JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Development and validation of a new model for predicting malignant pancreatic cystic lesions based on clinical and EUS characteristics

  • 0Department of Gastroenterology, The First Affiliated Hospital of the Naval Medical University, Shanghai, China.
Scandinavian Journal of Gastroenterology +

|

July 2, 2025

|

July 2, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

This study developed a predictive model using Endoscopic Ultrasound (EUS) and clinical data to accurately diagnose malignant pancreatic cystic lesions (PCLs). The model shows high accuracy, potentially reducing unnecessary surgeries for challenging cases.

Area Of Science

  • Gastroenterology and Hepatology
  • Surgical Oncology
  • Diagnostic Imaging

Background

  • Pancreatic cystic lesions (PCLs) present diagnostic challenges, particularly in differentiating benign from malignant types.
  • Accurate diagnosis is crucial for appropriate patient management and avoiding unnecessary surgical interventions.

Purpose Of The Study

  • To develop and validate a predictive model integrating clinical and Endoscopic Ultrasound (EUS) morphological features.
  • To enhance the diagnostic accuracy of malignant PCLs in radiologically challenging cases.

Main Methods

  • Retrospective analysis of 126 patients with pathologically confirmed PCLs.
  • Development of a predictive model using multivariate logistic regression on clinical and EUS data.
  • Model performance evaluation using Receiver Operating Characteristic Curve (AUC) and Decision Curve Analysis (DCA).

Main Results

  • Six independent predictors of malignancy identified: weight loss, elevated CA19-9, head-neck location, thickened cystic wall, solid component, and peripancreatic invasion.
  • The model achieved high discriminative ability with AUCs of 0.938 (training) and 0.951 (validation).
  • Decision Curve Analysis indicated potential to avoid approximately 10% of unnecessary surgeries.

Conclusions

  • An EUS-based nomogram effectively improves malignancy prediction for challenging PCLs.
  • The model offers clinical utility for personalized management strategies.
  • External validation is recommended to confirm the generalizability of the findings.

Keywords: