Infected pancreatic necrosis (IPN) represents a severe complication of acute pancreatitis, commonly linked with mortality rates ranging from 15% to 35%. However, the present mortality prediction tools for IPN are limited and lack sufficient sensitivity and specificity. This study aims to develop and validate an explainable machine learning (ML) model for death prediction among patients with IPN. We performed a prospective cohort study of 344 patients with IPN consecutively enrolled from a large Chinese tertiary hospital from January 2011 to January 2023. Ten ML models were developed to predict 90-day mortality in these patients. A benchmarking test, involving nested resampling, automatic hyperparameter tuning and random search techniques, was conducted to select the ML model. Sequential forward selection method was employed to select the optimal feature subset from 31 candidate subsets to simplify the model and maximize predictive performance. The final model was internally validated with the 1000 bootstrap method and externally validated using an independent cohort of 132 patients with IPN retrospectively collected from another Chinese tertiary hospital from January 2018 to January 2023. The SHapley Additive exPlanations (SHAP) method was employed to interpret the model in terms of features importance and features effect. The final model constructed with optimal feature subset was deployed as an interactive web-based Shiny app. Random survival forest (RSF) model showed the best predictive performance than other 9 ML models (internal validation, C-index = 0.863 [95% CI: 0.854-0.875]; external validation, C-index = 0.857 [95% CI: 0.850-0.865]). Multiple organ failure, Acute Physiology and Chronic Health Examination II (APACHE II) score ≥20, duration of organ failure ≥21 days, bloodstream infection, time from onset to first intervention <30 days, Bedside Index of Severity in Acute Pancreatitis score ≥3, critical acute pancreatitis, age ≥ 50 years, and hemorrhage were 9 most important features associated with mortality. Furthermore, SHAP algorithm revealed insightful nonlinear interactive associations between important predictors and mortality, identifying 9 features pairs with high interaction SHAP value and clinical significance. Two interactive web-based Shiny apps were developed to enhance clinical practicability: https://rsfmodels.shinyapps.io/IPN_app/ for cases where the APACHE II score was available and https://rsfmodels.shinyapps.io/IPNeasy/ for cases where it was not. An explainable ML model for death prediction among IPN patients was feasible and effective, suggesting its superior potential in guiding clinical management and improving patient outcomes. Two publicly accessible web tools generated for the optimized model facilitated its utility in clinical settings. The Natural Science Foundation of Hunan Province (2023JJ30885), Postdoctoral Fellowship Program of CPSF (GZB20230872), The Youth Science Foundation of Xiangya Hospital (2023Q13), The Project Program of National Clinical Research Center for Geriatric Disorders of Xiangya Hospital (2021LNJJ19).

Multidrug-resistant organisms (MDROs) is becoming a serious worldwide threat to public health. However, the impact of MDROs on the outcomes of the patients with infected pancreatic necrosis (IPN) remains unclear. This study aims to evaluate the roles of MDROs in IPN. A prospectively maintained database of 188 patients with IPN between January 2010 and May 2019 was analyzed. The microbiology profile of organisms isolated from wall-off necrosis (WON) was specifically investigated to correlate with the outcomes of the patients. Of the 188 patients with IPN, 108 patients (57.4%) had MDROs detected in aspirates from WON. Carbapenem-resistant Klebsiella pneumoniae (CRKP) accounted for 43.5% of the MDROs isolated (60/138), followed by Carbapenem-resistant Acinetobacter baumanii (CRAB) (34.8%, 48/138) and Escherichia coli producing an extended-spectrum beta-lactamase (ESBLp) (6.5%, 9/138). MDROs infection was associated with higher mortality (35.2% vs 11.3%, P < 0.001), higher rate of hemorrhage (36.1% vs 11.3%, P < 0.001), longer intensive care unit (ICU) stay (23 vs 12 days, P < 0.001), longer hospital stay (68 vs 51 days, P = 0.001) and more hospitalization expenses (45,190 ± 31,680 vs 26,965 ± 17,167 $, P < 0.001). Multivariate analysis of predictors of mortality indicated that MDROs infection (OR = 2.6; 95% confidence interval [CI], 1.0-6.5; P = 0.042), age ≥ 50 years (OR = 2.6; 95% CI, 1.2-5.8; P = 0.016), severe category (OR = 2.9; 95% CI, 1.1-8.0; P = 0.035), bloodstream infection (OR = 3.4; 95% CI, 1.5-7.6; P = 0.049), step-down surgical approach (OR = 2.7; 95% CI, 1.1-6.2; P = 0.023) were significant factors. MDROs infection was prevalent among patients with IPN and associated with adverse clinical outcomes and increased mortality.

