Predicting the risk of early intensive care unit admission for patients hospitalized with acute pancreatitis using
Hassam Ali1, Faisal Inayat2, Rubaid Dhillon3
1Department of Gastroenterology, East Carolina University Brody School of Medicine, Greenville, North Carolina, USA.
Insights
A new model predicts intensive care unit (ICU) admission risk for acute pancreatitis (AP) patients. This tool helps clinicians identify high-risk individuals early for timely intervention.
Area of Science:
- Medical research
- Clinical informatics
- Machine learning in healthcare
Background:
- Acute pancreatitis (AP) is a severe, life-threatening condition.
- Predicting patient outcomes and identifying those needing intensive care unit (ICU) admission early is critical for effective management.
- Developing a practical model to assess individual risk for early ICU admission in AP patients is essential.
Purpose of the Study:
- To develop and validate a pragmatic model for predicting the risk of early ICU admission in patients diagnosed with acute pancreatitis.
- To create an individualized risk score to guide clinical decision-making.
Main Methods:
- Utilized the 2019 Nationwide Readmission Database to identify AP patients not initially admitted to the ICU.
- Developed a matched cohort of AP patients admitted to the ICU within 7 days using the National Inpatient Sample and propensity score matching.
- Employed least absolute shrinkage and selection operator (LASSO) regression to select predictors and construct the ICU Acute Pancreatitis Risk (IAPR) score, validated via 10-fold cross-validation.
Main Results:
- The study included 1513 AP patients; the median age was 50 years.
- Key predictors for ICU admission identified were hypoxia (AUC 0.78), acute kidney injury (AUC 0.72), and cardiac arrhythmia (AUC 0.61).
- The developed nomogram demonstrated excellent discrimination (AUC 0.874) and was well-calibrated, with high sensitivity (68.94%) and specificity (92.66%) for identifying high-risk patients (score >6).
Conclusions:
- A supervised machine learning model, the IAPR score, effectively identifies AP hospitalizations at high risk for ICU admission.
- Clinicians can utilize the IAPR score to proactively manage AP patients who may require intensive care within the first week of hospitalization.
- This model aids in early recognition and intervention for severe acute pancreatitis cases.
Background:
Acute pancreatitis (AP) is a complex and life-threatening disease. Early recognition of factors predicting morbidity and mortality is crucial. We aimed to develop and validate a pragmatic model to predict the individualized risk of early intensive care unit (ICU) admission for patients with AP.
Methods:
The 2019 Nationwide Readmission Database was used to identify patients hospitalized with a primary diagnosis of AP without ICU admission. A matched comparison cohort of AP patients with ICU admission within 7 days of hospitalization was identified from the National Inpatient Sample after 1:N propensity score matching. The least absolute shrinkage and selection operator (LASSO) regression was used to select predictors and develop an ICU acute pancreatitis risk (IAPR) score validated by 10-fold cross-validation.
Results:
A total of 1513 patients hospitalized for AP were included. The median age was 50.0 years (interquartile range: 39.0-63.0). The three predictors that were selected included hypoxia (area under the curve [AUC] 0.78), acute kidney injury (AUC 0.72), and cardiac arrhythmia (AUC 0.61). These variables were used to develop a nomogram that displayed excellent discrimination (AUC 0.874) (bootstrap bias-corrected 95% confidence interval 0.824-0.876). There was no evidence of miscalibration (test statistic = 2.88; P = 0.09). For high-risk patients (total score >6 points), the sensitivity was 68.94% and the specificity was 92.66%.
Conclusions:
This supervised machine learning-based model can help recognize high-risk AP hospitalizations. Clinicians may use the IAPR score to identify patients with AP at high risk of ICU admission within the first week of hospitalization.
More Related Videos
07:38Preparing a Mice Model of Severe Acute Pancreatitis via a Combination of Caerulein and Lipopolysaccharide Intraperitoneal Injection
Published on: May 10, 2024
05:44Isolation of Proximal Fluids to Investigate the Tumor Microenvironment of Pancreatic Adenocarcinoma
Published on: November 5, 2020
Related Concept Videos
01:30Acute Pancreatitis II: Clinical Manifestations and Management
01:29Chronic Pancreatitis II: Collaborative Care
Assessment:
01:27Acute Pancreatitis I: Introduction
Acute pancreatitis is characterized by rapid inflammation of the pancreas, often caused by factors like gallstone blockage or excessive alcohol consumption. Chronic pancreatitis, on the other hand, is a slow, progressive inflammation that may result from long-term alcohol abuse, obstructions in the pancreatic duct, or genetic factors.
The causes of acute pancreatitis include: