Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 9, 2026

Stabilized Longitudinal In Vivo Cellular-Level Visualization of the Pancreas in a Murine Model with a Pancreatic Intravital Imaging Window
06:52

Stabilized Longitudinal In Vivo Cellular-Level Visualization of the Pancreas in a Murine Model with a Pancreatic Intravital Imaging Window

Published on: May 6, 2021

Pancreatic Cancer Risk Stratification Across Diabetes Stages: Development and Internal Validation of a Machine

Salman Khan1

  • 1The University of Texas Southwestern Medical Center Dallas United States.

Cancer Epidemiology, Biomarkers & Prevention : a Publication of the American Association for Cancer Research, Cosponsored by the American Society of Preventive Oncology
|June 8, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Prescription Opioid Use before and after Diagnosis of Cancer Among Older Cancer Survivors With Non-Cancer Chronic Pain Conditions (NCPCs): An Application of Group-Based Trajectory Modeling (GBTM).

Cancer control : journal of the Moffitt Cancer Center·2024
Same journal

Retraction: Menstrual Factors, Reproductive History and Liver Cancer Risk: Findings from a Prospective Cohort Study in Chinese Women.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2026
Same journal

Optimizing the Uptake and Completion of the Cervical Cancer Screening Continuum: Opportunity Knocks, Including at Home.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2026
Same journal

Sex Differences in Cancer Stage at Diagnosis of Nonreproductive Solid Organ Tumors in the United States, 2015 to 2022.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2026
Same journal

Evaluation of the 4Kscore in EPIC: Reply.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2026
Same journal

Evaluation of the 4Kscore in EPIC: Letter.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2026
Same journal

Dietary phytoestrogen intake and risk of receptor-defined breast cancer subtypes: a prospective analysis of the PLCO Cancer Screening Trial cohort.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2026
See all related articles

A new machine learning model effectively predicts pancreatic cancer in diabetes patients, even with incomplete data. This approach covers all patients, unlike older methods, improving early detection for both new-onset and prevalent diabetes.

Area of Science:

  • Oncology
  • Data Science
  • Diabetes Research

Background:

  • Pancreatic cancer is frequently diagnosed at advanced stages in patients with diabetes.
  • Existing prediction models have limitations, including requirements for complete historical data and a focus solely on new-onset diabetes, restricting their clinical utility.
  • There is a need for predictive models that can handle missing data and encompass the full spectrum of diabetes.

Purpose of the Study:

  • To develop and validate a machine learning model for predicting pancreatic cancer risk in patients with diabetes, addressing limitations of existing models.
  • To create a model capable of handling missing clinical data and applicable across different diabetes statuses (new-onset and prevalent).

Main Methods:

  • A retrospective cohort study was conducted using TriNetX electronic health records.

More Related Videos

Development and Validation of a Methodology for Establishing Obese Rat Models with Typical Fatty Pancreas
03:07

Development and Validation of a Methodology for Establishing Obese Rat Models with Typical Fatty Pancreas

Published on: November 11, 2025

Related Experiment Videos

Last Updated: Jun 9, 2026

Stabilized Longitudinal In Vivo Cellular-Level Visualization of the Pancreas in a Murine Model with a Pancreatic Intravital Imaging Window
06:52

Stabilized Longitudinal In Vivo Cellular-Level Visualization of the Pancreas in a Murine Model with a Pancreatic Intravital Imaging Window

Published on: May 6, 2021

Development and Validation of a Methodology for Establishing Obese Rat Models with Typical Fatty Pancreas
03:07

Development and Validation of a Methodology for Establishing Obese Rat Models with Typical Fatty Pancreas

Published on: November 11, 2025

  • Sixty-five clinical variables were extracted at 90-day intervals for patients with hemoglobin A1c ≥6.5%.
  • An XGBoost model was developed using 1:1 case-control sampling and compared against established models (ENDPAC, Boursi, Cheung) using AUROC, sensitivity, specificity, and lead time.

    • Main Results:

    • The XGBoost model achieved an AUROC of 0.78, demonstrating good predictive performance in a cohort of over 3.2 million patients.
    • At 90% sensitivity, the model achieved 50% specificity and a median lead time of 9 months for pancreatic cancer detection.
    • The developed model achieved 100% patient scoring, significantly outperforming existing models which scored less than 10% of patients and showing superior performance against ENDPAC and Cheung models on complete data subsets.

    Conclusions:

    • The XGBoost model effectively predicts pancreatic cancer in patients with both new-onset and prevalent diabetes, even with limited clinical information and missing data.
    • This model offers 100% patient coverage, a significant improvement over existing methods.
    • External validation is recommended prior to clinical implementation.