Applying Explainable Machine Learning Models for Detection of Breast Cancer Lymph Node Metastasis in Patients Eligible for Neoadjuvant Treatment

Simple Summary In this study, we trained and evaluated several machine-learning models with the aim of predicting breast cancer lymph node metastasis in patients eligible for neoadjuvant treatment. In neoadjuvantly treated patients, radiological and clinical methods are primary ways for determining axillary lymph node status, and radiological methods misdiagnose up to 30% of the patients. Hence, there is an unmet need for supplementary methods to aid oncologists and their multidisciplinary teams in assessing metastatic lymph node status and, consecutively, defining optimal treatment strategies. Good performance was achieved with a random forest algorithm (AUC: 0.79). We explored model explainability and, through it, exhibited how the models learned genuine relationships that were determined in previous studies. Such models can lead to more accurate disease stage prediction and consecutively better treatment selection, especially for NST patients, where radiological and clinical findings are often the only way of lymph node assessment. Background: Due to recent changes in breast cancer treatment strategy, significantly more patients are treated with neoadjuvant systemic therapy (NST). Radiological methods do not precisely determine axillary lymph node status, with up to 30% of patients being misdiagnosed. Hence, supplementary methods for lymph node status assessment are needed. This study aimed to apply and evaluate machine learning models on clinicopathological data, with a focus on patients meeting NST criteria, for lymph node metastasis prediction. Methods: From the total breast cancer patient data (n = 8381), 719 patients were identified as eligible for NST. Machine learning models were applied for the NST-criteria group and the total study population. Model explainability was obtained by calculating Shapley values. Results: In the NST-criteria group, random forest achieved the highest performance (AUC: 0.793 [0.713, 0.865]), while in the total study population, XGBoost performed the best (AUC: 0.762 [0.726, 0.795]). Shapley values identified tumor size, Ki-67, and patient age as the most important predictors. Conclusion: Tree-based models achieve a good performance in assessing lymph node status. Such models can lead to more accurate disease stage prediction and consecutively better treatment selection, especially for NST patients where radiological and clinical findings are often the only way of lymph node assessment.