Ge Chen, Li Changwei, Zhu Yaoqing, Yang Chonglin, Xu Xiangyang
Department of Orthopaedics, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Department of Orthopaedics, Shanghai Key Laboratory for Prevention and Treatment of Bone and Joint Diseases, Shanghai Institute of Traumatology and Orthopedics, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Int J Med Sci. 2025 Jul 11;22(13):3329-3341. doi: 10.7150/ijms.114419. eCollection 2025.
: Residual back pain (RBP) following vertebral augmentation (VA) represents a significant challenge in managing osteoporotic vertebral compression fractures (OVCFs). While conventional predictive models have shown moderate accuracy, their preoperative risk stratification capabilities remain suboptimal. CT-based radiomics has demonstrated success in vertebral fracture assessment, yet its integration with artificial intelligence (AI) for predicting RBP remains unexplored. : This study aims to identify the optimal AI model for predicting RBP by systematically comparing multiple algorithms that integrate CT radiomics features with clinical parameters, with the goal of enabling preoperative risk stratification for improved surgical decision-making. : This prospective study enrolled patients who underwent VA for OVCFs. Potential predictors were identified through clinical variable analysis. Radiomics features were extracted from preoperative CT images using standardized vertebral segmentation protocols. The study population was divided into training and testing cohorts at a ratio of 7:3. Five AI models were constructed through integration of clinical predictors and radiomics features. Model performance evaluation was conducted in the independent testing cohort through discrimination, calibration, and clinical utility analyses. The predictive mechanisms of the optimal model were interpreted through feature importance analysis. : Among 856 enrolled patients, RBP developed in 102 cases (11.9%). TabNet exhibited optimal performance metrics (AUROC: 0.927, Recall: 0.833) among all evaluated algorithms. Feature importance analysis revealed intravertebral vacuum cleft and bone mineral density as principal clinical predictors, complemented by wavelet-based texture parameters and quantitative intensity metrics. Ablation experiments demonstrated that clinical parameters were critical for false-positive reduction, while radiomics features enhanced specificity in non-RBP identification. The model maintained consistent clinical utility across varying threshold probabilities. The integration of clinical parameters and CT-based radiomics through a deep learning framework enabled accurate preoperative prediction of RBP.
椎体强化术（VA）后残留背痛（RBP）是骨质疏松性椎体压缩骨折（OVCFs）治疗中的一项重大挑战。虽然传统预测模型已显示出一定的准确性，但其术前风险分层能力仍不尽人意。基于CT的放射组学已在椎体骨折评估中取得成功，然而其与人工智能（AI）结合用于预测RBP的研究仍未开展。
本研究旨在通过系统比较多种将CT放射组学特征与临床参数相结合的算法，确定预测RBP的最佳AI模型，以期实现术前风险分层，改善手术决策。
本前瞻性研究纳入了接受VA治疗OVCFs的患者。通过临床变量分析确定潜在预测因素。使用标准化椎体分割方案从术前CT图像中提取放射组学特征。研究人群按7:3的比例分为训练组和测试组。通过整合临床预测因素和放射组学特征构建了五个AI模型。在独立测试组中通过区分度、校准度和临床效用分析对模型性能进行评估。通过特征重要性分析解释最佳模型的预测机制。
在856名纳入患者中，102例（11.9%）出现了RBP。在所有评估算法中，TabNet表现出最佳性能指标（AUROC：0.927，召回率：0.833）。特征重要性分析显示椎体内真空裂隙和骨密度是主要临床预测因素，基于小波的纹理参数和定量强度指标起到补充作用。消融实验表明临床参数对减少假阳性至关重要，而放射组学特征增强了非RBP识别的特异性。该模型在不同阈值概率下保持一致的临床效用。通过深度学习框架整合临床参数和基于CT的放射组学能够准确术前预测RBP。
