Scholarlink

Background <p>Spinal metastasis surgery frequently results in anemia, affecting patient recovery, yet lacks a quantitative method for assessing the risk of postoperative anemia.</p> Purpose <p>This study investigates the potential of MRI-based radiomics models to predict postoperative anemia, aiding in personalized treatment and improved outcomes.</p> Methods <p>247 patients diagnosed with spinal metastases pathologically and underwent surgery from December 2012 to December 2023 were enrolled and divided into postoperative anemia (<i>n</i> = 158) and non-anemia (<i>n</i> = 89) groups. Radiomics features were extracted from regions of interest on sagittal T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and fat-suppressed (FS)-T2WI sequences of preoperative MRI scans. Then, seven radiomics models were developed using logistic regression analysis, supported by a five-fold cross-validation technique. The Radscore, originating from the model with the highest predictive accuracy, was chosen for nomogram development. After variable selection via stepwise logistic regression analyses, clinical variables and the Radscore were included in the clinical and combined clinical and Radscore models. Ultimately, three models—clinical, Radscore, and combined clinical and Radscore models—were developed. Receiver operating characteristic analyses, Brier score, calibration curves, and decision curve analyses were used for model performance evaluation.</p> Results <p>Among the radiomics models, the one with feature integration based on T1WI and FS-T2WI sequences performed the best, with area under the curve (AUC) values of 0.844 (95% confidence interval [CI]: 0.789-0.9) and 0.819 (95% CI: 0.692–0.947), respectively in the training and test sets. The combined clinical and Radscore model (AUC: 0.747, 95% CI: 0.603–0.891) performs slightly better than the clinical model (AUC: 0.646, 95% CI: 0.474–0.817) (<i>P</i> = 0.148) and the Radscore model (AUC: 0.734, 95% CI: 0.584–0.844) (<i>P</i> = 0.759).</p> Conclusions <p>The combined clinical and Radscore nomogram could facilitate clinical decision-making for patients undergoing spinal metastasis surgery.</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

Multimodal MRI-based clinical radiomics model for predicting postoperative anemia in patients with spinal metastases

  • 期刊论文

  • 发表日期：

    2025年5月29日

查看全文
  • Weili Zhao,
  • Siyuan Qin,
  • Ruixin Yan,
  • Yongye Chen,
  • Qizheng Wang,
  • Ke Liu,
  • Ning Lang

摘要

Background

Spinal metastasis surgery frequently results in anemia, affecting patient recovery, yet lacks a quantitative method for assessing the risk of postoperative anemia.

Purpose

This study investigates the potential of MRI-based radiomics models to predict postoperative anemia, aiding in personalized treatment and improved outcomes.

Methods

247 patients diagnosed with spinal metastases pathologically and underwent surgery from December 2012 to December 2023 were enrolled and divided into postoperative anemia (n = 158) and non-anemia (n = 89) groups. Radiomics features were extracted from regions of interest on sagittal T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and fat-suppressed (FS)-T2WI sequences of preoperative MRI scans. Then, seven radiomics models were developed using logistic regression analysis, supported by a five-fold cross-validation technique. The Radscore, originating from the model with the highest predictive accuracy, was chosen for nomogram development. After variable selection via stepwise logistic regression analyses, clinical variables and the Radscore were included in the clinical and combined clinical and Radscore models. Ultimately, three models—clinical, Radscore, and combined clinical and Radscore models—were developed. Receiver operating characteristic analyses, Brier score, calibration curves, and decision curve analyses were used for model performance evaluation.

Results

Among the radiomics models, the one with feature integration based on T1WI and FS-T2WI sequences performed the best, with area under the curve (AUC) values of 0.844 (95% confidence interval [CI]: 0.789-0.9) and 0.819 (95% CI: 0.692–0.947), respectively in the training and test sets. The combined clinical and Radscore model (AUC: 0.747, 95% CI: 0.603–0.891) performs slightly better than the clinical model (AUC: 0.646, 95% CI: 0.474–0.817) (P = 0.148) and the Radscore model (AUC: 0.734, 95% CI: 0.584–0.844) (P = 0.759).

Conclusions

The combined clinical and Radscore nomogram could facilitate clinical decision-making for patients undergoing spinal metastasis surgery.