Prevalence and factors associated with adolescent idiopathic scoliosis in Shanghai, China: an artificial intelligence-assisted screening approach.

OBJECTIVE

To investigate the prevalence of adolescent idiopathic scoliosis (AIS) and major modifiable factors associated with AIS among school students in Shanghai, China, and assess the feasibility and validated accuracy of AI-assisted 3D screening in school health management.

METHODS

A multistage stratified cluster sampling design was employed in this cross-sectional study, conducted from July 2024 to June 2025. A structured-light 3D back-scanning AI system was used to screen 5,026 students aged 9-15 years from six schools in five districts of Shanghai. Physical fitness tests and questionnaires were used to collect data on body morphology, posture, physical activity, and lifestyle. Standing full-spine radiography was used as the reference standard for AIS diagnosis, defined as Cobb angle ≥10°. Because radiographic verification was performed for all screen-positive students but only for a random subset of screen-negative students, inverse probability weighting was applied to account for partial verification.

RESULTS

Among the 5,026 screened students, 160 AIS cases were confirmed among 185 rescreen-positive students, and 2 additional AIS cases were identified among 300 randomly verified screen-negative students. The crude radiographically confirmed detection rate was 3.2% (162/5,026), and the IPW-adjusted estimated population prevalence was 3.8%. Thoracic curves and Cobb angles of 10°- < 20° were most common. Girls and middle school students had higher crude radiographic detection rates than boys and primary school students, respectively. Multivariable binary logistic regression identified female sex, improper sitting posture among girls, very low post-exercise fatigue among boys, and frequent one-sided exertion sports as factors associated with screening-detected AIS, whereas higher BMI, balanced walking posture, and satisfactory sleep quality showed protective associations. The AI-assisted structured-light screening workflow showed IPW-adjusted sensitivity of 0.832, specificity of 0.995, PPV of 0.865, NPV of 0.993, and overall accuracy of 0.989.

CONCLUSION

AIS represents a non-negligible spinal health burden among school students in Shanghai. Most factors associated with AIS are modifiable. The AI-assisted structured-light screening workflow demonstrated acceptable diagnostic accuracy and promising feasibility for large-scale school-based health screening and management integration.