The aim is to study the prognostic potential of the parameters of the pulmonary function tests parameters in determining the risks of developing comorbid pathology. Material and methods. The study included 102 people, with an average age of 47 [43-52.7] years. Questionnaires, anthropometry, blood sampling for biochemical analysis, and spirometry were conducted. Cardiovascular risk (CVR) was calculated on the SCORE2 scale, stratification of the subjects by risk groups was carried out in accordance with the gradation on the scale used. Statistical processing was performed using nonparametric methods. Results. According to the calculation of the SSR on the SCORE2 scale, all the subjects were in the range of moderate (58.7 %) and high risk (41.3 %). The obtained data from the study of the respiratory function of the general sample were slightly lower in women than in men, with significant differences in the obtained FVC, FEV1, FEF2575. Depending on the presence of arterial hypertension (AH) it was found that the median values of both the actual and calculated lower limits of the norm (LLN) of spirometry indicators among people with AH were lower than those studied without hypertension. At the same time, significant differences depending on the presence of AH were revealed only in the case of LLN for FEV1, FEV1/FVC, FEF2575. In individuals with hypertension, the LLN-FEV1/FVC index was significantly lower than 70 %. In the group of subjects with hypertension, an inverse reliable relationship was found (p = −0.4; p < 0.001) between LLN-FEV1/FVC and the level of uricemia – a decrease in the index by 0.008 % will lead to an increase in uric acid by 1 mmol/l. A decrease in LLN-FEV1/FVC by 0.2 l and LLN-FEF2575 by 0.03 l/sec will increase the CVR on the SCORE2 scale by 1 % ((p = −0.5; p < 0.001) (p=−0.3; p=0.002), respectively). Conclusion. An assessment of the prognostic potential of the pulmonary function tests parameters in determining the risks of comorbid pathology, namely a combination of cardiovascular diseases and respiratory pathology, was carried out. A combined approach to the examination of the able-bodied population, taking into account spirometry data, will help to personify and in-depth assess the risks of developing significant diseases that affect the quality and life expectancy of the patient, his ability to work.

Aim. To assess the content of CO and COHb in exhaled air and the level of blood pressure (BP) in the working-age population of Yuzhno-Sakhalinsk when using various means of nicotine delivery.Materials and methods. The study participants (n = 503) were surveyed using a questionnaire. The BP and oxygen saturation parameters were assessed. The content of CO and COHb content in exhaled air was measured using a smokerlyzer. Statistical processing was performed using nonparametric methods.Results. The study group was dominated by males (58.3%). A high incidence of smoking was observed among females, with up to 42% in the general group and 48.8% in the group of consumers of alternative nicotine delivery systems (ANDS). A correlation between the content of CO and COHb and the smoking experience of more than 10 years was established, regardless of the means of nicotine delivery. Arterial hypertension was registered among 39.8% of the surveyed participants, with a higher frequency in cigarette smokers (28.8%, p = 0.02). This was associated with a greater proportion of individuals (62%) with a long smoking experience of more than 10 years (p = 0.003). A weak direct correlation was established between an increase in blood pressure and the content of CO and COHb (p < 0.001).Conclusion. The share of females as active consumers of tobacco products has grown, particularly in the form of ANDS. Among smokers, the average high level of CO and COHb prevails, which correlates with the smoking experience of more than 10 years and does not depend on the means of nicotine delivery. A direct relationship between the intensity of smoking and the risk of hypertension was established.

Introduction. Predicting the risk of cardiovascular diseases and adverse outcomes are a promising direction in medicine. Using machine learning methods to process large databases to identify new predictors and establish more complex and deeper interactions between them creates other predictive capabilities in a personalized approach to risk assessment. The new approach to improving forecasting is the ability to use artificial intelligence techniques by creating a combination of sophisticated mathematical models and algorithms under certain conditions of computational power and improved database quality. Aim. To estimate the accuracy and reliability of models based on machine learning for solving problems of cardiovascular disease risk prediction. Materials and Methods. Data from a one-stage anonymous survey of volunteers in Primorsky Krai were collected in a multicenter observational study «Epidemiology of Cardiovascular Diseases in the Regions of the Russian Federation». A total of 2 131 participants took part in the study. The main and additional predictors of cardiovascular diseases were selected for further analysis and inclusion in prediction models. Models were created and evaluated using statistical and neural network libraries of the Python programming language. The quality of the models was determined by calculating the total area under the receiver operating characteristic curve. Results and discussion. Compared to the established risk prediction algorithm by calculating the area under the receiver operating characteristic curve, machine-learning algorithms improved the prediction: random forest +1.7%, logistic regression +3.2%, neural networks +3.6%. The algorithm with the highest performance (neural networks) predicted 320 cases (sensitivity 70.2%) and 1217 non-cases (specificity 74.7%), correctly predicting 248 (+7.6%) more patients who developed cardiovascular disease compared to the established absolute cardiovascular risk calculation scale Systematic Coronary Risk Evaluation. Conclusion. The use of neural networks with multilayer perceptron, as one of the methods of layer-by-layer construction of machine learning algorithm, is the best option for creating a prognostic model and currently provides the most reliable results.

