脊柱活动过度与特发性脊柱侧凸患病风险的横断面研究:对人工智能筛查的启示OA

Objective To investigate the predictive value of spinal hypermobility for idiopathic scoliosis(IS),and evaluate its feasibility as a potential indicator for artificial intelligence(AI)screening.Methods A total of 586 children aged 9 to 18 years who presented for scoliosis screening or postural abnormalities were enrolled.The Beighton scale was used to assess generalized joint hypermobility(GJH)or hemi-generalized joint hypermobility(Hemi-GJH),and the palm-to-floor test was employed to evaluate spinal hypermobility.Multivariate Logistic regression analysis was used to examine the association between joint hypermobility and IS.Results Among the 586 children,439 were diagnosed with IS(Cobb angle≥10°)via standing full-spine anteroposterior X-ray,accounting for 74.9%.The Beighton scale results showed that the prevalence of spinal hypermobility was 24.2%.Specifically,the prevalence of spinal hypermobility in children with a Cobb angle≥10° was 26.9%,which was significantly higher than that in children with a Cobb angle<10°(16.3%,P=0.010).Multivariate Logistic regression analysis revealed that children with spinal hypermobility had a 1.78-fold higher risk of developing a Cobb angle≥10° than those without spinal hypermobility(OR=1.78,P=0.040).In contrast,neither GJH(OR=1.32,P=0.376)nor Hemi-GJH(OR=0.54,P=0.305)was associated with the risk of a Cobb angle≥10°.Conclusion Spinal hypermobility,a simple indicator based on the palm-to-floor test,is an independent risk factor for IS and has the potential to serve as a marker for AI-driven community-based screening.