The healthcare system faces growing challenges in delivering timely, equitable, and precise care, contributing to delayed diagnoses, avoidable complications, and poorer long-term outcomes. Machine learning models are now able to leverage longitudinal imaging, clinical, genetic, and demographic data to model individual health trajectories, detect early disease, and characterise progression for diverse populations.

In this seminar, Liane will present recent advances in AI that enable personalised temporal frameworks for preventive health, as well as previous research demonstrating the feasibility, robustness, and clinical relevance of these approaches. These frameworks provide insight into multi-organ ageing, flag emerging unhealthy patterns, and highlight windows of opportunity for intervention. By forecasting individual health pathways, they can optimise screening programmes and guide targeted preventive strategies, encouraging healthier lifestyles and improving quality of life, while also informing policy and resource planning. Ultimately, these approaches aim to relieve pressure on healthcare services and support optimal functioning across organ systems.

Sign up on Eventbrite.

This event is part of the King’s Institute for Artificial Intelligence’s AI Frontiers series.

Meet the speaker

Dr Liane Canas is a King’s AI+ Fellow in the Department of Biomedical Engineering at the School of Biomedical Engineering and Imaging Sciences, King’s College London. She completed her MSc at the University of Lisbon in 2015, focusing on multi-centre studies for disease diagnosis. Her PhD research at University College London (2020) was focused on the automatic extraction of imaging biomarkers to characterise prion disease.

In her current research, she develops machine learning models to investigate infectious and neurodegenerative diseases by integrating both imaging and textual data. At King’s, she is involved in projects that merge biomedical imaging, digital health, and precision medicine, with a particular emphasis on using digital twins for personalised prognosis and treatment modelling. Her work aims to advance responsible, interpretable, and equitable AI solutions that can be effectively implemented in clinical practice.