Актуальность. По сравнению с лабораторными методами проведения биохимических анализов крови алгоритмы искусственного интеллекта предлагают несколько ключевых преимуществ. Они сравнимы с традиционными методами по точности и эффективности, но значительно превосходят их по экономичности Целью исследования является разработка интерпретируемой модели вычисления липидного профиля пациента с помощью машинного обучения на основе деперсонализированных данных о диспансеризации (возраст, пол, общий анализ крови (ОАК), общий холестерин, глюкоза крови). Материалы и методы. Разработанный алгоритм представляет собой комплекс технологических решений, позволяющий рассчитывать взаимосвязь между различными биохимическими параметрами в организме человека с помощью передовых алгоритмов глубокого обучения, таких как градиентный бустинг на решающих деревьях и полносвязные нейронные сети. База данных включала в себя результаты лабораторных показателей 62 192 пациентов: холестерин (ХС), липопротеины высокой плотности (ЛПВП), триглицериды (ТГ), липопротеины низкой плотности (ЛПНП), ОАК, а также пол и возраст пациентов. Результаты. Была проведена оценка качества моделей на тестовой выборке с использованием метрик, таких как коэффициент детерминации (R2 ), средняя абсолютная ошибка (MAE), средняя абсолютная ошибка в процентах (MAPE). R2 для корреляции между концентрацией ЛПНП и группы данных о диспансеризации составила 0,94 при MAE 0,20 и MAPE 0,06. Корреляция между ЛПВП и ТГ с данными о диспансеризации была значительно ниже (R2 составил 0,51 и 0,41 соответственно, MAE 0,20 и 0,53 соответственно, а MAPE 0,15 и 0,40 соответственно). Заключение. Разработка алгоритма искусственного интеллекта, способного прогнозировать уровни ЛПНП, ЛПВП и триглицеридов на основе менее дорогостоящих лабораторных тестов, таких как уровень холестерина и глюкозы в крови, имеет огромный потенциал для повышения доступности здравоохранения. Хотя на сегодняшний день достигнута высокая точность (94%) только при прогнозировании ЛПНП, следующий важный шаг заключается в подборе способа обработки и расширении набора данных, используемого для обучения для более точного предсказания уровней ЛПВП и ТГ. Relevance. Compared to laboratory methods of performing biochemical blood tests, artificial intelligence algorithms offer several key advantages. They are comparable to traditional methods in accuracy and efficiency, but significantly superior to them in cost-effectiveness. The goal of the study is to develop an interpretable model for calculating a patient’s lipid profile using machine learning based on depersonalized medical examination data (age, gender, complete blood count (CBC), total cholesterol, blood glucose). Materials and methods. The developed algorithm is a set of technological solutions that allows one to calculate the relationship between various biochemical parameters in the human body using advanced deep learning algorithms, such as gradient boosting on decision trees and fully connected neural networks. The database included the results of laboratory parameters of 62,192 patients: cholesterol (C), high-density lipoprotein (HDL), triglycerides (TG), low-density lipoprotein (LDL), CBC, as well as the sex and age of the patients. Results. The quality of the models was assessed on the test set using metrics such as the coefficient of determination (R2), mean absolute error (MAE), mean absolute percentage error (MAPE). The R2 for the correlation between LDL concentration and followup data group was 0.94 with MAE 0.20 and MAPE 0.06. The correlation between HDL and TG with follow-up data was significantly lower (R2 was 0.51 and 0.41, respectively, MAE 0.20 and 0.53, respectively, and MAPE 0.15 and 0.40, respectively). Conclusion. The development of an artificial intelligence algorithm that can predict LDL, HDL and triglyceride levels based on less expensive laboratory tests such as cholesterol and blood glucose levels have enormous potential to improve access to healthcare. Although high accuracy (94%) has been achieved to date in LDL-C prediction alone, the next important step is to select the processing method and expand the training dataset to more accurately predict HDL and TG levels.

The review article is devoted to the history of the development of urine diversion methods, starting from the very first operations for the imposition of skin fistulas and ending with modern high-tech surgical interventions. The advantages and disadvantages of various methods of urine diversion are described. It is shown that the gold standard today is orthotopic bladder plastic surgery, which allows to achieve good functional results and a high quality of life for patients.

