Cardiovascular disease remains one of the leading causes of death worldwide and encompasses a wide range of conditions. Accurate diagnosis can be challenging in the medical field due to the overlap of cardiovascular symptoms with those of other diseases or with signs of natural aging. However, machine learning (ML) and its algorithms have proven effective in performing prediction and classification tasks on the vast amounts of healthcare data now available. In this research, the proposed work introduced an efficient hybrid recommender system for cardiovascular disease, leveraging the Internet of Medical Things (IoMT). This system offers personalized medical recommendations based on clinical test results, utilizing wireless sensor networks. To enhance feature selection, the system employs the Sequential Forward Selection (SFS) technique, that follows a greedy selection strategy. The dataset used for this study includes information from one hundred cardiac patients, each exhibiting varying levels of heart disease. Simulation results demonstrate that the proposed model delivers high accuracy in predicting heart disease cases. Moreover, the simulation not only identifies the condition but also suggests appropriate medical treatments for the patient.