Effects of acute kidney injury on acute pancreatitis patients’ survival rate in intensive care unit: A retrospective study

Predictive model of acute kidney injury in critically ill patients with acute pancreatitis: a machine learning approach using the MIMIC-IV database

BACKGROUND

Acute kidney injury (AKI) is a common and serious complication in severe acute pancreatitis (AP), associated with high mortality rate. Early detection of AKI is crucial for prompt intervention and better outcomes. This study aims to develop and validate predictive models using machine learning (ML) to identify the onset of AKI in patients with AP.

METHODS

Patients with AP were extracted from the MIMIC-IV database. We performed feature selection using the random forest method. Model construction involved an ensemble of ML, including random forest (RF), support vector machine (SVM), k-nearest neighbors (KNN), naive Bayes (NB), neural network (NNET), generalized linear model (GLM), and gradient boosting machine (GBM). The best-performing model was fine-tuned and evaluated through split-set validation.

RESULTS

We analyzed 1,235 critically ill patients with AP, of which 667 cases (54%) experienced AKI during hospitalization. We used 49 variables to construct models, including GBM, GLM, KNN, NB, NNET, RF, and SVM. The AUC for these models was 0.814 (95% CI, 0.763 to 0.865), 0.812 (95% CI, 0.769 to 0.854), 0.671 (95% CI, 0.622 to 0.719), 0.812 (95% CI, 0.780 to 0.864), 0.688 (95% CI, 0.624 to 0.752), 0.809 (95% CI, 0.766 to 0.851), and 0.810 (95% CI, 0.763 to 0.856) respectively. In the test set, the GBM's performance was consistent, with an area of 0.867 (95% CI, 0.831 to 0.903).

CONCLUSIONS

The GBM model's precision is crucial, aiding clinicians in identifying high-risk patients and enabling timely interventions to reduce mortality rates in critical care.

Predictive and Prognostic Potentials of Lymphocyte-C-Reactive Protein Ratio Upon Hospitalization in Adult Patients with Acute Pancreatitis

Purpose

In this study, our objective was to investigate the potential utility of lymphocyte-C-reactive protein ratio (LCR) as a predictor of disease progression and a screening tool for intensive care unit (ICU) admission in adult patients with acute pancreatitis (AP).

Methods

We included a total of 217 adult patients with AP who were admitted to the First Affiliated Hospital of Harbin Medical University between July 2019 and June 2022. These patients were categorized into three groups: mild AP (MAP), moderately severe AP (MSAP), and severe AP (SAP), based on the presence and duration of organ dysfunction. Various demographic and clinical data were collected and compared among different disease severity groups.

Results

Height, diabetes, lymphocyte count (LYMPH), lymphocyte percentage (LYM%), platelet count (PLT), D-Dimer, albumin (ALB), blood urea nitrogen (BUN), serum creatinine (SCr), glucose (GLU), calcium ion (Ca2+), C-reactive protein (CRP), procalcitonin (PCT), hospitalization duration, ICU admission, need for BP, LCR, sequential organ failure assessment (SOFA) score, bedside index for severity in AP (BISAP) score, and modified Marshall score showed significant differences across different disease severity groups upon hospitalization. Notably, there were significant differences in LCR between the MAP group and the MSAP and SAP combined group, and the MAP and MSAP combined group and the SAP group, and adult AP patients with ICU admission and those without ICU admission upon hospitalization.

Conclusion

In summary, LCR upon hospitalization can be utilized as a simple and reliable predictor of disease progression and a screening tool for ICU admission in adult patients with AP.

Development and validation of a prediction model for the early occurrence of acute kidney injury in patients with acute pancreatitis

BACKGROUND

Acute pancreatitis (AP) is associated with a high incidence of acute kidney injury (AKI). This study aimed to develop a nomogram for predicting the early onset of AKI in AP patients admitted to the intensive care unit.

