Artificial Intelligence-Guided Inverse Design of Deployable Thermo-Metamaterial Implants

Abstract

Current limitations in implant design often lead to trade-offs between minimally invasive surgery and achieving the desired post-implantation functionality. Here, we present an artificial intelligence inverse design paradigm for creating deployable implants as planar and tubular thermal mechanical metamaterials (thermo-metamaterials). These thermo-metamaterial implants exhibit tunable mechanical properties and volume change in response to temperature changes, enabling minimally invasive and personalized surgery. We begin by generating a large database of corrugated thermo-metamaterials with various cell structures and bending stiffnesses. An artificial intelligence inverse design model is subsequently developed by integrating an evolutionary algorithm with a neural network. This model allows for the automatic determination of the optimal microstructure for thermo-metamaterials with desired performance,i.e., target bending stiffness. We validate this approach by designing patient-specific spinal fusion implants and tracheal stents. The results demonstrate that the deployable thermo-metamaterial implants can achieve over a 200% increase in volume or cross-sectional area in their fully deployed states. Finally, we propose a broader vision for a clinically informed artificial intelligence design process that prioritizes biocompatibility, feasibility, and precision simultaneously for the development of high-performing and clinically viable implants. The feasibility of this proposed vision is demonstrated using a fuzzy analytic hierarchy process to customize thermo-metamaterial implants based on clinically relevant factors.