Methods Inf Med 1990; 29(01): 30-40 DOI: 10.1055/s-0038-1634764
Knowledge-based systems
Schattauer GmbH
Proposed Methodology for Knowledge Acquisition: A Study on Congenital Heart Disease Diagnosis
F. B. Leãot
1
Institute de Cardiologia do Rio Grande do Sul, Porto Alegre, Brazil
,
F. A. Rocha
2
Centro de Informática em Saúde da Escola Paulista de Medicina, São Paulo, Brazil
› InstitutsangabenThe authors express their gratitude to Prof. M. L. Leāo for the revision of the English text, as well as to Ms. Helena Rossi for the proper organization of the bibliography.
“Knowledge and human power are synonymous, since the ignorance of the cause frustrates the effect:…“
Francis Bacon1
This paper proposes a methodology for knowledge acquisition (KA) from multiple experts, in an attempt to elicit the heuristic rules followed by the physician in diagnosing twelve frequently occurring congenital heart diseases (CHD). Twenty-two pediatric cardiologists and twenty-three general cardiologists were interviewed with this technique; 274 interviews were conducted, 169 with the 22 experts, 105 with the 23 non-experts. A graph formalism was employed to represent their reasoning model, leading to the construction of a “mean reasoning model” for each diagnosis, separately for experts and non-experts. The results indicate that experts, compared to non-experts, tend to build knowledge representation models (KRM) that are smaller and less complex. Qualitative differences in information utilization between the two groups were also observed. Entropy analysis suggests a greater objectivity and cohesion of the experts’ model.
1
Barr A,
Cohen P R,
Feigenbaum E A.
Handbook of Artificial Intelligence (Vols 1-3). Los Altos Calif: Kaufmann; 1981/82.
2
Buchanan B G,
Shortliffe E H.
The context of the Mycin experiments. In: Rule- Based. Expert Systems. The Mycin Experiments of the Stanford Heuristic Programming Project. Reading: Addison-Wesley Publ Comp; 1985: 3-19.
5
Hayes-Roth F,
Waterman D A,
Lenat B D.
An overview of expert systems. In: Building Expert Systems.
Hayes-Roth F,
Watermann D A,
Lenat B D.
Reading Mass: Addison-Wesley Publ Comp; 1983: 3-30.
8
Miller R,
Pople H,
Myers J.
INTERNIST- 1 an experimental computer-based diagnostic consultant for general internal medicine. N Engl J Med 1982; 307: 468-76.
10
Shortliffe E H,
Buchanan B G,
Feigenbaum E A.
Knowledge engineering for medical decison making: a review of computer-based clinical decision aids. Proc IEEE 1979; 67: 1207-24.
15
Reggia J A,
Tuhrim S.
An overview of methods for computer-assisted medical decision making. In: Computer-Assisted Medical Decision Making.
Reggia J A,
Tuhrim S.
eds. New York: Springer Verlag; 1985: 45.
28
Kolodner J,
Kolodner R M.
Using experience in clinical problem solving: introduction and framework. IEEE Trans Syst Man C. ybcrn 1987; SCM-17: 420-31.
29
Kulikowsky C A.
Problems in the design of knowledge bases for medical consultation. In: Computer-Assisted Medical Decision Making.
Reggia A J,
Tuhrim S.
eds. New York: Springer-Verlag; 1985: 38-48.
31
Leão B.
Construcāo da base de conhecimento de um sistema especialista de apoio ao diagnóstico das cardiopatias congênitas (Ph D Thesis). Sāo Paulo: Escola Paulista de Medicina; 1988
32
Leāo B F,
Lucchese F A,
Rocha A F.
A methodology proposal of knowledge acquisition. In: Proc Seventh Intern Congr Med Inform Europe, Rome 1987; 1042-50.
39
Van Bemmel J H.
Formalization of medical knowledge, the basis for diagnostic strategies and expert systems. In:
Van Bemmel G J,
Grémy F,
Zvarova J.
eds. Medical Decision Making: Diagnostic Strategies and Expert Systems.. Amsterdam: North-Holland Publ Comp; 1985: 1-11.
40
Wielinga B J,
Breuker J A.
Interpretation of verbal data for knowledge acquisition. In:
O’Seha T.
Advances in Artificial Intelligence. Amsterdam: North-Holland Publ Comp; 1985: 3-12.
43
Roch A F.
Toward a theoretical and experimental approach of fuzzy learning. In:
Gupta M M,
Sanchez E.
eds. Approximate Reasoning in Decision Analysis. Amsterdam: North-Holland Publ Comp; 1982: 191-9.
