An Intelligent Assistant for Medical Knowledge Discovery

Nowadays the availability of a huge amount of raw medical data makes it possible to use suitable data mining techniques to produce new knowledge. Usually, only data mining experts are able enough to carry out such tasks, and not so many researchers in medical \uafeld are also skilled in data analysis. This paper describes the Medical Knowledge Discovery Assistant (MKDA), a web based framework able to advice a medical researcher in such tasks. MKDA plans a Knowledge Discovery Process (KDP) on the basis of the requests of the user and of a set of rules in a knowledge base. The requests of the user are related to accu- racy, computational load, type of the produced model. They de\uafne the goal to be reached by the planned process. The whole system relies on a database that contains medical data, e.g. images, text, examination results. The rules consider the logic schema of the database that is de- scribed semantically. The system's work is the result of the co-operation of di\uaeerent web services specialized in di\uaeerent tasks. The web services are chosen on the basis of their functionalities described by a common ontology. This ontology allows to integrate the process information and domain information about the knowledge discovery process. The paper presents a possible scenario and an experiment dealing with region clas- si\uafcation of medical images