Breast cancer is one of the leading causes of death among women around the globe. To make an accurate prognosis it is essential to provide an effective treatment and improve survival rates. However, breast cancer grading, an important component in predicting patient outcomes, due to the wide range of symptoms and complications like paraneoplastic syndrome, the grading system faces challenges and complications. Existing grading systems, such as the Nottingham Grading System, though widely used, often suffer from inconsistencies due to inter-observer variability and tumor heterogeneity, which decreases their reliability. This research focuses on the application of Artificial Intelligence (AI) techniques in breast cancer prognosis, focusing on predictive models that can assess disease progression and patient outcomes. Machine learning algorithms, such as Support Vector Machines (SVM), Random Forests, and deep learning approaches like Convolutional Neural Networks (CNNs), are used to analyze clinical, histopathological and genomic data. By giving a detailed review of AI applications in breast cancer prognosis, displaying its potential not only to improve the accuracy of diagnosis but also to enable radiologists with advanced tools to provide better care to patients. We have used the Random Forest model to calculate MSE and R squared values to improve the accuracy of prognosis of breast cancer.