Fig. 3From: Machine learning radiomics of magnetic resonance imaging predicts recurrence-free survival after surgery and correlation of LncRNAs in patients with breast cancer: a multicenter cohort studyPerformance of the RDeepNet model for recurrence risk prediction in patients with different therapy regimens. Kaplan–Meier curves of RFS according to the RDeepNet model in the subgroups of patients with a endocrine therapy and b HER2-targeted therapy. ROC curves and 1-, 2-, 3-year AUCs were used to assess the prognostic accuracy of the RDeepNet model in the subgroups of patients with c endocrine therapy and d HER2-targeted therapy. P values were calculated using the unadjusted log-rank test, and hazard ratios were calculated by a univariate Cox regression analysis. AUC, area under the receiver operating characteristics curve; CI, confidence interval; HR, hazard ratio; HER2, human epidermal growth factor receptor 2; RFS, recurrence-free survival; ROC, receiver operating characteristicBack to article page