Information Analysis for Medical Expert Systems

Summary

Much attention has been given to the deductive methods appropriate for medical diagnosis, but much less has been paid to the data structures required to support them. In this paper we apply the linguistically oriented information analysis technique NIAM to the problem and demonstrate how such a conceptual approach could be used for history taking, knowledge acquisition, and diagnosis. We outline the underlying structures in which medical knowledge is traditionally expressed, and use cardiorespiratory disorders as examples. The acyclic network structure of diagnostic categories suggested by this analysis is compared to traditional hierarchical approaches.

Den für die medizinische Diagnostik geeigneten deduktiven Methoden ist viel Aufmerksamkeit zuteil geworden, viel weniger jedoch den zu ihrer Unterstützung erforderlichen Datenstrukturen. In dieser Arbeit wenden wir die linguistisch ausgerichtete Informationsanalysetechnik NIAM auf das Problem an und zeigen auf, wie solch ein begrifflicher Ansatz für die Anamneseerhebung, Wissenserfassung und Diagnose benutzt werden könnte. Die mit dieser Analyse vorgeschlagene azyklische Netzstruktur diagnostischer Kategorien wird mit herkömmlichen hierarchischen Ansätzen verglichen.

Key-Words:

Information Analysis - Expert Systems - Medical Computing NIAM - Diagnostics

Schlüssel-Wörter:

Informationsanalyse - Expertensysteme - Medizinische Informatik - NIAM-Modell - Diagnostik

• References

• 1 Aikins J. S.. Prototypical Knowledge for Expert Systems. Artif. Intell 1983; 20: 163-210.
• 2 Dombal F. T.de, Leaper D. J., Stani-land J. R., Horrocks J. C. Computer-aided Diagnosis of Acute Abdominal Pain. Brit. med. J II 1972; 9-13.
• 3 Glasziou P. P., Vermeir D.. The Conceptual Walk: Schema Directed Data and Knowledge Acquisition without Programming. (In preparation)
• 4 Nijssen G. M.. An Architecture for Knowledge Base Systems. Proc. SPOT-2 Conf 1981
• 5 Nijssen G. M., Vermeir D.. A Procedure to Define the Object Type Structure of a Conceptual Schema. Inform. Syst 1982; 7: 329-336.
• 6 Pauker S. G., Gorry G. A., Kassirer J. P., Schwartz W. B.. Towards the Simulation of Clinical Cognition. Amer. J. Med 1976; 60: 981-995.
• 7 Prabhakaran N., Vermeir D.. On the Generation of Database Schemata. Austr. Comput. J 1983; 15: 91-102.
• 8 Rogers W., Ryack B., Moeller G.. Computer-aided Medical Diagnosis: Literature Review. Int. J. bio-med. Comput 1979; 10: 267-289.
• 9 Shortliffe E. H., Buchanan B. G., Feigenbaum E. A.. Knowledge Engineering for Medical Decision Making: A Review of Computer-based Clinical Decision Aids. Proc. IEEE 1979; 67: 1207-1223.
• 10 Szolovits P., Pauker S. G.. Categorical and Probabilistic Reasoning in Medical Diagnosis. Artif. Intell 1978; 11: 115-144.
• 11 Verheijen G. M. A., Bekkum J.van. NIAM: An Information Analysis Method. In Olle T. W., Sol H. G., Verrijn-Stuart A. A.. (Eds.) Information System Design Methodologies: A Comparative Review, pp. 537-589. Amsterdam: North-Holland; 1982
• 12 Weinstein M. C, Fineberg H. V. Clinical Decision Analysis. Philadelphia: W. B. Saunders; 1980