This paper analyzes the prospects for using machine learning to assess cardiovascular risk in patients with type 2 diabetes. It is shown that modern algorithms, particularly neural networks, demonstrate high efficiency in risk prediction. However, despite the high accuracy of the models, their implementation is limited by several issues, such as the lack of external validation on independent samples and the difficulty of integrating them into clinical decision support systems. The authors emphasize the need for standardized study design and transparency in algorithm performance to implement machine learning in widespread clinical practice.

The rapid integration of generative neural networks into the practice of medical research presents an unprecedented challenge to the system of academic certification. The ability to automatically generate coherent, scientifically plausible text calls into question the integrity of dissertation work and the validity of academic degrees as markers of genuine research competency. This paper analyzes the epistemological risks posed by "synthetic" dissertations, including the fabrication of data, the erosion of methodological transparency, and the degradation of established scientific schools. It examines contemporary methods for detecting AI-generated text — ranging from stylometric analysis to software-based detectors — and discusses their inherent limitations. As a systemic response to this crisis, a comprehensive set of measures is proposed: the introduction of mandatory in-person writing of the dissertation’s final section in a controlled environment with video surveillance; the tightening of quantitative criteria for admission to the dissertation defense (including H-index requirements, a multifold increase in the number of required publications, and a minimum length of professional service); and a fundamentally new model for the periodic recertification of academic degrees, similar to professional accreditation, which includes the possibility of degree revocation in cases of insufficient publication activity. The implementation of these measures would create a multi-layered system of protection for the body of medical science, preventing the infiltration of "synthetic" researchers and preserving the value of the academic degree as an authentic testament to scientific contribution.

Aim . To analyze the effect of elevated high-sensitivity C-reactive protein (hs-CRP) on the clinical course and complexity of coronary artery disease (CAD), and the risk of coronary artery bypass graft (CABG) failure. Material and methods . The study included 84 patients with stable CAD who underwent examination and isolated CABG. Evaluation of hs-CRP levels was performed before surgery, 24 hours and 7 days after CABG. Control coronary bypass angiography was performed intraoperatively and 1 year after CABG. Results . We found that chronic increase in hs-CRP levels affects the complexity of CAD (Syntax Score) and the development of critical unfavorable prognostic coronary lesions. The risk of hemodynamically significant stenosis of the left coronary artery trunk increases 6-fold (odds ratio 5,9; 95% confidence interval (CI): 1,89-18,5). Dysfunction of coronary conduits was determined in 12% of patients 1 year after CABG, which was caused by thrombotic vein graft occlusion in 70% and hemodynamically significant graft stenosis in 30% of cases. These patients had significantly higher hs-CRP levels at all testing time points (before surgery, 24 hours and 7 days after CABG), indicating a more pronounced activation of inflammatory mechanisms. Predictive analysis established a significant role of hs-CRP levels before surgery (relative risk (RR) 1,43; 95% CI: 1,23-1,67, p<0,001) and 24 hours after surgery (RR 1,16; 95% CI: 1,06-1,27, p<0,001) as a risk factor for coronary bypass graft failure in the midterm period after surgery. Conclusion . Our study confirmed the leading role of inflammation in triggering and maintaining the main mechanisms determining coronary conduit damage after CABG, which is the basis for bypass graft failure. Established elevated hs-CRP levels can be considered as predictors of bypass graft failure and unfavorable outcomes of myocardial revascularization.

Aim . To evaluate the phenotype of patients with secondary tricuspid regurgitation (STR) associated with acquired left heart defects (AHDs) requiring surgical treatment. Material and methods . We analyze data from a prospective observational registry including patients with AHDs to assess demographic characteristics, the nature of heart valve disease, and comorbidities among 1429 patients aged 18 to 80 years who were referred for surgical correction of noncommunicable AHDs between 2012 and 2023. Results . Among the 1429 patients with primary mitral and/or aortic valve disease, STR was detected in 28,2%. STR was most often associated with mitral valve di­sease (20,08%). STR was more common in women (62,3%) than in men (37,7%) (p<0,001). In addition, 53,6% of patients with STR had AHD due to rheumatic heart disease, while degenerative lesions occurred in 21,3%, and connective tissue dysplasia in 16,1% of patients. The odds of high pulmonary hypertension probability according to echocardiography were 2,5 times higher in patients with STR (95% confidence interval (CI): 1,833-3,420, p<0,001) compared to the group without STR. A multivariate model was used to identify predictors of left heart defects with indications for surgical treatment, including age, female sex, rheumatic origin, absence of degenerative valve disease, presence of atrial fibrillation (AF), lung di­sease, and obesity (area under the receiver operating characteristic (ROC) curve (AUC) =0,779; 95% CI: 0,750-0,808, p<0,001). Conclusion . The proportion of patients hospitalized for surgical treatment of left heart defects with STR is high (up to 30%). The phenotype of these patients is most often represented by elderly women with concomitant AF and pulmonary hypertension. We identified factors associated with left heart defects in patients with STR. These factors include age, female sex, rheumatic origin, absence of degenerative valve disease, presence of AF, lung disease, and obesity.

