Mostrar registro simples

dc.creatorLima, Vinicius Ferreira de
dc.date.accessioned2025-06-05T17:28:37Z
dc.date.available2025-06-05T17:28:37Z
dc.date.issued2025-01-31
dc.identifier.citationLIMA, Vinicius Ferreira de; OLIVEIRA, Flávio Rosendo da Silva. Aplicação de Técnicas Automatizadas de Aprendizagem de Máquina para Classificação de Óbitos em Pacientes com Covid-19. 2025. Trabalho de Conclusão de Curso (Tecnologia em Análise e Desenvolvimento de Sistemas) — Instituto Federal de Educação, Ciência e Tecnologia de Pernambuco, Campus Paulista, Paulista, 2025.pt_BR
dc.identifier.urihttps://repositorio.ifpe.edu.br/xmlui/handle/123456789/1709
dc.description.abstractThis study investigated the application of automated machine learning techniques in classifying cases with a potential risk of death among COVID-19 patients, using a histo- rical database from Fiocruz. This database contained data from COVID-19 patients in three different periods, corresponding to different phases of the disease’s circulation, classifying patients who succumbed to the disease. The aim was to apply AutoML tools adapted to this classification scenario and to evaluate their use and potential for research in the field of clinical analysis. By implementing well-established AutoML tools in the literature, such as H2O AutoML, AutoGluon and PyCaret, this study demonstrated how these technologies can simplify complex analytical processes, highlighting the relevance of these tools in making advanced machine learning techniques accessible to non-specialists and their efficiency in processing clinical data. Although challenges related to the processing time of some to- ols were identified, it was concluded that AutoML has significant potential to facilitate and enhance the application of machine learning models in clinical analytics.pt_BR
dc.format.extent19 p.pt_BR
dc.languagept_BRpt_BR
dc.relationAMORIM, Lucas B.V. de; CAVALCANTI, George D.C.; CRUZ, Rafael M.O. The choice of scaling technique matters for classification performance. Applied Soft Computing, v. 133, p. 109924, 2023. ISSN 1568-4946. DOI: 10.1016/j.asoc.2022.109924. Disponível em: https://www.sciencedirect.com/science/article/abs/pii/S1568494622009735. Acesso em: 24 fev. 2025. BERGSTRA, James; BENGIO, Yoshua. Random search for hyper-parameter optimization. Journal of Machine Learning Research, v. 13, p. 281–305, fev. 2012. Disponível em: https://www.jmlr.org/papers/volume13/bergstra12a/bergstra12a.pdf. Acesso em: 24 fev. 2025. BEYER, H. Tukey, John W.: Exploratory Data Analysis. Addison-Wesley Publishing Company Reading, Mass. — Menlo Park, Cal., London, Amsterdam, Don Mills, Ontario, Sydney 1977, XVI, 688 p. Biometrical Journal, v. 23, n. 4, p. 413–414, 1981. DOI: 10.1002/bimj.4710230408. Disponível em: https://onlinelibrary.wiley.com/doi/abs/10.1002/bimj.4710230408. Acesso em: 24 fev. 2025. BREIMAN, Leo. Random Forests. Machine Learning, v. 45, p. 5–32, out. 2001. DOI: 10.1023/A:1010950718922. Disponível em: https://www.researchgate.net/publication/275342330_Random_Forests. Acesso em: 24 fev. 2025. 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. [S.l.: s.n.], 2016. p. 785–794. Disponível em: https://arxiv.org/abs/1603.02754. Acesso em: 24 fev. 2025. DOMINGOS, Pedro. A few useful things to know about machine learning. Communications of the ACM, v. 55, n. 10, p. 78–87, 2012. Disponível em: https://dl.acm.org/doi/10.1145/2347736.2347755. Acesso em: 24 fev. 2025. ERICKSON, Nick et al. AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data. arXiv preprint arXiv:2003.06505, 2020. Disponível em: https://arxiv.org/abs/2003.06505. Acesso em: 24 fev. 2025. FEURER, Matthias et al. Efficient and Robust Automated Machine Learning. In: Advances in Neural Information Processing Systems. [S.l.]: Curran Associates, Inc., 2015. v. 28. FREUND, Yoav; SCHAPIRE, Robert E. A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. J. Comput. Syst. Sci., v. 55, n. 1, p. 119–139, 1997. DOI: 10.1006/jcss.1997.1504. Disponível em: https://doi.org/10.1006/jcss.1997.1504. Acesso em: 24 fev. 2025. FRIEDMAN, Jerome H. Greedy function approximation: A gradient boosting machine. The Annals of Statistics, v. 29, n. 5, p. 1189–1232, 2001. DOI: 10.1214/aos/1013203451. Disponível em: https://doi.org/10.1214/aos/1013203451. Acesso em: 24 fev. 2025. GIJSBERS, Pieter et al. An Open Source AutoML Benchmark. CoRR, v. 1907.00909, 2019. arXiv: 1907.00909. Disponível em: http://arxiv.org/abs/1907.00909. Acesso em: 24 fev. 2025. Instituto Federal de Educação, Ciências e Tecnologia de Pernambuco. Campus Paulista. Curso de Análise e Desenvolvimento de Sistemas. 31 de janeiro de 2025. HARRIS, Charles R. et al. Array programming with NumPy. Nature, v. 585, n. 7825, p. 357–362, 2020. DOI: 10.1038/s41586-020-2649-2. Disponível em: https://doi.org/10.1038/s41586-020-2649-2. Acesso em: 24 fev. 2025. HASTIE, Trevor; TIBSHIRANI, Robert; FRIEDMAN, Jerome. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. [S.l.]: Springer, 2009. (Springer Series in Statistics). DOI: 10.1007/978-0-387-84858-7. Disponível em: https://doi.org/10.1007/978-0-387-84858-7. Acesso em: 24 fev. 2025. HE, Xin; ZHAO, Kaiyong; CHU, Xiaowen. AutoML: A survey of the state-of-the-art. Knowledge-Based Systems, Elsevier BV, v. 212, p. 106622, jan. 2021. ISSN 0950-7051. DOI: 10.1016/j.knosys.2020.106622. Disponível em: http://dx.doi.org/10.1016/j.knosys.2020.106622. Acesso em: 24 fev. 2025. HOSMER, David W.; LEMESHOW, Stanley; STURDIVANT, Rodney X. Applied Logistic Regression. [S.l.]: John Wiley & Sons, Inc, 2000. ISBN 978-0-471-72214-4. DOI: 10.1002/0471722146. HUTTER, Frank; KOTTHOFF, Lars; VANSCHOREN, J. (Ed.). Automatic machine learning: methods, systems, challenges. Alemanha: Springer, 2019. (Challenges in Machine Learning). ISBN 978-3-030-05317-8. DOI: 10.1007/978-3-030-05318-5. KUNCHEVA, Ludmila. Combining Pattern Classifiers: Methods and Algorithms: Second Edition. [S.l.]: John Wiley & Sons, ago. 2014. v. 47. ISBN 978-1-118-91456-4. DOI: 10.1002/0471660264. LEDELL, Erin; POIRIER, Sebastien. H2O AutoML: Scalable automatic machine learning. In: ICML SAN DIEGO, CA, USA. Proceedings of the AutoML Workshop at ICML. [S.l.: s.n.], 2020. Disponível em: https://www.automl.org/wp-content/uploads/2020/07/AutoML_2020_paper_61.pdf. Acesso em: 24 fev. 2025. OOMS, Richard; SPRUIT, Marco. Self-Service Data Science in Healthcare with Automated Machine Learning. Applied Sciences, v. 10, p. 2992, abr. 2020. DOI: 10.3390/app10092992. Disponível em: https://www.mdpi.com/2076-3417/10/9/2992. Acesso em: 24 fev. 2025. PALADINO, L. M. et al. Evaluating the performance of automated machine learning (AutoML) tools for heart disease diagnosis and prediction. AI, v. 4, p. 1036–1058, 2023. DOI: 10.3390/ai4040053. Disponível em: https://www.mdpi.com/2673-2688/4/4/53. Acesso em: 24 fev. 2025. POL, Urmila; MOHAREKAR, Tejashree. AutoML: Building a classification model with PyCaret. Ymer, v. 20, p. 547–552, dez. 2021. Disponível em: https://www.researchgate.net/publication/356749319_AutoML_Building_An_Classification_Model_With_Pycaret. Acesso em: 24 fev. 2025. THIRUNAVUKARASU, Arun James et al. Clinical performance of automated machine learning: a systematic review. medRxiv, Cold Spring Harbor Laboratory Press, 2023. DOI: 10.1101/2023.10.26.23297599. Disponível em: https://www.medrxiv.org/content/10.1101/2023.10.26.23297599v1. Acesso em: 24 fev. 2025. TRUONG, Anh et al. Towards Automated Machine