Sistema de clasificación basado en redes neuronales artificiales para el diagnóstico precoz del dengue

• Autores: Shuña Zárate, Renzo Junior, Flores Rodríguez, Willy Javier
• Formato: tesis de grado
• Fecha de Publicación: 2025
• Institución: Universidad Nacional De La Amazonía Peruana
• Repositorio: UNAPIquitos-Institucional
• Lenguaje: español
• OAI Identifier: oai:repositorio.unapiquitos.edu.pe:20.500.12737/11481
• Enlace del recurso: https://hdl.handle.net/20.500.12737/11481
• Nivel de acceso: acceso abierto
• Materia: X; https://purl.org/pe-repo/ocde/ford#2.02.04

The objective of this research is to develop and validate a classification system based on artificial neural networks (ANN) for the early diagnosis of dengue, evaluating its performance using key indicators such as accuracy, sensitivity and specificity. The methodological approach is mixed, with a non-experimental predictive design, using clinical data from 10,000 patients from Bucaramanga and validating the system with an external sample of 30 patients from the Regional Hospital of Loreto. The system was implemented with advanced machine learning techniques, adjusting hyperparameters and evaluating its effectiveness through internal and external validations. The results show that the developed model achieved an accuracy of 98.2% in internal validation and 97.5% in external validation, with consistent levels of sensitivity (95.9% 96.8%) and specificity (97.5%-98.1%). Furthermore, the system's ability to classify dengue cases was assessed as "Excellent" according to the predefined quality ranges, highlighting its suitability for clinical settings. The study concludes that this classifier system is a reliable, efficient and applicable tool in real scenarios, improving the early detection of dengue and optimizing the allocation of medical resources. Its generalization capacity, validated with external data, highlights its robustness and potential impact on public health. Finally, this work lays the foundation for the implementation of similar models in the diagnosis of other infectious diseases.