Background: Spontaneous subarachnoid haemorrhage (SAH) represents a significant cerebrovascular disease with considerable morbidity and mortality. The aim of this study was to determine the demographic/clinical characteristics of spontaneous SAH patients admitted in the intensive care unit (ICU) and factors affecting the mortality. Methods: This study was designed as a retrospective cohort study that included patients with a diagnosis of spontaneous SAH hospitalized in the ICU. The clinical and radiological parameters were compared between mortality and survival cohorts. Univariate logistic regression analyses were performed for the effect profiles of the parameters on mortality. Results: ICU mortality was 41% in patients with spontaneous SAH. A number of factors have been identified as being independently associated with mortality in the studied cohort. These factors are hospital admission with loss of consciousness (Glasgow Coma Scale score 2 according to the Hunt and Hess grading system and complication status (meningitis and sepsis/septic shock). Conclusions: Spontaneous SAH is a condition associated with a high mortality in severe cases. Patients exhibiting these risk factors require meticulous monitoring in the ICU.

Background and Objectives: Ovarian cancer surgery requires multiple radical resections with a high risk of complications. The aim of this single-centre, retrospective study was to determine the best method for predicting Clavien–Dindo grade ≥ III complications using machine learning techniques. Material and Methods: The study included 179 patients who underwent surgery at the gynaecological oncology department of Antalya Training and Research Hospital between January 2015 and December 2020. The data were randomly split into training set n = 134 (75%) and test set n = 45 (25%). We used 49 predictors to develop the best algorithm. Mean absolute error, root mean squared error, correlation coefficients, Mathew’s correlation coefficient, and F1 score were used to determine the best performing algorithm. Cohens’ kappa value was evaluated to analyse the consistency of the model with real data. The relationship between these predicted values and the actual values were then summarised using a confusion matrix. True positive (TP) rate, False positive (FP) rate, precision, recall, and Area under the curve (AUC) values were evaluated to demonstrate clinical usability and classification skills. Results: 139 patients (77.65%) had no morbidity or grade I-II CDC morbidity, while 40 patients (22.35%) had grade III or higher CDC morbidity. BayesNet was found to be the most effective prediction model. No dominant parameter was observed in the Bayesian net importance matrix plot. The true positive (TP) rate was 76%, false positive (FP) rate was 15.6%, recall rate (sensitivity) was 76.9%, and overall accuracy was 82.2% A receiver operating characteristic (ROC) analysis was performed to estimate CDC grade ≥ III. AUC was 0.863 with a statistical significance of p < 0.001, indicating a high degree of accuracy. Conclusions: The Bayesian network model achieved the highest accuracy compared to all other models in predicting CDC Grade ≥ III complications following epithelial ovarian cancer surgery.

Background: Dyspnea is a frequent complaint during pregnancy and is often considered a benign physiological finding; however, it may also reflect underlying subclinical cardiovascular alterations. Pregnancy-related vascular remodeling and low-grade systemic inflammation may contribute to changes in aortic elastic properties and inflammatory biomarkers, particularly in symptomatic women. Objective: This study aimed to compare aortic elastic properties and albumin-based inflammatory indices between dyspneic and asymptomatic third-trimester pregnant women. A secondary aim was to establish reference values for echocardiographic and biomarker parameters in dyspneic pregnancy. Methods: In this prospective observational study, third-trimester pregnant women (≥27 gestational weeks) presenting to the emergency department (ED) with dyspnea were consecutively enrolled and compared with age-matched asymptomatic pregnant controls. Demographic, laboratory, and echocardiographic data were recorded. Aortic strain, aortic distensibility, and aortic stiffness were calculated using transthoracic echocardiography. Albumin-based inflammatory indices, including the hemoglobin–albumin–lymphocyte–platelet (HALP) score, prognostic nutritional index (PNI), C-reactive protein-to-albumin ratio (CAR), and RDW-to-albumin ratio (RAR), were analyzed. Receiver operating characteristic (ROC) and correlation analyses were performed. Results: A total of 241 pregnant women were included (121 dyspneic, 120 controls). Demographic characteristics were comparable between groups. Dyspneic pregnant women exhibited significantly lower aortic strain and aortic distensibility and higher aortic stiffness compared with controls (for all p < 0.05). Among laboratory parameters, CAR levels were significantly elevated in the dyspneic group (p < 0.001), whereas HALP, PNI, and RAR did not differ significantly. After adjustment for potential confounders, differences in aortic elastic properties remained significant. CAR demonstrated moderate discriminative ability for dyspnea (AUC = 0.692), while aortic elastic parameters showed modest predictive performance. In combined prediction models incorporating CAR with echocardiographic parameters, discriminatory performance improved, with area under the curve values exceeding 0.70. Weak positive correlations were observed between PNI and aortic strain and distensibility. Conclusions: Dyspneic third-trimester pregnant women exhibit impaired aortic elastic properties and increased CAR levels, suggesting the presence of subclinical vascular and inflammatory alterations. Assessment of aortic elasticity and CAR may provide a simple and practical approach for early cardiovascular risk stratification in symptomatic pregnancy, particularly in ED settings. Further multicenter studies with longitudinal follow-up are warranted to clarify their prognostic significance.

