Artificial intelligence in spine research: A multimodal perspective beyond imaging

Abstract

Recent advances in artificial intelligence (AI) have brought significant progress to the field of spine research. While image-based AI applications such as automated spine segmentation and pathology detection have garnered substantial attention, the potential of AI beyond imaging data remains less explored. These applications include predictive models built on electronic health records and spine registries, analytics of wearable sensors, genomics and other “omics” data, and AI-driven robotics for surgery. This review provides a comprehensive overview of AI applications in spine research from a multimodal perspective, tracing their historical development, highlighting current progress, and addressing key challenges including data integration, explainability, and regulatory hurdles. Additionally, we outline future directions to highlight AI’s expanding role in precision medicine, clinical decision-making, and ultimately the enhancement of patient outcomes in spinal disorders.