علي بخشيان طالخونچه

Adolescent Idiopathic Scoliosis (AIS) requires effective and personalized brace treatment strategies to prevent progression and potential need for surgery. However, monitoring and prediction of the spinal column deformities during bracing is not always possible. Relying only on traditional methods or clinicians’ experience may pose a complex challenge in orthopedic care. Patient-specific considerations in brace prescription significantly influence treatment effectiveness and patient comfort. In this study, a biomechanical modeling of the spine is conducted using finite element analysis, followed by training a neural network based on simulation data. This creates a platform to determine brace design parameters. The Rigo Chêneau-type brace, renowned for its biomechanical principles targeting lateral displacement and transversal derotation, serves as the foundation for this study. A dataset of 120 different scoliosis curves was initially classified according to the Rigo-Chêneau standard to determine the brace’s initial force pattern. After modeling these deformities, 30 simulations were performed for each model, and the effect of pressure in specified areas was examined. This study eva‎luates brace performance in terms of coronal correction, sagittal plane stability, and stress distribution. Subsequently, simulation data are utilized for training a Multi-layer Perceptron model to estimate the spinal column position after using the prescribed brace. Simulation findings indicate significant improvements in coronal alignment while preserving the physiological sagittal curves. The trained scoliosis model demonstrated 90.6% accuracy in predicting spinal deviation changes. This enables physicians to determine the required brace pressure by observing spinal displacement. By leveraging advanced computational tools and patient-specific biomechanical data, the current simulations offer a promising approach for optimizing brace treatment in AIS patients by predicting the outcomes.

مدلسازي بيومكانيكي , روش اجزاي محدود , تصميم‌گيري باليني , شبكه‌هاي عصبي , رباط , ديسك بين مهره‌اي

Biomechanical modeling , Finite element method , Clinical decision-making , Spinal brace , Neural networks , Ligament , Intervertebral disc

Ali Bakhshian Talkhoncheh

Borhan Beigzadeh