Aim . To identify the characteristics of doctor-­patient communication in pulmonary arterial hypertension (PAH) based on self-understanding of their condition. Material and methods . The study included 47 patients aged 46,4±11,5 years with a verified PAH (women, 89,4%). The study was based on qualitative data obtained through questionnaires. The results were interpreted using semantic and communicative-­pragmatic analysis. Results . The patients tend to focus on the semantic field of the word "Health". The response analysis allows us to conclude that participants who had already had some experience in communicating with healthcare specialists prefer to hear phrases about somatic maintenance and medical control over the disease. It does not fully fit into the patients’ worldview and the symptoms are on the periphe­ry of their perception. Finding out the treatment expectations will enable a doctor to minimize conflicts between the two sides of the therapeutic process concer­ning different treatment approaches and disease perception. Conclusion . The conducted research allows a doctor to choose a communicative tactic in conducting a conversation with a PAH patient. The findings also suggest that this approach may be useful for dialogue algorithmization during any medical consultation concerning other health conditions.

Implantable pacemakers are powered exclusively by nonrechargeable primary batteries, and battery depletion is the predominant and inevitable reason for device replacement. The need to extend the lifespan of implantable pacemakers is dictated not only by the increasing population life expectancy, but also by risk of surgical and infectious risks and the financial costs associated with device replacement. Pacemaker energy consumption is primarily determined by patient characteristics (continuous or intermittent pacing). Development of non-invasive charging systems to ensure the long-term operation of implantable devices is a key to the transition to next-generation pacemakers. The ultimate solution is to ensure battery charge, which will provide the operation of devices, including pacemakers, for a long period.

Aim . To optimize the risk assessment of hemodynamically significant coronary artery (CA) stenosis in COVID-19 survivors with chronic coronary syndrome (CCS) based on a comprehensive analysis of anamnestic, clinical and paraclinical parameters. Material and methods. The study included 431 patients with CCS and positive SARS-CoV-2 serological tests for >12 weeks prior to enrollment (203 with mild and 228 with moderate COVID-19). The examination included clinical and laboratory parameters (including apolipoprotein A1 and B, lipoprotein(a)), systemic inflammation biomarkers, echocardiography, coronary angiography, and residual risk assessment. Multivariate logistic regression analysis was performed to identify independent predictors of hemodynamically significant coronary artery stenosis. Statistical processing was performed using RStudio 2025.05.0 (R 4.4.2), with p<0,05 considered statistically significant. R e sults . Patients with moderate COVID-19 were more likely to have class II obesity (p=0,004), type 2 diabetes (p=0,007), C3-C4 chronic kidney disease (p<0,001), functional class III angina (p<0,001), heart failure with mildly reduced ejection fraction (p=0,003), as well as more pronounced metabolic disorders and inflammatory shifts. In this group, GZSCA (86,4% vs, 68,0%; p<0,001), multivessel disease (p=0,046), and coronary artery restenosis (p=0,042) were diagnosed significantly more often. Multivariate logistic regression analysis identified the following predictors for hemodynamically significant CA stenosis: moderate COVID-19 (odds ratio (OR) 1,84 [1,02; 3,39], p=0,047), aortic diameter >3,28 cm (OR 2,52 [1,42; 4,55], p=0,002), segmental myocardial contractility disorders (OR 3,72 [1,71; 9,06], p=0,002), extracranial artery atherosclerosis (OR 2,56 [1,37; 4,78], p=0,003), hyperuricemia >308,5 μmol/L (OR 2,22 [1,25; 3,95], p=0,006), high-density lipoprotein <1,27 mmol/L (OR 1,99 [1,11; 3,62], p=0,021), high residual risk for low density lipoprotein (OR 2,48 [1,31; 4,7], p=0,005), triglyceride-glucose index >9,46 (OR 1,89 [0,91; 4,22], p=0,102), fibrinogen >3,25 g/L (OR 1,62 [0,83; 3,12], p=0,149), history of hypertension >16 years (OR 1,85 [0,98; 3,6], p=0,064) and age >56 years (OR 1,65 [0,88; 3,09], p=0,116). Based on the resulting multifactorial model, an online risk prediction calculator for hemodynamically significant CA stenosis in COVID-19 survivors with CCS. Conclusion . Previous COVID-19, especially with moderate course, is associated with a more unfavorable clinical and angiographic phenotype of CCS. The developed risk prediction algorithm for hemodynamically significant CA stenosis can serve as a practical tool for early risk stratification and optimization of patient management in the post-COVID period.

