Department of Health, Medicine and Caring Sciences, Unit of Physiotherapy, Linköping University, Linköping, Sweden.
Department of Clinical Science, Intervention and Technology (CLINTEC), Division of Orthopaedics and Biotechnology, Karolinska Institutet, Stockholm; Department of Reconstructive Orthopaedics, Karolinska University Hospital Huddinge, Stockholm, Sweden.
Acta Orthop. 2024 Sep 13;95:536-544. doi: 10.2340/17453674.2024.41911.
The study's purpose was to develop and internally validate a prognostic survival model exploring baseline variables for adolescent idiopathic scoliosis curve progression.
A longitudinal prognostic cohort analysis was performed on trial data (n = 135) including girls and boys, Cobb angle 25-40°, aged 9-17 years, remaining growth > 1 year, and previously untreated. Prognostic outcome was defined as curve progression of Cobb angle of > 6° prior to skeletal maturity. 34 candidate prognostic variables were tested. Time-to-event was measured with 6-month intervals. Cox proportional hazards regression survival model (CoxPH) was used for model development and validation in comparison with machine learning models (66.6/33.3 train/test data set). The models were adjusted for treatment exposure.
The final primary prognostic model included 127 patients, predicting progress with acceptable discriminative ability (concordance = 0.79, 95% confidence interval [CI] 0.72-0.86). Significant prognostic risk factors were Risser stage of 0 (HR 4.6, CI 2.1-10.1, P < 0.001), larger major curve Cobb angle (HRstandardized 1.5, CI 1.1-2.0, P = 0.005), and higher score on patient-reported pictorial Spinal Appearance Questionnaire (pSAQ) (HRstandardized 1.4, CI 1.0-1.9, P = 0.04). Treatment exposure, entered as a covariate adjustment, contributed significantly to the final model (HR 3.1, CI 1.5-6.0, P = 0.001). Sensitivity analysis displayed that CoxPH maintained acceptable discriminative ability (AUC 0.79, CI 0.65-0.93) in comparison with machine learning algorithms.
The prognostic model (Risser stage, Cobb angle, pSAQ, and menarche) predicted curve progression of > 6° Cobb angle with acceptable discriminative ability. Adding patient report of the pSAQ may be of clinical importance for the prognosis of curve progression.
本研究旨在开发并内部验证一个预测性生存模型，用于探索青少年特发性脊柱侧凸曲线进展的基线变量。
对试验数据（n=135）进行了纵向预后队列分析，纳入了女孩和男孩，Cobb 角 25-40°，年龄 9-17 岁，剩余生长>1 年，且未经治疗。预后结果定义为在骨骼成熟前 Cobb 角进展>6°。测试了 34 个候选预后变量。使用 6 个月的时间间隔测量时间事件。使用 Cox 比例风险回归生存模型（CoxPH）与机器学习模型（66.6/33.3 训练/测试数据集）进行模型开发和验证。该模型针对治疗暴露进行了调整。
最终的主要预后模型纳入了 127 名患者，具有可接受的判别能力（一致性=0.79，95%置信区间[CI]0.72-0.86）。显著的预后危险因素包括 Risser 分期 0 期（HR4.6，CI2.1-10.1，P<0.001）、较大的主弯 Cobb 角（HR标准化1.5，CI1.1-2.0，P=0.005）和较高的患者报告的脊柱外观问卷（pSAQ）评分（HR标准化 1.4，CI1.0-1.9，P=0.04）。作为协变量调整纳入的治疗暴露对最终模型有显著贡献（HR3.1，CI1.5-6.0，P=0.001）。敏感性分析显示，CoxPH 与机器学习算法相比，保持了可接受的判别能力（AUC0.79，CI0.65-0.93）。
该预后模型（Risser 分期、Cobb 角、pSAQ 和初潮）预测 Cobb 角>6°的曲线进展，具有可接受的判别能力。增加患者对 pSAQ 的报告可能对曲线进展的预后具有重要的临床意义。