Aim. To study the profile of biochemical markers of the hemostasis system, to clarify their role and relationships in the pathogenesis of the development of thrombotic complications (TC) of ischemic stroke (IS) and the associated assessment of the possibilities of their diagnostic application. Materials and methods. The study group included 302 patients (164 men, 138 women) who were admitted to the hospital with a diagnosis of IS within 24 hours of the onset of the disease. The diagnosis was confirmed by computed tomography. The average age of patients was 69 (5088) years. Blood was taken from all patients on the 1st day of the disease to determine the profile of analytes presumably associated with the pathogenesis of TC. Levels of homocysteine, protein C inhibitor, thrombomodulin, plasminogen, tissue plasminogen activator, urokinase, plasminogen activator type 1 inhibitor, t-PA/PAI-1 complex, vitronectin, plasmin-2-antiplasmin complex, D-dimer, fibronectin were determined in blood serum by ELISA. Results. TC in the acute period of IS (up to 21 days) were recorded in 32 (10.6%, 95% CI 7.3714.3) patients, of which pulmonary embolism was observed in 27 (8.94%, 95% CI 5.9812.4) patients, deep vein thrombosis in 5 (1.66%, 95% CI 0.473.47) patients. The results of the study of a panel of specific proteins involved in pathogenetic processes accompanying necrosis of brain tissue in IS demonstrated that of the entire list of markers of the hemostasis system activation selected for the study, the most significant are: the concentration of fibronectin in the prognosis of the absence of TC with a threshold value of more than 61 mkg/ml and OR 4.4 (95% CI 1.512.9, p=0.011), and the concentration of the t-PA/PAI-1 complex in the prognosis of the development of TC with a threshold value of more than 14 ng/ml and OR 11.3 (95% CI 1.18109.3, p=0.03). Conclusion. The significance of the t-PA/PAI-1 complex and fibronectin as markers of TC in IS may be due to a violation of the activation processes of the fibrinolytic link of hemostasis and the accumulation of non-deposited compounds that damage the vascular wall.

BACKGROUND: Reverse transcription polymerase chain reaction (PCR) is the main method for detecting the viral agent of coronavirus disease-2019 (COVID-19). This analysis is performed in a non-automated mode in many medical laboratories, which implies a significant labor intensity of a test. However, its magnitude, as well as the workload on staff in the context of variability in testing volumes, has not yet been quantified due to the lack of systematic approaches to studying the labor costs of laboratory staff. AIM: This study aimed to investigate the structure and magnitude of the labor cost components of laboratory staff when performing manual PCR for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) ribonucleic acid (RNA) and obtain stratified data that characterize the labor intensity of the testing, which are suitable for workload modeling. MATERIALS AND METHODS: The study of the labor costs (as labor time) of the PCR laboratory staff was conducted based on the Clinical Diagnostic Laboratory of the Multidisciplinary Medical Center of the Bank of Russia using a time-and-motion study methodology. Hence, the authors method for researching the labor costs of medical laboratory staff was applied. RESULTS: The lists of standard manipulations of the time-studied labor process were formed workplaces, the manipulations were classified according to the labor cost components, and the duration of each component was statistically determined. The labor intensity per test under current working conditions was 110.2 s for the reception and registration, 144.6 s for RNA extraction, and 79.4 s for reaction mixture preparation/amplification workplaces. The workload magnitude for the personnel of these workplaces corresponded to 47%, 62%, and 34% of a lab specialists annual working rate budget. The stratification of labor costs into fixed and variable allowed us to model the workload depending on the change in the testing volume and the number of analytical runs, as well as develop nomograms for the annual total labor time calculation. CONCLUSION: The proposed approach to labor cost accounting and analysis makes it possible to obtain suitable stratified data for modeling the workload of personnel during manual PCR-testing for SARS-CoV-2 RNA. The developed nomograms based on them can serve the purposes of planning the laboratory work and increasing its efficiency by choosing the optimal schemes for organizing the labor process. The obtained data can be used in other laboratories that perform real-time PCR tests for molecular genetic markers.

