Abstract PS3-04-02: A Novel Non-invasive Machine Learning Model for Predicting Tertiary Lymphoid Structures and Treatment Response to Neoadjuvant Therapy in Triple-Negative Breast Cancer: A Multicenter Retrospective Study

Abstract Background: Triple-negative breast cancer (TNBC) is an aggressive subtype of breast cancer (BC) and neoadjuvant therapy (NAT) has become an essential treatment strategy. Recent studies have showed tertiary lymphoid structures (TLSs) is associated with better treatment response to NAT in BC. However, there is still a lack of non-invasive biomarkers to predict the presence of TLSs in TNBC. This study aimed to develop a novel non-invasive machine learning model for early identification and prediction of the presence of TLSs and treatment response to NAT in TNBC, which were essential for timely adjustments in treatment strategies for TNBC. Methods: In this study, 698 patients from multicenter were divided into a training cohort (n = 137), the TLSs validation cohort (n = 63) and the NAT response validation cohorts (n = 561). A total of 4788 radiomic features per patient were extracted from the intratumoral and peritumoral regions of DCE-MRI. After extracting the optimal features, five machine learning models were developed to predict the presence of TLSs, including K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Support Vector Machine (SVM) and Multilayer Perceptron (MLP) and were subsequently applied to predict the treatment response to NAT in NAT response validation cohorts. The performance of the models was assessed by accuracy, sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV), and area under curve values (AUC), and prognostic analysis were performed to evaluate its predictive value. Then,the rTLS predictive model was interpreted by SHapley Additive Explanations (SHAP). Finally, the correlation between key radiomic features extracted from H 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PS3-04-02.