The radiomics signature achieved a C-Index of 0.731 (95% confidence intervals [CI]: 0.645, 0.817) for the discovery data set, and 0.710 (95% CI: 0.588, 0.932) for the independent validation data set, demonstrating the predictive performance of the model. Based on the radiomics score of patients in the discov- ery data set, the optimal cutoff calculated by the X-tile plot was 0.1343235, as shown in Supplementary Figure 2. Then, patients in both the discovery and validation data sets were stratified into low-risk (Rad-score < 0.1343235) and high-risk (Rad-score>0.1343235) groups, as shown in Fig. 3. The significant association of the radiomics signature with OS was shown in discovery data set (P < 0.001, hazard ratio [HR] = 5.042, 95% CI: 2.624, 9.689), and confirmed in the validation data set (P < 0.001, HR = 5.128, 95% CI: 2.029, 12.960). The OS in the low-risk and high-risk groups in the discovery and validation data sets are listed in Supplementary Table 4. 解释

这段话描述了一项研究，研究者使用了放射学特征学（radiomics）来预测患者的生存情况。在发现数据集中，这个放射学特征学模型的C-Index为0.731，在独立验证数据集中为0.710，表明了该模型的预测性能。通过X-tile图计算得到的放射学分数的最优阈值为0.1343235。根据这个阈值，研究者将患者分为低风险组和高风险组，结果显示放射学特征学与患者的生存率显著相关，无论是在发现数据集中还是在验证数据集中，都表现出较高的预测力。