SYNTHESIS OF A COMBINED DIAGNOSTIC DECISION RULE IN A MEDICAL DECISION SUPPORT SYSTEM

Abstract

The work is devoted to solving the urgent scientific and technical problem of building a decision support system based on the implementation of the developed model of the diagnostic decision rule by means of modern information technologies, the use of which made it possible to ensure the operability of the system on various hardware platforms under the control of various operating systems. Based on the analysis of the methods which are used to construct decision rules in decision support systems, the components of the combined decision rule are proposed, expressing two approaches to the formulation of a diagnostic conclusion: objective, based on the analysis of the training sample, and subjective, based on expert information about the structure of symptom complexes. The aim of the study is to synthesize a combined decision rule based on the method of comparison with a prototype, which would take into account both the objective and subjective components of the diagnosis process. Results. It was developed a mathematical model of the combined diagnostic decision rule and was substantiated the choice of its components in the work. The method of comparison with the prototype, in which the diagnosed states are represented by their prototypes in the feature space, was chosen as an objective component. The expert information on the structure of symptom complexes is formalized by presenting the symptom complex of diseases with numerical intervals of linguistic variables. Variants of accounting of expert assessments on the structure of symptom complexes when calculating the coordinates of class prototypes are considered. Requirements for the functionality of the system are formulated, design tools, the main development platform (Java), and the database management system (MySQL) are defined. The design of a decision support system and a comprehensive check of the developed system on real medical data were carried out, which confirmed the efficiency of the system