Please use this identifier to cite or link to this item:
Title: Desarrollo de una aplicación web para la predicción de la salud lumbar, aplicando técnicas de aprendizaje automático sobre las características biomecánicas de pacientes ortopédicos
Author: Alarcón Vallejo, Damaris
Tutor: Rebrij, Romina  
Others: Perez-Navarro, Antoni  
Abstract: The vertebral column is the most important structure of the one of the fundamental parts of the locomotor system. The lower part of the vertebral column is called the lumbar column and is made up of larger vertebrae, since most of the body's weight is deposited in this area. Pain in the lumbar region is one of the main causes of medical consultation and occurs frequently in 80-90% of the adult population. Herniated discs and spondylolisthesis are degenerative pathologies that generally affect the lumbar column. The orthopedic condition of a person can be determined from their biomechanical characteristics. Machine learning in the field of health allows converting clinical data, from measures to images, into important conclusions for decision making about the diagnosis of diseases. Using a database of biomechanical characteristics of the spine, several machine learning algorithms were evaluated, the best predictive model was obtained with the support vector machine (SVM) algorithm, with an accuracy of 85%. Using this model, a web application with Shiny was developed, in which the user enters six biomechanical characteristics of the vertebral column, and the application returns the diagnosis predicted by the selected model. This application was developed to make it easier for doctors to diagnose these diseases, so that patients can immediately start with the appropriate treatment.
Keywords: web applications
herniated disc
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 24-Dec-2021
Publication license:  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
dalarconvaTFM0122memoria.pdfMemoria del TFM1,16 MBAdobe PDFThumbnail