Thermodynamics-informed Graph Neural Networks for anatomically accurate digital human twins.
DOI:
https://doi.org/10.26754/jjii3a.202410586Abstract
Digital twins have emerged as a way to simulate human physiology, aiming to reduce the need for costly and ethically challenging clinical trials. However, their complexity currently limits the scope of what can be simulated. Hybrid neural networks present a promising and transparent alternative, guiding AI-based methodologies away from opaque, black-box models.
Downloads
Download data is not yet available.
Downloads
Published
2024-07-17
How to Cite
Tesan, L., González, D., Chinesta, F., & Cueto, E. (2024). Thermodynamics-informed Graph Neural Networks for anatomically accurate digital human twins. Jornada De Jóvenes Investigadores Del I3A, 12. https://doi.org/10.26754/jjii3a.202410586
Issue
Section
Artículos (Ingeniería Biomédica)
License
Copyright (c) 2024 Lucas Tesan, David González, Francisco Chinesta, Elías Cueto
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.