AI-driven optimization of spinal implant design using parametric modelling.

This study aimed to enhance vertebral implant design by using a parametric spine model and advanced simulation techniques to evaluate biomechanical behaviours under dynamic physiological conditions using Finite Element Analysis (FEA) in ANSYS Workbench. The primary objective was to refine implant designs to improve surgical outcomes and patient safety. We incorporated the anisotropic material properties of Magnesium-Rare Earth-Zirconium (Mg-RE-Zr) alloys, focusing on their Young's modulus (40-50 GPa), Poisson's ratio (0.35), and yield strengths (0.193 GPa tensile, 0.255 GPa compressive) to simulate real-world stress and deformation scenarios. Using Finite Element Analysis (FEA), we conducted a series of simulations to examine stress distribution and deformation patterns across various implant models under static and dynamic loads. These simulations provided detailed insights, revealing that maximum equivalent stresses could reach up to 0.160 GPa, with deformations ranging from 0.01875 mm at a lower modulus to 0.015 mm at a higher modulus, showcasing the influence of material stiffness on implant performance. The model demonstrated high accuracy, with an error margin of less than 5 % when validated against analysis test data. This research makes a significant contribution to the field by providing a validated method for predicting and enhancing the biomechanical performance of spinal implants, thereby ensuring their reliability and efficacy in clinical applications.