Artificial intelligence (AI) has an enormous potential for improving the quality of medical care, diagnostic methods, and treatments. AI allows taking scientific research to a fundamentally new level. The article addresses the most important areas of using AI in cardiology. AI can be used to accelerate making clinical decisions, remote patient monitoring, tomographic image analysis, patient phenotyping, including metabolomic analysis, to assess the risk of complications and many other areas.

Aim      To identify predictors for the risk of in-hospital death and to develop a prognostic scale for individual risk of death in patients with acute coronary syndrome (ACS) at the hospital stage of treatment.

Material and methods  A sequential retrospective analysis was conducted, including 225 patients with ACS (n=101, main group of patients who died in hospital; n=124, control group) hospitalized in the Regional Vascular Center #2 of the Semashko Nizhny Novgorod Regional Clinical Hospital from January, 2021 through July, 2022. Clinical, demographic, laboratory and instrumental characteristics of patients were studied. Statistical analysis was performed using the Statistica version 10.0 and MedCalc version 20.0 software. The cutoff threshold for quantitative variables was determined by ROC analysis. Potential outcome predictors were identified by a univariate logical regression analysis followed by the construction of a multivariate model for predicting in-hospital mortality using the stepwise analysis with backward inclusion. The prognostic degree of a predictor was expressed as an odds ratio (OR) with a 95% confidence interval (CI). Differences were considered statistically significant at p<0.05. For each variable of the multivariate regression model, an individual score was calculated using a linear transformation of the beta coefficients of each variable.

Results Seven independent predictors of hospital death were identified in patients with ACS: Killip class II or higher acute heart failure (AHF) (OR 5.96; 95% CI 1.82-19.48; p=0.0031), low hemoglobin ≤127 g/l (OR 3.75; 95% CI 1.39-10.07; p=0.0087), elevated blood glucose on admission ≥9.7 mmol/l (OR 4.86; 95% CI 1.55-15.21; p=0.0065), high body mass index (BMI) ≥32 kg/m² (OR 7.18; 95% CI 2.65-19.42; p=0.0001), high pulmonary artery systolic pressure (PASP) ≥38 mmHg (OR 3.95; 95% CI 1.48-10.51; p=0.0059), reduced left ventricular ejection fraction (LVEF) according to Simpson (%) ≤42% (OR 5.80; 95% CI 2.15-15.68; p=0.0005), reduced glomerular filtration rate (GFR) according to CKD-EPI ≤55 ml/min (OR 5.75; 95% CI 2.16–15.28; p=0.0005). An individual score was calculated for each predictor. The total score of all predictors formed a scale that was ranged from score 0 to 43 with a cutoff threshold of 14, where a result >14 indicated a high probability of in-hospital death. This scale has a high prognostic potential with the sensitivity 93.07%, specificity 86.29%, and the area under the curve (AUC) 0.957.

Conclusion      Based on the obtained multifactorial model that included 7 major predictors, a scale (scoring system) was developed for predicting the risk of death for ACS patients at the hospital stage of treatment. This scale allows fast identification of patients with a high risk of in-hospital death with a high prognostic accuracy in real clinical practice

Aim      To evaluate the expression level of miR-145, tumor necrosis factor α (TNF-α), and vascular endothelial growth factor (VEGF) in patients with ischemic heart disease (IHD) and different, obstructive and non-obstructive, phenotypes of coronary artery disease (CAD).

Material and methods  This cross-sectional observational study included 107 patients aged 45-75 years with a verified diagnosis of stable IHD. Based on the data of coronary angiography or spiral multislice computed tomography of CA, the patients were divided into two groups, with no obstructive (NOCA, 51 patients) and with obstructive coronary artery (OCA, 56 patients). In the NOCA group, women predominated (62.5%), while among patients with OCA, men predominated (67.9%). Concentrations of VEGF and TNF-α and miRNA-145 expression were measured in patients of both groups.

Results In the NOCA group, the concentrations of VEGF (p=0.004) and TNF-α (p=0.002) and the miRNA-145 expression (p=0.014) were significantly higher. In this group, the miRNA-145 concentration was correlated with the concentrations of VEGF (ρ=0.442; p=0.013) and TNF-α (ρ=–0.386; p=0.032). In the OCA group, correlations were found between the concentrations of TNF-α and VEGF (ρ=0.645; p<0.001), miRNA-145 and VEGF (ρ=0.584; p<0.001), and miRNA-145c and TNF-α (ρ=0.421; p<0.001). According to the univariate logistic regression analysis, significant factors for the CAD type were miRNA-145 expression and female gender. A statistically significant ROC curve was constructed to evaluate the diagnostic capability of miRNA-145.