Every year, about a fifth of the Russian population undergoes laboratory testing for HIV infection, which creates a significant burden on the healthcare system. A significant part of the research on markers of HIV infection is performed using ELISA test systems, usually using manual labor of personnel. The decision to automate this process should be based on the results of a comparative analysis of the direct costs of manual and automated methods.The purpose statement is to evaluate the impact of automation on the labor intensity and cost of ELISA tests for antibodies to HIV1.2 / p24 antigen, depending on changes in the number of laboratory tests and the mode of operation of automatic equipment.Materials and methods. The study of costs was carried out for the manual ELISA method and for automated execution using the ELISA analyzer «Lazurit». To analyze the labor costs of the personnel, the timing of the workplaces of the medical laboratory was performed. When modeling various flows of biomaterial samples, the number of laboratory tests was used, which is a multiple of the 1st plate of the ELISA test system. The assessment of the influence of the operating modes of the automatic analyzer was carried out with a working shift of 7.2 hours and 12 hours.Results. Automation of ELISA in conditions of medium and large volumes of testing saves labor by more than 1.6 times with a work schedule of 7.2 hours, and more than 1.9 times with a schedule of 12 hours. At the same time, automation increases the technological cost at low flows by more than 2 times, and at high flows — by 1.2 times. Conclusion. Automation of HIV testing using an ELISA analyzer leads, in general, to a negative economic effect due to a significant excess of the cost of additional consumables and depreciation of equipment over the possible savings in the wage fund. However, with a load exceeding 3–4 ELISA plates per day per 1 medical laboratory technician, automation can be an effective alternative to increasing the laboratory staff. Optimal for automated ELISA at medium and high flows is a 12-hour work schedule.

Background. Bacterial pneumonia is a frequent complication of ischemic stroke at the hospital stage. The search for prognostic laboratory markers of pneumonia remains an urgent task, as it will allow to individualize the approach to the treatment and rehabilitation of such patients. Aim. To investigate the prognostic significance of proteins of the acute phase of inflammation, as well as to evaluate them as early predictors of the development of pneumonia in patients with ischemic stroke. Materials and methods. The study included 302 patients in the acute period of ischemic stroke. C-reactive protein (CRP), tumor necrosis factor , interleukin-6 (IL-6), neutrophil elastase, neopterin, serum amyloid A (SAA), secreted phospholipase type 2 (sPLA2) were determined in all patients on the first day by enzyme immunoassay. Statistical data processing was carried out using SPSS and Microsoft Excel software (USA). Results. At the hospital stage, pneumonia developed in 82/302 patients (27.2%; 95% confidence interval 22.332.3%). The levels of CRP, IL-6, sPLA2, SAA and neopterin significantly differed in the presence and absence of pneumonia. Step-by-step logistic regression analysis revealed the significance of IL-6 and CRP concentrations in the prognosis of pneumonia. The threshold value of IL-6 concentration was 3.45 pg/ml (sensitivity 82.4%, specificity 66.7%). The prognostic value of a positive result (PPR) in the prognosis of pneumonia was 40%, a negative result (PNR) 92%. The threshold value of CRP was 1640 mg/l with a sensitivity of 65.8% and a specificity of 74.8%. The PPR of the threshold value of the concentration of CRP was 45%, PNR 80%. Conclusion. The measurement of the concentration of IL-6 and CRP on the first day of ischemic stroke makes it possible to identify patients with the greatest risk of pneumonia at the hospital stage. The results of the work indicate the necessity to include CRP and IL-6 in the list of mandatory laboratory tests that should be carried out for each patient with ischemic stroke on the first day from the onset of the disease.

