Construction of a prediction model for axillary lymph node metastasis in stage cN0 hormone receptor-positive breast cancer: based on interpretable machine learning methods

TL;DR

This paper develops a machine learning model to predict lymph node metastasis in hormone receptor-positive breast cancer patients, using interpretable methods to guide preoperative decisions.

Contribution

The novel contribution is an interpretable KNN model for predicting axillary lymph node metastasis in cN0 HR+ BC patients using SHAP explanations.

Findings

The KNN model achieved an AUC of 0.898 in the test set and 0.774 in the external validation set.

SHAP analysis identified parity as the most critical predictor of axillary lymph node metastasis.

The model provides high net clinical benefit within the 30%–65% probability threshold range.

Abstract

Accurately predicting axillary lymph node metastasis (ALNM) preoperatively is crucial for optimizing management in patients with clinically node-negative (cN0) hormone receptor-positive (HR+) breast cancer (BC).

We retrospectively analyzed 816 cN0 HR+ BC patients (2016-2024). Data from 2016-2023 (n=726) were randomly assigned to a training set (n=503) or an internal test set (n=223) in a 7:3 ratio. Patients treated in the most recent year, 2024 (n=90), were reserved as a held-out temporal validation set. Following feature selection via Recursive Feature Elimination (RFE), five machine learning models—XGBoost, Random Forest, Logistic Regression, Support Vector Machine, and K-Nearest Neighbors (KNN)—were developed. Performance was assessed by the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). The optimal model was interpreted using SHapley Additive exPlanations (SHAP).

The incidence of ALNM was 30.9%. The KNN model demonstrated optimal performance, achieving an AUC of 0.898 (95% CI: 0.857–0.939) in the test set and 0.774 (95% CI: 0.655–0.892) in the external validation set. DCA indicated that the KNN model provided the highest net clinical benefit within the 30%–65% threshold probability range. SHAP analysis identified parity as the most critical predictor, followed by age, tumor location, menopausal status, tumor diameter, lymphocyte count, platelet count, alpha-fetoprotein (AFP), neutrophil count, and carcinoembryonic antigen (CEA).

The KNN model, integrated with the SHAP interpretability framework, shows favorable performance, interpretability, and clinical applicability for predicting ALNM in cN0 HR+ BC, offering a valuable tool for preoperative risk assessment and individualized decision-making.

Figures