Background: Duodenal fistula (DF) was reportedly thought to be the second most common type of gastrointestinal fistula secondary to acute necrotizing pancreatitis. However, infected pancreatic necrosis (IPN) associated DF (IPN-DF) was rarely specifically reported in the literature. The outcome of IPN-DF was also less well recognized, especially in the era of minimally invasive techniques. A retrospective cohort study was designed mainly focused on the management and outcomes of IPN-DF in the era of minimally invasive techniques. Methods: One hundred and twenty-one consecutive patients diagnosed with IPN between January 2015 and May 2018 were enrolled retrospectively. Among them, 10 patients developed DF. The step-up minimal invasive techniques were highlighted and outcomes were analyzed. Results: Compared with patients without IPN-DF, patients with IPN-DF had longer hospital stay (95.8 vs. 63.5 days, p < .01), but similar mortality rates (10% vs. 21.6%, p > .05). The median interval between the onset of acute pancreatitis (AP) and detection of DF was 2.4 months (1–4 months). The median duration of DF was 1.5 months (0.5–3 months). Out of the 10 patients with DF, 9 had their fistulas resolve spontaneously over time by means of controlling the source of infection with the use of minimally invasive techniques and providing enteral nutritional support, while one patient died of uncontrolled sepsis. No open surgery was performed. On follow-up, the 9 patients recovered completely and remained free of infection and leakage. Conclusion: IPN-DF could be managed successfully using minimally invasive techniques in specialized acute pancreatitis (AP) center. Patients with IPN-DF suffered from a longer hospital stay, but similar mortality rate compared with patients without DF.

Background: Infected pancreatic necrosis (IPN) is a severe complication of acute pancreatitis, with mortality rates ranging from 15 to 35%. However, limited studies exist to predict the survival of IPN patients and nomogram has never been built. This study aimed to identify predictors of mortality, estimate conditional survival (CS), and develop a CS nomogram and logistic regression nomogram for real-time prediction of survival in IPN patients. Methods: A prospective cohort study was performed in 335 IPN patients consecutively enrolled at a large Chinese tertiary hospital from January 2011 to December 2022. The random survival forest method was first employed to identify the most significant predictors and capture clinically relevant nonlinear threshold effects. Instantaneous death risk and CS was first utilized to reveal the dynamic changes in the survival of IPN patients. A Cox model-based nomogram incorporating CS and a logistic regression-based nomogram were first developed and internally validated with a bootstrap method. Results: The random survival forest model identified seven foremost predictors of mortality, including the number of organ failures, duration of organ failure, age, time from onset to first intervention, hemorrhage, bloodstream infection, and severity classification. Duration of organ failure and time from onset to first intervention showed distinct thresholds and nonlinear relationships with mortality. Instantaneous death risk reduced progressively within the first 30 days, and CS analysis indicated gradual improvement in real-time survival since diagnosis, with 90-day survival rates gradually increasing from 0.778 to 0.838, 0.881, 0.974, and 0.992 after surviving 15, 30, 45, 60, and 75 days, respectively. After further variables selection using step regression, five predictors (age, number of organ failures, hemorrhage, time from onset to first intervention, and bloodstream infection) were utilized to construct both the CS nomogram and logistic regression nomogram, both of which demonstrated excellent performance with 1000 bootstrap. Conclusion: Number of organ failures, duration of organ failure, age, time from onset to first intervention, hemorrhage, bloodstream infection, and severity classification were the most crucial predictors of mortality of IPN patients. The CS nomogram and logistic regression nomogram constructed by these predictors could help clinicians to predict real-time survival and optimize clinical decisions.