Chronic obstructive pulmonary disease (COPD) is considered a typical model of accelerated aging due to the variability and systemic nature of its manifestations. The leading factor in tissue remodeling in COPD is a change or reprogramming of the cellular metabolism in response to external factors such as tobacco combustion products, biofuels, viruses, etc. Mitochondrial biology dominates the spectrum of mechanisms of tissue and cellular reprogramming in COPD. Being parasymbiotic organelles, mitochondria have a complex system of interaction with other cells of the human body and participate in both biogenesis, or formation of new organelles, and mitophagy, or elimination of defective mitochondria by the host cell. Both of these mechanisms are dysregulated in COPD. The aim of this work is to combine the accumulated research experience in the field of cellular metabolism and the role of mitochondria for in-depth COPD phenotyping depending on the metabolic reprogramming variants and for development of new therapeutic possibilities to correct the reprogramming. Conclusion. Mitochondria are key regulators of metabolism, redox homeostasis, cell survival and proliferation. These processes are controlled by various intra- and intercellular signaling pathways and reflect the COPD-associated imbalance at the level of various tissue lineages: alveolocytes, epithelial cells of the lung tissue, smooth myocytes of the respiratory tract, alveolar macrophages, striated muscle cells, mesenchymal stromal cells, progenitor cells, etc. The studies of metabolome and mitochondrial function pointed out where to look for new therapeutic options for COPD.

ФЕДЕРАЛЬНЫЙ ИССЛЕДОВАТЕЛЬСКИЙ ЦЕНТР ФУНДАМЕНТАЛЬНОЙ И ТРАНСЛЯЦИОННОЙ МЕДИЦИНЫ ФЕДЕРАЛЬНЫЙ ИССЛЕДОВАТЕЛЬСКИЙ ЦЕНТР «КРАСНОЯРСКИЙ НАУЧНЫЙ ЦЕНТР СИБИРСКОГО ОТДЕЛЕНИЯ РОССИЙСКОЙ АКАДЕМИИ НАУК» ИНСТИТУТ ВЫЧИСЛИТЕЛЬНОГО МОДЕЛИРОВАНИЯ СО

Objective: to analyze the prevalence of smoking in the population of conditionally healthy residents of Primorsky Krai included in the regional stage of the ESSAY–RF study and establish its relationship with traditional cardiovascular risk factors.Materials and methods: the work uses the database of the study «Epidemiology of cardiovascular diseases in various regions of the Russian Federation» (ESSAY-RF) in Primorsky Krai. In the study population, age, gender, smoking fact, pack/years index (PYI), body mass index (BMI), systolic (SBP) and diastolic blood pressure (DBP) levels, heart rate (HR), lipid spectrum (total cholesterol (TC), low lipoproteins (LDL) and high-density lipoproteins (HDL), non-high-density lipoproteins (non-HDL), triglycerides (TG)), uric acid level (UA) were analyzed. Statistical data processing was carried out using the StatTech v. 2.7.1 program (developed by Stattech LLC, Russia).Results: predictors of the development of chronic non-communicable diseases (CNCD) in groups of smokers (n=327) and non-smokers (n=1160) were studied. In the general group of smokers, an increase in the level of UA was found. When dividing the group of smokers into subgroups depending on the intensity of smoking (I-A with a low-medium degree of nicotine dependence at PYI<10, and I-B with a high degree of nicotine dependence at PYI>10), higher values of SBP, DBP, HR, TG, UA and lower values of HDL between groups I-B and non-smokers. The conducted correlation analysis showed the presence of a direct relationship between the intensity of smoking and the indicators of SBP, DBP, HR, TG and the reverse — with the level of HDL. The use of the method of paired linear regression with the condition of an increase in PYI by 1 in intensely smoking individuals showed a slight effect on the growth of SBP, DBP, UA, TG and HDL. Obviously, a high degree of nicotine dependence per se is a factor closely associated with an increase in the level of SBP, DBP, HR, UA, TG content and a decrease in HDL. With its even greater increase, the change in the predictors of CNCD occurs less noticeably and may be influenced by other positions, indicating the need for complete cessation of smoking at the stage of the presence of risk factors.Conclusion: taking into account the established relationships, it is necessary to strengthen preventive-oriented measures and motivating the population to completely give up smoking, and it is also necessary to monitor the main and additional significant predictors in the framework of outpatient follow-up.

