n. 160035, 2016.
[4] CHEN, Tianqi; GUESTRIN, Carlos. XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016. p. 785–794.
[5] KE, Guolin et al. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In: Advances in Neural Information Processing Systems (NIPS 30). Long Beach, CA: Curran Associates, Inc., 2017. p. 3146–3154.
[6] FREUND, Yoav; SCHAPIRE, Robert E. A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. Journal of Computer and System Sciences, v. 55, n. 1, p. 119–139, 1997.
[7] CORTES, Corinna; VAPNIK, Vladimir. Support-vector networks. Machine Learning, v. 20, n. 3, p. 273–297, 1995.
[8] PLATT, John. Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods. In: Advances in Large Margin Classifiers. Cambridge, MA: MIT Press, 1999. p. 61–74.
[9] SAUNDERS, Craig; GAMMERAAN, Alexander; VOLKMER, Vovk. Ridge Regression Learning Algorithm in Dual Variables. In: Proceedings of the 15th International Conference on Machine Learning (ICML). San Francisco: Morgan Kaufmann, 1998. p. 515–521.
[10] HU, T. L. et al. Machine Learning-Based Predictions of Mortality and Readmission in Type 2 Diabetes Patients in the ICU. Applied Sciences, [S.l.], v. 14, n. 18, p. 8443, 2024.
[11] IM, S.; LEE, S. M. Development of mortality prediction model using electronic health record (EHR) data and machine learning algorithm in intensive care unit (ICU). Journal of the Korean Data Analysis Society, [S.l.], v. 25, n. 5, p. 1977–1994, 2023.
[12] JAIN, E.; SINGH, A. Optimizing Gradient Boosting Algorithms for Obesity Risk Prediction. In: IEEE INTERNATIONAL CONFERENCE ON CYBERNETICS AND COMPUTATIONAL INTELLIGENCE (CYBERCOM), 2024. Proceedings... [S.l.]: IEEE, 2024.
[13] MONTGOMERY, Douglas C. Design and Analysis of Experiments. 8. ed. New York: John Wiley & Sons, 2012.
[14] SCHMIDT, G. A.; HALL, J. B. Hypoxemia. In: HALL, J. B.; SCHMIDT, G. A.; KRESS, J. P. (Ed.). Principles of Critical Care. [S.l.]: McGraw-Hill Education, 2011. p. 144-154.