Aim: this paper presents a comparative analysis of biochemical and immunological blood parameters in high skilled combat athletes with different athletic achievements. Materials and methods. The study involved male combat athletes (n = 78) of the Russian national team; mean age - 25.2 (21.5-28.9) years, mean body weight - 76.9 (68.4-83.4) kg. The following biochemical and immunological laboratory tests were performed: urea content, transaminase activity - ALT, AST, creatine kinase - CK, testosterone, cortisol levels and their ratio, absolute and relative CD3+, CD4+, CD8+, CD16+, CD19+ lymphocytes, immunoregulatory index - CD4+/CD8+, phagocytosis, IgA, IgM, IgG, IgE. The subjects were divided into two groups with respect to athletic performance: the UHA group (ultra-high achievements) included Olympic, World and European champions and medal winners (n = 19), the MNT group involved national team mem-bers (n = 59). Results. A multifactorial assessment of the relationship between athletic performance and biochemical/immunological blood parameters showed two biomarkers of predictive importance: urea up to 5.75 mM/l (sensitivity - 73.3%, specificity - 68.7%) and absolute CD4+ count - 0.865 center dot 109/l (sensitivity - 81.3%, specificity - 59%); decreased serum urea and increased circulating CD4+ cells were associated with outstanding athletic performance typical of the UHA group. The simultaneous use of both markers and their reference values improves the predictive accuracy for the UHA group by 3 times compared to a single use of absolute CD4+ count. The odds ratios were 24 (95% CI 6.23- 2.5, p < 0.001) and 8.147 (95% CI 2.121-31.3, p = 0.001), respectively. Conclusion. Serum urea up to 5.75 mmol/l as the most important indicator of pro-tein metabolism and circulating CD4+ count of > 0.865 center dot 109/l as a factor of immune performance demon-strate the ability to better tolerate training and competitive loads and resist infections.

In September 2021, the European Society of Cardiology issued new guidelines on the management of patients with heart failure (HF). In the current version, experts have focused on the 4 most common variants: acute HF decompensation, acute pulmonary edema, cardiogenic shock, and isolated right ventricular failure. There has been a change in approaches to the initial management of patients with acute HF decompensation towards a decrease in the evidence-based use of peripheral vasodilators and a "return" to loop diuretics as the basis of treatment. This raises the question of monitoring the efficacy of diuretic therapy. The paper presents an algorithm proposed by the European Society of Cardiology.

Acute heart failure (HF) is a syndrome requiring urgent treatment. Due to drastic increase in the number of HF patients this problem is still of great importance for modern public health care and has a significant impact on morbidity and mortality. This article presents modern approaches to the classification of this condition, describes diagnostic algorithms, and discovers general methods of acute HF therapy. Two clinical axes are described the presence of stasis in one or two circuits of blood circulation and peripheral hypoperfusion, on the basis of which the individual approaches to treatment strategy of patients with this symptom complex are developed.

The basis for calculating the cost price of any product, including laboratory tests, is based on an estimate of direct costs of the production. At present, there are no systematic ideas about the structure of such costs, and approaches to their analysis have not been defined, in the management practice of medical laboratories. The purpose of this work was developing and testing a method for analyzing the structure of direct costs and their allocation bases when calculating the cost of a laboratory test. We analyzed data on the volume of laboratory tests performed in the clinical diagnostic laboratory of the National Medical Research Center of Cardiology, prices for purchased reagents and consumables, depreciation and maintenance costs of equipment, staff salaries. As a result, we proposed a typical component structure of direct costs, established the allocation bases of fixed costs, and determined the ratio of some variable cost components to onе product unit cost. On the basis of these concepts, an algorithm for calculating the total direct laboratory (technological) cost per test has been developed, which makes it possible to simulate the cost structure under conditions of arbitrarily specified variables. During the testing of the algorithm, the values of direct costs and the technological cost per test were calculated for billable (ordered) laboratory tests. Comparison of the economic efficiency of various methods, as well as modeling of changes in the cost depending on the volume of testing and the turn-around time (TAT) has been performed. It can be concluded that the approach to creating the tables of the technological cost per test based on dividing direct costs into variable and fixed costs and structuring them by components and allocation bases is an effective tool for medical laboratory management.

Aim. To evaluate the dynamics of cardiac arrhythmias on the background of cardiac contractility modulation (MCC) in patients with chronic heart failure (CHF) and various forms of atrial fibrillation (AF) on the basis of daily electrocardiogram (ECG) monitoring. Materials and methods. In 100 patients with CHF and AF, the following studies were performed before implantation of the MCC device and after 12 months of follow-up: 12-channel ECG with an estimate of the width of the QRS complex, transthoracic echocardiography (EchoCG), and Holter ECG monitoring. All patients received long-term optimal drug therapy for CHF before surgery. Results. The results obtained indicate that there is no effect of MCC on the development and progression of ventricular arrhythmias in patients with CHF and AF during the year of follow-up, both extrasystole and tachyarrhythmias, regardless of the etiology and LVEF (less than 35% or more than 35%), and a decrease in the frequency of AF paroxysms in patients with CHF during treatment. These results are due to the reverse remodeling of the LV myocardium under the influence of the MCC device. Conclusion. The use of MСС in patients with CHF and AF is a safe method of therapy that does not induce cardiac arrhythmias, including ventricular extrasystole. Large-scale comparative studies are required to evaluate these results.

