Development of a prediction model based on LASSO regression to evaluate the risk of non-sentinel lymph node metastasis in Chinese breast cancer patients with 1-2 positive sentinel lymph nodes

Abstract

Background: Our study aimed to investigate the correlative factors influencing non-sentinel lymph node (NSLN) metastasis in Chinese breast cancer patients with 1-2 positive sentinel lymph nodes (SLNs) and to develop an intraoperative prediction model based on the least absolute shrinkage and selection operator (LASSO) algorithm to evaluate the risk of NSLN metastasis.Methods: The factors affecting NSLN status were investigated in a cohort of 714 patients with 1-2 positive SLNs treated at The First Affiliated Hospital of Chongqing Medical University between January 2013 and December 2018. A new mathematical prediction model based on the LASSO algorithm was developed and was validated in a cohort of 131 patients treated between January 2019 and December 2019.Results: In the training cohort, 266/714 (37.3%) patients had NSLN metastasis. In univariate analysis, the histologic grade (P =0.010), number of positive SLNs (P<0.001), number of negative SLNs (P<0.001), number of SLNs dissected (P<0.001), SLN metastasis ratio (P <0.001), lymphovascular invasion (LVI) status (P <0.001), estrogen receptor (ER) status (P =0.011), human epidermal growth factor receptor 2 (HER2) status (P =0.005), molecular subtype (P =0.001), and risk score (P <0.001) were related with NSLN involvement. In multivariate analysis, the histologic grade (P =0.026), LVI status (P =0.005), number of positive SLNs (P=0.001), number of negative SLNs (P=0.005), SLN metastasis ratio (P =0.005), and molecular subtype (P=0.007) were identified as the independent predictors of NSLN metastasis. A LASSO regression-based mathematical prediction model was developed and had an area under the curve (AUC) of 0.764 (95% CI: 0.729-0.798). In the 131-patient validation cohort, the AUC was 0.777 (95% CI: 0.692-0.862).Conclusions: We present a new prediction model to assess the risk of NSLN metastasis in Chinese breast cancer patients with 1-2 positive SLNs. The model was further validated in the validation cohort and showed excellent clinical applicability and diagnostic performance. It can be used as an intraoperative clinical tool for clinicians to predict the risk of NSLN metastasis and make the final decision regarding axillary lymph node dissection (ALND).