Du Peng, Wu Xuefan, Liu Xiao, Chen Jiawei, Chen Lang, Cao Aihong, Geng Daoying
Department of Radiology, Huashan Hospital, Fudan University Shanghai 200040, China.
Department of Radiology, The Second Affiliated Hospital of Xuzhou Medical University Xuzhou 221000, Jiangsu, China.
Am J Cancer Res. 2023 Aug 15;13(8):3449-3462. eCollection 2023.
To develop a decision tree model based on clinical information, molecular genetics information and pre-operative magnetic resonance imaging (MRI) radiomics-score (Rad-score) to investigate its predictive value for the risk of recurrence of glioblastoma (GBM) within one year after total resection. Patients with pathologically confirmed GBM at Huashan Hospital, Fudan University between November 2017 and June 2020 were retrospectively analyzed, and the enrolled patients were randomly divided into training and test sets according to the ratio of 3:1. The relevant clinical and MRI data of patients before, after surgery and follow-up were collected, and after feature extraction on preoperative MRI, the LASSO filter was used to filter the features and establish the Rad-score. Using the training set, a decision tree model for predicting recurrence of GBM within one year after total resection was established by the C5.0 algorithm, and scatter plots were generated to evaluate the prediction accuracy of the decision tree during model testing. The prediction performance of the model was also evaluated by calculating area under the receiver operating characteristic (ROC) curve (AUC), ACC, Sensitivity (SEN), Specificity (SPE) and other indicators. Besides, two external validation datasets from Wuhan union hospital and the second affiliated hospital of Xuzhou Medical University were used to verify the reliability and accuracy of the prediction model. According to the inclusion and exclusion criteria, 134 patients with GBM were finally identified for inclusion in the study, and 53 patients recurred within one year after total resection, with a mean recurrence time of 5.6 months. According to the importance of the predictor variables, a decision tree model for predicting recurrence based on five important factors, including patient age, Rad-score, O-methylguanine-DNA methyltransferase (MGMT) promoter methylation, pre-operative Karnofsky Performance Status (KPS) and Telomerase reverse transcriptase (TERT) promoter mutation, was developed. The AUCs of the model in the training and test sets were 0.850 and 0.719, respectively, and the scatter plot showed excellent consistency. In addition, the prediction model achieved AUCs of 0.810 and 0.702 in two external validation datasets from Wuhan union hospital and the second affiliated hospital of Xuzhou Medical University, respectively. The decision tree model based on clinicopathological risk factors and preoperative MRI Rad-score can accurately predict the risk of recurrence of GBM within one year after total resection, which can further guide the clinical optimization of patient treatment decisions, as well as refine the clinical management of patients and improve their prognoses to a certain extent.
基于临床信息、分子遗传学信息和术前磁共振成像（MRI）影像组学评分（Rad-score）构建决策树模型，以研究其对胶质母细胞瘤（GBM）全切除术后一年内复发风险的预测价值。回顾性分析2017年11月至2020年6月在复旦大学附属华山医院经病理确诊为GBM的患者，并根据3:1的比例将纳入患者随机分为训练集和测试集。收集患者手术前后及随访的相关临床和MRI数据，对术前MRI进行特征提取后，采用LASSO滤波器筛选特征并建立Rad-score。利用训练集，通过C5.0算法建立预测GBM全切除术后一年内复发的决策树模型，并生成散点图评估模型测试期间决策树的预测准确性。还通过计算受试者操作特征（ROC）曲线下面积（AUC）、ACC、灵敏度（SEN）、特异性（SPE）等指标评估模型的预测性能。此外，使用来自武汉协和医院和徐州医科大学第二附属医院的两个外部验证数据集验证预测模型的可靠性和准确性。根据纳入和排除标准，最终确定134例GBM患者纳入研究，其中53例在全切除术后一年内复发，平均复发时间为5.6个月。根据预测变量的重要性，构建了基于患者年龄、Rad-score、O-甲基鸟嘌呤-DNA甲基转移酶（MGMT）启动子甲基化、术前卡氏评分（KPS）和端粒酶逆转录酶（TERT）启动子突变这五个重要因素的复发预测决策树模型。该模型在训练集和测试集的AUC分别为0.850和0.719，散点图显示出良好的一致性。此外，该预测模型在来自武汉协和医院和徐州医科大学第二附属医院的两个外部验证数据集中的AUC分别为0.810和0.702。基于临床病理危险因素和术前MRI Rad-score的决策树模型能够准确预测GBM全切除术后一年内的复发风险，可进一步指导临床优化患者治疗决策，在一定程度上细化患者的临床管理并改善其预后。
