Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/138549
Title: Diagnóstico de enfermedad hepática mediante técnicas de aprendizaje automático y su implementación en una aplicación web
Author: González Berruga, Santiago
Tutor: Rebrij, Romina  
Others: Perez-Navarro, Antoni  
Abstract: Liver diseases have increased considerably in recent years due to changes in lifestyle habits and are one of the leading causes of mortality worldwide. However, the diagnosis of liver diseases remains complex, expensive and most of the times late. This work seeks an automatic classification model that allows for an early and simple diagnosis of liver patients. To this end, models are generated using the ILPD liver patient dataset and the machine learning algorithms K-nearest neighbour (KNN), Naive Bayes (NB), Decision tree (DT), Random Forest (RF), Support Vector Machines (SVM), Artificial Neural Network (ANN) and Logistic Regression (LR). To determine the best model, the metrics accuracy, false negatives, false positives, error rate, kappa statistic, sensitivity, specificity, precision, recall and F1-score were used. Based on this, the ANN and RF models showed better results than the other models for the prediction of liver patients, with an accuracy of 75.1% and 74.6% and precision of 76.8% and 75.3%. Therefore, this work has demonstrated that it is possible to diagnose liver patients using automatic classification models trained with simple clinical variables, without having to use invasive methods on the patients. Furthermore, the ANN model has been implemented in a web application, generating a unique tool with great potential to support healthcare professionals during the diagnosis of liver diseases, allowing an early diagnosis without the need of intrusive techniques.
Keywords: machine learning
artificial neural networks
liver disease
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 24-Dec-2021
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
santiagogonzalezberrugaTFM1221memoria.pdfMemoria del TFM1,92 MBAdobe PDFThumbnail
View/Open