Optimization of radiation dose distribution in clinical planning using a Treatment Planning System (TPS) for radiotherapy patients is crucial to achieving a balance between therapeutic effectiveness and patient safety. However, this process is time-consuming and relies heavily on the expertise of medical physicists. In this study, dose prediction using machine learning was performed on the Planning Target Volume (PTV) and Organ at Risk (OAR) for brain cancer cases using the Volumetric Modulated Arc Therapy (VMAT) planning technique. The planning DICOM data were extracted for radiomic and dosiomic values, which were then used as input and output in this study using a random forest algorithm model. Model evaluation results indicated that the random forest model's performance in predicting dose had a Mean Square Error (MSE) value of 0.018. The Homogeneity Index (HI) and Conformity Index (CI) values for the clinical data were 0.136±0.134 and 0.939±0.131 respectively, while the predicted results were 0.136±0.039 and 0.949±0.006, with p-values for PTV and OAR features > 0.05. Thus, it can be concluded that the random forest model is effective in predicting dose for PTV brain cancer and OAR and can function as a reference in the planning process.