Aim. To develop and perform comparative assessment of the accuracy of models for predicting 5-year mortality risks according to the Epidemiology of Cardiovascular Diseases and their Risk Factors in Regions of Russian Federation (ESSE-RF) study in Primorsky Krai.Material and methods. The study included 2131 people (1257 women and 874 men) aged 23-67 years with a median of 47 years (95% confidence interval [46; 48]). The study protocol included measurement of blood pressure (BP), heart rate (HR), waist circumference, hip circumference, and waist-to-hip ratio (WHR). The following blood biochemical parameters: total cholesterol (TC), low and high density lipoprotein cholesterol, triglycerides, apolipoproteins AI and B, lipoprotein(a), N-terminal pro-brain natriuretic peptide (NT-proNBP), D-dimer, fibrinogen, C-reactive protein (CRP), glucose, creatinine, uric acid. The study endpoint was 5-year all-cause death (2013-2018). The group of deceased patients during this period consisted of 42 (2%) people, while those continued the study — 2089 (98%). The χ2, Fisher and MannWhitney tests, univariate logistic regression (LR) were used for data processing and analysis. To build predictive models, we used following machine learning (ML) methods: multivariate LR, Weibull regression, and stochastic gradient boosting.Results. The prognostic models developed on the ML basis, using parameters of age, sex, smoking, systolic blood pressure (SBP) and TC level in their structure, had higher quality metrics than Systematic COronary Risk Evaluation (SCORE) system. The inclusion of CRP, glucose, NT-proNBP, and heart rate into the predictors increased the accuracy of all models with the maximum rise in quality metrics in the multivariate LR model. Predictive potential of other factors (WHR, lipid profile, fibrinogen, D-dimer, etc.) was low and did not improve the prediction quality. An analysis of the influence degree of individual predictors on the mortality rate indicated the prevailing contribution of five factors as follows: age, levels of TC, NT-proNBP, CRP, and glucose. A less noticeable effect was associated with the level of HR, SBP and smoking, while the contribution of sex was minimal.Conclusion. The use of modern ML methods increases the accuracy of predictive models and provides a higher efficiency of risk stratification, especially among individuals with a low and moderate death risk from cardiovascular diseases.

The powerful development of modern technologies of laboratory diagnostics, including molecular diagnostics, offers a fairly large number of parameters for assessing the state of the body, the interpretation of which is difficult for doctors.

Aim. To assess the prospects of using artificial intelligence technologies in predicting the outcomes and risks of cardiovascular diseases (CVD) in patients with hypertension (HTN).Material and methods. A software application was created for data mining from respondent profiles in a semi-automatic mode; libraries with data preprocessing were analyzed. We analyzed the main and additional parameters (35) of CVD risk factors in 2131 people as a part of ESSE-RF study (2014-2019). To create a forecasting model, a high-level language Python 2.7 was used using object-oriented programming and exception handling with multithreading support. Using randomization, learning (n=488) and test (n=245) samples were formed, which included data from patients with an established diagnosis of HTN.Results. The prevalence of HTN among subjects was 34,39%. There were following significant factors for predicting CVD: anthropometric parameters, smoking, biochemical profile (total cholesterol, ApoA, ApoB, glucose, D-dimer, C-reactive protein). As a result of a 5-year follow-up, CVD was found in 235 people (32,06%) with HTN and 187 people (13,38%) without HTN; mortality rates were 1,27% in subjects with HTN and 1,12% — without HTN. The absolute mortality risk among participants with HTN (0,037) was significantly higher (p<0,05) than in patients without HTN (0,017). To create a neural network (NN), the basic Sequential model from the Keras library was used. During machine learning, 26 variables important for the CVD development were used as input and 9 neurons — as output, which corresponded to the number of established cardiovascular events. The created NN had a predictive value of up to 97,9%, which exceeded the SCORE value (34,9%).Conclusion. The data obtained indicate the importance of risk factor phenotyping using anthropometric markers and biochemical profile for determining their significance in the top 20 predictors of CVD. The Python-based machine learning provides CVD prediction according to standard risk assessments.

The development of trends and practice-oriented approaches to personalized programs for the diagnosis and correction depending on the clinical and phenotypic variants of the person is relevant. A software application was created for data mining from respondent profiles in a semi-automatic mode; libraries with data preprocessing were analyzed. The anthropometric measurements and serum lipoprotein spectrum of 2131 volunteers (average age 45.75 ± 11.7 years) were studied. To estimate the association of blood pressure and cardiovascular events markers was carried out by means of multivariate analysis of data by the methods of selection and classification significant signs. The machine learning was used to predict cardiovascular events. Depends on gender there was found the significant difference in atherogenic index of plasma (AIP) (F < 0.05). In young women (20–30 y.o.), the lipoproteins did not correlate with the presence of hypertension, whereas for older women the statistically significant markers were higher, such as cholesterol (CH, F = 0.03), low-density lipoproteins (LDL, F = 0.03) and AIP (F = 0.02). In men for identifying the risk of hypertension developing lipoproteins should be considered depending on age. Accuracy of the risk recognition for the cardiovascular disease (CVD) model was more than 89% with an average confidence of the model in each forecasted case of 90%. The markers for diagnosing the risk of CVD, the following indicators can be used according to their degree of significance: AIP, CH and LDL. Thus, the data obtained indicate the importance of risk factor phenotyping using anthropometric markers and biochemical profile for determining their significance in the top 17 predictors of CVD. The machine learning provides CVD prediction according to standard risk assessments.