Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, China.
Department of Radiology, Sichuan Provincial People's Hospital, Sichuan Academy of Medical Sciences, Chengdu, China.
Br J Radiol. 2022 Apr 1;95(1132):20210792. doi: 10.1259/bjr.20210792. Epub 2022 Jan 31.
To develop and evaluate a machine learning-based CT radiomics model for the prediction of hepatic encephalopathy (HE) after transjugular intrahepatic portosystemic shunt (TIPS).
A total of 106 patients who underwent TIPS placement were consecutively enrolled in this retrospective study. Regions of interest (ROIs) were drawn on unenhanced, arterial phase, and portal venous phase CT images, and radiomics features were extracted, respectively. A radiomics model was established to predict the occurrence of HE after TIPS by using random forest algorithm and 10-fold cross-validation. Receiver operating characteristic (ROC) curves were performed to validate the capability of the radiomics model and clinical model on the training, test and original data sets, respectively.
The radiomics model showed favorable discriminatory ability in the training cohort with an area under the curve (AUC) of 0.899 (95% CI, 0.848 to 0.951), while in the test cohort, it was confirmed with an AUC of 0.887 (95% CI, 0.760 to 1.00). After applying this model to original data set, it had an AUC of 0.955 (95% CI, 0.896 to 1.00). A clinical model was also built with an AUC of 0.649 (95% CI, 0.530 to 0.767) in the original data set, and a Delong test demonstrated its relative lower efficiency when compared with the radiomics model ( < 0.05).
Machine learning-based CT radiomics model performed better than traditional clinical parameter-based models in the prediction of post-TIPS HE.
Radiomics model for the prediction of post-TIPS HE was built based on feature extraction from routine acquired pre-operative CT images and feature selection by random forest algorithm, which showed satisfied performance and proved the advantages of machine learning in this field.
开发并评估一种基于机器学习的 CT 放射组学模型，用于预测经颈静脉肝内门体分流术（TIPS）后肝性脑病（HE）的发生。
本回顾性研究连续纳入了 106 例行 TIPS 治疗的患者。在未增强、动脉期和门静脉期 CT 图像上分别勾画感兴趣区（ROI），提取放射组学特征。采用随机森林算法和 10 折交叉验证建立放射组学模型，预测 TIPS 后 HE 的发生。分别在训练集、测试集和原始数据集上绘制受试者工作特征（ROC）曲线，验证放射组学模型和临床模型的效能。
放射组学模型在训练队列中表现出良好的鉴别能力，曲线下面积（AUC）为 0.899（95%可信区间，0.848 至 0.951），在测试队列中得到验证，AUC 为 0.887（95%可信区间，0.760 至 1.00）。将该模型应用于原始数据集，AUC 为 0.955（95%可信区间，0.896 至 1.00）。在原始数据集中，还建立了一个临床模型，AUC 为 0.649（95%可信区间，0.530 至 0.767），Delong 检验表明其与放射组学模型相比效率较低（<0.05）。
基于机器学习的 CT 放射组学模型在预测 TIPS 后 HE 方面优于传统的基于临床参数的模型。
基于术前常规 CT 图像特征提取和随机森林算法特征选择，建立了预测 TIPS 后 HE 的放射组学模型，表现出令人满意的性能，证明了机器学习在该领域的优势。