Russian Society of Cardiology (RSC)With the participation: Eurasian Association of Therapists (EUAT), Society of Specialists in Heart Failure (OSSN), Russian Scientific Medical Society of Therapists (RNMOT), Russian Society of Pathologists, Russian Society of Radiologists and Radiologists (RSR)Endorsed by: Research and Practical Council of the Ministry of Health of the Russian Federation

Objective: to conduct comparative analysis of blood biochemical parameters (urea, ALT, AST, creatinkinase, cortisol, testosterone and testosterone / cortisol ratio) in groups of high­class wrestlers with different levels of sports achievements.Materials and methods: male athletes (n = 78), members of the Russian national team in one of the types of wrestling (the average age is 25.2 (21.5–28.9) years, the average weight is 76.9 (68.4–83.4) kg) were recruited to this study. The examined athletes were divided into two groups according to their sporting achievements. The first one — SHA group (super­high achievements) which included athletes (n = 19) who had victories and prizes at the largest international competitions (European, World, Olympic Games), and the second group — MNT group (members of the national team) which included athletes that did not have similar achievements (n = 59). The following biochemical parameters were studied: urea, creatine kinase, ALT, AST, testosterone, cortisol, anabolic index (AI).Results: the absolute values of all metabolites in the examined athletes were within the reference intervals. Statistically significant differences in most of the biochemical parameters were revealed between the compared groups in terms of the level of sports achievements. The SHA group showed a statistically significant shift in relation to MNT group, in direction of increasing the level of metabolites that characterize the predominance of anabolic processes — ALT, testosterone, AI. Metabolite levels, increase which reflects catabolic processes activity and inadequate or insufficient adaptation processes, in the SHA group were significantly lower than in the MNT group. The above changes of the absolute values of biochemical parameters were confirmed by correlation analysis.Conclusions: the obtained results allow us to state the optimal adaptation of this sport, the adequacy of metabolic processes in the group of highly qualified athletes.

The development of clinical laboratory diagnostics is in line with the evidence-based medicine, which requires that clinical decisions have to be based on diagnostic methods with proven informativity. This creates a request for the scientific validity of the use of laboratory researches and application of probabilistic interpretation tools corresponding to the tasks. The concept of indefiniteness (analytical, biological and clinical) is at the heart of interpretation of laboratory results. The inclusion of laboratory research in clinical guidelines, the choice and appointment of this research to the patient should not be made from the position of ideas about increasing or decreasing the laboratory index in the disease, but on the basis of its scientifically proven characteristics as a laboratory biomarker sensitivity, specificity, predictive value, as well as the relationship with certain clinical events, outcomes, risks. These characteristics are probabilistic and can be defined.

Objective: to evaluatethe preventive immunotherapy's (PIT) influence on indicators of cellular immunity of highly qualified combat athletes, depending on the level of sporting achievements. Materials and methods: research included 79 sportsmen with average age of 25,2 years, average weight 76,9 kg, sports experience no less than 10 years and sports rank no less than master of sports. Participants were stratified by the level of achievements in sports. The group 1 with highest level of achievements consisted of 31 sportsmen, each of who earned victory or a prize place on biggest international competitions (such as championships of Europe, World and Olympic Games). Remaining 48 participants didn't have such achievements, but theywere a part of national team (Group 2). PIT included probiotic - Fervital, a complex preparation of omega 3-6-9 fatty acids, vitamin-mineral complex - the Alphabet-biorhythm; antioxidant complex - Ubigold Q10 (coenzyme Q + vitamin E); antihypoxant - Hypoxen; sedative - Novo-Passit; adaptogenic drug - Gerimax Ginseng; polyenzyme complex - Wobenzym. Results: there was a great balance of cellular immunity in the group 1 before the PIT due to the higher content of CD4 + and CD19 + cells. A statistically significant increase in the relative content of CD3 + and CD8 + cells and a decrease in the relative and absolute content of CD16 + cells was detected against the background of PIT in the group l. But the group 2, on the contrary, showed an increase in the relative and absolute content of CD16 + cells. Conclusions: the obtained results showed a different reaction in the both groups to the conducted preventive immunotherapy, which, apparently, was due to the initial difference in the biochemical, genetic, psychological potential of athletes of these two groups.

