Systematic knowledge base design for medical diagnosis

Oksana Senyk, Ramesh S. Patil, Frank A. Sonnenberg

Research output: Contribution to journalArticlepeer-review

9 Scopus citations

Abstract

Experienced diagnosticians draw on a rich variety of reasoning techniques, ranging from the association of symptoms and diseases to causal reasoning about disease mechanisms and first-principle analysis grounded in basic science. The entire range of diagnostic reasoning strategies is also necessary for a computer program to be truly proficient and robust. The development of such a program has been impeded by the inherent complexity of the domain and the consequent lack of an adequate methodology for knowledge organization and integration. We present a methodology for structuring medical knowledge and managing its complexity. We illustrate this methodology in the context of an experimental knowledge base in the domain of jaundice. We believe that this systematic knowledge base design will support the development of automated reasoning methods that span the entire range of reasoning techniques used by physicians.

Original languageEnglish (US)
Pages (from-to)249-274
Number of pages26
JournalApplied Artificial Intelligence
Volume3
Issue number2-3
DOIs
StatePublished - 1989
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Systematic knowledge base design for medical diagnosis'. Together they form a unique fingerprint.

Cite this