<p>Breast cancer continues to be a major worldwide health issue, requiring advanced predictive models for better healthcare outcomes and early detection. This research presents the novel quantum-enhanced neural network (QENN), a hybrid classical-quantum approach that integrates a classical neural network with a quantum feature map and a parameterized quantum circuit to enhance breast cancer classification performance. The QENN model is applied to both the wisconsin (diagnostic) breast cancer dataset (WBCD) and the SEER breast cancer dataset (SBCD). For the WBCD, QENN was able to deliver high-performance comparable to classical machine learning models and state-of-the-art research work, thus demonstrating the capability to extract complex patterns in biomedical datasets. For the SBCD, a dataset with class imbalance and high number of categorical features, QENN performed reasonably compared to classical machine learning models, after application of several preprocessing steps. However, it demonstrated a comparably high AUC-ROC score, which has been proven to be one of the most reliable metrics for imbalanced datasets. The study demonstrates the potential of QENN in biomedical applications, showing strong performance on balanced and well-processed datasets while maintaining comparable effectiveness on datasets with moderate class imbalance and high cardinality categorical features by leveraging quantum principles for distinct data representation and class separability.</p>