Department of Neurosurgery, Wuhan University Zhongnan Hospital, Wuhan, 430071, China.
Department of Radiology, Wuhan University Zhongnan Hospital, Wuhan, 430071, China.
Neurosurg Rev. 2024 Mar 8;47(1):109. doi: 10.1007/s10143-024-02339-7.
To develop a clinical-radiomics nomogram based on clinical information and radiomics features to predict the prognosis of percutaneous balloon compression (PBC) for the treatment of trigeminal neuralgia (TN).
The retrospective study involved clinical data from 149 TN patients undergoing PBC at Zhongnan Hospital, Wuhan University from January 2018 to January 2022. The free open-source software 3D Slicer was used to extract all radiomic features from the intraoperative X-ray balloon region. The relationship between clinical information and TN prognosis was analyzed by univariate logistic analysis and multivariate logistic analysis. Using R software, the optimal radiomics features were selected using the least absolute shrinkage and selection operator (Lasso) algorithm. A prediction model was constructed based on the clinical information and radiomic features, and a nomogram was visualized. The performance of the clinical radiomics nomogram in predicting the prognosis of PBC in TN treatment was evaluated using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA).
A total of 149 patients were eventually included. The clinical factors influencing the prognosis of TN in univariate analysis were compression severity score and TN type. The lasso algorithm Max-Relevance and Min-Redundancy(mRMR) was used to select two predictors from 13 morphology-related radiomics features, including elongation and surface-volume ratio. A total of 4 predictors were used to construct a prediction model and nomogram. The AUC was 0.886(95% confidence interval (CI), 0.75 to 0.96), indicating that the model's good predictive ability. DCA demonstrated the nomogram's high clinical applicability.
Clinical-radiomics nomogram constructed by combining clinical information and morphology-related radiomics features have good potential in predicting the prognosis of TN for PBC treatment. However, this needs to be further studied and validated in several independent external patient populations.
基于临床信息和放射组学特征开发临床放射组学列线图，以预测经皮球囊压迫（PBC）治疗三叉神经痛（TN）的预后。
本回顾性研究纳入了 2018 年 1 月至 2022 年 1 月期间在武汉大学中南医院接受 PBC 治疗的 149 例 TN 患者的临床数据。使用免费开源软件 3D Slicer 从术中 X 射线球囊区域提取所有放射组学特征。通过单因素逻辑分析和多因素逻辑分析分析临床信息与 TN 预后的关系。使用 R 软件，通过最小绝对收缩和选择算子（Lasso）算法选择最佳放射组学特征。基于临床信息和放射组学特征构建预测模型，并可视化列线图。使用受试者工作特征曲线（AUC）和决策曲线分析（DCA）评估临床放射组学列线图在预测 PBC 治疗 TN 预后中的性能。
最终共纳入 149 例患者。单因素分析影响 TN 预后的临床因素为压迫严重程度评分和 TN 类型。使用 Lasso 算法的最大相关性和最小冗余（mRMR）从 13 个形态相关的放射组学特征中选择了两个预测因子，包括伸长率和表面积-体积比。共选择 4 个预测因子构建预测模型和列线图。AUC 为 0.886（95%置信区间（CI），0.75 至 0.96），表明模型具有良好的预测能力。DCA 表明列线图具有较高的临床适用性。
结合临床信息和形态相关放射组学特征构建的临床放射组学列线图在预测 PBC 治疗 TN 的预后方面具有良好的应用潜力。然而，这需要在几个独立的外部患者群体中进一步研究和验证。
