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.

Postoperative atrial fibrillation (POAF) is a common complication after cardiac surgery, increasing morbidity and healthcare costs. This study aimed to identify echocardiographic predictors of POAF to improve risk stratification. A total of 131 patients undergoing cardiac surgery were analyzed and divided into two groups based on POAF occurrence. Echocardiographic analysis showed that patients with POAF had larger left and right atrial dimensions and impaired atrial function. Prolonged total atrial conduction time (TACT), reduced atrial emptying volumes, and contractile function were more common in the POAF group. Univariable analysis identified LAEF (χ² = 71.8, p < 0.001), LAKE (χ² = 70.1, p < 0.001), RATEF (χ² = 65.7, p < 0.001), and RAAEF (χ² = 66.8, p < 0.001) as significant predictors of POAF, each with an area under the curve (AUC) greater than 0.89. In multivariable analysis, LAKE (OR = 0.27, p < 0.001), hypertension (OR = 11.87, p = 0.035), left ventricular ejection fraction (OR = 1.08, p = 0.020), and peripheral vascular disease (OR = 40.28, p = 0.002) were independent predictors. The final model showed a significant discriminatory ability (AUC = 0.94). LAKE and clinical factors remained independent predictors after adjustment.

Background: Extra-abdominal manifestations of fat necrosis, like subcutaneous fat necrosis, polyarthritis, and polyserositis may appear with an occurrence rate of about 0.8%, wherein intraosseous fat necrosis is a more rare complication of pancreatitis, with few reports in English literature. Case report: A 34-year-old male with a 15-year-history of alcohol abuse was hospitalized several times in the last few years because of attacks of relapsed chronic pancreatitis. After the last attack, pancreatitis came in a stable state (“burned out”) with no symptoms and signs of the disease. The patient had been free of symptoms for 28 months since the last admission when he came with sub-febrile temperature, huge pain, swelling, and erythema in the area of the left lateral malleolar region with propagation in the foot. Blood biochemistry was normal. Conventional radiography showed multiple sites of osteolysis in the left calcaneus. Images on multislice computed tomography (MSCT) with 3D reconstruction revealed hypodense focuses that corresponded to osteonecrosis areas and bone marrow edema in the left calcaneus. Conclusions: The possibility of intraosseous fat necrosis should be considered in situations of unexplained polyarthritis or panniculitis, particularly in individuals with alcohol abuse or pancreatic disease.

Background and Objectives: Coagulation disorders during COVID-19 infection are associated with a poorer prognosis and higher disease severity because thrombosis and inflammation are two processes that interfere with each other. A very important issue for clinicians is timely and adequate hemostasis and inflammation monitoring to prevent and treat potentially lethal consequences. The aim of this study was to identify specific hemostatic parameters that are associated with a higher risk of intrahospital mortality. Materials and Methods: This study was approved by the Ethics Committee of the Clinical Center Nis in Serbia. One hundred and forty-two patients presented with COVID-19 ARDS and were admitted to the ICU in the Clinic for Anesthesiology at the Clinical Center Nis from 14 April 2020 to 25 May 2020. Upon admission, blood was collected for biochemical and coagulation testing. The data obtained were analyzed using the Statistical Package for Social Sciences (SPSS v. 25, Chicago, IL, USA). Results: Among all the parameters assessed, older age; increased levels of fibrinogen, INR, D-dimer, and presepsin; and higher results in the platelet aggregation tests (aggregation induced by adenosine diphosphate based on the ADP test (AU/min), aggregation induced by arachidonic acid based on the ASPI test (AU/min), and aggregation induced by thrombin based on the TRAP test (AU/min)) and some assays of the viscoelastic test (clot amplitude after 5 min in the extrinsic coagulation pathway based on the A5 EX-test (mm), clot amplitude after 10 min in the extrinsic coagulation pathway based on the A10 EX-test (mm), clot amplitude after 5 min regarding functional fibrinogen based on the A5 FIB-test (mm), clot amplitude after 10 min regarding functional fibrinogen based on the A10 FIB-test (mm), and maximum clot firmness based on the MCF FIB-test (mm)); and lower values of viscoelastic clotting time in the extrinsic coagulation pathway based on the CT EX-test (s) were significantly correlated with mortality. In the multivariate analysis, D-dimer levels above 860 ng/mL, higher TRAP test value bins, and values above the normal reference range of the A10 FIB test were found to be independent predictors of mortality. Conclusions: Sophisticated hemostasis parameters can contribute to early risk assessment, which has initially been performed only on the basis of patients’ clinical status. Hypercoagulability is the main coagulation disorder in COVID-19 infection.

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.

Breast cancer, a prevalent global malignancy in women, necessitates a com-prehensive treatment approach, with surgery playing a crucial role. Severe acute pain is common post-radical breast cancer surgery, emphasizing the significance of hemodynamic stability and postoperative pain control for optimal outcomes. This study evaluates the impact of ultra-sound-guided erector spinae plane block (ESPB) on these parameters in ASA scores 1-2 patients undergoing modified radical breast cancer surgery with general anesthesia. Methods: Forty-eight patients were divided into two groups: general anesthesia with erector spinae plane block (GA+ESPB) and a control group receiving only general anesthesia (GA). Hemodynamic parameters were continuously monitored, and postoperative pain was assessed using the visual analog scale (VAS) at various time points. Results: Ultrasound-guided ESPB effectively maintained hemody-namic stability and reduced postoperative pain in breast cancer surgery patients. Statistically significant differences were observed in heart rate, systolic and diastolic blood pressure, and mean arterial pressure between the GA and GA+ESPB groups at multiple time points (p<0.05). VAS scores showed a significant interaction time*group (p<0.001), with consistent differences between the groups at all time points (p≤0.001). Conclusion: Ultrasound-guided ESPB application proved ef-fective in preserving hemodynamic stability and managing postoperative pain in modified radical breast cancer surgery. The technique demonstrates promise in minimizing complications related to hemodynamic variations and postoperative pain, contributing to a comprehensive approach in breast cancer surgical treatment.