Enfermedades mentales y su relación con el microbioma intestinal
The relationship between the gut microbiome and some of the most common mental illnesses, it is a reality. It is a certainty that it cannot be verified which set of operational taxonomic unit are responsible for these mental disorders. Today it is used different treatments, depending on the disorder...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Fecha de publicación: | 2020 |
| País: | España |
| Institución: | Universitat Oberta de Catalunya (UOC) |
| Repositorio: | O2, repositorio institucional de la UOC |
| OAI Identifier: | oai:openaccess.uoc.edu:10609/144026 |
| Acceso en línea: | https://hdl.handle.net/10609/144026 |
| Access Level: | acceso abierto |
| Palabra clave: | Disbiosis, microbioma, microbiota, intestino-cerebro, mental, salud, enfermedad, transtorno, comportamiento, predicción, aprendizaje automático. disbiosis microbioma salud mental salut mental dysbiosis microbiome mental health Mental health -- TFM Salut mental -- TFM Salud mental -- TFM |
| Sumario: | The relationship between the gut microbiome and some of the most common mental illnesses, it is a reality. It is a certainty that it cannot be verified which set of operational taxonomic unit are responsible for these mental disorders. Today it is used different treatments, depending on the disorder and its severity. The most important in these cases is to be able to anticipate this degenerative situation and to be able to predict any of these diseases. This work focuses on this very thing, on predicting mental illnesses that can be developed by any person, mainly based on the intestinal microbiome and in certain behavior habits. Each individual has their own microbiota, formed by a certain type of bacteria, some with more presence than others, what is known as intestinal enterotype. From the analysis of the data provided, a software application has been developed of prediction to detect mental illnesses. This tool is the practical part of a study based on automatic training to fit a predictive model. The application allows the user to make adjustments before training, such as choosing the classification algorithms, decide the percentage of data balancing, or even insert the taxonomy of a group of patients to be diagnosed with a possible mental disorder. This document shows the methods and techniques used and the characteristics of the necessary tools. Finally, the results of the experiment are presented, that demonstrate the effectiveness of the analysis in its entirety. |
|---|