Zheng Bin, Zhu Zhenqi, Liang Yan, Liu Haiying
Spine Surgery, Peking University People's Hospital, Beijing, China.
Global Spine J. 2025 Aug 7:21925682251366947. doi: 10.1177/21925682251366947.
Study DesignRetrospective study.ObjectiveTo develop a machine learning model for predicting axial symptoms (AS) after unilateral laminoplasty by integrating C2 spinous process muscle radiomics features and cervical sagittal parameters.MethodsIn this retrospective study of 96 cervical myelopathy patients (30 with AS, 66 without) who underwent unilateral laminoplasty between 2018-2022, we extracted radiomics features from preoperative MRI of C2 spinous muscles using PyRadiomics. Clinical data including C2-C7 Cobb angle, cervical sagittal vertical axis (cSVA), T1 slope (T1S) and C2 muscle fat infiltration are collected for clinical model construction. After LASSO regression feature selection, we constructed six machine learning models (SVM, KNN, Random Forest, ExtraTrees, XGBoost, and LightGBM) and evaluated their performance using ROC curves and AUC.ResultsThe AS group demonstrated significantly lower preoperative C2-C7 Cobb angles (12.80° ± 7.49° vs 18.02° ± 8.59°, = .006), higher cSVA (3.01 cm ± 0.87 vs 2.46 ± 1.19 cm, = .026), T1S (26.68° ± 5.12° vs 23.66° ± 7.58°, = .025) and higher C2 muscle fat infiltration (23.73 ± 7.78 vs 20.62 ± 6.93 = .026). Key radiomics features included local binary pattern texture features and wavelet transform characteristics. The combined model integrating radiomics and clinical parameters achieved the best performance with test AUC of 0.881, sensitivity of 0.833, and specificity of 0.786.ConclusionThe machine learning model based on C2 spinous process muscle radiomics features and clinical parameters (C2-C7 Cobb angle, cSVA, T1S and C2 muscle infiltration) effectively predicts AS occurrence after unilateral laminoplasty, providing clinicians with a valuable tool for preoperative risk assessment and personalized treatment planning.
研究设计
回顾性研究。
目的
通过整合C2棘突肌肉的放射组学特征和颈椎矢状面参数，开发一种用于预测单侧椎板成形术后轴向症状（AS）的机器学习模型。
方法
在这项对2018年至2022年间接受单侧椎板成形术的96例颈椎病患者（30例有AS，66例无AS）的回顾性研究中，我们使用PyRadiomics从C2棘突肌肉的术前MRI中提取放射组学特征。收集包括C2-C7 Cobb角、颈椎矢状垂直轴（cSVA）、T1斜率（T1S）和C2肌肉脂肪浸润等临床数据用于构建临床模型。经过LASSO回归特征选择后，我们构建了六个机器学习模型（支持向量机、K近邻、随机森林、极端随机树、XGBoost和LightGBM），并使用ROC曲线和AUC评估它们的性能。
结果
AS组术前C2-C7 Cobb角显著更低（12.80°±7.49°对18.02°±8.59°，P = .006），cSVA更高（3.01 cm±0.87对2.46±1.19 cm，P = .026），T1S更高（26.68°±5.12°对23.66°±7.58°，P = .025），且C2肌肉脂肪浸润更高（23.73±7.78对20.62±6.93，P = .026）。关键的放射组学特征包括局部二值模式纹理特征和小波变换特征。整合放射组学和临床参数的联合模型表现最佳，测试AUC为0.881，灵敏度为0.833，特异性为0.786。
结论
基于C2棘突肌肉放射组学特征和临床参数（C2-C7 Cobb角、cSVA、T1S和C2肌肉浸润）的机器学习模型能有效预测单侧椎板成形术后AS的发生，为临床医生提供了一个用于术前风险评估和个性化治疗规划的有价值工具。
