Breast cancer is one of the main causes of death for women worldwide, and better patient outcomes are dependent on early identification. However, the complex nature and variety of disease appearances make correct diagnosis from medical imaging difficult. In order to deal with these issues, this paper presents unique hybrid method called HIRF (Hypergraph-Integrated Random Forest), which combines Random Forest (RF) with Hypergraph Neural Networks (HGNN). Medical picture classification is a good fit for the HIRF model, which makes use of both HGNN's ability to capture complicated data relationships and RF's strength in feature extraction. HIRF showed potential for increasing diagnosis accuracy in practical applications, as evidenced by its 90% accuracy on datasets related to breast cancer. The algorithm will be improved in the future for better interpretability and performance.