Aim . To study and compare the informative value of machine learning models based on radiomics parameters of non-contrast cine-cardiac magnetic resonance imaging (CMI) for differentiating between areas of post-infarction cardiosclerosis and intact myocardium in patients with ischemic cardiomyopathy (ICM). Material and methods. This retrospective study included 88 patients with indications for surgical treatment of ICM. Preoperatively, all patients underwent contrastenhanced cardiac MRI. Radiomics analysis was applied to unenhanced cine MRI images. All images were segmented using 3D slicer software (version 5.2.2), and radiomic features were extracted using the SlicerRadiomics module. Texture analysis was performed on 176 cine cardiac MRI image regions, with 107 texture features identified for each one. The following machine learning algorithms were used: random forest, logistic regression, and gradient boosting with and without feature selection. Statistical data processing and machine learning model generation were performed using the Python programming language. R e sults . Collinearity diagrams were constructed. Non-valuable features were identified. The cumulative value of features was estimated based on their total number, and the parameters with the least value were identified. Thirty-four features were found to contribute nothing to the total value. Lasso regularization resulted in the selection of the 10 most informative parameters (three shape features, two firstorder features, and five texture characteristics). Along with the logistic regression model (AUC=0,83), the CatBoost gradient boosting algorithm demonstrated high performance (AUC=0,8), and feature selection improved all models used in the study, with the highest CatBoost scores (AUC=0,83). The random forest algorithm demonstrated less reliable results compared to other models and can be considered as an additional method when feature interpretation is required. Conclusion . Radiomics analysis has demonstrated high potential for differentiating scarred and viable left ventricular myocardium in patients with ICM. This opens up the prospect of using it as an alternative to traditional delayed contrast-enhanced methods in these patients.

Aim . To substantiate the design characteristics of an innovative Russian-made selfexpanding nitinol stent prototype, as well as to evaluate the outcomes of its implantation in laboratory animals in an experimental study. Material and methods. We selected five domestic pigs for a study of the efficacy and safety of Russian-made self-expanding nitinol stents within the iliac artery. Animal measurements were regularly monitored throughout the experimental period. Three months after stenting, iliac and femoral vessels was assessed using angiography and ultrasound, after the animals were euthanized. Next, a histological analysis of the stented vascular segments followed. We also analyzed stent geometric characteristics and their impact on the external environment, including external pressure, using computer modeling methods. R e sults . During the three-month follow-up period, the health of all study animals remained stable and without abnormalities. Repeated examinations, including angiography and ultrasound, conducted after this period confirmed complete vascular patency and no hyperplasia in the implantation area. Histological revealed the integrity of the stent wall and no signs of damage. By modeling the implanted stent behavior under external pressure, we developed an optimal design for future medical devices. Conclusion . The developed models of all-metal nitinol stents have successfully completed preclinical testing in animal models, confirming their safety and efficacy. Furthermore, innovative bare-metal stent designs for the treatment of peripheral arterial diseases have been created, featuring a unique structure with adjustable spacing between the corrugations.

Aim . To evaluate the potential of a fixed-dose combination of amlodipine and indapamide in hypertensive (HTN) patients with high pulse pressure (PP). Material and methods. The study included 39 male and female patients aged 20 to 75 years (56,2±7,8 years) with HTN. Patients were examined using a standard protocol, including collecting a history and complaints, a physical examination, and laboratory and functional diagnostic tests, including electrocardiography, 24-hour blood pressure (BP) monitoring, echocardiography, and volume sphygmography with arterial stiffness measurements. Investigations were performed at baseline and after 3-month antihypertensive therapy with amlodipine and indapamide at doses of 5/1,5 mg or 10/1,5 mg. Statistical analysis of the obtained data was performed using Microsoft Office XP and Statistica 10 (StatSoft Inc., USA). R e sults . After 3-month therapy, significant improvements were recorded in office systolic and diastolic BP, which decreased from 163,2±6,72 to 134,6±5,81 mm Hg (p<0,001) and from 89,9±7,51 to 78,4±5,54 mm Hg (p<0,001), respectively. In addition, 24-hour BP profile were improved — the overwhelming majority of patients moved into "dipper" HTN phenotype (62%). Left ventricular mass index decreased from 115,6±7,1 to 95,3±5,21 g/m2 (p<0,01), and the transmitral E/A ratio increased from 0,88±0,04 to 0,94±0,06 (p<0,05). PP significantly decreased from 68,1±4,9 to 52,4±4,7 mm Hg (p<0,001). Initially elevated right and left CAVI decreased by 13,8% and 14,2%, respectively, reaching reference values (p<0,01), while the biological vascular age also decreased, reaching the rated value. Target BP values were achieved in 88% of patients. Conclusion . Achieving target levels and improving the 24-hour BP profile, echocardiographic parameters, and vascular stiffness parameters, along with PP normalization in the vast majority of study patients after 3-month therapy support the high efficiency of the fixed-dose combination of amlodipine and indapamide in real-world practice for hypertensive patients with high PP.