Aim. The aim of the study was to consolidate the principles and rules for building a regulatory and reference space based on the analysis of previous phases of implementation to prioritize the development and to create a single digital contour in health care.

Information sources. Data were obtained from the Regulatory Service at the Federal Registry of Regulatory and Reference Information (RRI), regulations of the Russian Ministry of Health in the field of information technology development, and the methodical and conceptual documents of the federal project “Creation of the integrated digital contour in healthcare based on the uniform state health information system”.

Results. The stages of creating a single system of regulatory and reference information in the health sector over the past decade were analyzed taking into account the continuity of goals and objectives consistently presented in the conceptual and strategic documents that define the process of creating unique state health information system, as well as the experience of their solution. The analysis allowed to formulate the basic principles of development, namely: central management, structural unity, functional unity, information unity, and prioritization of tasks. Consolidation of principles and rules provided the basis for a scientific and methodical approach to further development of a single RRI system at the stage of creating a single digital contour in health care and shaping priorities of the development.

Conclusion. At the stage of creating a single digital contour in health care, which has been approached by many countries, including Russia, the importance of a ubiquitous language of communication increases dramatically and, as the events associated with the COVID-19 pandemic have shown, the readiness of information systems directly determines the readiness of society to meet challenges and to protect the population.

The complexity of biological objects makes the development of computerized medical systems a difficult algorithmic decision due to the natural uncertainty inherent in these objects. Human thinking is based on vague and approximate data that can be analyzed to form clear decisions. An exact mathematical model of biological objects may not exist in practice, or such a model may be too complex to implement. In this case, fuzzy logic is a suitable tool for solving the specified problem. The problem of medical diagnosis can be viewed as a classification problem. The article presents a literature review of the use of fuzzy classifiers in diagnostics of cardiovascular diseases. The main advantage of fuzzy classifiers in comparison with other artificial intelligence methods is the ability to interpret the resulting classification result. The review aims to expand the knowledge of various researchers working in the field of medical diagnostics.

The paper presents the service for support of diagnostic decision-making in cardiology. The general principles for the development and conceptual architecture of smart service and its information and software components are described. The features of diagnosis and differential diagnosis of cardiac diseases on the medical portal of the IACPaaS cloud platform are presented.

Aim. To develop and implement into clinical practice six calculators of risk for various cardiovascular diseases in the form of mobile application for iOS/Android and module for the 1C: Medicine software.

Material and Methods. At the premises of Tyumen Cardiology Research Center (TCRC) of Tomsk NRMC, we developed the mobile application for iOS/Android and module for the 1C: Medicine software based on six mathematical models that were invented and patented in our center earlier.

Results and Discussion. The use of mobile application improved the convenience of working with the mathematical formulas and reduces the time for obtaining results of calculations. Implementation of 1C as a programming environment allowed to perform automatic filling out the calculator fields with medical data from individual patients, which significantly simplified and accelerated the rate of work with mathematical models.

Conclusion. The developed mobile application and external processing for 1C allowed to implement research products of TCRC in the form of mathematical formulas into real-life clinical practice. These developments contributed to speeding up the process for acquisition of results and partial automatization of filling out the form fields.

Aim. To evaluate the clinical efficacy and safety of direct oral anticoagulants versus warfarin as part of antithrombotic therapy (ATT), namely, to study the frequency of bleeding and thromboembolic complications in patients with atrial fibrillation (AF) after direct myocardial revascularization in combination with radiofrequency isolation of pulmonary veins.

Material and Methods. A total of 44 patients (36 men) aged 44–77 years (average age of 63.5 ± 7.8 years) with coronary heart disease, indications for direct myocardial revascularization, and AF were included in the study from 2014 to 2016. The observation period was 24 months.

