Leveraging Machine Learning for Predictive Modelling in Alzheimer’s Disease - Integrating Trained Immunity, Infectious Burden, and Serum Cytokine Data

Aug 4, 2026

Upload by Quinn

Leveraging machine learning for predictive modelling in Alzheimer’s disease focuses on integrating three biomedical data streams: trained immunity signals, infectious burden indicators, and serum cytokine measurements. The dissertation frames these inputs to support stronger risk prediction and more interpretable modeling of disease-related processes. It is developed as a master’s thesis in Computational Biology and Bioinformatics at NOVA Information Management School, University NOVA de Lisboa, under adviser Prof. Dr. Leonardo Vanneschi and co-adviser Liah Rosenfeld.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages190

Reading Time7 h 59 min

AccessFree to download

Acknowledgements

Supervisors and academic guidance

Collaborators and supporting institutions

Personal acknowledgements

ANA MARTA RODRIGUES PEREIRA DA COSTA BSc in Cellular and Molecular Biology Leveraging Machine Learning for Predictive Modelling in Alzheimer’s Disease: Integrating Trained Immunity, Infectious Burden, and Serum Cytokine Data Sep, 2024 NOVA Information Management School Instituto Superior de Estatística e Gestão de Informação Universidade NOVA de Lisboa LEVERAGING MACHINE LEARNING FOR PREDICTIVE MODELLING IN ALZHEIMER’S DISEASE by Ana Marta Rodrigues Pereira da Costa Dissertation presented as partial requirement for obtaining the Master’s degree in Computational Biology and Bioinformatics Adviser: Prof. Dr. Leonardo Vanneschi Co-adviser: Liah Rosenfeld September, 2024 Leveraging Machine Learning for Predictive Modelling in Alzheimer’s Disease Integrating Trained Immunity, Infectious Burden, and Serum Cytokine Data Copyright © Ana Marta Rodrigues Pereira da Costa, NOVA Information Management School, NOVA University Lisbon. The NOVA Information Management School and the NOVA University Lisbon have the right, perpetual and without geographical boundaries, to file and publish this dissertation through printed copies reproduced on paper or on digital form, or by anyother means known or that may be invented, and to disseminate through scientific repositories and admit its copying and distribution for non-commercial, educational or research purposes, as long as credit is given to the author and editor. This document was created with the (pdf/Xe/Lua)LATEX processor and the NOVAthesis template (v7.1.14) [1] . To grandma. Acknowledgements During the course of this thesis, I have received a great deal of support and assistance, whithout which this work wouldn’t have been possible, and for this I would like to express my deepest gratitude. Firstly, I’m extremely grateful to my esteemed professor and supervisor, Leonardo Vanneschi, for his mentorship, constructive feedback and reassuring words. He has been an inspiration in my academic endeavours, and it was through his guidance and encouragement that I was able to delve into the world of data science. I would also like to express my sincere appreciation to my co-supervisor, Liah Rosenfeld, who provided me with her expertise and kind advisement, along with patience and understanding througout this learning process. This work would also not have been possible without the continuous support, advice and proficiency of Dr. Paola Bossú and Iliana Piccolino at Santa Lucia Foundation, as well as Professor Francesco Fontanella and Professor Claudio De Stefano. In addition, I would like to extend my heartfelt gratitude for everyone at the PhD hall, especially Davide Farinati, Berfin Sakallioglu, Emanuele Nardone, Giovanni Pinna and Lena Dewaele. For all the scientific support, friendly incentives and sharing of knowledge, but mostly for the sunny lunch breaks and cheerful discussions in english, portuguese, italian or dutch. I bask in the friendship you have surrounded me with, this year. Lastly, my thanks to all the wonderful people in my life. My dear family, especially my mom who taught me all about the difference women can make in the academic field and whose journey I always carry with me. To my sweet and bright best friend, Beatriz Xavier, to whom I pass the torch. And to my boyfriend, Rafael Borralho, as the saying goes "to be loved is to be known", what a privilege it is to be seen for who we truly are. „“We all woke up this morning and we had with it the amazing return of our conscious mind. We recovered minds with a complete sense of self and a complete sense of our own existence—yet we hardly ever pause to consider this wonder.” —António Damásio, Self Comes to Mind: Constructing the Conscious Brain (Professor of Neuroscience)

FAQs

What is the main goal of the thesis?

To leverage machine learning for predictive modelling in Alzheimer’s disease by integrating multiple biomedical data sources.

Which data types are integrated in the proposed modelling framework?

Trained immunity information, infectious burden indicators, and serum cytokine data.

Who supervised the dissertation?

The adviser is Prof. Dr. Leonardo Vanneschi, with Liah Rosenfeld as co-adviser.

Aug 4, 2026

Upload by Quinn