Category Archives: Biotechnical and medical systems

DESIGNING REFERENCE INFORMATION SYSTEM FOR MEDICAL LABORATORY


UDC 004.415.2
DOI:10.26102/2310-6018/2020.30.3.037

E.Y. Sobolevskaya, D.A. Kiikova

The article is discusses to the design of a reference information system for a medical laboratory evidence from «Unilab» LLC, Vladivostok. According to research of existing medical information systems, mainly implemented systems is used in medical organizations in which patients are receiving, or there are directories that do not meet the requirements of the laboratory. The system under review will provide access to complete and up-to-date medical research information to company employees, improve the quality of call center consultations, and speed up the introduction of changes to medical research information on the company’s website and in 1C system. As a result of the work, user classes were identified and their characteristics described, requirements (business requirements, user requirements, functional requirements) of users were identified using the following methods: interviewing, document analysis, analysis of the user interface of the company’s information systems. The reference information system was designed using the UML modeling language according to the identified requirements according to the ICONIX methodology, the following diagrams were presented: use case diagrams, suitability diagrams, sequence diagrams, and a class diagram. In addition to the diagrams of the selected methodology, a contextual data flows diagram was constructed. Designed prototypes of user interfaces (block diagrams of pages).

Keywords: reference information system, designing, information technology, ICONIX, medical laboratory, healthcare digitalization.

Full text:
SobolevskayaKiikova_3_20_1.pdf

PREDICTING CORONARY HEART DISEASE IN LOCOMOTIVE CREW EMPLOYEES BASED ON HYBRID FUZZY MODELS


UDC 616.5-002
DOI:10.26102/2310-6018/2020.30.3.034

N.A. Korenevsky, D.A. Mednikov, S.N. Rodionova, V.V. Starodubtsev

The aim of the study is to improve the quality of predicting coronary heart disease in railway locomotive crews by developing hybrid fuzzy mathematical models that work under conditions of incomplete and fuzzy description of the object of research. Taking into account the poorly formalized structure of the studied class of States, the technology of soft computing and, in particular, the methodology for the synthesis of hybrid fuzzy decision rules, which has proven itself well in solving problems with a similar data structure and type of uncertainty, is chosen as the basic mathematical apparatus. The chosen synthesis method allows us to take into account the multiplicative effect of heterogeneous and unstable endogenous and exogenous risk factors on the human body in the locomotive cabs. The obtained mathematical models for predicting ischemic heart disease in locomotive crew workers take into account cabin ergonomics, levels of psycho-emotional stress and fatigue, mixed electromagnetic fields in combination with individual risk factors for systemic ischemic damage as initial data. In the course of mathematical modeling and expert evaluation, it was shown that the obtained predictive model provides confidence in the correct forecast of at least 0.89, which is a fairly “good” result for medical diagnostics tasks.

Keywords: mathematical model, fuzzy logic, forecasting, locomotive crew, coronary heart disease.

Full text:
KorenevskySoavtors_3_20_1.pdf

SIMULATION OF EPIDEMICS: AGENT-BASED APPROACH


UDC 004.94, 616.9
DOI:10.26102/2310-6018/2020.30.3.030

A.F. Ageeva

The consequences of the epidemics can be extremely negative, causing significant social and economic losses. The perspectivity of using agent-based models for these purposes are substantiated using agent-based models of epidemics developed by foreign researchers as examples. An analysis of the architecture of agent-based models of epidemics is carried out, which allows determining the key components for modeling epidemic processes. The advantages of the agent-based approach of simulation are identified, which allow modeling the dynamics of the infectious diseases spread in a heterogeneous synthetic population as close to real society as possible, as well as reproducing numbers of patterns and mechanisms of transmission of specific contagious diseases, taking into account demographic, socio-economic and spatial factors. Applying the agent-based approach provides an opportunity to study the progression of epidemic and infectious processes at a micro-level, as well as run scenarios of epidemic outbreaks, test varied strategies for controlling the epidemic, and assess the impact of multicomponent intervention strategies on the epidemic dynamics.

Keywords: agent-based modeling, computational epidemiology, agent-based models of the epidemic spread.

