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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Prevalence and Factors Associated With Financial Toxicity Among Patients With GI Cancer in Pakistan.

JCO global oncology·2026
Same author

Uncovering the Roots of Inequity: Social Determinants and Racial Disparities Among Gastrointestinal Cancer Patients.

Journal of racial and ethnic health disparities·2026
Same author

Identifying Factors Associated With Postdischarge Mortality After Readmission Following Pancreaticoduodenectomy.

The Journal of surgical research·2026
Same author

Cancer Surgery at a Cost: Understanding Financial Toxicity Among Patients in Pakistan.

The Journal of surgical research·2026
Same author

Presentation of Metastatic Colorectal Carcinoma at a Tertiary Care Center in Pakistan.

Journal of cancer & allied specialties·2026
Same author

Characterizing Social Determinants of Health in GI Cancer Surgery: Insights From the All of Us Research Program.

Cancer reports (Hoboken, N.J.)·2026

Related Experiment Video

Updated: Jun 15, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K

Machine Learning to Predict Early Death Despite Pancreaticoduodenectomy.

Kaleem S Ahmed1, Clayton T Marcinak1, Sheriff M Issaka1

  • 1Division of Surgical Oncology, Department of Surgery, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin.

The Journal of Surgical Research
|April 27, 2025
PubMed
Summary
This summary is machine-generated.

Machine learning models can predict futile pancreaticoduodenectomy (PD) in pancreatic ductal adenocarcinoma (PDAC) patients with moderate accuracy. This aids in shared decision-making for optimized patient care.

Keywords:
Futility predictionMachine learningPancreatic cancerPancreaticoduodenectomyRisk stratification

More Related Videos

Author Spotlight: Reprogramming Cancer Cells to iPSCs to Study Disease Progression and Treatment Targets
07:08

Author Spotlight: Reprogramming Cancer Cells to iPSCs to Study Disease Progression and Treatment Targets

Published on: February 2, 2024

747
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

Related Experiment Videos

Last Updated: Jun 15, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Author Spotlight: Reprogramming Cancer Cells to iPSCs to Study Disease Progression and Treatment Targets
07:08

Author Spotlight: Reprogramming Cancer Cells to iPSCs to Study Disease Progression and Treatment Targets

Published on: February 2, 2024

747
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

Area of Science:

  • Oncology
  • Machine Learning
  • Surgical Outcomes

Background:

  • Pancreaticoduodenectomy (PD) for right-sided pancreatic ductal adenocarcinoma (PDAC) has a 25% 1-year mortality rate.
  • A significant portion of patients experience morbidity without survival benefits from PD compared to non-surgical options.

Purpose of the Study:

  • To compare the accuracy of machine learning models against traditional regression models in predicting futile surgery for PDAC patients.
  • To identify key preoperative factors associated with futile PD.

Main Methods:

  • Analysis of National Cancer Database data (2004-2020) for PDAC patients undergoing PD.
  • Definition of futile PD as death within 12 months of cancer diagnosis.
  • Training and testing of logistic regression, multilayer perceptron, decision tree, random forest, and gradient boosting models using 16 preoperative variables.

Main Results:

  • Out of 66,331 patients, 25.3% met criteria for futile surgery.
  • Gradient boosting model achieved the highest accuracy (AUC 0.689), outperforming logistic regression, random forest, and decision tree.
  • Predictors of futile PD included advanced age, larger tumor size, and poor differentiation; neoadjuvant therapy reduced futility risk.

Conclusions:

  • Machine learning models demonstrate moderate accuracy in predicting futile PD for PDAC patients.
  • Findings support improved shared decision-making and optimized care strategies for PDAC.
  • Further research with more granular data is warranted.