Category Archives: Biotechnical and medical systems

FUZZY MODELS OF THE ESTIMATION OF THE LEVEL OF ERGONOMICS OF TECHNICAL SYSTEMS AND ITS EFFECTS ON THE STATE OF HEALTH OF A HUMAN OPERATOR TAKING INTO ACCOUNT THE FUNCTIONAL RESERVE OF THE BODY

UDC 614.2
doi: 10.26102/2310-6018/2019.24.1.015

N.A.Korenevskiy, S.N.Rodionova, T.N.Govorukhina, M.A.Myasoedova

The paper studies the impact of the ergonomics of technical systems on the emergence and development of occupational diseases of a human operator, taking into account the functional reserve of his body. In view of the complexity of the analytical description of the interaction mechanisms of the human-technical system, a methodology for the synthesis of hybrid fuzzy decision rules, focused on solving poorly formalizable problems, was chosen as the mathematical apparatus of research. In the framework of the chosen methodology, the individual estimates of the ergonomic level by basic indicators are averaged by the functions of the ergonomic level, which are aggregated into final decision rules. Evaluation of the impact of ergonomic level and other significant risk factors is carried out using the appropriate membership functions, which are aggregated into fuzzy models of forecasting and early diagnosis of occupational diseases. Using the example of diseases of the nervous system in drivers of Russian-made tractors, it has been shown that the simultaneous consideration of ergonomic risk factors and the size of the functional reserve with other significant endogenous and exogenous factors helps to improve the quality of decisions made about the health status of the human body. At the same time, confidence in the correctness of the prognosis and early diagnosis exceeds 0.86, which allows us to recommend the resulting decision-making models in the practice of occupational physicians.

Keywords: : ergonomics, functional reserve, health status, membership functions, fuzzy logic, prediction, early diagnosis.

Full text:
KorenevskiySoavtori_1_19_1.pdf

A MATHEMATICAL MODEL OF THE ASSESSMENT OF THE SEVERITY OF GENITAL HERPES ON THE BASIS OF FUZZY LOGIC

UDC 615.47
doi: 10.26102/2310-6018/2019.24.1.009

M.I. Lukashov, E.V Pismennaya, O.Y. Olisova, L.V. Starodubtseva, L.V. Shulga


The work is devoted to the urgent problem of improving the quality of medical care for the population suffering from genital herpes due to the timely and qualitative assessment of the severity of the disease under study. In the course of the research, a fuzzy mathematical model was obtained, which allows to distinguish four classes of patient’s conditions: patients with clinically undetectable genital herpes; patients with detected traces of herpes; patients with detected herpes; patients with clinically observed herpes. The methodology used in the synthesis of hybrid fuzzy decision rules allows to reliably separate the selected classes of States in the conditions of incomplete and fuzzy representation of the original data with a strongly overlapping structure of classes. The chosen classification system allows to rationalize the choice of treatment regimens depending on the individual condition of patients. As a result of the research it was found that the use of fuzzy logic of decision-making, can improve the quality of decision-making, according to the stages of disease by 10,…, 15% and reduce the duration of treatment by 5,…10%, which allows us to recommend the results for use in medical practice.

Keywords: : mathematical model, genital herpes, fuzzy logic of decision – making, laboratory indicators.

Full text:
LukashovSoavtori_1_19_1.pdf

ANALYSIS OF THE IMPORTANCE OF SURVIVAL PREDICTORS AFTER MYOCARDIAL INFARCTION USING THE CAPLAN-MEIER METHOD

UDC 314.48
doi: 10.26102/2310-6018/2019.24.1.007

I.L. Kashirina, M.A. Firyulina, E.Y. Gafanovich


This article analyzes the nature of the influence of some factors on the survival rate of patients after myocardial infarction (MI). This study is necessary for the subsequent development of algorithms for predicting the risk of mortality from myocardial infarction, as well as planning treatment and preventive measures. Cardiovascular diseases make the largest contribution to the mortality rate of the population, they account for about 33% of the total number of deaths. After analyzing the nature of the influence of some factors, it is possible to draw conclusions that contribute to the reduction of these mortality indicators. The analysis was carried out by the Kaplan-Meier method using the STATISTICA 12 software package, module “Survival Analysis”. For the analysis, a non-personalized sample of patients admitted to hospitals in the Voronezh Region diagnosed with MI in 2015–2017, was supplemented with information on registered deaths after discharge of patients. The study showed that the greatest risk of death in the first five days after the onset of myocardial infarction. At the same time, 20-day survival is observed in 86% of patients undergoing MI. The analysis showed that the history of the disease arterial hypertension does not affect mortality in myocardial infarction. Gender of the patient is also not important. The effect of thrombolytic therapy is controversial (does not affect or worsens the prognosis of survival).

