Automated Food Ontology Construction Mechanism for Diabetes Diet Care

Medical nutrition therapy (MNT) is important in preventing diabetes, managing existing diabetes, and preventing, or at least slowing, the rate of development of diabetes complications. The most common way for Diabetes Educators to inform diabetes patients of their nutrition therapy is by introducing food substitution. Patients are taught to replace food items from the same food group based on the quantity of the desired nutrients. However, this method may not provide the best results because it does not accurately take into account of all the food characteristics, diabetes diet care requirements, and the relationships between the different types of food. The goal of our study is to propose an automated food ontology constructed for diabetes diet care. Our methods include generating an ontology skeleton with hierarchical clustering algorithms (HCA), class naming by intersection naming, and instance ranking by granular ranking and positioning. Our proposed approach will be helpful to nutritionists in creating new food groups and hierarchically rank food replacements and recommendations.