Nomogram model based on multimodal ultrasound for predicting sentinel lymph node metastasis in patients with breast cancer
10.3760/cma.j.cn131148-20240517-00291
- VernacularTitle:基于多模态超声特征构建乳腺癌前哨淋巴结转移列线图预测模型
- Author:
Xiao ZU
1
;
Weilu DONG
;
Ting CAI
;
Qin ZHANG
;
Chun ZHAO
;
Ye QIANG
;
Yiyun WU
Author Information
1. 南京中医药大学附属医院超声医学科，南京 210029
- Keywords:
Ultrasonography;
Sentinel lymph node;
Breast cancer;
Prediction model;
Nomogram
- From:
Chinese Journal of Ultrasonography
2024;33(10):862-870
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To analyze the multimodal ultrasound characteristics of primary breast cancer and sentinel lymph node (SLN) and to establish a nomogram model for predicting SLN metastasis in invasive breast cancer, thereby providing reference for precise clinical diagnosis and treatment.Methods:A total of 329 patients diagnosed with invasive breast cancer and admitted to the Affiliated Hospital of Nanjing University of Chinese Medicine from June 2018 to October 2023 were retrospectively enrolled. They were randomly divided into a training cohort ( n=230) and a validation cohort ( n=99) in a ratio of 7 to 3. In the training cohort, ultrasound findings and clinical parameters were analyzed, univariate and multivariate Logistic regression analyses were used to identify independent predictive factors for SLN metastasis, and a nomogram model was constructed based on these factors. The ROC curve, calibration curve, and decision curve analysis (DCA) were plotted between the training and validation cohorts to assess the discrimination, calibration, and clinical applicability of the nomogram model. Results:Regression analysis identified 3 independent risk factors for establishing the nomogram prediction model: ratio of the long diameter to the short diameter of SLN ( P=0.020), lymphatic contrast-enhanced ultrasound (LCEUS) enhancement pattern ( P<0.001) and intravenous contrast-enhanced ultrasound (ICEUS) enhancement mode ( P=0.002). The area under the curve (AUC) of the training cohort was 0.888, the accuracy was 0.865; the AUC of the validation cohort was 0.870, the accuracy was 0.859, demonstrating good predictive performance of the model in both cohorts. The calibration curve demonstrated that the nomogram has a strong concordance between predicted and actual probability. DCA demonstrated that the nomogram could increase net benefit within a certain probability threshold range. Conclusions:The nomogram based on ratio of the long diameter to the short diameter of SLN, LCEUS enhancement pattern and ICEUS enhancement mode can effectively predict SLN status in patients with invasive breast cancer, facilitating precise diagnosis and treatment.
