Tecnologia aplicada a saúde: uso de Inteligência Artificial na predição de Diabetes para adultos
This study aims to evaluate the use of machine learning (ML) techniques in predicting diabetes mellitus, using a clinical dataset with variables such as age, blood pressure, and glucose levels. The performance of Random Forest, Logistic Regression, K Nearest Neighbors (KNN), and Decision Tree m...
| Autor principal: | Santos, Dionara Pereira dos |
|---|---|
| Grau: | Trabalho de Conclusão de Curso |
| Idioma: | por |
| Publicado em: |
Brasil
2025
|
| Assuntos: | |
| Acesso em linha: |
http://riu.ufam.edu.br/handle/prefix/8426 |
| Resumo: |
|---|
|
This study aims to evaluate the use of machine learning (ML) techniques in predicting
diabetes mellitus, using a clinical dataset with variables such as age, blood pressure,
and glucose levels. The performance of Random Forest, Logistic Regression, K
Nearest Neighbors (KNN), and Decision Tree models was compared to identify the
most effective for disease prediction. The analyses were performed using Python and
R, which offer powerful tools for data modeling.The results showed that Random
Forest had the best performance, followed by Logistic Regression and KNN. When
compared to previous studies, the findings reinforce the effectiveness of machine
learning in healthcare. The study also discusses the limitations of the models and
suggests using biomarkers and temporal data to improve predictions. |