COMPUTATIONAL INTELLIGENCE TECHNIQUES FOR DATA ANALYSIS AND PROCESSING: APPLICATION OF MACHINE LEARNING MODELS IN THE DIAGNOSIS OF GERIATRIC DISEASES
Abstract
Stroke is one of the leading causes of death and disability worldwide, requiring rapid diagnosis to minimize sequelae and improve patient prognosis. Therefore, some Machine Learning techniques have shown promising as tools to support pre-hospital triage. This work presents the implementation and evaluation of four classification models: K-Nearest Neighbors, Random Forest, eXtreme Gradient Boosting and Support Vector Machine. These models were applied to the Kaggle "Stroke Prediction" dataset, which was subjected to preprocessing, class balancing, and hyperparameter. Furthermore, the SelectKBest technique was applied to identify the most relevant variables, targeting future applications in embedded systems. The results indicated good performance across all models, with Random Forest standing out, achieving 98.9% accuracy with 12 variables and maintaining 96.9% accuracy when reduced to just four key variables (age, hypertension, heart disease, and average blood glucose). The experiments demonstrate that models can effectively support early stroke detection, enabling their integration into mobile applications or low-cost devices for rapid and reliable screening.
Author Biographies
Universidade Federal da Paraíba.
Universidade Federal da Paraíba.
Universidade Federal Rural do Semi-Árido: Mossoró.
Universidade Federal da Paraíba.
References
ADDAN, D. Support Vector Machine. [S. l.]: Unibrasil, 2019. Presentation slides (34 pages).
AGÊNCIA NACIONAL DE VIGILÂNCIA SANITÁRIA (ANVISA). Resolução de Diretoria Colegiada – RDC n.º 657, de 24 de março de 2022. Dispõe sobre software como dispositivo médico (SaMD). 2022. Disponível em: https://in.gov.br/en/web/dou/-/resolucao-de-diretoria-colegiada-rdc-n-657-de-24-de-marco-de-2022-389603457
ALOBAIDA, M.; JODDRELL, M.; ZHENG, Y.; LIP, G. Y. H.; ROWE, F. J.; EL-BOURI, W. K.; HILL, A.; LANE, D. A.; HARRISON, S. L. Systematic review and meta-analysis of prehospital machine learning scores as screening tools for early detection of large vessel occlusion in patients with suspected stroke. J Am Heart Assoc., v. 13, n. 12, p. e033298, jun. 2024. DOI: https://doi.org/10.1161/JAHA.123.033298
BRASIL. Lei n.º 13.709, de 14 de agosto de 2018. Lei Geral de Proteção de Dados Pessoais (LGPD). Brasília: Casa Civil, 2018. Disponível em: https://www.planalto.gov.br/ccivil_03/_ato2015-2018/2018/lei/l13709.htm#art65
CHEN, Z.; ZHANG, R.; XU, F.; GONG, X.; SHI, F.; ZHANG, M.; LOU, M. Novel prehospital prediction model of large vessel occlusion using artificial neural network. Frontiers in Aging Neuroscience, v. 10, p. 181, jun. 2018. Erratum in: Front Aging Neurosci., v. 10, p. 222, 17 jul. 2018 DOI: https://doi.org/10.3389/fnagi.2018.00222 DOI: https://doi.org/10.3389/fnagi.2018.00181
HAYASHI, Y.; SHIMADA, T.; HATTORI, N.; SHIMAZUI, T.; YOSHIDA, Y.; MIURA, R. E.; YAMAO, Y.; ABE, R.; KOBAYASHI, E.; IWADATE, Y.; NAKADA, T. A. A prehospital diagnostic algorithm for strokes using machine learning: a prospective observational study. Scientific Reports, v. 11, n. 1, p. 20519, out. 2021. DOI: https://doi.org/10.1038/s41598-021-99828-2
JIANG, F.; JIANG, Y.; ZHI, H.; DONG, Y.; LI, H.; MA, S.; WANG, Y.; DONG, Q.; SHEN, H.; WANG, Y. Artificial intelligence in healthcare: past, present and future. Stroke and Vascular Neurology, v. 2, p. e000101, 2017. Publicado online em 22 jun. 2017. DOI: https://doi.org/10.1136/svn-2017-000101
KUANG, Q.; ZHAO, L. A practical gpu based knn algorithm. In: HUANGSHAN, P. R. China. p. 151–155, Dec. 26–28 2009. AP-PROC-CS-09CN005. Supported by National Natural Science Foundation of China (No. 60873047) and Natural Science Foundation of Jiangsu Province (No. BK2008154).
LOBO, L. C. Inteligência artificial e medicina. Revista Brasileira de Educação Médica, v. 41, n. 2, p. 185–193, 2017. Texto em português. Disponível em: https://doi.org/10.1590/1981-52712015v41n2esp DOI: https://doi.org/10.1590/1981-52712015v41n2esp
MACHADO, A. L. A.; JUNIOR, L. G. de Q. S.; NUNES, M. A. XGBoost na Previsão da Geração de Energia Elétrica em Parques Eólicos. [S. l.: s. n.], 2021. p. 1–6. Documento em português. Extraído do PDF fornecido. DOI: https://doi.org/10.17648/cbqee-2021-130586
MIRANDA, F. J.; RIBEIRO, R. M. (Ed.). Manual de metodologia da pesquisa científica: diretrizes e métodos. Sobral, CE: Faculdade Luciano Feijão, 2024. Disponível em: https://fucianofeijao.com.br/ff/wp-content/uploads/2024/02/MANUAL-DE-METODOLOGIA-DA-PESQUISA_ADMINISTRACAO.pdf
MIRANDA, M. Acidente Vascular Cerebral. [S. l.: s. n.], 2025. Disponível em: https://avc.org.br/pacientes/acidente-vascular-cerebral/
SILVA, R.; NETO, D. R. S. Inteligência artificial e previsão de óbito por covid-19 no brasil: uma análise comparativa entre os algoritmos logistic regression, decision tree e random forest. Saúde em Debate, v. 46, n. Especial 8, p. 118–129, dec. 2022. DOI: https://doi.org/10.1590/0103-11042022e809
TARKANYI, G.; TENYI, A.; HOLLOS, R.; KALMAR, P. J.; SZAPARY, L. Optimization of large vessel occlusion detection in acute ischemic stroke using machine learning methods. Life (Basel), v. 12, n. 2, p. 230, fev. 2022. DOI: https://doi.org/10.3390/life12020230
UCHIDA, K.; KOUNO, J.; YOSHIMURA, S.; KINJO, N.; SAKAKIBARA, F.; ARAKI, H.; MORIMOTO, T. Development of machine learning models to predict probabilities and types of stroke at prehospital stage: the japan urgent stroke triage score using machine learning (just-ml). Translational Stroke Research, v. 13, n. 3, p. 370–381, jun. 2022. DOI: https://doi.org/10.1007/s12975-021-00937-x
