Purpose: Early detection and intervention can decrease the mortality of breast cancer significantly. Assessments of genetic/ genomic variants in circulating tumor DNA (ctDNA) have generated great enthusiasm for their potential application as clinically actionable biomarkers in the management of earlystage breast cancer.Experimental Design: In this study, 861 serial plasma and matched tissue specimens from 102 patients with early-stage breast cancer who need chemotherapy and 50 individuals with benign breast tumors were deeply sequenced via nextgeneration sequencing (NGS) techniques using large gene panels.Results: Cancer tissues in this cohort of patients showed profound intratumor heterogeneities (ITHGs) that were properly reflected by ctDNA testing. Integrating the ctDNA detection rate of 74.2% in this cohort with the corresponding predictive results based on Breast Imaging Reporting and Data System classification (BI-RADS) could increase the positive predictive value up to 92% and potentially dramatically reduce surgical overtreatment. Patients with positive ctDNA after surgery showed a higher percentage of lymph node metastasis, indicating potential recurrence and remote metastasis. The ctDNA-positive rates were significantly decreased after chemotherapy in basal-like and Her2 þ tumor subtypes, but were persistent despite chemotherapy in luminal type. The tumor mutation burden in blood (bTMB) assessed on the basis of ctDNA testing was positively correlated with the TMB in tumor tissues (tTMB), providing a candidate biomarker warranting further study of its potentials used for precise immunotherapy in cancer.Conclusions: These data showed that ctDNA evaluation is a feasible, sensitive, and specific biomarker for diagnosis and differential diagnosis of patients with early-stage breast cancer who need chemotherapy.

Background: Several studies have shown that women have a higher mortality rate than do men from ST-segment elevation myocardial infarction (STEMI). The present study was aimed at developing a new risk-prediction model for all-cause in-hospital mortality in women with STEMI, using predictors that can be obtained at the time of initial evaluation. Methods: We enrolled 8158 patients who were admitted with STEMI to the Tianjin Chest Hospital and divided them into two groups according to hospital outcomes. The patient data were randomly split into a training set (75%) and a testing set (25%), and the training set was preprocessed by adaptive synthetic (ADASYN) sampling. Four commonly used machine-learning (ML) algorithms were selected for the development of models; the models were optimized by 10-fold cross-validation and grid search. The performance of all-population-derived models and female-specific models in predicting in-hospital mortality in women with STEMI was compared by several metrics, including accuracy, specificity, sensitivity, G-mean, and area under the curve (AUC). Finally, the SHapley Additive exPlanations (SHAP) value was applied to explain the models. Results: The performance of models was significantly improved by ADASYN. In the overall population, the support vector machine (SVM) combined with ADASYN achieved the best performance. However, it performed poorly in women with STEMI. Conversely, the proposed female-specific models performed well in women with STEMI, and the best performing model achieved 72.25% accuracy, 82.14% sensitivity, 71.69% specificity, 76.74% G-mean and 79.26% AUC. The accuracy and G-mean of the female-specific model were greater than the all-population-derived model by 34.64% and 9.07%, respectively. Conclusions: A machine-learning-based female-specific model can conveniently and effectively identify high-risk female STEMI patients who often suffer from an incorrect or delayed management.