Visualisation model construction and effectiveness verification of risk prediction of postoperative recurrence and metastasis of triple-negative breast cancer
Objective To construct a visual risk prediction model for postoperative recurrence and metastasis of tri-ple negative breast cancer,and verify the predictive efficacy of the model.Methods The clinical data of 390 triple nega-tive breast cancer patients who received surgical treatment in the First Affiliated Hospital of Zhengzhou University from Janu-ary 2017 to December 2019 were retrospectively analyzed,and they were randomly divided into training set(273 cases)and verification set(117 cases)according to the ratio of 7:3.The postoperative recurrence and metastasis of triple negative breast cancer patients were counted,and the risk factors of postoperative recurrence and metastasis of triple negative breast cancer were analyzed using Cox regression analysis.The risk prediction Nomogram model was constructed with R3.5.3 soft-ware,and the effectiveness of the model was verified by consistency index,receiver operating characteristic(ROC)curve,calibration curve,and decision curve.Results The 390 cases of triple negative breast cancer were followed up for 42-78 months,and the rate of recurrence and metastasis was 23.85%.T3(OR=2.291,95%CI:1.344-3.904,P=0.002),N1～3(OR=3.053,95%CI:1.380-6.753,P=0.006),vascular tumor thrombus(OR=2.147,95%CI:1.165-3.957,P=0.015),high neutrophil-to-lymphocyte ratio(NLR)(OR=1.189,95%CI:1.057-1.337,P=0.004),and positive expression of nuclear proliferation antigen(Ki-67)(OR=1.716,95%CI:1.128-2.610,P=0.011)were independent risk factors for postoperative recurrence and metastasis of triple negative breast cancer patients.The Nomogram model was constructed to predict the risk of postoperative recurrence and metastasis of triple negative breast cancer patients according to the above five independent risk factors.The consistency indexs of the training set and the validation set were 0.861(95%CI:0.819-0.903)and 0.807(95%CI:0.746-0.870),respectively,and the area under the curve was 0.849(95%CI:0.804-0.892)and 0.796(95%CI:0.732-0.858),respectively.The calibration curve showed that the calibration curve of the model in training set and verification set to predict the recurrence and metastasis of triple negative breast cancer after surgery was consistent with the ideal curve and fits well.The decision curve showed that the model had a high net benefit within the threshold probability range of 0.00%to 90.20%.Conclusion Nomogram model was constructed to predict the risk of recurrence and metastasis of triple negative breast cancer patients after surgery based on T stage,N stage,vascular tumor thrombus,NLR and Ki-67 expression.The model has good consistency and predictive ability after verification.
triple negative breast cancerrecurrencemetastasisrisk prediction model
万方数据
维普