Full text:
Ageeva_3_20_1.pdf

COMPARISON OF THE EFFICIENCY OF DIFFERENT SELECTING FEATURES METHODS FOR SOLVING THE BINARY CLASSIFICATION PROBLEM OF PREDICTING IN VITRO FERTILIZATION PREGNANCY


UDC 519.683, 519-7
DOI:10.26102/2310-6018/2020.30.3.025

S.L. Sinotova, O.V. Limanovskaya, A.N. Plaksina, V.A. Makutina

Determination of the range of factors affecting the object of research is the most important task of medical research. Its solution is complicated by a large amount of diverse data, including extensive anamnestic information and data from clinical studies, often combined with a limited number of observed patients. This work is devoted to the comparison of the results obtained by various feature selection methods for the search for a set of predictors, on the basis of which a model with the best forecast quality was created, for solving the problem of binary classification of predicting the onset of pregnancy during in vitro fertilization (IVF). The data from the anamnesis of women, presented in binary form, were used as features. The sample consisted of 68 features and 689 objects. The signs were examined for the presence of cross-correlation, after which methods and algorithms were applied to search for a selection of significant factors: nonparametric criteria, interval estimate of the shares, Z-criterion for the difference of two shares, mutual information, RFECV, ADD-DELL, Relief algorithms, algorithms based on the permutation importance (Boruta, Permutation Importance, PIMP), feature selection algorithms using model feature importance (lasso, random forest). To compare the quality of the selected sets of features, various classifiers were built, their metric AUC and the complexity of the model were calculated. All models have high prediction quality (AUC above 95%). The best three of them are based on features selected using nonparametric criteria, model selection (lasso regression), Boruta, Permutation Importance, RFECV and ReliefF algorithms. The optimal set of predictors is a set of 30 binary features obtained by the Boruta algorithm, due to the lower complexity of the model with a relatively high quality (AUC of the model 0.983). Significant signs includes: data about pregnancies in the anamnesis in general, ectopic and regressive pregnancies, independent and term childbirth, abortions up to 12 weeks; hypertension, ischemia, stroke, thrombosis, ulcers, obesity, diabetes mellitus in the immediate family; currently undergoing hormonal treatment not associated with the IVF procedure; allergies; harmful professional factors; normal duration and stability of the menstrual cycle without taking medication; hysteroscopy, laparoscopy and laparotomy; resection of any organ in the genitourinary system; is it the first IVF, the presence of any surgical interventions, diseases of the genitourinary system; the age and BMI of the patient; absence of chronic diseases; the presence of diffuse fibrocystic mastopathy, hypothyroidism.

Keywords: feature selection, binary classification problem, small data analysis, machine learning, assisted reproductive technologies.

Full text:
SinotovaSoavtors_3_20_1.pdf

THE STUDY OF THE EFFECTIVENESS OF CLASSIFICATION OF IMAGES OF BONE MARROW CELLS IN COMPUTER SYSTEMS FOR DIAGNOSTICS OF ACUTE LEUKEMIA AND MINIMAL RESIDUAL DISEASE


UDC 004.633.2+611.018.5
DOI:10.26102/2310-6018/2020.30.3.011

V.V. Dmitrieva, N.N. Tupitsyn, E.V. Polyakov, A.D. Samsonova

At present, unmanned vehicle (UV) to provide the accurate navigation under motion are in majority cases depended on GPS, what makes the access to the Network of importance for correct performance in the smart city environment. To implement the smart city conception, the search of alternative techniques of UV localization is vital, since in real conditions GPS signal may be either absent, or its accuracy may be found insufficient to move over a route or to implement maneuvers. One should note that there exist problems for putting in operation the UV technologies: ethical (confidentiality and trust) and cybersecurity. Since in the smart city environment all UVs are to be connected to the Network, then cybersecurity issues also require an additional attention. Cyber threats can provoke violations in both individual UVs and the transportation system as a whole. The paper emphasizes three main categories of UV program systems providing, correspondingly, sampling and processing data, planning, and control. An approach to the UV performance architecture is presented, based on the sampling and processing data, decision making, network and computational multi-level analytics. To increase the UV security in a smart city, the paper proposes to utilize a safety management system based on the factor analysis and risks calculation techniques. To increase the UV security in the part of unobstructed motion, local positioning network models are proposed enabling to work out motion schemes.

