This The study goal is to build a more sophisticated machine learning framework based on Support Vector Machine (SVM) for brain tumor prognosis. Especially the SVM incorporated feature selection goes a long way in improving the accuracy and the efficiency of the tumor classification and progression analysis. For this study a diversity of datasets is used so as to delineate important features the model can use in improving its accuracy in distinguishing tumor types and prognosis predictions. The selection of features minimizes the amount of data that needs to be processed by ensuring that only the most important information sets are used, thus increasing the interpretability of the SVM model. Highlights include the framework’s deployment for early diagnosis, personalized treatment and effective clinical decision-making with regards to the management of a brain tumor. This study addresses the increasing need for enhanced oncology AI-driven health care solutions that are cost-effective and reliable for health practitioners and patients alike.