Scholarlink

Objective <p>To develop machine-learning model that combines pre-operative vertebral-body CT radiomics with clinical data to predict cage subsidence after single-level ACDF with Zero-P.</p> Methods <p>We retrospectively review 253 patients (2016–2023). Subsidence is defined as ≥ 3&#xa0;mm loss of fused-segment height at final follow-up. Patients are split 8:2 into a training set (<i>n</i> = 202; 39 subsidence) and an independent test set (<i>n</i> = 51; 14 subsidence). Vertebral bodies adjacent to the target level are segmented on pre-operative CT, and high-throughput radiomic features are extracted with PyRadiomics. Features are z-score–normalized, then reduced by variance, correlation and LASSO. Age, vertebral Hounsfield units (HU) and T1-slope entered a clinical model. Eight classifiers are tuned by cross-validation; performance is assessed by AUC and related metrics, with thresholds optimized on the training cohort.</p> Results <p>Subsidence patients are older, lower HU and higher T1-slope (all <i>P</i> &lt; 0.05). LASSO retained 11 radiomic features. In the independent test set, the clinical model had limited discrimination (AUC 0.595). The radiomics model improved performance (AUC 0.775; sensitivity 100%; specificity 60%). The combined model is best (AUC 0.813; sensitivity 80%; specificity 80%) and surpassed both single-source models (<i>P</i> &lt; 0.05).</p> Conclusion <p>A pre-operative model integrating CT-based radiomic signatures with key clinical variables predicts cage subsidence after ACDF with good accuracy. This tool may facilitate individualized risk stratification and guide strategies—such as endplate protection, implant choice and bone-quality optimization—to mitigate subsidence risk. Multicentre prospective validation is warranted.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Radiomics-based machine learning model integrating preoperative vertebral computed tomography and clinical features to predict cage subsidence after single-level anterior cervical discectomy and fusion with a zero-profile anchored spacer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月26日

查看全文
  • Bin Zheng,
  • Panfeng Yu,
  • Ke Ma,
  • Zhenqi Zhu,
  • Yan Liang,
  • Haiying Liu

摘要

Objective

To develop machine-learning model that combines pre-operative vertebral-body CT radiomics with clinical data to predict cage subsidence after single-level ACDF with Zero-P.

Methods

We retrospectively review 253 patients (2016–2023). Subsidence is defined as ≥ 3 mm loss of fused-segment height at final follow-up. Patients are split 8:2 into a training set (n = 202; 39 subsidence) and an independent test set (n = 51; 14 subsidence). Vertebral bodies adjacent to the target level are segmented on pre-operative CT, and high-throughput radiomic features are extracted with PyRadiomics. Features are z-score–normalized, then reduced by variance, correlation and LASSO. Age, vertebral Hounsfield units (HU) and T1-slope entered a clinical model. Eight classifiers are tuned by cross-validation; performance is assessed by AUC and related metrics, with thresholds optimized on the training cohort.

Results

Subsidence patients are older, lower HU and higher T1-slope (all P < 0.05). LASSO retained 11 radiomic features. In the independent test set, the clinical model had limited discrimination (AUC 0.595). The radiomics model improved performance (AUC 0.775; sensitivity 100%; specificity 60%). The combined model is best (AUC 0.813; sensitivity 80%; specificity 80%) and surpassed both single-source models (P < 0.05).

Conclusion

A pre-operative model integrating CT-based radiomic signatures with key clinical variables predicts cage subsidence after ACDF with good accuracy. This tool may facilitate individualized risk stratification and guide strategies—such as endplate protection, implant choice and bone-quality optimization—to mitigate subsidence risk. Multicentre prospective validation is warranted.