Background and Objectives: Despite significant advances in surgical techniques and perioperative care, major adverse cardiovascular events (MACE) remain a leading cause of postoperative morbidity and mortality in patients undergoing coronary artery bypass grafting and/or aortic valve replacement. Accurate preoperative risk stratification is essential yet often limited by models that overlook atrial mechanics and underutilized biomarkers. Materials and Methods: This study aimed to develop an interpretable machine learning model for predicting perioperative MACE by integrating clinical, biochemical, and echocardiographic features, with a particular focus on novel physiological markers. A retrospective cohort of 131 patients was analyzed. An Extreme Gradient Boosting (XGBoost) classifier was trained on a comprehensive feature set, and SHapley Additive exPlanations (SHAPs) were used to quantify each variable’s contribution to model predictions. Results: In a stratified 80:20 train–test split, the model initially achieved an AUC of 1.00. Acknowledging the potential for overfitting in small datasets, additional validation was performed using 10 independent random splits and 5-fold cross-validation. These analyses yielded an average AUC of 0.846 ± 0.092 and an F1-score of 0.807 ± 0.096, supporting the model’s stability and generalizability. The most influential predictors included total atrial conduction time, mitral and tricuspid annular orifice areas, and high-density lipoprotein (HDL) cholesterol. These variables, spanning electrophysiological, structural, and metabolic domains, significantly enhanced discriminative performance, even in patients with preserved left ventricular function. The model’s transparency provides clinically intuitive insights into individual risk profiles, emphasizing the significance of non-traditional parameters in perioperative assessments. Conclusions: This study demonstrates the feasibility and potential clinical value of combining advanced echocardiographic, biochemical, and machine learning tools for individualized cardiovascular risk prediction. While promising, these findings require prospective validation in larger, multicenter cohorts before being integrated into routine clinical decision-making.

Background and Objectives: Postoperative delirium (POD) is a frequent and severe complication following cardiac surgery, particularly in high-risk patients undergoing coronary artery bypass grafting (CABG) and aortic valve replacement (AVR). Despite extensive research, predicting POD remains challenging due to the multifactorial and often non-linear nature of its risk factors. This study aimed to improve POD prediction using an interpretable machine learning approach and to explore the combined effects of clinical, biochemical, and perioperative variables. Materials and Methods: This study included 131 patients who underwent CABG or AVR. POD occurrence was assessed using standard diagnostic criteria. Clinical, biochemical, and perioperative variables were collected, including patient age, sedation type, and mechanical ventilation status. Machine learning analysis was performed using an XGBoost classifier, with model interpretation achieved through SHapley Additive exPlanations (SHAP). Univariate logistic regression was applied to identify significant predictors, while SHAP analysis revealed variable interactions. Results: POD occurred in 34.3% of patients (n = 45). Patients who developed POD were significantly older (67.7 ± 6.5 vs. 64.5 ± 8.7 years, p = 0.020). Sedation with mechanical ventilation and the type of sedative used were strongly associated with POD (both p < 0.001). Sedation during mechanical ventilation showed the strongest association (OR = 2520.0; 95% CI: 80.9–78,506.7; p < 0.00001). XGBoost classifier achieved excellent performance (AUC = 0.998, accuracy = 97.6%, F1 score = 0.976). SHAP analysis identified sedation, mechanical ventilation, and their interactions with fibrinogen, troponin I, leukocyte parameters, and lung infection as key predictors. Conclusions: This study demonstrates that an interpretable machine learning approach can enhance POD prediction, providing insights into the combined impact of multiple clinical, biochemical, and perioperative factors. Integration of such models into perioperative workflows may enable early identification of high-risk patients and support individualized preventive strategies.

