Breast cancer is the most common cancer among women worldwide, and its five-year survival rate is strongly associated with the stage at diagnosis. However, mammography, the current standard screening method, has limitations: the procedure often causes discomfort and the equipment is costly, leading to low participation rates and consequently reduced effectiveness of early diagnosis. This study explores the use of chest X-ray (CXR), a more affordable and widely accessible modality, combined with artificial intelligence (AI) to extract breast cancer-related features as an opportunistic screening tool. The aim is to identify high-risk individuals who can then undergo mammography for confirmation. We employed a CXR pretrained model based on the CLIP architecture and applied linear probing to build a classifier for breast cancer risk prediction. Cases with BI-RADS scores of 4A or higher were considered positive, and model performance was evaluated using receiver operating characteristic (ROC) curves and the area under the curve (AUC). Preliminary results indicate that the AI model demonstrates a certain level of discriminative ability for breast cancer in CXR, achieving an AUC of 0.682. These findings suggest that CXR combined with AI analysis has the potential to serve as a low-cost, scalable method for early breast cancer screening. Moreover, since chest radiography (CXR) is a routine component of general health examinations, this opportunistic screening approach can substantially enhance breast cancer prevention and early detection without incurring additional costs or patient discomfort. Keywords Breast cancer, Chest X-ray, Artificial intelligence