Speaker

Speaker Info

Name
Martina Montenegro
Organization
KU Leuven
Country
Belgium
Biography
Martina embarked on her PhD at KU Leuven in 2024, where she joined both the M3-BIORES research group led by Prof. Jean-Marie Aerts and the e-Media research group led by Prof. Bart Vanrumste. Her doctoral research centers on predictive modeling for remote monitoring of exacerbations in chronic obstructive pulmonary disease (COPD) patients, leveraging data from wearable and home sensors. She holds a BSc and MSc in Biomedical Engineering from Politecnico di Milano, where she specialized in biomedical electronics and medical AI, with a focus on wearable health technologies.

Photo

Photo

Presentation Info

Title
Rethinking COPD Exacerbation Prediction: What Data Can (and Can’t Yet) Tell Us
Summary
In the context of the Interreg project “RM@H”, KU Leuven is developing a predictive framework for exacerbations of Chronic Obstructive Pulmonary Disease (COPD), a major global health burden and one of the leading causes of death worldwide. Acute exacerbations are key drivers of disease progression, hospitalizations, and healthcare costs. Early prediction of these events can significantly improve patient outcomes and reduce economic impact. This talk presents our current work on building a predictive model for 30-day hospital readmission, used as a proxy for exacerbations, based on hospital data. Using the MIMIC-IV dataset, we explore how different types of clinical information, including structured data and discharge notes, can be combined through machine learning approaches to identify patients at higher risk. We will highlight the most relevant features associated with readmission risk and discuss the challenges of modeling COPD. Finally, we will outline the next steps of the project, where ongoing data collection from wearable devices and home monitoring systems will be integrated to move toward continuous, real-world prediction of patient deterioration.
Keynote
Presentation
GFHEU Year
2026

Info

Info