Adolescent idiopathic scoliosis is a complex three-dimensional spinal deformity that affects a significant proportion of the adolescent population and its progressive nature complicates therapeutic decisions. Artificial intelligence and machine learning are emerging as promising tools for improving diagnostics, predicting the risk of progression and optimizing the treatment of this disease. A rapid review including five systematic reviews published up to April 2025 found that 55% of the included studies used algorithms with convolutional neural networks, artificial neural networks, decision trees and other models. The main applications of AI in scoliosis care include automatic measurement of the Cobb angle with high accuracy (less than 3° in some models), classification of curve type and prediction of its progression. Language models are also used for patient education and clinical decision support. The combination of deep learning models with clinical data has the potential to change future practice, but external validation and clinical integration of these systems need to be strengthened for effective implementation.