In this paper, we develop an automated system that can potentially be used in medical centers to detect breast cancer (BC) early, based on electronic health records (EHR) data, which can be gathered in routine blood analysis. Such a system makes it possible to detect BC without collecting mammographic images (the standard BC screening tool) from patients. Our system comprises three steps: data preparation, parameters selection, and classification. The utilized EHR data includes 9 parameters: age, BMI, Glucose, Insulin, HOMA, Leptin, Adiponectin, Resistin, and MCP-1. The experimental results show that our system achieves a promising BC detection results (AUC = 0.86) compared to related studies.