Development of a Technique for Discrete-Logical Decision-Making in Medical Information Systems

One of the urgent directions in solving medical diagnostic tasks is to develop new and improved decision support systems capable of efficiently processing polymodal data. Humans cannot always process large arrays of medical information and determine an accurate diagnosis in complex situations. Thus, improving the functioning of the industry requires implementing a variety of systems capable of supporting decision-making of one kind or another. The presented technique aims to steadily increase the level and speed, and demonstrate the feasibility of integrating non-classical logic into the structure of the decision-making system in medical research by using non-classical logic complexes. The main advantage of the proposed approach is that it achieves the necessary level of information criteria; in particular, it provides the required information quality, high reliability of the decision, its value, preserves the amount of information, and searches and decision-making take relatively small-time intervals. This paper presents an overview of various non-classical logics and, based on the analytical findings, delineates the optimal choice of logic for each stage in the development of a decision support system. The processing and feedforward structures for DSS are presented based on selected types of non-classical logic. The algorithms presented for solving decision-making problems are based on discrete-logic approximations of a priori and actual data, which are optimal or suboptimal, and they use information and value criteria. The abstraction of any problem situation relies on using means operating with frequency and comparative logic to provide logical approximations of the sought characteristics. The accuracy of the diagnostic decisions reached 97% when using the developments presented in this study.

Doi: 10.28991/HIJ-2024-05-04-010

Full Text: PDF