Conclusion      According to the study results, the highest level of miRNA-145 expression was found in the NOCA group. The ROC analysis showed that a level of miRNA-145 expression higher than 1.084 REU can be a factor of the NOCA phenotype presence in patients with stable IHD. A lower level of miRNA-145 expression can be associated with more severe atherosclerotic CAD.

Aim      To study the prevalence of senile frailty syndrome (FS), its impact on the functional activity, quality of life, management tactics, and prognosis in patients with acute decompensated heart failure (ADHF).

Material and methods  The study included 108 patients (58 men and 50 women, mean age 69.2±10.7 years) admitted for ADHF. FS was diagnosed based on the presence of the clinical signs of ADHF requiring intravenous therapy with diuretics, vasodilators or inotropic drugs. Screening for FS was performed using the "Age is Not a Hindrance" questionnaire. Patients who scored ≥3 performed a brief array of physical functioning tests (BAPFT) to assess the functional activity, and took the Mini-Cog test to assess the psycho-emotional state. A BAPFT score ≤7 and/or Mini-Cog score <3 were criteria of FS.

Results The prevalence of FS was 39.8%. "Fragile" patients were older than individuals without FS (mean age 75.5±7.7 vs. 65.0±10.4 years, respectively; p<0.0001). Among them, there were more women (65.0 and 33.8%, respectively; p=0.006), higher prevalences of arterial hypertension (AH) (97.7 and 7.7%, respectively; p=0.0351), ischemic heart disease (IHD) (69.8 and 49.2%, respectively; p=0.03), iron deficiency (97.7 and 72.3%, respectively; p<0.0001), and hypocalcemia (16.3 and 1.5%, respectively; p=0.013). FS patents had lower exercise tolerance (distance covered in a 6-min walk test, 141.6±42.4 and 215.7±73.0 m, respectively; p<0.0001) and lower quality of life according to the visual analogue scale (score 32.8±12.0 and 40.8±17.8, respectively; p=0.011). “Fragile” patients were more frequently prescribed angiotensin II receptor blockers (20.9 and 4.6%, respectively; p=0.017); the frequency of dosing and target doses of other drug groups did not differ. The following factors associated with an unfavorable one-year prognosis after an episode of ADHF were identified: FS (relative risk, RR 2.94; 95% confidence interval, CI 1.46-5.94; p = 0.003), valve stenosis (RR 3.44; 95% CI 1.60-7.39; p = 0.001), history of acute cerebrovascular accident (RR 3.98; 95% CI 1.65-7.39; p = 0.002), leukocytosis (RR 2.83; 95% CI 1.34-5.97; p = 0.007), and a concentration of N-terminal fragment of pro-B-type natriuretic peptide (NT-proBNP) >5000 pg/ml (RR 2.47; 95% CI 1.24-4.91; p=0.010).

Conclusion      The prevalence of senile FS among patients hospitalized with ADHF was 39.8%. "Fragile" patients had higher prevalences of AH, IHD, iron deficiency, and hypocalcemia. The presence of FS impaired the exercise tolerance, quality of life, prognosis, and did not influence approaches to the drug therapy for ADHF.

Aim    Pericardial effusion is relatively common in daily clinical practice. To our knowledge, no study to date has been conducted on any laboratory parameter that predicts mortality in patients presenting with pericardial effusion. The present study evaluated the prognostic factors of patients with moderate to large pericardial effusions requiring pericardiocentesis.
Material and methods    This retrospective study included 156 patients who underwent pericardiocentesis in our hospital between 2013 and 2022.
Results    73 of the patients (46.8 %) survived. Nonsurvivors had hypoalbuminemia more often than survivors (p<0.001). Median follow-up time in non-survivors was 274.5 [4.0–3507.0] days, while median follow-up time in survivors was 1490.0 [109.0–3209.0]. In-hospital mortality was seen in only 8 patients. The median neutrophil / lymphocyte ratio was significantly lower in survivors than nonsurvivors (p=0.005). The ROC curve analysis showed that the neutrophil / lymphocyte ratio was higher than 4.49, with sensitivity and specificity rates of 78.57 % and 51.75 % in predicting mortality (AUC=0.622, 95 % confidence interval: 0.541–0.698, p=0.013).
Conclusions    The present study showed that the neutrophil / lymphocyte ratio and hypoalbuminemia, which are laboratory values at the time of admission, albumin in the pericardial fluid, and malignant pathology all play roles in the prognosis of pericardial effusion requiring pericardiocentesis.

