Evaluation of Foundation Models for Physiological Signals

• Grant number: 25/19417-6
• Support Opportunities: Regular Research Grants
• Start date: February 01, 2026
• End date: January 31, 2027
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Diego Furtado Silva
• Grantee: Diego Furtado Silva
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• City of the host institution: São Carlos
• Associated research grant: 22/03176-1 - Machine learning for time series obtained in mHealth applications, AP.PNGP.PI

Abstract

Foundation models have become central to advancing machine learning applications across multiple domains, including healthcare. However, despite extensive exploration in computer vision tasks within this field, their application to physiological signals remains incipient. With the exception of electrocardiograms (ECG), few efforts have been dedicated to developing and evaluating such models for other signals. Furthermore, analyses in the literature are often limited to specific tasks directly related to the data for which the models were trained. This project proposes a thorough technical evaluation of foundation models for physiological signals, considering criteria such as computational cost and performance across multiple tasks. The aim is to contribute to scientific progress at the intersection of artificial intelligence and healthcare, while also providing the fellow with high-level training in machine learning focused on interdisciplinary applications. (AU)