Search This Issue

Home Site

   Page 38
Sample Issue - Subscribe TODAY to see the entire issue
18.3 Table of ContentsBottom of PageSite Map
resulting in a suggested treatment or test. The knowledge base, a collection of if-then rules and other data, captured the clinical protocols. Opal translated the expert's input, via graphical forms, into an internal representation specifically tailored for Oncocin. This project identified three different levels of knowledge for this particular information:

     1. Structural domain concepts used by the knowledge engineer to create the Opal knowledge- acquisition application;
     2. The domain expert (oncologist) knowledge - oncology protocols;
     3. Case data entered by the user to exercise the expert system decision capability.

     Since Opal was inference engine based, it enabled reuse by knowledge engineers to create different knowledge bases - ultimately creating domain specific expert systems. The knowledge engineer was responsible for the knowledge acquisition; a tedious and time-intensive task. Unfortunately, the concept of a knowledge engineer separated the domain experts from the domain knowledge bases and this separation introduced a potentially large source of incorrect knowledge.
     In 1987, Mark Musen built an application for knowledge-based systems with a goal of building knowledge-acquisition application as part of Oncocin. Based on these three different levels of knowledge, he believed that knowledge acquisition occurs in phases with knowledge obtained in one phase defining the structural knowledge for subsequent phases. Musen's goal was to reduce the work engineers did to construct knowledge bases during knowledge-acquisition. He noticed that knowledge obtained during a specific phase influences the knowledge related application required for later stages.
     From this early concept, Protégé evolved through four phases, resulting in a rich development environment available for both research and knowledge-management. (see /SMI-2002-0943.html for more information on the evolution of Protégé.

Protégé-I - Knowledge Bases
     This early phase, where Protégé-I simplified the knowledge acquisition process for building medical expert systems, learned from the earlier OPAL- based system. The intent of the tool was to simplify the knowledge acquisition process for the knowledge engineer, already overloaded with complex tasks to perform - a key issue with early expert system development. One goal of Protégé was to provide an application that


Figure 1: Evolution and enhancements of Protégé from 1986 to present.

created Knowledge Acquisition tools (KA) from a formally defined collection of concepts. This enabled the domain expert to create the knowledge base, eliminating the time consuming process of the knowledge engineer learning the domain. Early assumptions for Protégé 1 included:

To Page 37

18.3 Table of Contents
Top of Page

To Page 49


PC AI Magazine - -
e-mail: PCAI.TH @ - Comments: webmaster @