Background/Aim. Coronary artery bypass grafting (CABG) is the treatment of choice for significant number of the patients with ischemic heart disease. Some of the postoperative complications are closely linked with the preoperative antiplatelet therapy (APT). The aim of this study was to compare the early clinical outcomes of CABG in patients with preserved platelet (PLT) function and patients with platelet function impaired by the residual therapeutic effect of APT. Methods. A total of 181 patients with isolated CABG were enrolled in this prospective, nonrandomized, observational study. Subjects were divided in four groups: Control (arachidonic acid-dependent PLT aggregation - ASPI) ≥ 790 AU/min, adenosine diphosphate (ADP) ≥ 406 AU/min, Mild acetylsalicylic acid - ASA (ASPI 410-789 AU/min), Pronounced ASA (ASPI ≤ 409 AU/min) and dual APT (DAPT) (ASPI ≤ 789 AU/min; ADP ≤ 405 AU/min). Preoperative data, intraoperative characteristics and postoperative outcomes were obtained and compared between groups. Results. A significant difference was found regarding the average time of APT cessation between groups (p < 0.001). DAPT group had significantly higher drainage compared to Control group (p = 0.004), Mild ASA group (p = 0.001) and compared to Pronounced ASA group (p = 0.006). Pronounced ASA group had significantly higher rate of chest reexploration compared to Mild ASA group (p = 0.032). DAPT group required significantly more packed red blood cells (PRBC) compared to Control group (p < 0.001) and Mild ASA group (p = 0.009). Pronounced ASA group received significantly more PRBC compared to Control group (p < 0.001) and Mild ASA group (p = 0.019). DAPT group required higher amounts of PLT compared to Control group (p < 0.001), Mild ASA group (p = 0.002) and Pronounced ASA group (p < 0.001). DAPT group received higher amounts of cryoprecipitate compared to Control group (p = 0.002), Mild ASA group (p = 0.009) and Pronounced ASA group (p = 0.016). Conclusion. Patients with a residual effect of DAPT as well as patients with a pronounced residual effect of ASA have a higher risk of postoperative bleeding and chest reexploration, and increased transfusions demands.

In the context of pharmacological intervention for pain, Transient Receptor Potential Vanilloid, member 1 (TRPV1), as a non-selective cation channel belonging to the transient receptor potential (TRP) family of ion channels, has emerged as a promising target. However, the availability of selective TRPV1 antagonists and their associated pharmacological properties remains limited. This research paper explores various QSAR modeling techniques applied to a range of piperazinyl-aryl compounds acting as TRPV1 antagonists. The descriptors utilized in the creation of conformation-independent QSAR models included local molecular graph invariants and the SMILES notation, along with the incorporation of the Monte Carlo optimization method as a model development technique. Several statistical methods were employed to evaluate the quality, robustness, and predictive capacity of the developed models, yielding positive results. For the best developed QSAR model following statistical parameters were obtained for training set R2 = 0.7155, CCC = 0.8134, IIC = 0.7430, Q2 = 0.6970, RMSE = 0.645, MAE = 0.489 and F = 157; and for test set R2 = 0.9271, CCC = 0.9469, IIC = 0.9635, Q2 = 0.9241, RMSE = 0.367, MAE = 0.329 and F = 328. Additionally, molecular fragments derived from SMILES notation descriptors, which explain observed changes in the evaluated activity, were identified, leading to the design of four new antagonists. The final validation of the QSAR model and the designed antagonists was conducted through molecular docking, which demonstrated strong correlation with the QSAR modeling results.

Introduction/Objective. The significant difference in the patency of venous coronary grafts in relation to sex still does not have a clearly defined cause. Our research determined the existence of morphometric differences in the wall of the great saphenous vein, in relation to sex. Methods. The research included 268 patients classified by sex in five age groups, who underwent morphometric measurement of the wall of the great saphenous vein. Results. In our research, no significant difference was found in the total thickness of the vein wall between the sexes (p = 0.111), nor was significant association found between wall thickness, age, and sex. The average thickness of the intimal layer of the vein wall was significantly higher in male subjects (p = 0.005), and multivariate regression analysis found a significant correlation between intimal thickness, age and sex (p < 0.001). The medial layer of the vein in women was significantly larger (p < 0.001), both overall and in all age groups. Multivariate regression analysis confirmed a significant association between media thickness, age and sex (p < 0.001). The thickness of the adventitial layer was significantly higher in men (p = 0.031) and a significant association between the thickness of the adventitia, age and sex was also determined (p < 0.001). Conclusion. Our results indicate significant morphometric differences in the wall of the great saphenous vein in relation to sex and age of the patients, which can be related to significant difference in the flow rate of vein grafts in coronary surgery in relation to sex.