Background    The quality of life of the patient is diminished by chronic heart failure (CHF), which also costs the healthcare system. This study examined the benefits of individualized nutritional support provided by a specialized nursing team on the nutritional status and cardiac function of elderly patients with CHF.
Material and methods    This study included 102 elderly, hospitalized CHF patients. The patients were randomly assigned to two groups of 51 each. During the study protocol, the control group received regular nursing care, while the experimental group received individualized nutritional support by a specialized nursing team. Nutritional-related and cardiac function indicators, inflammatory factors, and life quality scores measured before and after the protocol were compared.
Results    There was a significant increase in total albumin, hemoglobin, and protein in both groups during the protocol, but the final concentrations were significantly higher in the experimental group (p<0.05). In both groups, the left ventricular ejection fraction was increased after the protocol, while the left ventricular end-systolic dimension and the left ventricular end-diastolic dimension significantly decreased. The improvements in these variables were greater in the experimental group (p<0.05). The experimental group also exhibited significantly reduced tumor necrosis factor-α, interleukin-6, and high sensitivity C-reactive protein (p<0.05), and the experimental group reported higher quality of life (p<0.05) and nursing satisfaction (p<0.05).
Conclusion    Nutritional support of elderly CHF patients administered by a specialized nursing team improved nutrition, cardiac function, inflammatory status, and quality of life compared to standard nutrition and regular nursing care.

Aim    Aortic aneurysm is characterized by localized expansion and damage to the vessel wall. While apolipoprotein B (ApoB) has been linked to atherosclerosis, its causal relationship with aortic aneurysm remains unclear. This study used a Mendelian randomization (MR) approach to explore the causal relationships between ApoB, aortic aneurysm, and potential mediators.
Material and methods    Single nucleotide polymorphism (SNP) data related to ApoB, apolipoprotein A1 (ApoA1), triglycerides, frailty index, and aortic aneurysm were obtained from large-scale genome-wide association studies. MR analysis was conducted to evaluate causal relationships, using inverse variance weighting (IVW) as the primary statistical method. Additionally, we assessed whether the frailty index mediates the relationship between ApoB and aortic aneurysm.
Results    Univariate MR analysis revealed that ApoB is significantly associated with aortic aneurysm (IVW odds ratio (OR) = 1.443, 95 % confidence interval (CI) = 1.273–1.637, p < 0.001). Multivariable MR (MVMR) analysis, adjusted for ApoA1 and triglycerides, confirmed these results. In mediation analysis, the frailty index was found to partially mediate the effect of ApoB on aortic aneurysm (mediation contribution: 20.1 %–23.1 %). The ORs for ApoB and the frailty index with respect to aortic aneurysm were 1.325 (95 % CI = 1.168–1.505) and 4.188 (95 % CI = 1.859–9.435), respectively.
Conclusion    ApoB has a causal relationship with aortic aneurysm, with the frailty index acting as a partial mediator in this pathway.

Aim    To evaluate the efficacy of the I NEED HELP scale in determining the six-month prognosis for patients on the heart transplant waiting list (HTWL) of the Almazov National Medical Research Center of the Russian Ministry of Health.
Material and methods    This retrospective study included 42 patients from the HTWL. The patients’ survival for more than 6 months was assessed. The composite end point (CEP) of adverse outcome was all-cause death, heart transplantation (HT) due to the increased urgency of surgical intervention according to UNOS within 6 months after the inclusion in the HTWL. Patients were evaluated using the I NEED HELP scale. Statistical analysis was performed by nonparametric methods.
Results    The median I NEED HELP score was 4 [from 1 to 7]. The increase in score was positively correlated with the incidence of adverse outcomes (r=0.5; p=0.0007). The group of patients with an unfavorable outcome had a median score higher by one than for the survivors (score 5 vs. 4, respectively; p=0.001). The greatest effect on the prognosis was exerted by low systolic blood pressure (SBP) (p=0.003); the failure to increase or the necessity to decrease the doses of disease-modifying drugs (p=0.039); and target organ dysfunction (p=0.039). The sensitivity and specificity of the scale at a score 5 or higher were 100% and 84%, respectively.
Conclusion    This pilot study demonstrated the efficacy of the I NEED HELP scale in a patient population from a specialized center HTWL with high sensitivity and specificity at the determined threshold score 5 for an unfavorable outcome. It is appropriate to continue the study with an expanded sample and validation of the scale on patient cohorts from hospitals of various healthcare system levels.

Currently, the diagnosis of amyloid cardiomyopathy (ACM) causes great difficulties both for practicing primary care physicians and specialists. One of the reasons is the variety of symptoms in patients with ACM. The most common ACM manifestations include heart failure with preserved left ventricular ejection fraction, hypertrophic phenotype of cardiomyopathy, thromboembolic complications, and valvular apparatus damage. Common valvular manifestations are mitral and tricuspid valve insufficiency and aortic stenosis (AS). Diagnosis is particularly difficult in patients with AS requiring differentiation between AS as a degenerative defect and AS of amyloid origin. According to the literature, in 4-16% of cases of older patients (≥65 years), the genesis of AS is precisely the amyloid damage.