Data_Sheet_1_Machine Learning Analytics of Resting-State Functional Connectivity Predicts Survival Outcomes of Glioblastoma Multiforme Patients.DOCX

Glioblastoma multiforme (GBM) is the most frequently occurring brain malignancy. Due to its poor prognosis with currently available treatments, there is a pressing need for easily accessible, non-invasive techniques to help inform pre-treatment planning, patient counseling, and improve outcomes. In this study we determined the feasibility of resting-state functional connectivity (rsFC) to classify GBM patients into short-term and long-term survival groups with respect to reported median survival (14.6 months). We used a support vector machine with rsFC between regions of interest as predictive features. We employed a novel hybrid feature selection method whereby features were first filtered using correlations between rsFC and OS, and then using the established method of recursive feature elimination (RFE) to select the optimal feature subset. Leave-one-subject-out cross-validation evaluated the performance of models. Classification between short- and long-term survival accuracy was 71.9%. Sensitivity and specificity were 77.1 and 65.5%, respectively. The area under the receiver operating characteristic curve was 0.752 (95% CI, 0.62–0.88). These findings suggest that highly specific features of rsFC may predict GBM survival. Taken together, the findings of this study support that resting-state fMRI and machine learning analytics could enable a radiomic biomarker for GBM, augmenting care and planning for individual patients.

多形性胶质母细胞瘤（Glioblastoma multiforme, GBM）是最常见的脑部恶性肿瘤。由于当前临床现有治疗手段下其预后极差，因此亟需便捷易用、无创的技术，以辅助治疗前规划、患者咨询，并改善治疗结局。本研究评估了静息态功能连接（resting-state functional connectivity, rsFC）在依据报道的中位生存期（14.6个月）将GBM患者划分为短期生存组与长期生存组方面的可行性。本研究采用以感兴趣区（regions of interest）之间的rsFC作为预测特征的支持向量机（support vector machine）。我们创新性地采用了混合特征选择方法：首先通过rsFC与总生存期（overall survival, OS）之间的相关性对特征进行筛选，随后采用经典的递归特征消除（recursive feature elimination, RFE）方法选取最优特征子集。采用留一受试者交叉验证（leave-one-subject-out cross-validation）评估模型性能。短期与长期生存分类的准确率为71.9%，灵敏度与特异度分别为77.1%与65.5%。受试者工作特征曲线（receiver operating characteristic curve）下面积为0.752（95%置信区间CI：0.62~0.88）。上述结果表明，rsFC的高特异性特征可预测GBM患者的生存情况。综上，本研究结果证实，静息态功能磁共振成像（resting-state fMRI）与机器学习分析可构建针对GBM的放射组学生物标志物，从而为个体化患者的诊疗与规划提供辅助。