Background and Objectives: Early identification of patients with acute pancreatitis (AP) who will require operative intervention remains a major clinical challenge. Traditional severity scores and delayed inflammatory biomarkers offer limited early predictive accuracy. This study aimed to evaluate the combined predictive value of IL-6, necrotic burden, and organ failure parameters for determining the need for surgical management in AP. Materials and Methods: We performed a retrospective cohort study of 325 consecutive patients with AP admitted to Floreasca Emergency Hospital between January 2020 and December 2024. Clinical, laboratory, and imaging parameters were collected, including IL-6 at 24 h, CRP at 48–72 h, SOFA and BISAP scores, and morphologic complications. The primary endpoint was the requirement for operative intervention. Univariate and multivariable logistic regression analyses were conducted, and model performance was assessed using ROC curves and calibration testing. Results: Sixty patients (18.5%) underwent surgery for pancreatitis-related complications. Operated patients demonstrated higher IL-6 levels (median 120 vs. 55 pg/mL), necrosis >30% (68.3% vs. 14%), infected necrosis (55% vs. 2.3%), and persistent organ failure (46.7% vs. 9.8%) (all p < 0.001). In multivariable analysis, IL-6 at 24 h (OR 1.35 per 50 pg/mL), necrosis > 30% (OR 4.80), infected necrosis (OR 6.20), persistent organ failure ≥48 h (OR 2.60), SOFA score (OR 1.18 per point), and CRP at 48–72 h (OR 1.09 per 50 mg/L) independently predicted surgery. The final model showed excellent discrimination (AUC 0.88) and good calibration. Conclusions: IL-6-driven inflammatory escalation, combined with necrotic burden and persistent organ dysfunction, provides a robust early predictive framework for identifying AP patients likely to require surgical intervention. Integration of these parameters may improve triage, timing of intervention, and multidisciplinary decision-making in acute pancreatitis.

Background/Objectives: Acute gastrointestinal (GI) emergencies require timely and accurate prediction of surgical necessity to avoid delayed intervention and improve patient outcomes. Traditional scoring systems offer limited accuracy and fail to integrate multimodal data. This study aimed to develop and validate an explainable machine learning model for early prediction of surgical necessity in patients presenting with GI emergencies. Methods: A retrospective cohort of 1032 consecutive adult patients admitted with acute GI emergencies at a tertiary referral center (2019–2024) was analyzed. Three predictive models were developed: logistic regression, Random Forest, and XGBoost. Features included clinical, laboratory, and contrast-enhanced CT imaging variables available within the first 24 h. Model performance was evaluated using AUC, sensitivity, specificity, PPV, NPV, and F1-score. Shapley Additive Explanations (SHAP) were applied for global and individual-level interpretability. The study followed STROBE and TRIPOD+AI reporting guidelines. Results: Surgical intervention was required in 312 patients (30.2%). The XGBoost model achieved the highest AUC (0.89; 95% CI: 0.86–0.92), outperforming Random Forest (AUC 0.86) and logistic regression (AUC 0.79), with sensitivity 0.84, specificity 0.81, and NPV 0.90. The most influential predictors were serum lactate, CT findings (free intraperitoneal air, bowel ischemia), IL-6, and shock index. Decision curve analysis confirmed net clinical benefit across threshold probabilities of 10–70%. Subgroup performance remained robust across diagnostic categories (AUC 0.87–0.91). Conclusions: An explainable XGBoost model integrating early clinical, laboratory, and imaging data accurately predicts surgical necessity in GI emergencies and outperforms traditional scoring systems. SHAP-based explainability supports clinical adoption and transparency. Prospective multicenter validation is warranted. The positive predictive value of 0.74 indicates that approximately one in four patients flagged as requiring surgery may not need operative intervention. The model should be regarded as a decision-support adjunct, rather than a standalone surgical decision tool, that is most relevant in settings where immediate experienced surgical judgment is limited.

Background/Objectives: Five-day treatment failure after acute variceal bleeding combines failure of bleeding control and early rebleeding, which may reflect different clinical processes. We explored whether admission scores and endoscopic findings relate similarly to these components. Methods: All 303 consecutive admissions treated with band ligation at a tertiary centre during 2021–2025 were analysed. Six scores were compared using paired AUROCs and Holm adjustment. Results: Failure occurred in 31 admissions (10.2%): 15 failures of primary haemostasis and 17 rebleeds, with one admission meeting both components. Point estimates of discrimination were higher for rebleeding for all six scores (differences 0.123–0.236), but intervals were wide, and no formal between-component test was performed. No comparison among the six scores using the primary score definitions survived the Holm adjustment for the composite or either component; this does not establish equivalence. Active bleeding at endoscopy was associated with failure of primary haemostasis (odds ratio 4.52, 95% CI 1.40–14.53), whereas its association with rebleeding was uncertain (1.07, 0.40–2.90). Red wale markings showed no clear association. Conclusions: This exploratory pattern suggests that the components may capture different clinical processes, a hypothesis requiring prospective confirmation in a larger cohort. Non-standardised outcome classification, uncertain follow-up after transfer, intervening TIPS and sensitivity to recorded versus recomputed scores limit inference.