This study, which included patients over the age of 18 who were diagnosed with coronavirus disease 2019 (COVID-19) in the emergency clinic, aims to determine the relationship between coagulation parameters and mortality. Epidemiologic data such as age, gender, medical history, vital parameters at emergency department admission, clinical findings, coagulation parameters such as d-dimer, prothrombin time (PT), active partial thromboplastin time (aPTT), international normalized ration (INR), fibrinogen, and platelet were evaluated. Patients with positive computerized tomography (CT) findings and positive polymerase chain reaction (PCR) together were included in the study. It was revealed that d-dimer, fibrinogen, INR, and PT values were higher in the elderly group. It was shown that there was a significant relationship between hospitalization days (ward or intensive care unit) and d-dimer levels. It was observed that d-dimer, fibrinogen elevation was significantly associated with prognosis by increasing mortality, and that platelet and aPTT values were also associated with prognosis and were lower in the mortality group. On the other hand, in receiver operating characteristic (ROC) analysis, the sensitivity and specificity data were 80.3%/80.0% for d-dimer, 70.5%/72.2% for fibrinogen, 58.2%/59.4% for aPTT, and 59.7%/59.2% for platelet, respectively. The overall classification success was 88.6% and mortality prediction success was 37.7% in the regression model of some coagulation parameters (d-dimer, fibrinogen, aPTT, and platelet) which were effective on prognosis. In conclusion, it was determined that d-dimer, fibrinogen, aPTT, and platelet parameters were directly associated with mortality and when these coagulation parameters were used together with the clinical, vital, and demographic data of the patients, the success of mortality prediction increased significantly.

Background/Objectives: Pneumonia remains a leading cause of emergency department visits worldwide, requiring rapid and objective risk stratification. While traditional scoring systems like CURB-65 and the Pneumonia Severity Index (PSI) are well-established, there is a constant need for dynamic biomarkers reflecting the underlying pathophysiology. This study aims to investigate the prognostic value of the hemoglobin-to-lactate ratio (HLR) in predicting mortality among pneumonia patients. Methods: This retrospective cohort study included 183 adult patients diagnosed with pneumonia at a tertiary training and research hospital between October 2024 and November 2025. Demographic data, clinical findings, laboratory parameters, and prognostic scores (CURB-65, PSI) were recorded. The impact of HLR on mortality was evaluated using univariate and multivariate logistic regression, while its predictive performance was assessed via Receiver Operating Characteristic (ROC) analysis and compared with clinical scores using DeLong’s method. Results: The overall mortality rate was 32.8%. HLR values were significantly lower in the exitus group compared to survivors (4.68 vs. 6.92, p < 0.001). Multivariate analysis revealed that an HLR ≤ 5.65 was an independent predictor of mortality, associated with a 10-fold increase in risk (OR: 10.0; 95% CI: 4.15–24.19; p < 0.001). HLR demonstrated high predictive power (AUC = 0.802), comparable to CURB-65 (AUC = 0.807) and PSI (AUC = 0.829). Notably, the combined HLR + CURB-65 model provided the highest diagnostic accuracy (AUC = 0.857, p = 0.037). Conclusions: HLR is a low-cost and easily accessible biomarker for predicting mortality in pneumonia. It effectively reflects the physiological balance between tissue oxygenation and metabolic failure. Integrating HLR into clinical practice, particularly when combined with traditional scores, can enhance risk (decision of discharge, admission unit [ward, ICU], evaluation of prognosis) in the emergency department.

Aims: This study aimed to assess the predictive performance of artificial intelligence–based models in estimating progressionfree survival (PFS) in patients with epithelial ovarian cancer and to compare various interpretable machine learning approaches. Methods: Between January 2015 and December 2020, a total of 167 patients who underwent surgical intervention at the Gynaecological Oncology Department of Antalya Training and Research Hospital were retrospectively included in the study if their data were complete. Clinical data were analysed, and the dataset was randomly divided into a training group (n=117; 75%) and a validation group (n=42; 25%). A machine learning (ML) analysis was conducted using the eight most relevant and widely applied algorithmic models for this study design. Model development time, mean absolute error (MAE), root mean square error (RMSE), and correlation coefficient (CC) were evaluated. Results: Random Forest demonstrated the highest accuracy (MAE=16.45, CC=0.571, RMSE=20.98, time=0.03) and thus became the focus of subsequent analyses. Other algorithms included Linear Regression, Bootstrap Aggregating, Additive Regression, Random Committee, and Regression by Discretization (CC=0.533, 0.492, 0.449, 0.408, and 0.382, respectively). For Random Forest, a moderate correlation was observed between actual and predicted PFS values (CC=0.4–0.6), indicating moderate predictive performance. Conclusion: The findings of this study demonstrate that machine learning models, particularly Random Forest, can achieve moderate yet clinically relevant prognostic performance based on routinely collected clinical data. In particular, Random Forest demonstrates potential clinical value in guiding patient follow-up strategies and supporting individualized management in ovarian cancer, although further research is required to enhance its clinical validity and applicability.