A review of system implementations for diabetes trend identification

• Autores: Benites Loja, Rocio Isabel, Coral Ygnacio, Marco Antonio
• Formato: artículo
• Fecha de Publicación: 2022
• Institución: Universidad de Lima
• Repositorio: Revistas - Universidad de Lima
• Lenguaje: español
• OAI Identifier: oai:revistas.ulima.edu.pe:article/5957
• Enlace del recurso: https://revistas.ulima.edu.pe/index.php/Interfases/article/view/5957
• Nivel de acceso: acceso abierto
• Materia: diabetes mellitus; trend identification; preventive software; construction methods; logistic regression; artificial neural networks; identificación de tendencias; software preventivo; métodos de construcción; regresión logística; redes neuronales artificiales

Diabetes mellitus is a chronic disease that appears when the pancreas does not secrete enough insulin or the body does not properly use the insulin it produces. Insulin is a hormone that regulates glucose concentration in the blood: one of the most common effects of uncontrolled diabetes is hyperglycemia, which seriously damages many organs and body systems over time. In this sense, the development of predictive software, the diagnosis, and subsequent treatment of diabetes, especially of type 1 and 2, which are the most frequent, deserve attention. This paper presents a systematic review of the literature to determine the methods and problems in constructing diabetes-oriented trend identification systems. The results show 16 construction methods used in these systems, the most efficient being logistic regression and artificial neural networks.