Effects of Specific Exercise Therapy on Adolescent Patients With Idiopathic Scoliosis: A Prospective Controlled Cohort Study.

STUDY DESIGN: A prospective controlled cohort study. OBJECTIVE: The aim of this study was to explore the interventional effect of exercise therapy on idiopathic scoliosis (IS) and identify an optimal intervention window. SUMMARY OF BACKGROUND DATA: Early conservative treatment is helpful for IS. In addition to bracing, current evidence suggests that exercise can play an important role. METHODS: We included 99 patients with IS who were treated at the Guangdong Xinmiao Scoliosis Center from August 2013 to September 2017. The inclusion criteria were: new IS diagnosis, Cobb angle 10° to 25°, Risser 0 to 3 grade, only treated with the Xinmiao treatment system (XTS; >3 days/week, >1 h/day), and follow-up >1 year. Patients were divided into three age groups: A, <10 years (n = 29); B, 10 to 12 years (n = 24); and C, 13 to 15 years (n = 46). The percentages of curve improvement (Cobb angle decrease ≥5°), stability (Cobb angle change × ±5°), and progression (Cobb angle increase ≥5°) were compared. RESULTS: The groups showed significant differences for major curve correction, Risser sign, first referral, and final follow-up of the main curve (all P < 0.05). The major curve in group A decreased significantly by 6.8° (44% correction), compared to 3.1° (18% correction) and 1.5° (9% correction) in groups B and C, respectively. In group A, 69.0% (20/29) had curve improvement, 27.6% (8/29) stabilized and 3.4% (1/29) progressed. In group B, 45.8% (11/24) improved, 50% (12/24) stabilized, and 4.2% (1/24) progressed. In group C, 26.1% (12/46) improved, 63.0% (29/46) stabilized, and 10.9% (5/46) progressed. There was also a significant difference in final Risser grade among the groups (P < 0.05). CONCLUSION: For IS patients with Cobb angles between 10° and 25°, our exercise protocol can effectively control or improve curve progression. Younger patients with a lower Risser grade are most likely to respond. LEVEL OF EVIDENCE: 2.

Development and validation of deep learning algorithms for scoliosis screening using back images.

Adolescent idiopathic scoliosis is the most common spinal disorder in adolescents with a prevalence of 0.5-5.2% worldwide. The traditional methods for scoliosis screening are easily accessible but require unnecessary referrals and radiography exposure due to their low positive predictive values. The application of deep learning algorithms has the potential to reduce unnecessary referrals and costs in scoliosis screening. Here, we developed and validated deep learning algorithms for automated scoliosis screening using unclothed back images. The accuracies of the algorithms were superior to those of human specialists in detecting scoliosis, detecting cases with a curve ≥20°, and severity grading for both binary classifications and the four-class classification. Our approach can be potentially applied in routine scoliosis screening and periodic follow-ups of pretreatment cases without radiation exposure.