The value of the nomogram model based on ultrasound multi-parameter scoring combined with clinical data in predicting local recurrence after radical mastectomy for breast cancer
BAI Lingjiao
QI Yan
DUAN Liangliang
WANG Shengli
Abstract：Objective To explore the value of the nomogram model based on ultrasound multi-parameter scoring combined with clinical data in predicting local recurrence after radical mastectomyfor breast cancer.Methods A retrospective analysis was conducted on the clinical data of 300 breast cancer patients admitted from March 2019 to March 2023.All of them were treated with radical mastectomy for breast cancer.The patients were randomly divided into the training set and the validation set at a ratio of 7:3,and according to the occurrence of local recurrence within one year after surgery,they were divided into the recurrence group and the non-recurrence group.Multivariate Logistic regression equation was used in the training set to analyze the influencing factors of local recurrence after breast cancer surgery.The nomogram model of local recurrence after radical mastectomy for breast cancer was constructed using R4.2.1 software.Then,10-fold cross-validation was conducted on the prediction results of the nomogram in the training set and the validation set respectively.The receiver operating characteristic(ROC)curve,calibration curve and decision curve were used to analyze the value of the nomogram model in predicting local recurrence after breast cancer surgery.Results The local recurrence rate within one year after surgery for 300 breast cancer patients was 24.33%.Multivariate Logistic regression analysis showed that positive Ki-67,color Doppler ultrasound score,UE score and ultrasound multi-parameter score were the influencing factors of local recurrence after breast cancer surgery(P<0.01).The ROC curve with 10-fold cross-validation was used to analyze the discrimination of the nomogram model in predicting local recurrence after radical mastectomy for breast cancer.The areas under the curves in the training set were 0.885 and 0.869,respectively,and the slopes of the calibration curves were close to 1.When the threshold probabilities of the training set and validation set were 0 to 80.00%,the clinical net benefit rate of the nomogram prediction model was the largest.Conclusion The nomogram model constructed by combining ultrasound multi-parameter scores with clinical data can accurately predict local recurrence after radical mastectomy for breast cancer,which is helpful for guiding clinical treatment.
Keywords：breast neoplasmsradical mastectomy for breast cancerneoplasm recurrencelocalnomogram modelcolor Doppler ultrasoundultrasonic elastographyKi-67 positivity
Publication Date：2025-09-28
Online Publishing Date：2025-10-17(First online date of this platform, not the publication date of the document)
Pages：7( 86-92 )