Prostate cancer remains one of the most prevalent and deadly cancers among men worldwide, highlighting the urgent need for effective early detection methods. The model uniquely combines both clinical information (biopsy results, Gleason scores) and multiparametric MRI characteristics (from T2-weighted, DWI, and DCE imaging), yielding a more comprehensive, richer representation of every case than models using a single source of information. The integration enhances the model’s sensitivity in detecting faint markers of cancer detection. In the project we acquired MRI scans and utilized 3D Slicer to extract 2D slice images from the volumetric data. All the machine learning models were manually fine-tuned, and to address the dataset imbalance (254 false cases vs. 76 true cases), we applied SMOTE-Tomek oversampling. A wide range of machine learning algorithms was used in the study to compare their performance and determine the most effective model for accurately detecting prostate cancer, as each algorithm may capture patterns and relationships in the data differently. Several machine learning algorithms, including Naive Bayes, Bagging Classifier, Decision Tree, Random Forest, XGBoost, Extra Trees Classifier, K-Nearest Neighbors (KNN), Gradient Boosting, Logistic Regression, Linear Discriminant Analysis (LDA), SVM (linear, RBF, and polynomial kernels), AdaBoost, and CatBoost Classifier, were employed to predict prostate cancer grades and malignancy. Because it can be included into actual diagnostic workflows to help radiologists detect prostate cancer early and accurately, the suggested framework has high practical and clinical applicability. This could lead to better patient outcomes and less diagnostic workload. The goal is to identify the most accurate model for early diagnosis by evaluating the algorithms’ performance with metrics like accuracy, precision, recall, and F1-score. This research aims to enhance the precision of prostate cancer detection, supporting better diagnosis and personalized treatment strategies.