In most parts of the world, breast cancer ranks among the most common types of cancer that cause death. The ability to synthesize accurate information is crucial for the planning of effective treatment, particularly in the case of very early-stage cancers. This work investigates a new method that combines Genetic Algorithms (GA) and Explainable AI (XAI) to identify influential genes in each stage of breast cancer. In this research work, data from The Cancer Genome Atlas (TCGA) were used to search for gene markers linked to several stages of cancer. To do this, we applied a Genetic Algorithm to enhance the targeting of selected genes to be featured in further analysis. Gene interpretation via SHAP sought to explain the relevance of each gene included in the list, explaining which stage the cancer was at. Then, several machine learning models were applied to enhance gene data with the highest accuracy to distinguish cancer stages recorded by Support Vector Machines at 94.12%. It was found that SLC27A5, GGTL3, and CDK10 were among the significant genes helpful in classifying the stages. These are a few of the genes that are implicated in crucial mechanisms of cancer and, therefore, are central to breast cancer biology. Since GA and SHAP are used in this approach, they provide a basis for interpretable and thus tailored cancer treatment approaches, which are likely to lead to better and more personalized clinical management.