Acute pancreatitis (AP) can result in severe complications, with acute respiratory failure (ARF) being among the most critical. Research on ARF in AP remains limited. This study aims to investigate the occurrence, outcomes, and predictors of ARF in AP patients at Cho Ray Hospital, a tertiary care center in Vietnam.

A prospective cohort study was conducted with 230 AP patients at a national hospital in Ho Chi Minh City, Vietnam. Patients were divided into ARF and non-ARF groups, and clinical characteristics were compared. Key outcomes included invasive mechanical ventilation, in-hospital mortality, and length of hospital stay.

ARF developed in 26.1% of patients, with a mortality rate of 25.0% in the ARF group versus 1.2% in the non-ARF group. Mechanical ventilation was required in 48.3% of ARF patients. Significant predictors of ARF were abnormal body mass index (BMI) (p = 0.021), prolonged systemic inflammatory response syndrome (SIRS) (p < 0.001), modified computed tomography severity index (mCTSI) (p = 0.041), and a high bedside index for severity in acute pancreatitis (BISAP) score (p < 0.001). BISAP scores ≥ 2 had a sensitivity of 90.0%, specificity of 73.5%, and AUC of 0.878 (95% CI 0.829-0.921) for predicting ARF. Predictors of mortality in ARF patients included cardiovascular failure (HR 15.83, p = 0.001), prolonged SIRS (HR 4.76, p = 0.038), and high BISAP scores (HR 3.41, p = 0.015).

ARF significantly worsens outcomes in AP patients. Early identification of key predictors, like abnormal BMI, prolonged SIRS, mCTSI, and BISAP scores, could improve interventions and patient prognosis.

Acute respiratory distress syndrome (ARDS) is a clinical syndrome of acute hypoxic respiratory failure caused by diffuse lung inflammation and edema. ARDS can be precipitated by intrapulmonary factors or extrapulmonary factors, which can lead to severe hypoxemia. Patients suffering from ARDS have high mortality rates, including a 28-day mortality rate of 34.8% and an overall in-hospital mortality rate of 40.0%. The pathophysiology of ARDS is complex and involves the activation and dysregulation of multiple overlapping and interacting pathways of systemic inflammation and coagulation, including the respiratory system, circulatory system, and immune system. In general, the treatment of inflammatory injuries is a coordinated process that involves the downregulation of proinflammatory pathways and the upregulation of anti-inflammatory pathways. Given the complexity of the underlying disease, treatment needs to be tailored to the problem. Hence, we discuss the pathogenesis and treatment methods of affected organs, including 2019 coronavirus disease (COVID-19)-related pneumonia, drowning, trauma, blood transfusion, severe acute pancreatitis, and sepsis. This review is intended to provide a new perspective concerning ARDS and offer novel insight into future therapeutic interventions.

Acute kidney injury (AKI) represents a frequent and grave complication associated with acute pancreatitis (AP), substantially elevating both mortality rates and the financial burden of hospitalization. The aim of our study is to construct a predictive model utilizing automated machine learning (AutoML) algorithms for the early prediction of AKI in patients with AP.

We retrospectively analyzed patients who were diagnosed with AP in our hospital from January 2017 to December 2021. These patients were randomly allocated into a training set and a validation set at a ratio of 7:3. To develop predictive models for each set, we employed the least absolute shrinkage and selection operator (LASSO) algorithm along with AutoML. A nomogram was developed based on multivariate logistic regression analysis outcomes. The model's efficacy was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Additionally, the performance of the model constructed via AutoML was evaluated using decision curve analysis (DCA), feature importance, SHapley Additive exPlanations (SHAP) plots, and locally interpretable model-agnostic explanations (LIME).

This study incorporated a total of 437 patients who met the inclusion criteria. Out of these, 313 were assigned to the training cohort and 124 to the validation cohort. In the training and validation cohorts, AKI occurred in 68 (21.7%) and 29(23.4%) patients, respectively. Comparative analysis revealed that the AutoML models exhibited enhanced performance over traditional logistic regression (LR). Furthermore, the deep learning (DL) model demonstrated superior predictive accuracy, evidenced by an area under the ROC curve of 0.963 in the training set and 0.830 in the validation set, surpassing other comparative models. The key variables identified as significant in the DL model within the training dataset included creatinine (Cr), urea (Urea), international normalized ratio (INR), etiology, smoking, alanine aminotransferase (ALT), hypertension, prothrombin time (PT), lactate dehydrogenase (LDH), and diabetes.

The AutoML model, utilizing DL algorithm, offers considerable clinical significance in the early detection of AKI among patients with AP.

To assess the performance of validated prediction models for acute respiratory distress syndrome (ARDS) by systematic review and meta-analysis.

Eight databases (Medline, CINAHL, Embase, The Cochrane Library, CNKI, WanFang Data, Sinomed, and VIP) were searched up to March 26, 2023. Studies developed and validated a prediction model for ARDS in adult patients were included. Items on study design, incidence, derivation methods, predictors, discrimination, and calibration were collected. The risk of bias was assessed by the Prediction model Risk of Bias Assessment Tool. Models with a reported area under the curve of the receiver operating characteristic (AUC) metric were analyzed.

A total of 25 studies were retrieved, including 48 unique prediction models. Discrimination was reported in all studies, with AUC ranging from 0.701 to 0.95. Emerged AUC value of the logistic regression model was 0.837 (95% CI: 0.814 to 0.859). Besides, the value in the ICU group was 0.856 (95% CI: 0.812 to 0.899), the acute pancreatitis group was 0.863 (95% CI: 0.844 to 0.882), and the postoperation group was 0.835 (95% CI: 0.808 to 0.861). In total, 24 of the included studies had a high risk of bias, which was mostly due to the improper methods in predictor screening (13/24), model calibration assessment (9/24), and dichotomization of continuous predictors (6/24).

This study shows that most prediction models for ARDS are at high risk of bias, and the discrimination ability of the model is excellent. Adherence to standardized guidelines for model development is necessary to derive a prediction model of value to clinicians.

Early identification and intervention of acute respiratory distress syndrome (ARDS) are particularly important. This study aimed to construct predictive models for ARDS following severe acute pancreatitis (SAP) by artificial neural networks and logistic regression. The artificial neural networks model was constructed using clinical data from 214 SAP patients. The patient cohort was randomly divided into a training set and a test set, with 149 patients allocated to the training set and 65 patients assigned to the test set. The artificial neural networks and logistic regression models were trained by the training set, and then the performance of both models was evaluated using the test set. The sensitivity, specificity, PPV, NPV, accuracy, and AUC value of artificial neural networks model were 68.0%, 87.5%, 77.3%, 81.4%, 80.0%, 0.853 ± 0.054 (95% CI: 0.749-0.958). The sensitivity, specificity, PPV, NPV, accuracy and AUC value of logistic regression model were 48.7%, 85.3%, 65.5%, 74.4%, 72.0%, 0.799 ± 0.045 (95% CI: 0.710-0.888). There were no significant differences between the artificial neural networks and logistic regression models in predictive performance. Bedside Index of Severity in Acute Pancreatitis score, procalcitonin, prothrombin time, and serum calcium were the most important predictive variables in the artificial neural networks model. The discrimination abilities of logistic regression and artificial neural networks models in predicting SAP-related ARDS were similar. It is advisable to choose the model according to the specific research purpose.

In this editorial we comment on the article published in the recent issue of the World Journal of Gastroenterology [2022; 28 (19): 2123-2136]. We pay attention to how to construct a simpler and more reliable new clinical predictive model to early identify patients at high risk of acute respiratory distress syndrome (ARDS) associated with severe acute pancreatitis (SAP), and to early predict the severity of organ failure from chest computed tomography (CT) findings in SAP patients. As we all know, SAP has a sudden onset, is a rapidly changing condition, and can be complicated with ARDS and even multiple organ dysfunction syndrome, and its mortality rate has remained high. At present, there are many clinical scoring systems for AP, including the bedside index for severity in AP, acute physiology and chronic health evaluation II, systemic inflammatory response syndrome, Japanese severe score, quick sepsis-related organ failure assessment, etc. However, some of these scoring systems are complex and require multiple and difficult clinical parameters for risk stratification. Although the aforementioned biomarkers are readily available, their ability to predict ARDS varies. Accor-dingly, it is extremely necessary to establish a simple and valuable novel model to predict the development of ARDS in AP. In addition, the extra-pancreatic manifestations of AP patients often involve the chest, among which pleural effusion and pulmonary consolidation are the more common complications. Therefore, by measuring the semi-quantitative indexes of chest CT in AP patients, such as the amount of pleural effusion and the number of lobes involved as pulmonary consolidation, it has important reference value for the early diagnosis of SAP complicated with ARDS and is expected to provide a basis for the early treatment of ARDS.