A Food Recommender System for Patients with Diabetes and Hypertension

Abraham Eseoghene Evwiekpaefe, Mariam Ugbede Akpa and Oghenegueke Fortune Amrevuawho

Keywords: diabetes, hypertension, meal, prediction, k-means clustering, random forest, recommendation.  


Diabetes and hypertension are examples of non-communicable diseases that are becoming a severe problem in the world today. A number of diseases have been connected to unhealthy eating habits. In this study, a recommender system that uses nutritional knowledge to suggest meals that are nutrient-dense to patients suffering from either ailments or one of it. The Study looked into computer models for tailored meal suggestions based on dietary data and user data in recent years. It examined physical traits, physiological data, and other personal information. A general framework for daily eating plan selections is presented in this article. The system used machine learning methodologies and techniques to generate recommendations for the necessary food items. K[1]means clustering and Random Forest classification technique were used which concentrates on providing meal recommendations that help the user maintain and enhance his or her health. The model was able to achieve an accuracy of 95% with 100 decision trees.