Resumen

APARICIO-MONTENEGRO, Pablo Roberto et al. Predictive Models in Public Health: The Approach to Diabetes using Artificial Intelligence. Cuest. Pol. [online]. 2025, vol.43, n.82, pp.91-106.  Epub 06-Jun-2025. ISSN 0798-1406.  https://doi.org/10.5281/zenodo.15565315.

This paper aimed to develop an application based on artificial intelligence, whose purpose is the early detection and care of type 2 diabetes mellitus, a disease that affects 9.3% of adults globally. Methodologically, a non-experimental quantitative approach was used, making use of a dataset of 800 patients, from which 160 were selected to train a predictive model, implementing machine learning algorithms, such as K-Nearest Neighbors (KNN) and Random Forest (RF), which facilitated the analysis of clinical and biometric data. Among the main results, the KNN model showed an accuracy of 95.5%, while RF showed 92.16% accuracy. Likewise, logistic regression achieved an accuracy of 79.33%. These models identified glucose as the most significant predictor, with a correlation of 0.49 with respect to diabetes. It was concluded that the use of Artificial Intelligence models constitutes an effective, accessible, non-intrusive and economical way to facilitate early detection and care of diabetes, improving the quality of personalized care, demonstrating the public health benefits that can be achieved.

Palabras clave : diabetes; artificial intelligence; public health; machine learning; deep learning.

        · resumen en Español     · texto en Español     · Español ( pdf )