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

NCT07045181 | Completed DMC

• 1 other identifier: IPNPM
• Study Type: observational
• Target: 113
• Locations: 1 country
• Sites: 1

Brief Summary

This study aims to develop XGBoost machine learning model to predict pancreatic neoplasms in CP patients with focal pancreatic lesions.

Conditions

Chronic Pancreatitis; Pancreatic Neoplasm; Machine Learning

Keywords

Pancreatic neoplasm; chronic pancreatitis; machine learning; SHAP

Outcome Measures

Primary Outcomes (1)

• Diagnostic yield

  The diagnostic yield of XGBoost machine learning, including AUC、Sensitivity、Specificity

  10 years

Study Arms (2)

Pancreatic neoplasm group

This cohort consists of chronic pancreatitis patients whose focal pancreatic lesions were diagnosed as pancreatic neoplasm

Diagnostic Test: XGBoost machine learning

Non-pancreatic neoplasm group

This cohort consists of chronic pancreatitis patients whose focal pancreatic lesions were diagnosed as benign lesions

Diagnostic Test: XGBoost machine learning

Interventions

XGBoost machine learning DIAGNOSTIC_TEST

XGBoost is a powerful machine learning algorithm known for its efficiency and performance. It is an optimized gradient boosting library designed to be highly efficient, flexible, and portable. XGBoost works by combining multiple weak prediction models, typically decision trees, to produce a strong predictive model. It supports various objective functions and evaluation metrics, making it suitable for a wide range of tasks, including classification and regression. XGBoost also includes features like regularization to prevent overfitting and can handle missing data effectively.

Non-pancreatic neoplasm group; Pancreatic neoplasm group

Eligibility Criteria

• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Chronic pancreatitis patients who has indeterminate focal pancreatic lesions discovered through contrast-enhanced CT scans

You may qualify if:

• Diagnosis of chronic pancreatitis
• Patients has indeterminate focal pancreatic lesions discovered through contrast-enhanced CT scans

You may not qualify if:

• 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

Sponsors & Collaborators

• Changhai Hospital: lead

Study Sites (1)

Changhai Hospital

Shanghai, Shanghai Municipality, 200433, China

Location

Related Publications (3)

• Kirkegard J, Mortensen FV, Cronin-Fenton D. Chronic Pancreatitis and Pancreatic Cancer Risk: A Systematic Review and Meta-analysis. Am J Gastroenterol. 2017 Sep;112(9):1366-1372. doi: 10.1038/ajg.2017.218. Epub 2017 Aug 1.

  PMID: 28762376 BACKGROUND

• Hao L, Zeng XP, Xin L, Wang D, Pan J, Bi YW, Ji JT, Du TT, Lin JH, Zhang D, Ye B, Zou WB, Chen H, Xie T, Li BR, Zheng ZH, Wang T, Guo HL, Liao Z, Li ZS, Hu LH. Incidence of and risk factors for pancreatic cancer in chronic pancreatitis: A cohort of 1656 patients. Dig Liver Dis. 2017 Nov;49(11):1249-1256. doi: 10.1016/j.dld.2017.07.001. Epub 2017 Jul 15.

  PMID: 28756974 BACKGROUND

• Korpela T, Udd M, Mustonen H, Ristimaki A, Haglund C, Seppanen H, Kylanpaa L. Association between chronic pancreatitis and pancreatic cancer: A 10-year retrospective study of endoscopically treated and surgical patients. Int J Cancer. 2020 Sep 1;147(5):1450-1460. doi: 10.1002/ijc.32971. Epub 2020 Apr 3.

  PMID: 32162688 BACKGROUND

MeSH Terms

Conditions

Pancreatitis, Chronic; Pancreatic Neoplasms

Condition Hierarchy (Ancestors)

Pancreatitis; Pancreatic Diseases; Digestive System Diseases; Chronic Disease; Disease Attributes; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Digestive System Neoplasms; Neoplasms by Site; Neoplasms; Endocrine Gland Neoplasms; Endocrine System Diseases

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: June 22, 2025
• First Posted: July 1, 2025
• Study Start: July 1, 2025
• Primary Completion: August 1, 2025
• Study Completion: August 5, 2025
• Last Updated: September 30, 2025

Record last verified: 2025-09

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)