Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/150935
Title: Modelo predictivo en el desarrollo de enfermedades cardiovasculares a partir de factores de riesgo
Author: Valderrama Cardenas, Alejandro
Director: Julbe López, Francesc
Tutor: Solé Ribalta, Albert
Abstract: Cardiovascular diseases are the leading cause of death worldwide. Given their importance in public health, it is necessary to understand the risk factors that contribute to the development of these diseases and how to prevent and treat them effectively. This work aimed to develop a predictive model for cardiovascular diseases using machine learning techniques and a dataset of risk factors collected by the Centers for Disease Control and Prevention (CDC) in the United States. Furthermore, the goal was to identify the most significant risk factors associated with these diseases. Various sampling techniques were applied to address class imbalance, and multiple machine learning algorithms were trained. The Light GBoost model with SMOTEENN, trained on a dataset with 29 variables and 353,968 records, demonstrated the best performance, with a recall of 0.8450 and an AUC-ROC of 0.8139. Key risk factors identified included advanced age, male gender, low socioeconomic status (encompassing income and educational attainment), and insufficient sleep duration. The findings underscore the importance of considering socioeconomic and lifestyle factors, in addition to traditional factors, in the assessment of cardiovascular risk. Although limitations such as the self-reported nature of the data and the absence of some clinical variables are acknowledged, this work contributes to the development of more accurate prediction tools and emphasizes the need to address social determinants in cardiovascular disease prevention policies.
Keywords: enfermedades cardiovasculares
factores de riesgo
aprendizaje automático
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 11-Jun-2024
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Bachelor thesis, research projects, etc.

Files in This Item:
File Description SizeFormat 
avalderramacarTFM0624.pdf2,15 MBAdobe PDFThumbnail
View/Open
Share:
Export:
View statistics

Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.