By utilizing cutting-edge machine learning and deep learning techniques, this study seeks to improve predictive analysis for brain tumors and overall survival prediction. We use imaging data, radiomics properties, and clinical information to create a strong model that outperforms current techniques. Our method combines logistic regression, random forests, and support vector machines (SVMs) to predict survival and uses convolutional neural networks (CNNs) to detect tumors. The findings demonstrate notable gains in accuracy and dependability, which support improved patient outcomes and individualized treatment plans. Brain tumors have a dismal prognosis and are among the most aggressive types of cancer, especially glioblastomas. Improving patient outcomes requires early identification and precise survival prediction. Using clinical variables, radiomics data, and imaging modalities, this work suggests an improved prediction model that combines deep learning (DL) and machine learning (ML) approaches. We significantly increased accuracy by integrating machine learning techniques for survival prediction with convolutional neural networks (CNNs) for tumor identification. The suggested framework outperformed current techniques with a tumor detection accuracy of 99% and a survival prediction C-Index of 0.85. Our results demonstrate the promise of AI-powered strategies in neuro-oncology.