Results. Warfarin was one of the components of ATT in 20 patients (48%). However, the target values of international normalized ratio (INR) within the therapeutic range for over 70% of the time were achieved only in seven patients. Two patients who were taking warfarin without achieving target INR values for 24 months suffered from ischemic stroke. One patient taking warfarin (without regular INR control) had gastrointestinal bleeding requiring hospitalization and conservative therapy; ten patients had minor bleedings (nasal and gingival bleeding). All patients, who suffered from thromboembolic and hemorrhagic complications and had inadequate warfarin intake, were recommended to switch to direct oral anticoagulants (DOAC). Thirteen patients (29%) were administered with DOAC: five patients took rivaroxaban 20 mg/day, four patients took dabigatran 300 mg/day, and four patients took apixaban 10 mg/day. DOAC therapy was administered in combination with one of the antiplatelet drugs (aspirin or clopidogrel). In the case of DOAC administration, only minor bleedings were observed: one patient had hemorrhoidal bleeding and four patients had nasal bleedings, which did not require hospitalization, medical intervention, or suspension of anticoagulant therapy. There were no other adverse events in patients taking DOAC.

Conclusions. Patients administered with DOAC as a part of antithrombotic therapy after coronary bypass surgery and surgical epicardial radiofrequency isolation of the pulmonary veins had lower incidence rates of thromboembolic and hemorrhagic complications compared with the rates in patients taking warfarin. However, no statistically significant differences were found between the groups due to the small sample size.

The aim. To study the features of the breathing process based on the breathing curve analysis in patients with various forms of bronchial asthma using computer visualization methods.

Material and Methods. The experimental data comprised breathing curves registered with the MONITOR device in patients with various bronchial asthma types and a group of apparently healthy people. The original algorithm of spectral-time analysis was used to identify the characteristic features of the breathing curves in each group at the stage of digital processing.

Results. Breathing curves were analyzed and typical images were obtained for the group of apparently healthy individuals and four groups of patients with various types of bronchial asthma (following the classification of E.V. Nemerov). 

Conclusion. A spectral-time analysis allowed us to obtain characteristic “single” graphical images of the breath curve in patients with various forms of bronchial asthma. The resulting images can be used as an additional diagnostic criterion. The algorithm proposed by the authors can also be used in the analysis of any other biosignals.

Purpose. To determine the risk of macrosomia in pregnant women as a function of body weight.

Material and Methods. The study included 754 patients. All patients were divided into three groups. Group 1 included 262 obese patients with an average body mass index (BMI) of 33.1 (31.4; 35.9) kg/m2, aged 30 (27; 34) years. Group 2 comprised 260 overweight patients with an average body mass index of 27.5 (26.4; 28.7) kg/m2, aged 29 (25; 33) years. Group 3 (control) included 232 patients with normal body weight, BMI of 22.6 (21.0; 23.8) kg/m2, aged 28 (25; 31.5) years. Anthropometric data were assessed in all patients with the performance of general clinical and laboratory examinations.

Results. Based on the results of logistic regression analysis for continuous variables, a prognostic model for the birth of a large fetus with a probability of up to 70.3% was constructed.

Aim. The aim of the study was to create a computer decision support system using expert knowledge for the diagnosis of rare hereditary diseases due to the difficulty of their identification at the pre-laboratory stage.

Material and Methods. Descriptions of the clinical picture of lysosomal storage diseases from literature sources were used as the research material. The methods included knowledge extraction, expert assessments, quantization of age intervals, and applied intelligent services to form a knowledge base.

Results. The results of the study include the construction of models for a complex assessment of a sign and an integral assessment of a disease, on the basis of which the comparative analysis algorithm is implemented to assess each of the hypotheses put forward by the system. The results of testing the prototype of the created expert system on a control sample of patients with mucopolysaccharidosis showed the efficiency of 90%. Discussion. In the discussion, several diagnostic systems are considered and their distinction from the system, presented in this work, is shown.

Conclusion. The results of the development of intelligent system based on knowledge for the diagnosis of lysosomal storage diseases are summarized and the perspectives for its development are highlighted.

