MINI REVIEW article
Front. Med.
Sec. Rheumatology
This article is part of the Research TopicTherapeutic Strategies: Rehabilitation, Complementary and Alternative Therapies for Musculoskeletal DiseasesView all 27 articles
The Role of Artificial Intelligence in Advancing Scoliosis Care: A Rapid Review of Current Evidence and Future Opportunities
Provisionally accepted
- 1Rehabilitation Department, Pediatric Development Unit, Hospital Nostra Sra. de Meritxell; University of Andorra, Escaldes-Engordany, Andorra
- 2Physical Medicine and Rehabilitation Service, Hospital Campus Vall Hebron; Autonomus University of Barcelona, Barcelona;, Spain
- 3Padova Neuroscience Center, Padova, Italy
- 42nd Physical Medicine and Rehabilitation Department, National Rehabilitation Center EKA, Athens, Greece
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Background: Adolescent idiopathic scoliosis (AIS) is a complex three-dimensional spinal deformity with variable progression, complicating clinical decision-making. More accurate tools are needed for diagnosis, progression prediction, and treatment optimization. Artificial intelligence (AI) and machine learning (ML) show increasing potential in AIS management, but important limitations remain. This rapid review aimed to synthesize current evidence and assess the quality of published reviews on AI applications in AIS. Methods: English-language systematic reviews and meta-analyses published up to April 2025 addressing AI-based interventions in scoliosis were identified through Embase, the Cochrane Review Database, and PubMed/MEDLINE. Study selection followed PRISMA-RR guidelines. Two independent reviewers screened articles and assessed methodological quality using the AMSTAR 2 tool, with disagreements resolved by a third reviewer. Results: Five systematic reviews met inclusion criteria. Among the included studies, 55% employed AI models such as convolutional neural networks, artificial neural networks, decision trees, support vector machines, and hybrid approaches. Key applications included automated Cobb angle measurement—achieving high accuracy (errors <3° in some models)—curve classification, progression prediction, and clinical decision support. Conclusions: AI demonstrates promising potential in AIS management, particularly for automated measurements and progression prediction. However, broader clinical integration requires improved external validation and stronger evidence of real-world applicability.
Keywords: Adolescent, artificial intelligence, Idiopathic scoliosis, machine learning, Systematic review
Received: 24 Dec 2025; Accepted: 12 Feb 2026.
Copyright: © 2026 Avellanet, Sanchez-Raya, Maccarone and Dionyssiotis. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Yannis Dionyssiotis
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.