Presently, the medical recommender system is applied for diverse healthcare applications, spanning from bioinformatics to forecasting the spread of infectious diseases, which is beneficial to provide better healthcare outcomes. As a specialized recommendation system, the medical recommender system mainly focuses on providing clinical decision-making support and healthcare service for the respective individual patients. The medical recommendation system collects trusted information from the Internet and patient health records to analyze and suggest the best medications. Various recommendation systems such as Collaborative-based, Content-based, Knowledge-based, Context-based, and Hybrid approaches are evolved in medical recommender systems with the help of several learning methods. Machine learning and deep learning techniques have recently been exploited for healthcare recommendation systems.
Recently, a smart and intelligence-based healthcare recommendation system was developed for better multi-disciplinary disease prediction and effective recommendation with the help of big data analytics. Food Recommendation, Drug Recommendation, Health Status Recommendation, Healthcare Service Recommendation, Healthcare Professional Recommendation, Personalized Healthcare Recommendation, Clinical Recommendation, and Medicine Recommendation are some of the significant medical recommender systems. Some of the open problems and future scopes of healthcare recommender systems are a proliferation of healthcare standards, cold-start problems, scalability, reliability, accuracy, patient and their relative disagreement, authorization, and access to electronic medical records. Several literature surveys and reviews have been published on medical recommendation system, which provides information on healthcare recommender system scenarios, learning techniques, categories of recommender system, challenges, future scopes, and open problems. Some of the surveys and reviews are listed below;