All articles by Kobrinskii. B. A.
-
2019 № 4 Knowledge-based diagnostic system for orphan diseases development
The paper discusses the problems of early diagnosis of rare hereditary origin diseases in children, presents a brief description of previously created systems aimed at providing support for physician assistance in diagnosis. The prototype of an expert diagnostic system is presented, the knowledge which combines bibliographic data on clinical cases, the coefficients of modality of signs (based on expert evaluations) and certainty factors for manifestation and severity of signs over four age periods. Such an approach to the formation of a knowledge base allows improving the quality of differential diagnosis of a rare pathology at an early age in order to start treatment on time to prevent the development of pathological manifestations caused by the accumulation of macromolecules in organs and tissues.
-
2020 № 4 Radiological Images in the Construction of Hybrid Intelligent System
So far, the concept of image row or tuples in the development of intelligent systems has been discussed in relation to
the role of phenotypic (external) manifestations of diseases in diagnostics. This study introduces the idea of neuroimaging tuples as a tool to make a prognosis of the course of chronic cerebral ischemia. The phenomenon of leukoaraiosis is analyzed as a radiological feature of chronic brain ischemia and a predictor of stroke. Image tuples are formed from the results of computed tomography, computed tomography angiography, magnetic resonance imaging, of 85 patients with chronic cerebral ischemia. Native computed tomography images were processed with adaptive filtering methods. Computed tomography angiography results were processed through a vesselness filter that allows development of 3D reconstructions of vasculature in leukoaraiosis areas. The problem of fuzzy images, the principles of comparative analysis of images and the possibility of using confidence factors in the image tuples are discussed in the article. A scheme of a hybrid intelligent system that combines traditional logic-linguistic rules and images based on primary information and reconstruction of the original DICOM images in the knowledge base was developed. The sphere of the application is stroke risk prediction using an intelligent system. -
2018 № itm Diagnosis and treatment of liver failure: multiset model
The paper considers the use of multisets or sets with repeating elements in the modeling of diagnosis and treatment of hepatic failure, taking into account various forms of the disease, the stages of its course, variants of therapeutic tactics depending on the form of liver failure. Models “Patient with hepatic failure“ and “Treatment of hepatic failure“ allow to provide an effective selection of personalized medical tactics.
-
2018 № 2 Model of the patient with liver failure for use in meta-analysis, focused on selection of adequate therapy
The features of classification of liver failure in various regions of the world are analyzed. Methods for constructing mathematical models of patients and diseases have been studied. A settheoretical model of the complex clinical presentation of a patient with hepatic insufficiency, used in the process of metaanalysis, is proposed. The model takes into account the etiology and features of the disease course, as well as regional variants of classification of hepatic insufficiency in Russia, Europe, America and Asia. An example of conducting a metaanalysis according to specified criteria is given
-
2016 № 5 Fuzzy in clinical medicine and the need to reflect in expert systems.
At the paper considered of physician problems at describing of subjective clinical characteristics for which there is no single and consistent opinion (certainty factor). Point out to reflection of patients and physicians to describe them. It sets out methods for their formal presentation with the use of logical-linguistic scales and expert certainty factors for creating expert systems.
-
2015 № 3 Register rare chronic lung disease in children.
The article addresses the problem of the computer monitoring of rare (orphan) diseases of the lungs in children. Creating a computer register allows you to monitor and optimize patient monitoring systems with different rare bronchopulmonary diseases, organize rare form of chronic lung disease in children to determine their course of modern features of the dynamics of the disease and prognosis of various therapeutic effects. Register creates the conditions for the analysis of the main causes of diagnostic errors at various stages of specialized medical care, which improves the effectiveness of treatment. The article describes the structure and functions of the register are presented on-screen form.