Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/150903
Title: AlzheimInk: A Mobile Web Application for Detecting Alzheimer’s Disease through Handwriting Analysis
Author: Soriano Reos, Jordi
Director: Rebrij, Romina
Tutor: Ventura, Carles
Abstract: Early diagnosis of Alzheimer’s disease, one of the major neurodegenerative diseases of this century, is crucial for delaying the onset of symptoms, despite the lack of a definitive cure. However, diagnosis remains a challenge due to the need for various tests (cognitive, biomarker and protein analysis, neuroimaging, etc.) and the reality that it is frequently diagnosed by excluding other potential diseases. In this context, this study aims to develop an accessible alternative for most people: a mobile web application that adapts a diagnostic test based on handwriting, a process that involves cognitive, kinesthetic, and perceptual-motor skills. This test, which was originally performed with a graphic tablet in a prior study, can now be conducted over the internet using only a stylus. To achieve this goal, several supervised machine learning classifiers were trained using the original study’s database. The best model, achieving a theoretical accuracy of 88%, was implemented in the web application. This application, accessible online, performs a series of 19 tasks involving drawing or handwriting and can make diagnostic predictions based on the collected data. In addition, it offers the ability to track users and collect new data to generate an exclusive database for the application. In conclusion, the tool developed in this study, or future versions of it, has demonstrated the potential to be used as a support in the diagnosis of Alzheimer’s disease. It offers an easily accessible, quick, and non-invasive test, making it a valuable addition to existing diagnostic tools.
Keywords: alzheimer’s disease, early diagnosis, handwriting, machine learning, neurodegenerative diseases
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 18-Jun-2024
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 
jordisorianoreosFMDP0624.pdfReport of the FMDP5,41 MBAdobe PDFThumbnail
View/Open
Share:
Export:
View statistics

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