Keywords: : Kaplan-Meier method, statistics, survival analysis.

Full text:
KashirinaSoavtori_1_19_1.pdf

OPTIMIZATION OF SCHEMES OF MEDICAL AND RECREATIONAL ACTIVITIES FOR CHRONIC OBLITERATING DISEASES OF ARTERIES OF THE LOWER EXTREMITIES USING THE THEORY OF MEASUREMENT OF LATENT VARIABLES

UDC 616.5-002.4

A.V.Bykov , N.A.Korenevsky , A.I.Kolesnik, T.N.Govorukhina


The aim of the proposed study is to increase the effectiveness of medical treatment activities of patients with chronic obliterating diseases of the arteries of the lower limbs, including their malignant development – critical ischemia of the lower limbs, due to the use of adequate mathematical methods. As an adequate mathematical apparatus, the theory of measuring latent variables with the G.Rush model is chosen, with the help of which hidden connections are established between known variables (indicator variables) and a variable that does not have an explicit analytic connection with indicator variables, but in relation to which, at a conceptual level, it is known , that such a connection can exist. This variable is called hidden or latent. From the point of view of the choice of the optimal schemes of medical and recreational activities, specific drugs, their dosage, rates and methods of administration, etc. serve as indicator variables, and the effectiveness of treatment as a latent variable. The evaluation of the effectiveness of medical and recreational activities selected at the expert level is provided by the interactive package RUMM 2020, which implements the model of G. Rush, which processes the initial statistical information that was formed during five years when observed by 400 patients of the Kursk Regional Clinical Hospital suffering from different stages of the HOZANK and receiving various treatment regimens. The effectiveness of the treatment measures was controlled by the change in the intensity of the pain syndrome in the lower limbs according to the author’s questionnaire.Using the RUMM 2020 package, it was found that, as effective drugs in the treatment of chronic obliterating diseases, it is advisable to use a combination of such drugs as alprostan, vesel-duf, fractiparin, actovegin, 6% reforming, pradax and ethoxidol. In the online mode of experts with the RUMM 2020 package for these drugs, the treatment regimens were refined and it was shown that the intensity of the pain syndrome, the effectiveness of treatment for newly received treatment regimens is increased by an average of 75%, which allows them to be recommended to the medical practice of vascular surgeons and angiologists.

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

Full text:
BykovSoavtors_4_18_2.pdf

NEURAL NETWORK MODELING OF THE PROCESS OF SELECTING A PATTERN FOR THE TREATMENT OF PATIENTS WITH CHRONIC PYELONEPHRITIS AND UROLITHIASIS

UDC 681.3

K.O. Levenkov, E.N. Korovin, E.I. Novikova


The article deals with the basic aspects of designing a neural network model for choosing a treatment regimen for chronic pyelonephritis and urolithiasis. One of the most common non-specific chronic kidney diseases is a chronic pyelonephritis. Currently, mathematical modeling of biological systems is one of the main directions of mathematical methods in medical practice. The paper demonstrates network operation. The construction of a multilayer perceptron was carried out on the basis of the Neural Networks module in the Statistica program. The resulting neural network model has 5 outputs, each of which is identical to the types of treatment present in the training set. The developed model provides an opportunity to choose one of 5 types of treatment: Y1 – conservative therapy with antibacterial, antispasmodic and anti-inflammatory drugs in combination with physiotherapeutic procedures; Y2 – conservative therapy in combination with surgical treatment in the amount of contact lithotripsy (KLT); Y3 – conservative therapy in combination with surgical treatment in the volume of distant lithotripsy (DLT); Y4 – conservative therapy in combination with surgical treatment in the amount of percutaneous nephrolitholapaxy (PNLT); Y5 is an open surgery and conservative treatment. The developed model makes it possible to choose one of 5 types of treatment. The reliability of this model was 94%.

Keywords: : neural network modeling, chronic pyelonephritis, urolithiasis, multilayer perceptron, neuron, test set, pattern recognition system.

