Sean Benson
[intermediate] Digital Twins and Generative AI for Personalised Medicine
Summary
This intermediate course explores the convergence of digital twin technology and generative AI in revolutionizing personalized medicine. Students will learn how digital twins, i.e. virtual representations of patients and cohorts, can create powerful predictions for individualized simulated healthcare outcomes. The course introduces students to the large landscape of often interdisciplinary digital twin models, with a focus on cardiology applications. Students will learn to work with synthetic patient data to develop digital twins and explore how generative AI can be used to simulate treatment responses and predict patient outcomes.
Syllabus
Introduction
- Health data modalities
- Digital twins as a subset of AI
Simulations of organs and systems
- Finite element models
- Electrophysiological and electromechanical models
ML digital twins
- GANs
- Transformers
- Physics informed neural networks
Multi-modal digital twins
References
Thangaraj, P. et al (2024). Cardiovascular care with digital twin technology in the era of generative artificial intelligence, European Heart Journal, Volume 45, Issue 45, 1 December 2024, 4808–4821. https://doi.org/10.1093/eurheartj/ehae619
Fedele, M. et al (2023). A comprehensive and biophysically detailed computational model of the whole human heart electromechanics. Computer Methods in Applied Mechanics and Engineering, 410, 115983. https://doi.org/10.1016/j.cma.2023.115983
Sachdeva, R. et al (2024). Novel Techniques in Imaging Congenital Heart Disease. Journal of the American College of Cardiology, 83(1), 63–81. https://doi.org/10.1016/j.jacc.2023.10.025
Pre-requisites
Linear algebra, probability, statistics. Experience with medical data formats is desirable.
Short bio
Sean Benson is an Assistant Professor in the Cardiology department of Amsterdam UMC, specialising in digital twin models and generative AI. After studying Mathematics and Physics, Sean completed a PhD on the LHCb experiment at CERN, focusing on AI models to enhance statistical analyses. After Marie-Curie and CERN fellowships, where he developed real-time analysis models, Sean became a Lead Data Scientist at KPMG, working on explainable AI models. In 2020, he joined the Netherlands Cancer Institute, leading a team developing deep learning models using multi-modal medical imaging to predict treatment outcomes and detect regrowth, before moving to the Amsterdam UMC in 2023.
