Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Journal . 2025
License: CC BY
Data sources: ZENODO
ZENODO
Journal . 2025
License: CC BY
Data sources: Datacite
ZENODO
Journal . 2025
License: CC BY
Data sources: Datacite
versions View all 3 versions
addClaim

Modelos predictivos en la Salud Pública: El abordaje de la diabetes mediante la Inteligencia Artificial

Authors: Aparicio-Montenegro, Pablo Roberto; Narro Andrade, Manuel Guillermo; León-Velarde, César Gerardo; Morales Romero, Guillermo Pastor; Fernández-Flores, Silvia Milagros;

Modelos predictivos en la Salud Pública: El abordaje de la diabetes mediante la Inteligencia Artificial

Abstract

Resumen: El artículo tuvo como objetivo desarrollar una aplicación basada en la inteligencia artificial, cuya finalidad es la detección y atención temprana de la diabetes mellitus tipo 2, una enfermedad que afecta al 9.3% de los adultos a nivel global. Metodológicamente, se empleó un enfoque cuantitativo no experimental, haciendo uso de un conjunto de datos de 800 pacientes, de los que se seleccionaron 160 para entrenar un modelo predictivo, implementando algoritmos de machine learning, tales como K-Nearest Neighbors (KNN) y Random Forest (RF), que facilitaron el análisis de datos clínicos y biométricos. Entre los principales resultados se destaca que el modelo KNN evidenció una precisión del 95,5%, mientras que RF demostró un 92.16% de precisión. Asimismo, la regresión logística alcanzó una precisión del 79,33%. Estos modelos identificaron la glucosa como el factor predictivo más significativo, con una correlación de 0.49 respecto a la diabetes. Se concluyó que el uso de modelos de Inteligencia Artificial constituye una forma eficaz, accesible, no intrusiva y económica para facilitar la detección y atención temprana de la diabetes, mejorando la calidad en la atención personalizada, demostrando los beneficios que se pueden alcanzar en materia de salud pública.

Abstract: 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.

Keywords

machine learning, diabetes, inteligencia artificial, salud pública, public health, deep learning, artificial intelligence

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green