Full text:
LevenkovSoavtors_4_18_1.pdf

STUDY OF THE SPREAD OF TRANSVERSE ELASTIC WAVES IN BIOLOGICAL TISSUES

UDC 534.222

А.I. Mikhraliyeva, V. A. Karstin, N.P. Zagray, N.N. Chernov


The method of excitation of transverse acoustic waves in biological tissues for the purpose of visualization of the subcutaneous structures of the peripheral vascular system is considered. The separation of longitudinal and transverse acoustic waves is carried out by measuring the speed of sound over the time of its propagation in the measuring and reference lines. A laboratory setup for the excitation of a transverse acoustic wave in biological tissues and a technique for measuring the characteristics of the propagation of transverse waves are described. The installation had two acoustic measuring and reference lines. A high-frequency pulse was simultaneously applied to the piezoelectric transducers of the measuring line and the reference line. The measurements were carried out first with no sample in the measuring line, then with a tissue sample. The readings of the micrometer screw, which determine the thickness of the reference liquid layer, were recorded. The velocity of the transverse wave in biological tissue was calculated according to the equality of the time gaps of the passage of acoustic waves through the sample of biological tissue and the layer of reference fluid. The results of measuring the speed of propagation of transverse waves in various biological tissues are given. Measuring the speed of propagation of transverse elastic waves in various samples of healthy and pathological tissues allows you to create a database of velocities of propagation of ultrasonic waves, which makes it possible to conduct an early and reliable diagnosis of pathologies.

Keywords: : transverse and longitudinal acoustic waves in biological tissue, the peripheral vascular system, visualization.

Full text:
MikhraliyevaSoavtors_4_18_1.pdf

MATHEMATICAL MODELS FOR PREDICTION AND EARLY DIAGNOSIS OF DISEASES OF THE NERVOUS SYSTEM PROVOKED BY CONTACTS WITH TOXIC CHEMICALS

UDC 615.47

L.V. Starodubtseva, R.V. Stepashov, L.P. Lazurina, R.A. Krupchatnikov,
L.V. Shulga


The work is devoted to the urgent problem of improving the quality of medical care to workers in contact with toxic chemicals in the process of their production or during the production process. In the course of studies, it was shown that contact with toxic chemicals causes a range of diseases among which occupy a significant place disease of the nervous system. One of the ways to combat this class of diseases is timely and qualitative prognosis and early diagnosis allows to prescribe adequate schemes of prevention and treatment. Taking into account the multiplicative and prolonged effect of toxтв ic chemicals on the human body, as well as the heterogeneity and fuzziness of the description of the studied classes of States for the synthesis of the relevant decision rules, the methodology of synthesis of hybrid fuzzy decision rules developed at the Department of biomedical engineering of Southwestern state University was used. In the course of application of this methodology mathematical models of forecasting of emergence of diseases of nervous system with the reliable three-year forecast and diagnostics of early stages of this class of diseases were received. In the course of statistical tests on representative control samples, it was shown that the confidence in the decisions made exceeds 0.85. Practical applications of the proposed method and models will improve the quality of medical services to employees of the agro-industrial complex by increasing the working age and reducing disability.

Keywords: : models, forecasting, early diagnostics, diseases, nervous system, toxic chemicals.

Full text:
StarodubzevaSoavtors_4_18_1.pdf

MATHEMATICAL MODELS OF THE CHOICE OF THE PATTERNS OF PREVENTION OF THE RECURRENCE OF GANGRENE OF THE LOWER LIMBS

UDC 615.47

A.V. Bykov, N.A. Korenevsky, S.A. Parkhomenko, A.V. Boytsov, E.V. Cymbal, L.V. Starodubtseva


The work is devoted to the actual problem of improving the quality of care for patients suffering from critical ischemia of the lower extremities, turning into gangrene, which may result in amputation and even death. In the course of the research it was shown that the task of predicting the recurrence of lower extremity gangrene belongs to the class of poor results, which was the basis for choosing the method of synthesis of hybrid fuzzy decision rules as the basic method for studying the methodological synthesis. During the synthesis of fuzzy decision rules, the choice of informative features obtained during surveys and inspections, instrumental and laboratory research methods was justified. As the basic elements of fuzzy decision rules applied to a class of high risk of gangrene recurrence, which are aggregated into a fuzzy rule for assessing the confidence that the patient will have a relapse of the lower extremities. : Scale of confidence in the development of gangrene: – confidence in the recurrence of gangrene; II-medium confidence in the recurrence of gangrene; III – high confidence in the recurrence of gangrene; IV – very high confidence in the recurrence of gangrene. The classification decision is made based on the maximum value of the prediction functions. For each of the selected classes, the appropriate scheme for the prevention of lower extremity gangrene recurrence, whose effectiveness was tested using measurement theory, as well as the analyzed mathematical model of their choice depending on the degree of lower extremity gangrene recurrence. In the course of statistical tests, it was shown that, compared with traditional schemes to prevent the use of the proposed technologies, increase the rate of positive results by 2.4 times (58%) and reduce the risk of limb amputation by 2.5 times (73%). The results obtained guarantee the proposed mathematical models for use in the practice of vascular surgeons and angiologists.

