2026/02/27 11h – Beyond the Black Box: Interpretable AI and Foundation Models in Modern Healthcare – Sonia Laguna

Sonia Laguna

ETH AI Center – ETH Zürich

Fecha:27-02-2026

Hora: 11.00 – 12.00  

Lugar: Aula A.06 del edificio Ada Byron

As machine learning transitions from research labs to the clinical bedside, the «Black Box» nature of deep learning presents a significant barrier to trust and safety. This session explores the intersection of high-performance predictive modeling and clinical interpretability. We will cover how interpretability techniques enable translational applications to align model reasoning with medical expertise. Furthermore, we will discuss the modern paradigm shift from task-specific models to Foundation Models, exploring how representation learning across diverse data modalities, i.e., imaging, genomics, and electronic health records, is setting the stage for the next generation of predictive models, especially relevant in healthcare.

Abstract

The world is becoming unprecedentedly connected thanks to emerging media and cloud-based technologies. The holy grail of metaverse requires recreating a remotely shared world as a digital twin of the physical planet. In this world, the human is probably the most complex mechanical, physical, and biological system. Unlike computers, it is remarkably challenging to model and engineer how humans perceive and react in a virtual environment. By leveraging computational advancements such as machine learning and biometric sensors, this talk will share some recent research on altering and optimizing the human visual and behavioral perception toward creating the ultimate metaverse.