Franco Rugolon PhD Student

I am currently involved in teaching the laboratory sessions of the Foundations of Data Science course during the Fall semester. In the Spring semester, I am available for Master’s thesis supervision.

My proposed thesis topics focus on the application of machine learning to dyadic interactions in psychotherapy, cancer development, and data mining from electronic health records (EHRs). However, I am also open to supervising projects in other areas, provided the student demonstrates a strong interest and commitment to the chosen topic.

Some of the previous thesis projects that I supervised or co-supervised in the past years:

• Predicting the Onset of Metastasis by Multimodal Machine Learning in Lung cancer and Melanoma patients
• Evaluating Explainability Techniques for Machine Learning in Healthcare

• Predicting Chronic Kidney Disease in Jalisco - An XAI-Enhanced Multimodal Approach with Geospatial and Demographic Data

• Predicting Symptom Change in Functional Somatic Syndromes through Multimodal Machine Learning and Explainability

• Integrating Genetics and Epigenetics for Predicting the Mutational Landscape in Lung Adenocarcinoma

My research focuses on the development and application of machine learning methods in healthcare and psychotherapy. I am particularly interested in dyadic interactions in psychotherapy, where I explore how machine learning can capture and model the complex dynamics between patients and therapists. In parallel, I apply machine learning to Electronic Health Records (EHRs) to predict disease progression, aiming to support early intervention and improve clinical outcomes.

A central theme of my work is the design of novel explainability methods that make machine learning models more transparent and trustworthy for practitioners. Across these domains, I focus on multimodal data and the modelling of interactions between modalities, as I believe that integrating diverse sources of information provides deeper insights and more robust predictions.