Introduction. The potential of a new compound in the ongoing drugs discovery process is initially explored using virtual instruments, where its activity is predicted based on its molecular structure.

Aim. This study aimed to evaluate the pharmacokinetic parameters and possible toxicity of isobornyl compounds based on virtual tools.

Material and Methods. Several free Internet resources were used to assess the absorption, distribution, metabolism, excretion (ADME), and toxicity (T) of 2,6-diisobornyl-4-methylphenol (1, Dibornol), 2-hydroxy-3-isobornyl-5-methylbenzaldehyde (2), and 2-((di-n-butylamino) methyl)-6-isobornyl-4-methylphenol (3). Pharmacokinetic properties were calculated on ADMETlab platform. Toxicity and physical properties were evaluated using TEST software based on the structure-property quantification models of organic substances according to structure–property principle. Web server ProTox_II was used for acute toxicity assessment.

Results. Plasma protein binding degrees were 76,9% for (1), 85,9% for (2), and 91,8% for (3). All three compounds were capable of penetrating the blood-brain barrier. Dibornol was identified neither as a substrate nor as an inhibitor of P-glycoprotein unlike (2) and (3). The half-life of all compounds was short (about 2 hours); the clearance was slow (about 2 mL/min*kg). The study showed that (2) and (3) potentially exert the toxic effects during the developmental stage of the organism, while ADMETlab showed potential cardio- and hepatotoxicity for (2) and (3), respectively. All compounds had extremely low solubility in water, which affected the assessments of other indicators by TEST software. The ProTox_II server showed the extremely low toxicity LD50 for all compounds (toxicity class 5).

Purpose of work. An implementation of small-sized high-resolution radar systems is proposed to solve both the problem of access to digital technologies and the development of preventive medicine and telemedicine.

Method of research. The use of ultra-wideband video pulses, stroboscopic receivers, and laptops with specialized software allows to create an inexpensive diagnostic medical device. Working with such a diagnostic medical device does not require participation of highly qualified medical and radio engineering specialists.

Research materials. The block diagram of the diagnostic device and experimental methodology are described. Preliminary tests of the diagnostic device are carried out. A capability to provide a millimeter-accuracy spatial resolution of a human body internal structure is presented. The mathematical model of interaction between the radio pulse and internal in homogeneities in the human body and the principle of processing the reflected signal are described.

Results. The results of obtained measurements are presented as a sequence of time wavelet tomograms where the different wavelet cross-sections in the frequency domain allow to diagnose the state of internal organs based on the spectral characteristics.

Conclusion. Digital representation of diagnostic results makes it possible to model health state and to create and exchange patient databases.

Introduction. The problem of access to medical care remains extremely relevant in many countries in the world nowadays. In this context, it is advisable to optimize patients’ flow, that is, primary and repeated admissions and appointments for preventive and medical care purposes, and information. The document titled “The Standard for Organizing Outpatient Care in the Tomsk Region” was developed to solve this problem in the region. The document regulates the organizational features of providing medical care to the residents in state polyclinics. The document addresses the following: service parameters, issues of routing patient flows, and the procedures for organizing workplaces and specialists’ behavior.

Objective. To evaluate the effectiveness of the solutions proposed in “the Standard for Organizing Outpatient Care in the Tomsk Region” for routing patient flows in outpatient clinics.

Material and Methods. The effectiveness of measures was evaluated for 35 medical organizations with outpatient departments based on the temporal changes in eight indicators in 2018–2019.

Results and discussion. Except for the percentage of children who passed preventive examination out of the number of children subject to preventive examination, positive dynamics were observed for all study parameters. First of all, this observation suggests the adequacy of proposed solutions from the perspective of the health care system, and secondly, it indicates their acceptance by the patient community. However, the extent of growth/decline is extremely uneven depending on the medical organization, which requires further research.

Conclusion. Standardization of patient flow routing within the state regional health system through the issuance of appropriate orders and further monitoring of their implementation is an effective way to increase the medical care availability.

Aim. To develop and implement a decision support system for a software product – medical information system “1C: Medicine” in the form of calculator for assessment of the absolute risk of death from cardiovascular diseases (CVD) and to show the prospects of using this system for patients with coronary artery disease (CAD) after coronary stenting.

Material and Methods. The medical information system “1C: Medicine” software interface was developed in Tyumen Cardiology Research Center. It was designed to assess 10-year absolute total mortality risk from CVD in males of working age (Tyumen Risk Scale (TRS)) to provide medical decision support. The program was tested in 764 male patients from the Prospective Registry of Percutaneous Coronary Interventions (PCI). The mean age of patients was 56.9 ± 8.8 years. All death cases, recorded within a year after PCI (n = 23), were used as the status check variable. The following algorithms were chosen to compare the predictive accuracy of the integrated model: PROCAM and FRAMINGHAM. The Schwarz information test and ROC analysis data were used to assess the predictive accuracy of the models.

Results. The values of Schwarz’s criterion in males were 283 for TRS, 235 for PROCAM, and 490 for FRAMINGHAM model. AUC indicator for TRS was 0.655 (95% CI 0.510–0.800), suggesting the satisfactory quality of resulting model. AUC indicators for FRAMINGHAM and PROCAM algorithms were 0.599 (95% CI 0.442–0.757) and 0.653 (95% CI 0.509–0.796), respectively.

Conclusion. The created TRS, integrated into the medical information system with psychosocial factors, may be quickly and successfully implemented to determine mortality risk in CAD patients within one year after coronary stenting. The TRS has an advantage over the traditional FRAMINGHAM risk scale and non-inferior to the PROCAM scale. Therefore, TRS may be used as a medical decision support program.

Purpose. To assess the frequency of detection of essential hypertension in persons aged over 60 years depending on the socio-economic risk factors.

Material and Methods. A total of 582 people aged 60 to 70 years were studied. All participants were surveyed to determine the level of education, income, professional affiliation, and family composition. Statistical data processing was carried out using Statistica 6.0 software. The significance level for statistical hypothesis testing in the study was <0.05.

Results and Discussion. Hypertension occurred in 87.2% of rural residents and in 84.6% of urban residents (p = 0.429). This condition was diagnosed in 82.7% of men and 86.1% of women (p = 0.339). Regression analysis showed that holding a managerial position was associated with an increase in mean systolic blood pressure (SBP) by 3.1 mmHg (p = 0.013). Formal marriage or common-law marriage was associated with an increase in mean SBP by 2.4 mmHg (p = 0.034) and diastolic blood pressure (DBP) by 2.2 mmHg (p = 0.002). Living in rural areas was associated with decreased mean DBP by 1.66 mmHg (p = 0.015). The prevalence rates of hypertension were 90.5% in widows and 73.7% in women who had never been married (p = 0.031). No statistically significant differences were found between men with different marital status; however, the maximum prevalence of hypertension was observed among divorced men; the minimum prevalence was observed among widowers.

Conclusions. There was no difference in the frequency of detection of hypertension between urban and rural older adults. The highest prevalence of hypertension among women was observed in widows; the lowest prevalence was found in women who had never been married. Among men, the highest prevalence of hypertension was observed in divorced persons; the minimum prevalence was detected in widowers, but the difference was not statistically significant.

Aim. The aim of the study was to select, based on mathematical apparatus of artificial neural networks (ANN), the most sen- sitive parameters for creating an ANN model aimed at prediction of atrial fibrillation (AF) in men with coronary artery disease (CАD).

Material and Methods. The study focused on data of men from the register of coronary angiography with angiographically proven coronary artery disease: the main group comprised 180 men with AF; the comparison group comprised 713 men of comparable age without AF. The ANN mathematical model, a multilayer perceptron with one hidden layer, was used to assess the risk of AF. The initial group of patients was divided into three samples: the training, test, and control samples.