Keywords: pattern recognition, image processing, microscopic analysis automation, acute leukemia diagnosis.

Full text:
DmitrievaSoavtors_3_20_1.pdf

MATHEMATICAL MODELS FOR PREDICTING AND EARLY DIAGNOSIS OF DISEASES CAUSED BY ELECTROMAGNETIC FIELDS OF LOW-FREQUENCY RADIO FREQUENCY RANGE


UDC 616.5-002.4
DOI:10.26102/2310-6018/2020.29.2.032

N.A. Korenevsky, A.V. Titova, T.N. Govorukhina, D.A. Mednikov

The paper proposes mathematical models for predicting and diagnosing diseases provoked by exposure to electromagnetic fields of the radio frequency range, which make it possible to control the current state of a person in order to make further decisions about possible correction of body functions, if necessary. Given the incomplete and fuzzy description of the studied class of diseases, soft computing technology was chosen as the basic mathematical apparatus, and, in particular, the synthesis methodology of hybrid fuzzy decision rules, which has proven itself in solving problems with a similar data structure and type of uncertainty. The selected synthesis method allows us to take into account the multiplicative effect of exposure to the human body of electromagnetic fields (EMF) of various modality and intensity, taking into account other endogenous and exogenous risk factors. For powerful and stable EMFs, it is proposed to use a modification of well-known models obtained for industrial power grids. To assess the effect of low-intensity, unstable electromagnetic fields of the radio frequency range on the human body, it is proposed to use fuzzy tabular models and a number of indicators sensitive to the action of the electromagnetic field of the radio frequency range. Such indicators include the state of attention, memory, thinking, as well as the dynamics of changes in the energy state of biologically active points associated with the pathology under study. On the example of electric train drivers, mathematical models for predicting and early diagnosis of the appearance and development of diseases of the nervous system are obtained. It is shown that if additional information about the health status of the subjects is used with electromagnetic risk factors, then confidence in the correct prognosis reaches 0.85, and in the presence of early stages of diseases of the nervous system – 0.95.

Keywords:chronic obliterating diseases of lower limbs, theory of latent variables measurement, optimal treatment regimens.
Full text:
KorenevskySoavtors_2_20_1.pdf

IMPROVING THE QUALITY AND EFFICIENCY OF IDENTIFICATION OF SPECIAL STATES OF MONITORED OBJECTS BASED ON THE DEVELOPMENT OF MATHEMATICAL AND SOFTWARE FOR PROCESSING COMPUTER IMAGES USING LARGE DATABASES

UDC 004.932.2
DOI:10.26102/2310-6018/2020.29.2.030

V.A. Vasilchenko, V.L. Burkovsky

The relevance of the study is due to an increase in human diseases, which are associated with significant socio-economic damage and give a significant burden on health. According to WHO recommendations, a disease prevention system should include prevalence assessment, correction, and risk factor management (WHO, 2009). A special place in this set of measures is occupied by the mass disease monitoring system, both a mechanism for assessing the situation and the need for implementing preventive measures, and a method for monitoring the effectiveness of implemented preventive measures. In this regard, this article considers the creation of an algorithm for processing images of a computer tomography scan of a human lung using software. The leading method to study this problem are neural networks. The article presents a convolutional neural network model of Chexnet X-ray processing developed by scientists from Stanford University. An algorithm for developing a mechanism for analyzing images based on modern x-ray images of organs – computed tomography images, which are obtained using a complex software and hardware complex with ultra-sensitive detectors for recording x-ray radiation, as well as an extensive software package that allows you to obtain images with high spatial resolution, is considered. The developed algorithm is implemented on the basis of the Densenet convolution network, the depth of which is 201 layers. Changes were made to it in the form of using the ReLU activation function (short for English rectified linear unit), which can significantly speed up the learning process and at the same time significantly simplify calculations. As a result, the developed convolutional neural network helps the continuity of data collection, which allows to improve the process of strategic decision-making, to develop action programs in the field of public health.

Keywords:computer image processing, convolutional neural network, ReLU activation function, disease diagnosis.

