dc.contributor.advisor | Peñaherrera Larenas, Milton Fabian | |
dc.contributor.author | Montiel Olvera, Fernando Stiven | |
dc.date.accessioned | 2025-04-23T03:40:33Z | |
dc.date.available | 2025-04-23T03:40:33Z | |
dc.date.issued | 2025 | |
dc.identifier.uri | http://dspace.utb.edu.ec/handle/49000/17825 | |
dc.description | Depression disorder is a silent but deadly condition, which millions of people suffer from, and its consequences can be devastating, especially because those who suffer from it rarely seek professional help, aggravating the symptoms over time. Furthermore, one of the biggest problems that this condition encompasses is the lack of early detection. The emergence of new technologies is emerging as a possible solution to this problem, specifically the use of machine learning applied in the detection of depression disorder can be the tool that helps overcome the lack of access to a diagnosis and allow many people to have timely help, so this research work aims to analyze studies carried out where this technology is applied and be able to compare the results with each other, managing to find out which of the machine learning algorithms is the most efficient and demonstrate that its use can achieve equal or more precise results than the methods. traditional ones used in the detection of the disorder. In this research, it was possible to obtain information from several algorithms in which machine learning models were applied for the detection of the disorder using different data sources for their training, with the sociodemographic data set being the most used by researchers for the detection of depression. | es_ES |
dc.description | Depression disorder is a silent but deadly condition, which millions of people suffer from, and its consequences can be devastating, especially because those who suffer from it rarely seek professional help, aggravating the symptoms over time. Furthermore, one of the biggest problems that this condition encompasses is the lack of early detection. The emergence of new technologies is emerging as a possible solution to this problem, specifically the use of machine learning applied in the detection of depression disorder can be the tool that helps overcome the lack of access to a diagnosis and allow many people to have timely help, so this research work aims to analyze studies carried out where this technology is applied and be able to compare the results with each other, managing to find out which of the machine learning algorithms is the most efficient and demonstrate that its use can achieve equal or more precise results than the methods. traditional ones used in the detection of the disorder. In this research, it was possible to obtain information from several algorithms in which machine learning models were applied for the detection of the disorder using different data sources for their training, with the sociodemographic data set being the most used by researchers for the detection of depression. | es_ES |
dc.description.abstract | El trastorno de la depresión es un padecimiento silencioso pero mortal, el cual sufren millones de personas, y que sus consecuencias pueden ser devastadoras, sobre todo por que aquellos que lo padecen pocas veces buscan ayuda profesional, agravando los síntomas con el pasar del tiempo. A demás, uno de sus mayores problemas que engloba este padecimiento es la falta de su detección temprana. El surgimiento de nuevas tecnologías se perfila como una posible solución a este problema, específicamente el uso del aprendizaje automático aplicado en la detección del trastorno de la depresión puede ser la herramienta que ayude a superar la falta de acceso a un diagnóstico y permitir que muchas personas logren tener ayuda oportuna, por lo que este trabajo de investigación tiene como objetivo analizar estudios realizados en donde se aplica esta tecnología y poder comparar los resultados entre sí, logrando averiguar cuál de los algoritmos de aprendizaje automático es el mas eficiente y demostrar que su uso puede lograr resultados igual o mas precisos que los métodos tradicionales utilizados en la detección del trastorno. En esta investigación se logró obtener información de varios algoritmos en los cuales fueron aplicados modelos de aprendizaje automático para la detección del trastorno utilizando diferentes fuentes de datos para su entrenamiento, siendo el conjunto de datos sociodemográficos el más utilizado por los investigadores para la detección de la depresión. | es_ES |
dc.format.extent | 62 p. | es_ES |
dc.language.iso | es | es_ES |
dc.publisher | Babahoyo: UTB-FAFI. 2025 | es_ES |
dc.rights | Attribution-NonCommercial-NoDerivs 3.0 United States | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/us/ | * |
dc.subject | Aprendizaje automático | es_ES |
dc.subject | Trastorno | es_ES |
dc.subject | Depresión | es_ES |
dc.subject | Algoritmo | es_ES |
dc.subject.other | Sistema de Información | es_ES |
dc.title | El aprendizaje automático y su uso en la detección del trastorno de la depresión. | es_ES |
dc.type | bachelorThesis | es_ES |