Results. Patients with AF were significantly less likely to be employed in budget organizations (55.0% vs 63.7%, p = 0.040) and more often showed higher (III–IV) heart failure NYHA classes (49.2% vs 21.1%, p < 0.001), higher body mass index (BMI) (30.2 [27.4; 33.2] kg/m² vs 29.0 [26.1; 32.3] kg/m², p = 0.002), and higher echocardiographic indices of the left ventricular (LV) myocardial mass (163.7 [144.5; 192.4] g/m² vs 143.9 [126.1; 169.0] g/m², p < 0.001), left (25.8 [24.1; 29.1] mm/m² vs 25.6 [23.9; 27.5] mm/m², p = 0.020) and right ventricular dimensions, and the left atrial diameter (23.6 [21.7; 25.7] mm/m² vs 21.1 [19.7; 22.7] mm/m², p < 0.001). The group of AF patients had higher rate of hemodynamically significant mitral regurgitation (48.2% vs 14.1%, p < 0.001). In this group of patients, the index of aortic root dimensions (7.7 [16.4; 19.0] mm/m² vs 18.3 [17.8; 20.0] mm/m², р = 0.002) and LV ejection fraction (EF) were lower (49 [42; 56]% vs 56 [47; 60]%, p < 0.001); coronary calcification (23.2% vs 15.7%, p = 0.024 ) and proximal lesions of the right coronary artery (RCA) (28.3% vs 22.7%, p = 0.025) were detected more often. The final model, which included 10 parameters, had the diagnostic accuracy of 85%, sensitivity of 85%, and specificity of 86%.

Conclusion. Atrial fibrillation in men with coronary artery disease can be predicted by ANN model that takes into account the presence of significant mitral regurgitation, extra-budgetary employment, severity of heart failure, coronary calcification, proximal lesion of RCA, BMI, echocardiographic indexes of left heart, aortic root dimensions, and LV EF.

Introduction. Postoperative atrial fibrillation (POAF) is one of the most common complications of coronary artery bypass grafting (CABG) and occurs in 25–65% of patients.

Aim. The study aimed to assess the predictive potential of preoperative risk factors for POAF in patients with coronary artery disease (CAD) after CABG based on machine learning (ML) methods.

Material and Methods. An observational retrospective study was carried out based on data from 866 electronic case histories of CAD patients with a median age of 63 years and a 95% confidence interval [63; 64], who underwent isolated CABG on cardiopulmonary bypass. Patients were assigned to two groups: group 1 comprised 147 (18%) patients with newly registered atrial fibrillation (AF) paroxysms; group 2 included 648 (81.3%) patients without cardiac arrhythmia. The preoperative clinical and functional status was assessed using 100 factors. We used statistical analysis methods (Chi-square, Fisher, Mann – Whitney, and univariate logistic regression (LR) tests) and ML tests (multivariate LR and stochastic gradient boosting (SGB)) for data processing and analysis. The models’ accuracy was assessed by three quality metrics: area under the ROC-curve (AUC), sensitivity, and specificity. The cross-validation procedure was performed at least 1000 times on randomly selected data.

Results. The processing and analysis of preoperative patient status indicators using ML methods allowed to identify 10 predictors that were linearly and nonlinearly related to the development of POAF. The most significant predictors were the anteroposterior dimension of the left atrium, tricuspid valve insufficiency, ejection fraction <40%, duration of the P–R interval, and chronic heart failure of functional class III–IV. The accuracy of the best predictive multifactorial model of LR was 0.61 in AUC, 0.49 in specificity, and 0.72 in sensitivity. The values of similar quality metrics for the best model based on SGB were 0.64, 0.6, and 0.68, respectively.

Conclusion. The use of SGB made it possible to verify the nonlinearly related predictors of POAF. The prospects for further research on this problem require the use of modern medical care methods that allow taking into account the individual characteristics of patients when developing predictive models.

