To examine the hemoglobin, albumin, lymphocyte, and platelet (HALP) scores' predictive power in predicting short-term mortality from acute pancreatitis (AP). The study was conducted at the emergency department (ED) of tertiary care hospital. The medical records of patients who admitted to the ED and were diagnosed with AP were reviewed retrospectively. İt was analyzed that the ability of the HALP score in predicting short-term mortality of these patients. The study was achieved with a total of 634 patients. The mean age of these patients was 59.7±16.6 and 381 (60.1%) were female. While 42 (6.6%) of the total included patients were required to the intensive care unit, 58 (9.1%) died. To examine the HALP scores' predictive power in predicting short-term mortality, the Receiver Operating Characteristic (ROC) analysis was utilized. The value of the area under the curve was found as 0.891 (95% CI: 0.833-0.949). When the cut-off value of the HALP score in determining short-term mortality is >15, the Sensitivity of the score was found to be 82.8%, Specificity 86.8%, Positive Predictive Value 38.7%, and Negative Predictive Value 98.0%. AP is a disease that requires early diagnosis and adequate treatment if not it can cause a high rate of mortality and morbidity. As a result of this study, it was concluded that the HALP score can be utilized during the prediction of short-term mortality for patients diagnosed with AP.

The aim of this study was to evaluate the role of the prognostic nutritional index in predicting in-hospital mortality among patients with acute ischemic stroke.

Background/Objectives: Severe acute pancreatitis (SAP) carries substantial morbidity and resource burden, and early risk stratification remains challenging with conventional scores that require serial observations. The aim of this study was to develop and compare supervised machine-learning (ML) pipelines—integrating feature selection and SHAP-based explainability—for early prediction of SAP at emergency department (ED) presentation. Methods: This retrospective, single-center cohort was conducted in a tertiary-care ED between 1 January 2022 and 1 January 2025. Adult patients with acute pancreatitis were identified from electronic records; SAP was classified per the Revised Atlanta criteria (persistent organ failure ≥ 48 h). Six feature-selection methods (univariate AUROC filter, RFE, mRMR, LASSO, elastic net, Boruta) were paired with six classifiers (kNN, elastic-net logistic regression, MARS, random forest, SVM-RBF, XGBoost) to yield 36 pipelines. Discrimination, calibration, and error metrics were estimated with bootstrapping; SHAP was used for model interpretability. Results: Of 743 patients (non-SAP 676; SAP 67), SAP prevalence was 9.0%. Compared with non-SAP, SAP patients more often had hypertension (38.8% vs. 27.1%) and malignancy (19.4% vs. 7.2%); they presented with lower GCS, higher heart and respiratory rates, lower systolic blood pressure, and more frequent peripancreatic fluid (31.3% vs. 16.9%) and pleural effusion (43.3% vs. 17.5%). Albumin was lower by 4.18 g/L, with broader renal–electrolyte and inflammatory derangements. Across the best-performing models, AUROC spanned 0.750–0.826; the top pipeline (RFE–RF features + kNN) reached 0.826, while random-forest-based pipelines showed favorable calibration. SHAP confirmed clinically plausible contributions from routinely available variables. Conclusions: In this study, integrating feature selection with ML produced accurate and interpretable early prediction of SAP using data available at ED arrival. The approach highlights actionable predictors and may support earlier triage and resource allocation; external validation is warranted.

BACKGROUND: Aortic dissection (AD) is a serious cardiovascular condition associated with high mortality rates. The systemic inflammatory response can influence the prognosis of AD, and in this context, the neutrophil-to-lymphocyte ratio (NLR) emerges as a simple and rapid inflammatory biomarker. METHODS: This retrospective cohort study included 103 patients diagnosed with AD and treated in the emergency department between 2018 and 2023. Patient demographics, clinical features, and laboratory results were evaluated. Multivariate logistic regression analysis was performed to adjust for potential confounders such as age, mean systolic blood pressure, oxygen saturation, hemoglobin, lactate values, and the presence of coronary artery disease. The ability of NLR to predict mortality was analyzed using receiver operating characteristic (ROC) analysis. RESULTS: The study population was divided into two groups: non-survivors (68% mortality rate) and survivors (32% survival rate). The non-survivor group had significantly higher NLR values compared to the survivor group (median NLR 7.66 vs. 2.5, p<0.001). Multivariate logistic regression analysis identified NLR as an independent predictor of in-hospital mortality (adjusted odds ratio [OR] 2.33, 95% confidence interval [CI] 1.42-3.82, p5.08 with a sensitivity of 77.14% and specificity of 81.82%. CONCLUSION: The findings indicate that high NLR is strongly associated with increased mortality risk in patients with AD and can be used in emergency clinical settings to predict mortality.

Background/Objectives: Non-variceal upper gastrointestinal bleeding (NVUGIB) is associated with considerable morbidity and mortality, particularly in emergency department (ED) settings. While traditional clinical scores such as the Glasgow-Blatchford Score (GBS), AIMS65, and Pre-Endoscopic Rockall are widely used for risk stratification, their accuracy in mortality prediction is limited. This study aimed to evaluate the performance of multiple supervised machine learning (ML) models in predicting 30-day all-cause mortality in NVUGIB and to compare these models with established risk scores. Methods: A retrospective cohort study was conducted on 1233 adult patients with NVUGIB who presented to the ED of a tertiary center between January 2022 and January 2025. Clinical and laboratory data were extracted from electronic records. Seven supervised ML algorithms—logistic regression, ridge regression, support vector machine, random forest, extreme gradient boosting (XGBoost), naïve Bayes, and artificial neural networks—were trained using six feature selection techniques generating 42 distinct models. Performance was assessed using AUROC, F1-score, sensitivity, specificity, and calibration metrics. Traditional scores (GBS, AIMS65, Rockall) were evaluated in parallel. Results: Among the cohort, 96 patients (7.8%) died within 30 days. The best-performing ML model (XGBoost with univariate feature selection) achieved an AUROC > 0.80 and F1-score of 0.909, significantly outperforming all traditional scores (highest AUROC: Rockall, 0.743; p < 0.001). ML models demonstrated higher sensitivity and specificity, with improved calibration. Key predictors consistently included age, comorbidities, hemodynamic parameters, and laboratory markers. The best-performing ML models demonstrated very high apparent AUROC values (up to 0.999 in internal analysis), substantially exceeding conventional scores. These results should be interpreted as apparent performance estimates, likely optimistic in the absence of external validation. Conclusions: While machine-learning models showed markedly higher apparent discrimination than conventional scores, these findings are based on a single-center retrospective dataset and require external multicenter validation before clinical implementation.