2 - Knowledge Development Expert Systems and Their Application in Nutrition

Abstract

Improving people's long-term diet habits is a socially important task that could help decrease the frequency of cardiovascular accidents and the morbidity of many chronic diseases, such as diabetes. This chapter discusses issues related to knowledge-based tutoring systems acting on problem-solving domains. The Nutri-Expert system is presented in detail in the chapter that uses possibility theory to take the inherent imprecision of the database numbers and the input data into account properly and introduces the educational aspects via the daily use of an algorithm that finds a minimal transformation of a given meal to make it well balanced. This algorithm is based on a heuristic search in a state space of hypothetical meals. Different versions have been developed and evaluated using a test database of real meals. The educational benefits of Nutri-Expert for users are not explicitly planned or represented; rather, they emerge from its use. Nutri-Expert is not yet a real intelligent tutoring system, because it has a very limited user model and only an implicitly represented nutrition knowledge model. Nutri-Expert is widely used by patients at home, and several medical validations have measured its biological and educational benefits.