Learning: Evaluation and Comparison of AutoML Approaches and Tools. CoRR, v. 1908.05557, 2019. arXiv: 1908.05557. Disponível em: http://arxiv.org/abs/1908.05557. Acesso em: 24 fev. 2025. WERTH, Alexandra et al. Engagement in collaboration and teamwork using Google Colaboratory. In: 2022 Physics Education Research Conference Proceedings. [S.l.: s.n.], set. 2022. p. 481–487. DOI: 10.1119/perc.2022.pr.Werth. Disponível em: https://ui.adsabs.harvard.edu/abs/2022perc.conf..481W. Acesso em: 24 fev. 2025. WYNANTS, L. et al. Prediction models for diagnosis and prognosis of COVID-19: systematic review and critical appraisal. BMJ, v. 369, p. m1328, 2020. Disponível em: https://www.bmj.com/content/369/bmj.m1328. Acesso em: 24 fev. 2025. YANG, J.; SHI, R.; NI, B. MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis. CoRR, v. 2010.14925, 2020. arXiv: 2010.14925. Disponível em: https://arxiv.org/abs/2010.14925. Acesso em: 24 fev. 2025. ZÖLLER, Marc-André; HUBER, Marco F. Benchmark and Survey of Automated Machine Learning Frameworks. Journal of Artificial Intelligence Research, v. 1904.12054, p. 409–472, 2021. Disponível em: http://arxiv.org/abs/1904.12054. Acesso em: 24 fev. 2025.pt_BR
dc.rightsAcesso Abertopt_BR
dc.rightsAn error occurred on the license name.*
dc.rights.uriAn error occurred getting the license - uri.*
dc.subjectAprendizagem de Máquinapt_BR
dc.subjectAutomated Machine Learningpt_BR
dc.subjectCOVID-19pt_BR
dc.subjectClassificação de óbitospt_BR
dc.titleAplicação de técnicas automatizadas de aprendizagem de máquina para classificação de óbitos em pacientes com covid-19.pt_BR
dc.title.alternativeApplication of automated machine learning techniques for classification of mortality in covid-19 patients.pt_BR
dc.typeArticlept_BR
dc.creator.Latteshttp://lattes.cnpq.br/4339235212808169pt_BR
dc.contributor.advisor1Oliveira, Flávio Rosendo da Silva
dc.contributor.advisor1Latteshttp://lattes.cnpq.br/6828380394080049pt_BR
dc.contributor.referee1Silva, Rodrigo Cesar Lira da
dc.contributor.referee2Cordeiro, Paulo Roger Gomes
dc.contributor.referee1Latteshttp://lattes.cnpq.br/2442224050349612pt_BR
dc.contributor.referee2Latteshttp://lattes.cnpq.br/7671177677866299pt_BR
dc.publisher.departmentPaulistapt_BR
dc.publisher.countryBrasilpt_BR
dc.subject.cnpqCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAOpt_BR
dc.description.resumoNeste estudo, foi investigada a aplicação de técnicas de Automated Machine Learning na classificação de casos com potencial risco de óbito entre pacientes com COVID-19, utilizando um banco de dados histórico da Fiocruz, com dados de pacientes com COVID-19 em três períodos de tempo diferentes, correspondentes a diferentes fases de circulação da doença, classificando os pacientes que chegaram a óbito. O objetivo foi empregar ferramentas de AutoML ajustadas a esse cenário de classificação, avaliando o uso e potencial para pesquisas na área de análises clínicas. Com a implementação de ferramentas consolidadas na literatura de AutoML, como H2O AutoML, AutoGluon e PyCaret, a pesquisa indicou como essas tecnologias podem simplificar processos analíticos complexos, mostrando a relevância que essas ferramentas têm em tornar técnicas avançadas de aprendizagem de máquina acessíveis a profissionais não especializados e sua eficiência no processamento de dados clínicos. Embora tenham sido identificados desafios relacionados ao tempo de processamento de algumas ferramentas, concluiu-se que o AutoML possui um potencial significativo para facilitar e aprimorar a aplicação de modelos de aprendizagem de máquina na área de análises clínicas.pt_BR


Arquivos deste item

Thumbnail
Thumbnail

Este item aparece na(s) seguinte(s) coleção(s)

Mostrar registro simples