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

Editorial: Artificial intelligence and machine learning in pediatrics.

Frontiers in artificial intelligence·2026
Same author

Predicting time-to-first cancer diagnosis across multiple cancer types.

Scientific reports·2025
Same author

Randomized phase II trial of weekly ixabepilone ± biweekly bevacizumab for platinum-resistant or refractory ovarian/fallopian tube/primary peritoneal cancer (NCT03093155): Updated survival and subgroup analyses.

BJC reports·2024
Same author

Trastuzumab deruxtecan (DS-8201a), a HER2-targeting antibody-drug conjugate, demonstrates in vitro and in vivo antitumor activity against primary and metastatic ovarian tumors overexpressing HER2.

Clinical & experimental metastasis·2024
Same author

ARID1A in Gynecologic Precancers and Cancers.

Reproductive sciences (Thousand Oaks, Calif.)·2024
Same author

Integrated mutational landscape analysis of poorly differentiated high-grade neuroendocrine carcinoma of the uterine cervix.

Proceedings of the National Academy of Sciences of the United States of America·2024

Related Experiment Video

Updated: Nov 12, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

511

Population-Based Screening for Endometrial Cancer: Human vs. Machine Intelligence.

Gregory R Hart1, Vanessa Yan2, Gloria S Huang3

  • 1Department of Therapeutic Radiology, Yale University, New Haven, CT, U.S.A.

Frontiers in Artificial Intelligence
|March 18, 2021
PubMed
Summary

Machine learning models using personal health data significantly improve endometrial cancer risk prediction. These non-invasive tools outperform traditional methods and physicians in identifying high-risk individuals for early screening and prevention.

Keywords:
cancer screeningearly detectionendometrial cancermachine learningstatistical biopsy

More Related Videos

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

7.1K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.7K

Related Experiment Videos

Last Updated: Nov 12, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

511
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

7.1K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.7K

Area of Science:

  • Oncology
  • Machine Learning
  • Public Health

Background:

  • Endometrial cancer incidence and mortality are rising.
  • Existing risk prediction models show moderate accuracy (AUC 0.68-0.77).
  • There is a need for improved endometrial cancer risk stratification for screening and prevention.

Purpose of the Study:

  • To develop and evaluate a population-based machine learning model for endometrial cancer screening.
  • To compare the performance of machine learning models against clinical experts in risk stratification.
  • To assess the potential of machine learning for non-invasive, cost-effective early detection and prevention.

Main Methods:

  • Trained seven machine learning algorithms using personal health data from the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial (PLCO).
  • Evaluated models based on testing AUC and compared performance against 15 gynecologic oncologists and primary care physicians.
  • Focused on models utilizing only personal health data, excluding genomic, imaging, or biomarker information.

Main Results:

  • A random forest model achieved a testing AUC of 0.96; a neural network model achieved 0.91.
  • The random forest model was 2.5 times better at identifying high-risk women with a 2-fold reduction in false positives compared to physicians.
  • The neural network model was 2 times better at identifying high-risk women with a 3-fold reduction in false positives.

Conclusions:

  • Machine learning models offer a highly accurate, non-invasive method for endometrial cancer risk prediction.
  • These models can effectively identify high-risk populations for targeted early screening.
  • This approach represents a significant advancement in early cancer detection and personalized prevention strategies.