An approach for solving multi-level diagnosis in high sensitivity medical diagnosis systems through the application of semantic technologies

Abstract

The capability of medical diagnosis systems to provide results in different situations depends on the modeling of the knowledge base. In the case of high sensitivity systems, the capability of having an adequate model allows to increase the accuracy of the system even in situations where the number of input elements is low. In this context the concept of multi-level diagnosis emerges, where a pathology can be assumed as a diagnostic element of another pathology (acting as a finding). In this paper this concept is studied in depth from the modeling point of view, providing a solution based on rule inference techniques modeled with semantic technologies, and allowing solving the problem generated by multi-level diagnosis.