RUS  ENG
Full version
JOURNALS // Artificial Intelligence and Decision Making // Archive

Artificial Intelligence and Decision Making, 2018 Issue 2, Pages 62–72 (Mi iipr207)

This article is cited in 5 papers

Methods of reasoning and knowledge representation

Certainty factors triunity in the medical diagnostics tasks

B. A. Kobrinskii

Medicine of the Federal Research Center "Informatics and Contro" of the Russian Academy of Sciences, Moscow, Russia

Abstract: The paper suggests approaches to investigating and solving the problem of three factors characterizing the measure of the experts' confidence in the occurrence of symptoms in diseases, the timing of the manifestation of symptoms and the frequency of symptoms in progressive hereditary diseases in five age groups that differ in clinical manifestations (polyvariant character space). Linguistic scales of fuzzy characteristics (interval age and occurrence of signs) and certainty factors should contribute to a more accurate and accurate evaluation of diagnostically significant traits and to increase the effectiveness of diagnosis at different ages. The measure of confidence is determined with respect to each characteristic used for a given nosological form. In the process of assessing risk factors, specific features of experts' thinking are considered – intuition, confidence in their knowledge and reflexivity (regarding emerging hypotheses). Extraction of knowledge is expected from two or more experts. Various stages and variants of group expertise with the participation of a cognitive scientist are considered. Certainty factors are an important condition for increasing the reliability of expert decisions in the diagnosis of orphan hereditary diseases, which does not allow to draw on the extraction of knowledge from the databases of case histories or on a set of literary sources.

Keywords: knowledge engineering, three certainty factors for a feature, fuzzy knowledge, linguistic scales, expert reflexivity, group knowledge extraction, orphan diseases, lysosomal storage diseases.

DOI: 10.14357/20718594180205


 English version:
, 2019, 46:5, 321–327

Bibliographic databases:


© Steklov Math. Inst. of RAS, 2024