《中国康复理论与实践》

《中国康复理论与实践》 ›› 2026, Vol. 32 ›› Issue (7): 850-860.doi: 10.3969/j.issn.1006-9771.2026.07.012

• 应用研究 • 上一篇    下一篇

基于治疗前和支具初配信息的青少年特发性脊柱侧凸支具治疗失败风险预测模型构建与初步验证

马颖1, 任君1, 王首鉴1, 周鑫1, 何天翔1, 孔令军1(), 房敏1,2()   

  1. 1 上海中医药大学附属曙光医院， 上海市 201203
    2 上海市中医推拿研究所， 上海市 200437
  • 收稿日期:2026-04-19 修回日期:2026-06-26 接受日期:2026-07-01 出版日期:2026-07-25 发布日期:2026-07-30
  • 通讯作者: 房敏，E-mail：fm-tn0510@shutcm.edu.cn；
    孔令军，E-mail：chunyong01@163.com
  • 作者简介:马颖(1991-)，女，回族，甘肃天水市人，博士研究生，主治医师，主要研究方向：脊柱病的推拿研究。
  • 基金资助:
    国家自然科学基金项目(82374607);国家中医药管理局儿童青少年脊柱侧弯中医药干预试点项目(上海市黄浦区);上海申康医院发展中心新兴前沿技术联合攻关项目(SHDC12024110);上海市筋骨病中医推拿技术重点实验室(24dz2260200);上海市卫生健康委员会卫生行业临床研究专项(202340157);上海市浦东新区卫健委卫生科技项目(PW2024D-14)

Development and preliminary internal validation of a prediction model for brace treatment failure in adolescent idiopathic scoliosis using pretreatment and initial brace-fitting information

Ma Ying1, Ren Jun1, Wang Shoujian1, Zhou Xin1, He Tianxiang1, Kong Lingjun1(), Fang Min1,2()   

  1. 1 Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China
    2 Institute of Tuina, Shanghai Academy of Traditional Chinese Medicine, Shanghai 200437, China
  • Received:2026-04-19 Revised:2026-06-26 Accepted:2026-07-01 Published:2026-07-25 Online:2026-07-30
  • Supported by:
    National Natural Science Foundation of China(82374607);Pilot Project of Traditional Chinese Medicine Intervention for Scoliosis in Children and Adolescents, National Administration of Traditional Chinese Medicine(Huangpu District);Pilot Project of Traditional Chinese Medicine Intervention for Scoliosis in Children and Adolescents, National Administration of Traditional Chinese Medicine(Huangpu District, Shanghai);Joint Research Project on Emerging Cutting-Edge Technologies, Shanghai Shenkang Hospital Development Center(SHDC12024110);Shanghai Key Laboratory of Traditional Chinese Medicine Tuina for Musculoskeletal Diseases(24dz2260200);Special Project for Clinical Research in the Health Industry, Shanghai Municipal Health Commission(202340157);Health Science and Technology Project of Pudong New Area Health Commission(PW2024D-14)

RichHTML

PDF (PC)

摘要：

目的 构建并初步验证基于支具治疗前及初配阶段信息的青少年特发性脊柱侧凸(AIS)支具治疗失败风险预测模型。

方法 回顾性纳入2015年3月至2024年8月于上海中医药大学附属曙光医院启动胸腰骶支具治疗且结局可判定的AIS患者191例，按预设方案划分为训练集(n = 133)和验证集(n = 58)。支具治疗失败定义为随访或脱支时主弯Cobb角较基线进展≥ 5°，或末次主弯Cobb角> 45°。基于支具治疗前及初配阶段常规可得的临床和影像学变量，构建逻辑回归、随机森林、径向基核支持向量机和极限梯度提升(XGBoost)模型。训练集内采用分层5折交叉验证进行超参数调优，验证集中采用受试者工作特征曲线下面积(AUC)、精确率-召回率曲线下面积(AUPRC)、Brier分数、校准曲线和决策曲线分析(DCA)评价模型表现，并采用沙普利可加解释(SHAP)对主要可解释性展示模型进行特征贡献分析。

结果 训练集交叉验证中，随机森林和XGBoost均显示较好判别表现，交叉验证AUC分别为0.871和0.880。验证集中，随机森林和XGBoost的AUC分别为0.888和0.899，AUPRC分别为0.678和0.830，Brier分数分别为0.086和0.076。随机森林模型作为主要可解释性展示模型，其失败风险校准截距为0.091，校准斜率为0.995。SHAP分析显示，支具矫正率和支具内主弯Cobb角对模型预测贡献最大。

结论 基于支具治疗前及初配阶段常规可得变量构建的随机森林模型，对AIS支具治疗失败风险具有初步预测价值，可为随访频率调整、支具适配复核和依从性支持前置提供量化参考。

关键词: 青少年特发性脊柱侧凸, 侧弯进展, 支具, 机器学习, 预测模型

Abstract:

Objective To develop and preliminarily validate a prediction model for brace treatment failure risk in patients with adolescent idiopathic scoliosis (AIS), based on information obtained before brace treatment and during initial brace fitting.

Methods A total of 191 patients with AIS who initiated thoracolumbosacral orthosis treatment at Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine from March, 2015 to August, 2024 and had determinable outcomes were retrospectively included. Patients were divided according to a prespecified scheme into a training set (n= 133) and a validation set (n= 58). Brace treatment failure was defined as progression of the major-curve Cobb angle by ≥ 5° from baseline during follow-up or at brace weaning, or a final major-curve Cobb angle > 45°. Logistic regression, random forest, support vector machine with radial basis function kernel, and extreme gradient boosting (XGBoost) models were developed using routinely available clinical and radiographic variables before brace treatment and during initial brace fitting. Stratified five-fold cross-validation was used for hyperparameter tuning in the training set. Model performance was evaluated in the validation set using the area under the receiver operating characteristic curve (AUC), area under the precision-recall curve (AUPRC), Brier score, calibration curves, and decision curve analysis (DCA). SHapley Additive exPlanations (SHAP) was used to interpret the main explanatory model.

Results In cross-validation of the training set, both random forest and XGBoost showed good discriminative performance, with cross-validation-AUC values of 0.871 and 0.880, respectively. In the validation set, the AUC values of random forest and XGBoost were 0.888 and 0.899, the AUPRC values were 0.678 and 0.830, and the Brier scores were 0.086 and 0.076, respectively. Random forest was selected as the primary model for interpretation, with a calibration intercept of 0.091 and a calibration slope of 0.995. SHAP analysis indicated that the in-brace correction rate and the major-curve Cobb angle measured in the brace contributed most to the model predictions.

Conclusion The random forest model developed using routinely available pretreatment and initial-fitting variables shows preliminary predictive value for brace treatment failure risk in AIS, and may provide quantitative support for follow-up scheduling, brace-fit reassessment and early adherence-oriented management.

Key words: adolescent idiopathic scoliosis, curve progression, brace, machine learning, prediction model

中图分类号: