Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/89560
Título: | Predictive analytics to support diabetic patient detection |
Autor(es): | Vaz, Maria João Lopes, João Peixoto, Hugo Santos, Manuel |
Palavras-chave: | Artificial Intelligence Diabetes Predictive Analytics |
Data: | 2022 |
Editora: | Elsevier 1 |
Revista: | Procedia Computer Science |
Citação: | Vaz, M. J., Lopes, J., Peixoto, H., & Santos, M. F. (2022). Predictive Analytics to support diabetic patient detection. Procedia Computer Science. Elsevier BV. http://doi.org/10.1016/j.procs.2022.03.092 |
Resumo(s): | The strong growth in the number of diabetics in recent years has become a major health concern. The dependence on sugar consumption has caused a rapid growth in the level of diagnoses and in the number of deaths associated. In this context, the project developed allowed a study on how Diabetes can be detected in a timely manner, through the existence of pre-indicators of the disease, defining factors that may determine its onset. For this study, data are collected from Hospital de Santa Luzia (ULSAM), considering aspects such as patient profile, prescribed drugs and previous diagnoses. The results prove that machine learning models using profile data with medical drugs produced the best results, optimizing the predictive ability of Diabetes. |
Tipo: | Artigo em ata de conferência |
URI: | https://hdl.handle.net/1822/89560 |
DOI: | 10.1016/j.procs.2022.03.092 |
ISSN: | 1877-0509 |
Versão da editora: | https://www.sciencedirect.com/science/article/pii/S1877050922005051 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
1-s2.0-S1877050922005051-main.pdf | 513,71 kB | Adobe PDF | Ver/Abrir |
Este trabalho está licenciado sob uma Licença Creative Commons