Título: Análise de Desfechos de COVID-19 no RJ através de Técnicas de Aprendizado de Máquina
Autores: Jorge Zavaleta, Robson Eduardo da Silva, Fabiano Saldanha G. Oliveria, Luciane de Souza Velasque, Karla Figueiredo
Resumo: Given the rapid spread of COVID-19, having tools to screen patients and reduce the risk of death is crucial. This study focuses on the outcomes (cures and deaths) of confirmed COVID-19 cases in Rio de Janeiro State for both vaccinated and unvaccinated patients. Machine Learning (ML) algorithms were used to classify outcomes based on symptom, comorbidity, and age data obtained from the State Health Secretariat of Rio de Janeiro. After cleaning the dataset and selecting relevant attributes, the final model achieved an accuracy of 87,3% and a precision of 86,6% in predicting outcomes for unvaccinated patients. Similarly, the final model for vaccinated patients achieved an accuracy of 86,3% and a precision of 83,1% in predicting outcomes. In addition, the attributes of patients that stand out with and without the vaccine were evaluated. Overall, these results demonstrate the potential benefits of using machine learning methods to improve patient screening and reduce the risk of COVID-19-related deaths.
Palavras-chave: outcomes, vaccine, COVID-19, machine learning methods, health surveillance
Páginas: 8
Código DOI: 10.21528/CBIC2023-072
Artigo em pdf: CBIC_2023_paper072.pdf
Arquivo BibTeX: CBIC_2023_072.bib