A Method for the Acquisition of Formalized Knowledge in Pathology

Abstract

A tool is introduced for the acquisition of pathology knowledge in a formalized form, directly by the expert. Formalization of the knowledge is intended to make descriptive pathology knowledge more suitable for computerized diagnostic support since a formal representation of knowledge allows more extensive indexing, hence more flexible access. The knowledge acquisition (KA) tool also provides a useful research instrument to investigate to what extent pathology knowledge can be made explicit, to what degree ambiguity is present, in what way experts differ when formalizing knowledge, and whether it is feasible to incrementally acquire decision criteria on the basis of the formalized descriptive knowledge.

Crucial in the design of the KA tool is the incorporated meta-knowledge, which is reflected by the knowledge-base structure and is used to elicit knowledge from the expert. Knowledge is acquired from the expert via a menu-driven user interface, which follows the general steps of the pathologist when describing a case. The paper discusses the considerations underlying the design, the implementation of the KA tool, and the research goals.

Key-Words

Knowledge Acquisition - Knowledge Formalization - Computer-Assisted Diagnosis - Pathology

• REFERENCES

• 1 van Ginneken AM, Baak JPA, Jansen WJ, Smeulders AWM. Evalution of a diagnostic encyclopedia workstation for ovarian pathology. Submitted for publication in Hum Pathol.
• 2 Buchanan BG, Shortliffe EH. Rule-Based Expert Systems: The MYCIN Experiments of the Stanford Heuristic Programming Project. Reading MA: Addison-Wesley; 1984
• 3 Alvey PL, Graves MF. Oberservations on the development of a high performance system for leukemia diagnosis. In: Bramer MA. ed. Research and Development in Expert Systems 111. Cambridge University Press; 1986: 99-110.
• 4 Conference digest of: The First International Conference on Artificial Intelligence Systems (EXPERT SYSTEMS) as Diagnostic Consultants for the Cytologic and Histologic Diagnosis of Cancer. Universal City CA: 1987
• 5 Conference digest of: The Second International Conference of Artificial Intelligence Systems (EXPERT SYSTEMS) as Diagnostic Consultants for the Cytologic and Histologic Diagnosis of Cancer. Chicago ILL: 1988
• 6 Hayes-Roth F. Rule-based systems. Comm ACM 1985; 28: 921-32.
• 7 Kingsland LC, Lindberg DAB, Sharp GC. Anatomy of a knowledge-based consultant system: AI/RHEUM. M.D. Computing 1986; 03: 18-26.
• 8 Potter B, Ronan SG. Computerized dermatopathologic diagnosis. J Am Acad Dermatol 1987; 17: 119-31.
• 9 Miller RA, Pople HE, Myers JD. INTER-NIST-I, An experimental computer-based diagnostic consultant for general internal medicine. N Eng J Med 1982; 307: 468-76.
• 10 Horvitz EJ, Heckerman DE, Nathwani BN, Fagan LM. Diagnostic strategies in the hypothesis-directed PATHFINDER system. In: Proceedings of The First Conference on Artificial Intelligence Applications. New York: IEEE Computer Society; 1984: 630-6.
• 11 Musen MA, van der Lei J. Knowledge engineering for clinical’consultation programs: modeling the application area. Meth Inform Med 1989; 28: 28-35.
• 12 Gaines BR. An overview of knowledge-acquisition and transfer. Int J Man-Machine Studies 1987; 26: 453-72.
• 13 Hunter L, Silbert JA. Progress Report on IVY: A learning system for intelligent information retrieval in pathology. Artificial Intelligence in Medicine Workshop; Yale University New Haven CT: 1987
• 14 Walton JD, Musen MA, Combs DM, Lane CD, Shortliffe EH, Fagan LM. Graphical access to medical expert systems: III. Design of a knowledge acquisition environment. Meth Inform Med 1987; 26: 78-88.
• 15 Gevarter B. The nature and evalution of commercial expert system building tools. Computer May 1987; 24-41.
• 16 Vittal J. Languages for use in artificial intelligence research. Analyt Quant Cytol Histol (accepted for publication).
• 17 Salzman GC, Krall RB, Marinuzzi JG. Knowledge engineering software. A demonstration of a high-end tool. Anal Quant Cytol Histol 1988; 10: 219-224.
• 18 van Melle W. A domain-independent production-rule system for consultation programs. In: Proceedings of the Sixth International Joint Conference on Artificial Intelligence. Tokyo: 1979: 260-2.
• 19 Musen MA. Generation of visual languages for development of knowledge-based systems. In: Korfhage RR, Jungert E. Ichikawa eds. Visual Languages and Applications. Vol II, New York: Plenum; in print.
• 20 van Ginneken AM, Smeulders AWM. Reasoning in uncertainties: an analysis of five strategies and their suitability in pathology. Analyt Quant Cytol Histol. (accepted for publication).
• 21 Gammerman A, Creaney N. Modelling of uncertainty in expert systems. Second International Expert Systems Conference. Learned information 1986; 265-74.
• 22 Kong A, Barnett GO, Mosteller F. How medical professionals evaluate expressions of probability. N Eng J Med 1986; 315: 740-4.
• 23 Toogood JH. What do we mean by “usually”?. Lancet 1980; 01: 1094.
• 24 Musen MA. Automated Generation of Model-Based Knowledge-Acquisition Tools. London: Pitman; San Mateo CA: Morgan Kaufmann; 1989
• 25 Epitool Development Environment. (Copyright 1986 by Epitcc AB), S:t Larsgatan 12, S-582 24 Linkoping, Sweden.:
• 26 Fikes R, Kehler T. The role of frame-based representation in reasoning. Comm ACM 1985; 28: 904-20.
• 27 Minsky M. A framework for representing knowledge. In: Winston PM. ed. The Psychology of computer vision. New York: McGraw-Hill; 1957: 211-77.
• 28 Serov SF, Scully RE, Sobin LH. Histological typing of ovarian tomors. In: International Histological Classification of Tumours. Vol 9. Geneva: World Health Organization; 1973: 37-54.
• 29 Kolodner JL. Towards an understanding of the role of experience in the evolution from novice to expert. Int J Man-Machine Stud 1983; 19: 497-518.
• 30 Leao BF, Rocha AF. Proposed methodology for knowledge acquisition: A study on congenital heart disease diagnosis. Meth Inform Med 1990; 29: 30-40.