 

Keywords: : gangrene, lower limbs, prediction, mathematical model, fuzzy logic, prevention, model G. Rush.

Full text:
BykovSoavtors_4_18_1.pdf

FORECASTING OF THE GENERATION OF THE LOWER LIMBS ON THE BASIS OF HYBRID FUZZY MODELS

UDC 616.31

N.A. Korenevskiy, T.I. Subbotina, I.I. Khripina, S.A. Parkhomenko,
S.N. Rodionova


The work is devoted to the urgent problem of improving the quality of care for patients suffering from critical ischemia of the lower limbs, passing into gangrene, which can result in amputation and even death. In the course of the studies, it was shown that the task of predicting the origin and development of gangrene of the lower limbs belongs to the class of poorly formalizable problems with an indistinct data structure, which served as the basis for choosing as a basic research apparatus the methodology for the synthesis of hybrid fuzzy decision rules. During the synthesis of fuzzy decisive rules, the selection of informative signs obtained during surveys and examinations, instrumental and laboratory methods of investigation was justified. As the basic elements of fuzzy decision rules, the functions of belonging to the class of high risk of gangrene development are obtained, which are aggregated into an unclear rule of confidence assessment that the patient will develop gangrene of the lower limbs. On a scale of confidence in the development of gangrene, experts determined the secondary functions of belonging to such predictable classes of patient conditions as: I – low confidence in gangrene development; II – moderate confidence in the development of gangrene; III – high confidence in the development of gangrene; IV – very high confidence in the development of gangrene. The decision to classify is taken based on the maximum value of prognostic membership functions.The performed mathematical modeling and expert evaluation of the fuzzy models obtained showed that their predictive confidence is at least 0.9. The same quality of forecasting was confirmed during statistical tests on control samples of 100 persons per class for such indicators as diagnostic specificity, sensitivity and efficiency, as well as prognostic significance of positive and negative results.
The results obtained make it possible to recommend the proposed mathematical models for use in the practice of cardiovascular surgeons and angiologists.

Keywords: : gangrene, lower extremities, prediction, mathematical model, fuzzy logic.

Full text:
KorenevskiySoavtori_4_18_1.pdf

PREDICTING THE EMERGENCE AND RECURRENCE OF BRAIN STROKE BASED ON HYBRID FUZZY MODELS

UDC 616-005.4

N.A. Korenevskiy, A.V. Bykov, E.V. Tsymbal, V.V. Aksenov, D.S. Rodionov


The work is devoted to the actual problem of improving the quality and efficiency of predicting the occurrence and recurrence of brain stroke by using the methodology of synthesis of hybrid fuzzy mathematical models developed at the Department of biomedical engineering of Southwestern state University.In the course of the conducted research the space of informative signs was formed in three subgroups: data of surveys and examinations; instrumental methods of research; Doppler ultrasound (27 signs in total). In accordance with the General methodology for the synthesis of hybrid fuzzy decision rules using informative features as basic variables in the interactive mode, the corresponding functions of belonging to the classes of high risk of occurrence and recurrence of brain stroke for which, using modified models E. Shortlife synthesized final predictive model.As a result of expert evaluation and mathematical modeling, it was shown that the obtained models of occurrence and recurrence of brain stroke provide confidence in the correct prognosis at the level of 0.9 and higher, depending on the amount and quality of information collected about the patient’s condition. This quality indicator was confirmed during statistical tests on representative control samples, which allows to recommend them for use in the practice of vascular surgeons and angiologists.

Keywords: astroke, cerebral membership function, the confidence in the decision being taken, the prognosis.

Full text:
KorenevskiySoavtori_3_18_1.pdf