Full text:
VasilchenkoBurkovsky_2_20_2.pdf

DEVELOPMENT OF A SYSTEM OF MASS MONITORING SPECIAL CONDITIONS

UDC 004.042
DOI:10.26102/2310-6018/2020.29.2.029

V.A. Vasilchenko, V.L. Burkovsky

The relevance of the study is due to the high level of lung disease according to WHO. The annual mortality from chronic lower respiratory diseases is 3 million, and from lung cancer 1.7 million. According to information from the Ministry of Health of the Russian Federation, early diagnosis and planning of preventive measures based on it will significantly reduce the mortality rate from lung diseases and improve the quality of life of the population. To implement the tasks of mass processing of medical information, increase the effectiveness of treatment and prophylactic measures to detect lung diseases in the early stages, it is proposed to create a software package. The developed software makes it possible to assess the situation in the studied territorial area and monitor both the state of health and the effectiveness of measures taken.The article presents methods for automating the analysis of laboratory analysis data, as well as research data of a computer tomograph.The materials of the article are of practical value for medical institutions, allowing you to identify lung pathologies in the early stages, as well as for decision centers, where the quality of medical services is assessed by age and gender groups, both in each region individually and at the state level whole.

Keywords:computer image processing, convolutional neural network, ReLU activation function, disease diagnosis.

Full text:
VasilchenkoBurkovsky_2_20_1.pdf

DECISION SUPPORT SYSTEM FOR DETERMINING THE DOSAGE OF MEDICATIONS IN THE TREATMENT TECHNOLOGY OF PREECLAMPSIA OF PREGNANT WOMEN


UDC 004.891
DOI:10.26102/2310-6018/2020.29.2.017

M.V. Grankov, I.A. Tarasova

The problem of preeclampsia is one of the urgent in modern obstetrics, since this disease is the most common and serious complication of pregnancy, and the problem of treating severe forms of preeclampsia is one of the most difficult in obstetric anesthesiology and resuscitation. The high mortality rate is based on the lack of accurate knowledge about the pathogenesis of the disease, which depends on many factors, diagnostic criteria, which leads to inadequate therapy and various complications, depending on the timeliness and method of delivery, the volume of anesthetic and resuscitation care. Therefore, the study of methods for constructing automated and expert systems using modern methods of artificial intelligence and allowing to increase the effectiveness of the treatment of preeclampsia of pregnant women is relevant. This article discusses the development of a decision support system for determining the dosage of medications in the treatment technology of preeclampsia of pregnant women based on membership functions of several arguments. As a result of experimental tests, it was found that the relative deviation of the dosages calculated by the decision support system from the dosages established in the comparative tests by a qualified doctor does not exceed five percent. At the same time, the use of the results of the work made it possible to increase the number of severe patients served by one resuscitation doctor by at least two times, by reducing the time to establish a diagnosis.

Keywords:decision support system, diagnostics, treatment technology, preeclampsia of pregnant women, membership function of several arguments.

Full text:
GrankovTarasova_2_20_1.pdf

MODIFICATION OF GENETIC ALGORITHM WITH ADAPTIVE CROSSOVER SWITCHING


UDC 681.3
DOI:10.26102/2310-6018/2020.29.2.009

Y.A. Asanov, S.Y. Beletskaya, Al-Saedi Mohanad Ridha Ganim

The aim of this work is to develop a modification of the adaptive genetic algorithm based on switching crossover in accordance with the degree of elitism of individuals in the population. Despite the enormous amount of research done in the field of evolutionary calculus in recent years, algorithms of this class today have a high prospect of modification. The main aim of research is carried out in order to improve the convergence rate of algorithms (to obtain high-performance optimization methods) and increase the accuracy of the solutions obtained. In the article, for the adaptive tuning of the crossover operator, the concepts of discrete and continuous degree of elitism of individuals are used. In addition, an elitism score is used to adjust the probability of a mutation. This modification has a serious advantage superiority in test problems which are traditionally used to analyze the efficiency of genetic algorithms. The test set used was a quadratic function with three variables, a Rosenbrock function, a step function, a complex fourth-order function with noise, and the Sheckel function. The results of comparing classical genetic algorithms with algorithms using the considered crossover and mutation tuning strategies are presented. An analysis of the results of a computational experiment is presented.

Keywords:genetic algorithm, switching crossover, adaptive mutation tuning, elitism, evolutionary calculus.

Full text:
AsanovSoavtors_2_20_1.pdf