Purpose. To build a system for making diagnostic decisions based on multiparametric ultrasound examination of the mammary gland.

Material and Methods. A total of 277 women with various complaints of breast diseases were examined using a wide range of ultrasound technologies, including elastography and contrast enhancement. To verify the lesions, the patients underwent histological or cytological examination. The results of ultrasound examination, histological and cytological conclusions were entered into the database. The system was trained with 219 patient samples selected from the database. The patient’s samples were grouped according to the visual ultrasound characteristics. The data groups’ analysis allowed the compilation of a table with relative frequencies (probability) of symptoms for this diagnosis. Based on the convolution and the Bayesian method, the system for support of the medical decision by age, clinical picture, and ultrasound diagnostics results were built. Sensitivity and specificity were determined for software implementation in the initial database.

Conclusion. The proposed decision support system allows us to determine the probability of malignancy and standardize decision-making in the differential diagnosis of breast masses.

Introduction. Endometriosis is a difficult-to-diagnose pathology due to the diversity of clinical manifestations and the lack of high-precision markers necessary for rapid noninvasive diagnosis and timely administration of pathogenetically justified treatment.

The aim of this work was to develop a computer system that allows us to assess the probability of endometriosis with various localizations in women, based on artificial neural networks.

Material and Methods. The neural network mathematical models were constructed and tested based on data from 110 patients with morphologically pre-confirmed endometriosis. Patients were divided into training and test samples. The models were built based on anamnestic data and results of proteomic and enzyme immunoassays in blood plasma samples.

Results and Discussion. In the course of the study, four mathematical models of neural networks were constructed to predict the presence or absence of endometriosis in a woman and its localization if present. Based on these mathematical models, a computer system “Differential diagnosis of endometriosis” was developed. This system allowed to assess the probability and localization of endometriosis in a patient based on parameters obtained as a result of neural network training.

Conclusion. The developed computer diagnostic system allowed predicting the presence of endometriosis and its localization with a probability over 80%, depending on the predicted localization, based on data about the patient and the results of her examination. This system may be used for differential diagnosis of endometriosis from other diseases of the female reproductive system, as well as for differential diagnosis of various endometriosis localizations.

Aim. To formulate the methodology for developing the interactive virtual computer simulations with a rating assessment of trainees’ decisions and the capability of remote access.

Material and Methods. The methods of knowledge engineering were used to extract and formalize expert knowledge about the structure, significance, and relevance of clinical diagnostic information. The materials for creating virtual computer simulations were based on texts from the archival medical records, laboratory data, and multimedia results of instrumental methods of study. A three-tier network architecture was applied to provide the capabilities of remote access. It was organizationally represented by three components: a client layer, a business logic layer, and a data layer. Data transfer was provided by the Web protocols while microservices represented the infrastructure.

Results. The information was formalized and structured after expert analysis and identification of significant diagnostic and prognostic data. The process included defining the domain model, identifying the aggregates and connections between them, and designing software and user interfaces. Possible solutions for trainees are now presented in the form of interactive reference lists. The artifacts of the user’s work are saved in the storage represented by the module for working with the server file system and the object-relational database management system. Each task module contains static and interactive blocks of information. The purpose of static blocks is to provide trainees with the necessary information for making clinical and diagnostic decisions. The interactive blocks allow selecting one or more solutions from the list. The content and sequence of further information presentation are determined by the trainees’ answers to the questions of an interactive block. Trainees’ decision-making competencies are evaluated using the rating system. The final personal rating is calculated as a multiplication of all coefficients related to the trainees’ decisions. This approach integrates a rating system with the trajectory chosen by the trainee for task completion.

Conclusions. The distance learning technologies, developed for clinical disciplines in this study, are quite new and innovative. The repository of virtual computer simulations is under development to improve the methodological support of remote clinical training.