Сердечный белок, связывающий жирные кислоты, в прогнозе течения ишемического инсульта на госпитальном этапе Сердечный белок, связывающий жирные кислоты (сБСЖК), помимо миокарда, содержится также в клетках головного мозга. Концентрация сБСЖК в кровотоке при церебральной ишемии может служить маркером течения ишемического инсульта (ИИ). Цель исследования - изучение значимости сБСЖК в прогнозе течения ИИ. Материалы и методы. В исследование включено 302 пациента в остром периоде ИИ. У всех пациентов определяли концентрацию сБСЖК в сыворотке крови в 1-е сутки после поступления методом иммуноферментного анализа. Для статистической обработки данных использовалось программное обеспечение SPSS и Microsoft Excel. Результаты. Наиболее частыми неблагоприятными событиями на госпитальном этапе оказались летальный исход (ЛИ), тромботические осложнения и пневмония. Были выявлены статистически значимые различия уровня сБСЖК между группами наличия и отсутствия ЛИ как по доверительным интервалам центральных значений, так и по статистическим критериям. ROC-анализ значений сБСЖК по наличию ЛИ подтвердил его прогностическую значимость, площадь под кривой составила 0,776±0,061 (0,655-0,896; р<0,001). Рассчитанное пороговое значение сБСЖК составило 2757 пг/мл с чувствительностью 80% и специфичностью 74,4%. Прогностическая ценность положительного результата сБСЖК в прогнозе летального исхода составила 71%, прогностическая ценность отрицательного результата - 83%. Отношение шансов ЛИ по данному пороговому значению сБСЖК составило 11,6 (3,68-36,5). Заключение. Результаты проведенного исследования показали, что сБСЖК является значимым лабораторным биомаркером в прогнозе летального исхода у больных с ИИ. В связи с отсутствием статистически значимого влияния на концентрацию сБСЖК особенностей лечения, причин смерти и сердечно - сосудистых заболеваний в анамнезе увеличение концентрации сБСЖК выше порогового значения 2757 пг/мл можно считать независимым фактором риска ЛИ у больных с ИИ.

Heart - type fatty acid binding protein (h-FABP), in addition to myocardium, is also contained in the brain cells. The blood concentration of h-FABP in cerebral ischemia can be a marker of ischemic stroke course. AIM To investigate the importance of h-FABP in the prognosis of ischemic stroke (IS). MATERIALS AND METHODS The study included 302 patients in the acute period of ischemic stroke. All patients were determined the concentration of h-FABP in the serum 1 day by enzyme immunoassay. SPSS and Microsoft Excel software were used for statistical data processing. RESULTS The most frequent adverse events at the hospital stage were lethal outcome (LO), thrombotic complications and pneumonia. Statistically significant differences in the level of h-FABP between the groups of presence and absence of LO were revealed both by confidence intervals of Central values and by statistical criteria. The ROC analysis values of h-FABP in the presence of the LO confirmed its predictive value, area under the curve amounted to 0.776±0.061 (0.655-0.896), p.

1ФГАОУ ВО «Российский университет дружбы народов», Москва, Россия; 2ФГБОУ ВО «Российский национальный исследовательский медицинский университет им. Н.И. Пирогова» Минздрава России, Москва, Россия; 3Автономное Учреждение ХМАО-Югры «Центр профессиональной патологии», Ханты-Мансийск, Россия; 4ФГБУ «Национальный медицинский исследовательский центр кардиологии» Минздрава России, Москва, Россия; 5АНО ДПО «Институт лабораторной медицины», Москва, Россия