Prestigious Women Researchers Lecture Series | María A. Zuluaga: 'Advancing healthcare research and clinical practice through trustworthy AI'

Trustworthiness is crucial in the development and deployment of AI systems. In this talk, María A. Zuluaga will explore various pathways to establish trust in AI systems, focusing on four key aspects: robustness, uncertainty estimation, quality control, and explainability. Robustness helps build trust by developing techniques to manage variability in a model’s inputs. Meanwhile, uncertainty estimation, quality control, and explainability enhance trust by analyzing a model's behavior based on its outputs. After introducing these four aspects, she will present some of her team’s work on creating trustworthy AI methods and systems specifically for healthcare research and clinical practice.

The talk is aimed at a general audience with basic computer science and artificial intelligence knowledge. 

About the speaker

María A. Zuluaga is a senior lecturer at EURECOM with an affiliate position within the School of Biomedical Engineering & Imaging Sciences at King’s College London. She holds a PhD in Signal and Image Processing from Université de Lyon, France. Within her research team, she focuses on developing novel machine learning methods from multi-modal data that can be safely used to advance healthcare research and improve clinical practice. From an application standpoint, her work aims to answer questions arising from neurovascular and cardiovascular imaging, as well as cancer research. She was awarded an ERC Consolidator Grant in 2024.