Prediction Model of Pancreatic Neoplasms in CP Patients With Focal Pancreatic Lesions

Launched by CHANGHAI HOSPITAL · Jun 22, 2025

Keywords

ClinConnect Summary

This clinical trial is working on a new way to predict whether patients with chronic pancreatitis (a long-lasting inflammation of the pancreas) and certain unclear spots on their pancreas have pancreatic tumors. The researchers plan to use a computer program called XGBoost, which is a type of machine learning, to help make these predictions more accurate.

People who might join this study are those who have been diagnosed with chronic pancreatitis and have these unclear pancreatic spots found during a special type of CT scan. To be part of the trial, patients need to have complete medical information and a confirmed diagnosis of the pancreatic spots through surgery or follow-up tests. The study is not yet recruiting participants, but if you qualify, doctors will use your health data to help develop this prediction tool, which could improve how pancreatic tumors are detected in the future.

Gender

ALL

Eligibility criteria

• Inclusion Criteria:
• • Diagnosis of chronic pancreatitis
• • Patients has indeterminate focal pancreatic lesions discovered through contrast-enhanced CT scans
• Exclusion Criteria:
• • Patients had incomplete clinical data
• • Patients had no surgical pathology results for the focal pancreatic lesions and loss to follow-up, indicating that a final diagnosis of the focal pancreatic lesions could not been established