Peer-reviewed article
AI-based mid-term effectiveness prediction of bracing treatments for adolescent idiopathic scoliosis.
Guilin Chen, Huimin Xiong, Ziquan Li, Jie Wang, Jing Yuan et al. ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001This is a medical study about using artificial intelligence to predict how well bracing treatments work for adolescents with idiopathic scoliosis, a condition affecting spine curvature. The research developed a deep learning model to forecast treatment outcomes based on X-ray images and clinical data. While the study involves adolescents, it is a clinical technology paper focused on diagnostic prediction rather than child well-being, health outcomes, or intervention effectiveness in the context of child development or protection.
Key points
- The study developed a deep learning model to predict mid-term effectiveness of brace treatment for adolescent scoliosis
- The model achieved moderate to good predictive accuracy in both cross-validation and external validation
- The approach may help clinicians make individualized treatment decisions
- The research used radiographic imaging and clinical variables from 294 patients across two centers
- Predictions focused on Cobb angle measurements at follow-up timepoints
Limitations
This study focuses on a specific medical technology for a particular orthopedic condition and does not address broader child well-being outcomes, health equity, or implementation in resource-limited settings. The document provides no information about how the tool might affect children's quality of life, access to care, or developmental outcomes.
Abstract
Brace treatment is the standard non-operative treatment of moderate adolescent idiopathic scoliosis (AIS). Yet reliable quantitative prediction of mid-term treatment response remains limited. The mid-term effectiveness of bracing is crucial because the risk of progression begins to increase when the curve exceeds 30° after skeletal maturity has been achieved. This study aimed to develop and externally validate a deep learning regression model to predict the mid-term Cobb angle following brace treatment using baseline and early post-brace radiographs. A retrospective multicenter cohort study was conducted including 294 patients with AIS treated with bracing at two tertiary referral centers. Standing full-spine radiographs were obtained at baseline (pre-brace), immediately post-brace and follow-ups, along with clinical variables including age, sex, and Risser stage. In cross-validation, the model achieved MAEs of 4.06° (T curve; R2 = 0.811) and 3.75° (TL/L curve; R2 = 0.746). External validation produced MAEs of 5.13° (R2 = 0.678) and 3.89° (R2 = 0.723) for T and TL/L curves, respectively. This imaging-based deep learning regression model provides precise and interpretative predictions of mid-term bracing outcomes. This approach may assist clinicians in individualized risk stratification and shared decision-making regarding brace management.