MS033 - Advanced and hybrid computational modeling (FEM, AI, MR) for evidence-based diagnosis in Healthcare
Keywords: Artificial Intelligence in Healthcare, Computaional Modelling, digital twins, finite element method, hybrid physics/AI approaches
The objectives of the mini-symposium will address the state-of-art biomechanical modelling and simulation studies using finite element method (FEM) and their combination with artificial intelligence (AI) and mixed reality (MR) for evidence-based diagnosis, clinical decision in Healthcare. Moreover, digital twins refer to their virtual representations combining real time data and advanced modelling techniques.
Biomechanical simulations are widely used to describe the mechanical behavior of the biological systems at different scale (system, organ, tissue, molecular). These simulations are dedicated to get a better understanding of their functionality in order to develop innovative technologies to compensate the deficiencies, to plan surgery or else. Nowadays, subject or patient specific, personalized models demonstrate their evolution during the last two decades thanks to data derived from medical imaging techniques or sensors allowing to assess geometrical, mechanical, physiological characteristics of the subject.
Besides, novel AI algorithms are powerful to provide new input in the modelling process or to contribute to effective scenarios for clinical aided decision (surgery, rehabilitation …). In particular, MR technologies combine virtual data and augmented reality creating an environment mixing the real physical world and the virtual world.
The combination of these methods in a hybrid modeling approach represents a significant improvement in the evidence-based diagnosis, in surgery or rehabilitation planning for the benefit of the patient.
Biomechanical simulations are widely used to describe the mechanical behavior of the biological systems at different scale (system, organ, tissue, molecular). These simulations are dedicated to get a better understanding of their functionality in order to develop innovative technologies to compensate the deficiencies, to plan surgery or else. Nowadays, subject or patient specific, personalized models demonstrate their evolution during the last two decades thanks to data derived from medical imaging techniques or sensors allowing to assess geometrical, mechanical, physiological characteristics of the subject.
Besides, novel AI algorithms are powerful to provide new input in the modelling process or to contribute to effective scenarios for clinical aided decision (surgery, rehabilitation …). In particular, MR technologies combine virtual data and augmented reality creating an environment mixing the real physical world and the virtual world.
The combination of these methods in a hybrid modeling approach represents a significant improvement in the evidence-based diagnosis, in surgery or rehabilitation planning for the benefit of the patient.
