Automatic knowledge base refinement: learning from examples and deep knowledge in rheumatology

MESICAR is a second generation expert system which contains very general descriptions of rheumatological disorders in the primary medical care field. With the help of a detailed hierarchical description of the human anatomy the system is able to support diagnostic decisions. The paper describes how machine learning techniques are used to automatically construct more specific disease descriptions for common, frequently occurring cases. The system MESICAR-LEARN implements a learning method which integrates analytical and empirical learning techniques. Cases diagnosed by MESICAR form the training examples, and MESICAR's knowledge base is used as domain theory. The learned concepts are integrated into a hierarchy of disease descriptions. They support efficient and fast reasoning on common cases in addition to the general diagnostic support afforded by MESICAR's deep knowledge.

[1]  Werner Horn,et al.  Utilizing detailed anatomical knowledge for hypothesis formation and hypothesis testing in rheumatological decision support , 1991, Artif. Intell. Medicine.

[2]  Elpida T. Keravnou,et al.  What is a deep expert system? An analysis of the architectural requirements of second-generation expert systems , 1989, The Knowledge Engineering Review.

[3]  Paul E. Utgoff,et al.  Machine Learning of Inductive Bias , 1986 .

[4]  E. Shortliffe.  Computer-based medical consultations: mycin (elsevier north holland , 1976 .

[5]  Jon Sticklen,et al.  Mdx2: an integrated medical diagnostic system , 1987 .

[6]  Tom Michael Mitchell,et al.  Explanation-based generalization: A unifying view , 1986 .

[7]  Luc Steels,et al.  Components of Expertise , 1990, AI Mag..

[8]  Tom M. Mitchell,et al.  LEAP: A Learning Apprentice for VLSI Design , 1985, IJCAI.

[9]  Reid G. Simmons,et al.  Generate, Test and Debug: Combining Associational Rules and Causal Models , 1987, IJCAI.

[10]  Christian Holzbaur,et al.  Synthesis of Hybrid Languages , 1987, Appl. Artif. Intell..

[11]  Ryszard S. Michalski,et al.  A Theory and Methodology of Inductive Learning , 1983, Artificial Intelligence.

[12]  Werner Horn.  MESICAR - A medical expert system integrating causal and associative reasoning , 1989, Appl. Artif. Intell..

[13]  Andrea Pohoreckyj Danyluk,et al.  The Use of Explanations for Similarity-based Learning , 1987, IJCAI.

[14]  Gerhard Widmer,et al.  Using Plausible Explanations to Bias Empirical Generalizations in Weak Theory Domains , 1991, EWSL.

[15]  John R. Anderson,et al.  MACHINE LEARNING An Artificial Intelligence Approach , 2009 .

[16]  Luc Steels,et al.  Diagnosis with a function-fault model , 1989, Appl. Artif. Intell..

[17]  Thomas G. Dietterich,et al.  A Study of Explanation-Based Methods for , 1989 .

[18]  David C. Wilkins,et al.  Knowledge Base Refinement Using Apprenticeship Learning Techniques , 1988, AAAI.

[19]  Edward H. Shortliffe,et al.  Computer-based medical consultations, MYCIN , 1976 .

[20]  Igor Mozetic.  Diagnostic efficiency of deep and surface knowledge in KARDIO , 1990, Artif. Intell. Medicine.

[21]  Jon Sticklen,et al.  Integrating classification-based complied level reasoning with function-based deep level reasoning , 1989, Appl. Artif. Intell..

[22]  Ivan Bratko,et al.  KARDIO - a study in deep and qualitative knowledge for expert systems , 1989 .