Journal of Clinical Hepatology
This article constructs and validates a nomogram prediction model based on inflammatory factors, lung ultrasound (LUS), and CT scoring systems for evaluating the risk of adverse prognosis in patients with acute pancreatitis (AP). The study retrospectively analyzed 409 AP patients, divided into a modeling group and a validation group in a 7:3 ratio. LASSO regression was used to screen out 6 independent risk factors: CRP, IL-6, TNF-α, LUS score, MCTSI score, and EPIC score, and a nomogram model was established accordingly. The model achieved an AUC of 0.924 in the modeling group and 0.889 in the validation group, demonstrating good discriminative ability and calibration ability. Decision curve analysis shows that the model has a net benefit in clinical intervention and is practical. The innovation lies in the first integration of systemic inflammatory markers (CRP, IL-6, TNF-α), lung ultrasound scores, and multidimensional CT scores (MCTSI, EPIC), achieving multimodal data fusion, overcoming the problem of insufficient prediction accuracy of single indicators, and improving the accuracy and clinical applicability of the model. This model helps in early identification of high-risk patients and guides individualized treatment.
This study constructs and validates a nomogram prediction model based on inflammatory factors, lung ultrasound (LUS), and CT scoring systems for early prediction of the risk of adverse prognosis in patients with acute pancreatitis (AP). The study included 409 AP patients, and CRP, IL-6, TNF-α, LUS score, MCTSI, and EPIC score were identified as independent risk factors through LASSO and multifactor logistic regression analysis, and a nomogram model was established accordingly. The model achieved an AUC of 0.924 in the modeling group and 0.889 in the validation group, with good discriminative ability and calibration ability, high sensitivity and specificity. Compared with traditional single indicators, this model integrates multidimensional information of systemic inflammatory response and organ injury, significantly improving the accuracy of prognosis judgment. The application of bedside lung ultrasound enhances the ability to early and non-invasively evaluate pulmonary complications, helping to dynamically monitor changes in the condition. Decision curve analysis shows that the model has good clinical applicability and can provide a basis for early intensive intervention, improving patient prognosis. Therefore, this nomogram model has important clinical application value, helping to achieve individualized risk stratification and precise treatment for AP patients.
Objective: To investigate the independent risk factors for poor prognosis in patients with acute pancreatitis (AP) by analyzing infla…
