Neutrophil Lymphocyte Ratio for Assessing Severity of Acute Pancreatitis

<ns3:p>Background Acute pancreatitis (AP) is a common gastrointestinal emergency with unpredictable clinical progression. Early identification of severe cases is essential to reduce morbidity and mortality. The Neutrophil-to-Lymphocyte Ratio (NLR), a marker of systemic inflammation, has emerged as a potential prognostic tool. This study investigates the utility of NLR in assessing AP severity using data from the National Health and Nutrition Examination Survey (NHANES) 2017–2018 cycle. Methods A retrospective analysis was performed on 1,250 NHANES participants diagnosed with AP. Descriptive statistics and exploratory data analysis (EDA) summarized demographic and clinical variables, including age, BMI, WBC, neutrophils, lymphocytes, and NLR. Chi-square and t-tests assessed associations between variables and disease severity. Logistic regression identified independent predictors. Three machine learning models Logistic Regression, Random Forest, and XGBoost were trained to classify AP severity. Feature importance and performance metrics were evaluated. Results NLR was significantly higher in severe AP (p &lt; 0.001) and correlated with WBC (r = 0.62) and lymphocytes (r = -0.55). Logistic regression confirmed NLR as a strong predictor (OR = 2.43). Random Forest and XGBoost models showed superior performance, with XGBoost achieving an F1-score of 0.91. Feature importance ranked NLR, WBC, and triglycerides among top predictors. Conclusion NLR is a clinically relevant, low-cost biomarker that enhances early severity prediction in AP. Combined with machine learning, it provides robust risk stratification to aid clinical decision-making.</ns3:p>