METHOD

Clinical data for 799 patients diagnosed with AP were extracted from the Medical Information Mart for Intensive Care IV database. Eligible AP patients were randomly divided into training and validation cohorts. The independent prognostic factors for the early development of AKI in AP patients were determined using the all-subsets regression method and multivariate logistic regression. A nomogram was constructed for predicting the early occurrence of AKI in AP patients. The performance of the nomogram was evaluated based on the area under the receiver operating characteristic curve (AUC), calibration curves and decision curve analysis (DCA).

RESULTS

Seven independent prognostic factors were identified as predictive factors for early onset AKI in AP patients. The AUC of the nomogram in the training and validation cohorts were 0.795 (95% CI, 0.758-0.832) and 0.772 (95% CI, 0.711-0.832), respectively. The AUC of the nomogram was higher compared with that of the BISAP, Ranson, APACHE II scores. Further, the calibration curve revealed that the predicted outcome was in agreement with the actual observations. Finally, the DCA curves showed that the nomogram had a good clinical applicability value.

CONCLUSION

The constructed nomogram showed a good predictive ability for the early occurrence of AKI in AP patients.

Role of neutrophil extracellular traps in inflammatory evolution in severe acute pancreatitis

ABSTRACT

Severe acute pancreatitis (SAP) is a life-threatening acute abdominal disease with two peaks of death: the first in the early stage, characterized by systemic inflammatory response-associated organ failure; and the second in the late stage, characterized by infectious complications. Neutrophils are the main immune cells participating in the whole process of SAP. In addition to the traditional recognition of neutrophils as the origination of chemokine and cytokine cascades or phagocytosis and degranulation of pathogens, neutrophil extracellular traps (NETs) also play an important roles in inflammatory reactions. We reviewed the role of NETs in the occurrence and development of SAP and its fatal complications, including multiple organs injury, infected pancreatic necrosis, and thrombosis. This review provides novel insights into the involvement of NETs throughout the entire process of SAP, showing that targeting NETs might be a promising strategy in SAP treatment. However, precision therapeutic options targeting NETs in different situations require further investigation.

Acute Changes in Serum Creatinine and Kinetic Glomerular Filtration Rate Estimation in Early Phase of Acute Pancreatitis

In patients with acutely changing kidney function, equations used to estimate glomerular filtration rate (eGFR) must be adjusted for dynamic changes in the concentrations of filtration markers (kinetic eGFR, KeGFR). The aim of our study was to evaluate serum creatinine-based KeGFR in patients in the early phase of acute pancreatitis (AP) as a marker of changing renal function and as a predictor of AP severity. We retrospectively calculated KeGFR on day 2 and 3 of the hospital stay in a group of 147 adult patients admitted within 24 h from the onset of AP symptoms and treated in two secondary-care hospitals. In 34 (23%) patients, changes in serum creatinine during days 1-3 of the hospital stay exceeded 26.5 µmol/L; KeGFR values almost completely differentiated those with increasing and decreasing serum creatinine (area under receiver operating characteristic curve, AUROC: 0.990 on day 3). In twelve (8%) patients, renal failure was diagnosed during the first three days of the hospital stay according to the modified Marshall scoring system, which was associated with significantly lower KeGFR values. KeGFR offered good diagnostic accuracy for renal failure (area under receiver operating characteristic-AUROC: 0.942 and 0.950 on days 2 and 3). Fourteen (10%) patients developed severe AP. KeGFR enabled prediction of severe AP with moderate diagnostic accuracy (AUROC: 0.788 and 0.769 on days 2 and 3), independently of age, sex, comorbidities and study center. Lower KeGFR values were significantly associated with mortality. Significant dynamic changes in renal function are common in the early phase of AP. KeGFR may be useful in the assessment of kidney function in AP and the prediction of AP severity.

A prediction model with measured sentiment scores for the risk of in-hospital mortality in acute pancreatitis: a retrospective cohort study

Background

Accurate and prompt clinical assessment of the severity and prognosis of patients with acute pancreatitis (AP) is critical, particularly during hospitalization. Natural language processing algorithms gain an opportunity from the growing number of free-text notes in electronic health records to mine this unstructured data, e.g., nursing notes, to detect and predict adverse outcomes. However, the predictive value of nursing notes for AP prognosis is unclear. In this study, a predictive model for in-hospital mortality in AP was developed using measured sentiment scores in nursing notes.

Methods

The data of AP patients in the retrospective cohort study were collected from the Medical Information Mart for Intensive Care III (MIMIC-III) database. Sentiments in nursing notes were assessed by sentiment analysis. For each individual clinical note, sentiment polarity and sentiment subjectivity scores were assigned. The in-hospital mortality of AP patients was the outcome. A predictive model was built based on clinical information and sentiment scores, and its performance and clinical value were evaluated using the area under curves (AUCs) and decision-making curves, respectively.

Results

Of the 631 AP patients included, 88 cases (13.9%) cases were dead in hospital. When various confounding factors were adjusted, the mean sentiment polarity was associated with a reduced risk of in-hospital mortality in AP [odds ratio (OR): 0.448; 95% confidence interval (CI): 0.233–0.833; P=0.014]. A predictive model was established in the training group via multivariate logistic regression analysis, including 12 independent variables. In the testing group, the model showed an AUC of 0.812, which was significantly greater than the sequential organ failure assessment (SOFA) of 0.732 and the simplified acute physiology score-II (SAPS-II) of 0.792 (P<0.05). When the same level of risk was considered, the clinical benefits of the predictive model were found to be the highest compared with SOFA and SAPS-II scores.

Conclusions

The model combined sentiment scores in nursing notes showed well predictive performance and clinical value in in-hospital mortality of AP patients.

Continuous Renal Replacement Therapy With oXiris Filter May Not be an Effective Resolution to Alleviate Cytokine Release Syndrome in Non-AKI Patients With Severe and Critical COVID-19

In this study, we aimed to determine whether continuous renal replacement therapy (CRRT) with oXiris filter may alleviate cytokine release syndrome (CRS) in non-AKI patients with severe and critical coronavirus disease 2019 (COVID-19). A total of 17 non-AKI patients with severe and critical COVID-19 treated between February 14 and March 26, 2020 were included and randomly divided into intervention group and control group according to the random number table. Patients in the intervention group immediately received CRRT with oXiris filter plus conventional treatment, while those in the control group only received conventional treatment. Demographic data were collected and collated at admission. During ICU hospitalization, the concentrations of circulating cytokines and inflammatory chemokines, including IL-2, IL-4, IL-6, IL-10, TNF-α, and IFN-γ, were quantitatively measured daily to reflect the degree of CRS induced by SARS-CoV-2 infection. Clinical data, including the severity of COVID-19 white blood cell count (WBC), neutrophil proportion (NEUT%), lymphocyte count (LYMPH), lymphocyte percentage (LYM%), platelet (PLT), C-reaction protein (CRP), high sensitivity C-reactive protein (hs-CRP), alanine aminotransferase (ALT), aspartate aminotransferase (AST), total bilirubin (TB), albumin (ALB), serum creatinine (SCr), D-Dimer, fibrinogen (FIB), IL-2, IL-4, IL-6, IL-10, TNF-α, IFN-γ, number of hospital days and sequential organ failure assessment (SOFA) score were obtained and collated from medical records, and then compared between the two groups. Age, and SCr significantly differed between the two groups. Besides the IL-2 concentration that was significantly lower on day 2 than that on day 1 in the intervention group, and the IL-6 concentrations that were significantly higher on day 1, and day 2 in the intervention group compared to the control group, similar to the IL-10 concentration on day 5, there were no significant differences between the two groups. To sum up, CRRT with oXiris filter may not effectively alleviate CRS in non-AKI patients with severe and critical COVID-19. Thus, its application in these patients should be considered with caution to avoid increasing the unnecessary burden on society and individuals and making the already overwhelmed medical system even more strained (IRB number: IRB-AF/SC-04).