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

Cancer Survival Analysis01:21

Cancer Survival Analysis

853
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
853

You might also read

Related Articles

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

Sort by
Same author

An Evaluation of Pretrained Generative Models for Augmenting Small Health Data: Comparative Modeling Study.

Journal of medical Internet research·2026
Same author

Circulating Cell-Free DNA Methylation Profiling Enables Detection, Distinction, and Estrogen Receptor Status Classification of Advanced Breast Cancer.

Cancer research·2026
Same author

Assessment of Risks and Outcomes of Sinusoidal Obstruction Syndrome/Veno-Occlusive Disease in Allogeneic Stem Cell Transplant Recipients Including Potentially Undiagnosed Cases-A Multicenter Canadian Study.

Current oncology (Toronto, Ont.)·2026
Same author

Incidence and Management Trends in Advanced Head and Neck Non-Melanoma Skin Cancer in Ontario.

Current oncology (Toronto, Ont.)·2026
Same author

A Randomized Trial Evaluating Personalized Versus Guideline-Based Well Follow-Up Strategies for Patients with Early Breast Cancer: Feasibility Outcomes.

Current oncology (Toronto, Ont.)·2026
Same author

Paving the Way for ERAS in German Gynecologic and Gynecologic Oncology Departments: Insights into Barriers, Facilitators and Practical Strategies.

Healthcare (Basel, Switzerland)·2026
Same journal

Comparative Effectiveness of AI-Assisted Telerehabilitation, Telerehabilitation, In-Person Care, and Usual Care for Chronic Nonspecific Low Back Pain: Bayesian Network Meta-Analysis.

Journal of medical Internet research·2026
Same journal

Effectiveness of WeChat Public Account Intervention Based on the Information-Motivation-Behavioral Skills Model Among College Students With Internet Addiction: Randomized Controlled Trial.

Journal of medical Internet research·2026
Same journal

Are Traditional Registries Becoming Obsolete in the Modern Digital Health Ecosystem?

Journal of medical Internet research·2026
Same journal

Detecting and Preventing Fraudulent Participation in Qualitative Research: Content Analysis of Two Multisite Studies.

Journal of medical Internet research·2026
Same journal

Patient Perceptions of Artificial Intelligence-Supported Shared Decision-Making in UK Primary Care for Multiple Long-Term Conditions: Qualitative Study.

Journal of medical Internet research·2026
Same journal

Impact of Telemedicine-Enhanced Integrated Management of Gestational Diabetes on Pregnancy Outcomes and Glycemic Control: Real-World Study Using TangMama App.

Journal of medical Internet research·2026
See all related articles

Related Experiment Video

Updated: Apr 16, 2026

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

8.9K

Transfer Learning and Machine Learning for Training Five-Year Survival Prognostic Models in Early Breast Cancer:

Lisa Pilgram1,2,3, Kai Yang1,2, Ana-Alicia Beltran-Bless4

  • 1School of Epidemiology and Public Health, Faculty of Medicine, University of Ottawa, Ottawa, ON, Canada.

Journal of Medical Internet Research
|April 14, 2026
PubMed
Summary
This summary is machine-generated.

Machine learning and ensemble methods enhance breast cancer survival prognostication, improving calibration and handling missing data compared to PREDICT v3. These advanced techniques offer more reliable predictions for better patient care.

Keywords:
breast cancer survivalensemblesmachine learningprognostic modelstransfer learning

More Related Videos

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

874
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

7.7K

Related Experiment Videos

Last Updated: Apr 16, 2026

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

8.9K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

874
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

7.7K

Area of Science:

  • Oncology
  • Bioinformatics
  • Machine Learning in Healthcare

Background:

  • Accurate breast cancer prognostication is crucial for treatment decisions.
  • Genomic tools are increasingly used, but clinicopathological methods remain accessible.
  • PREDICT v3 is a promising prognostic tool, but advances in machine learning (ML) offer potential improvements, especially with diverse patient data.

Purpose of the Study:

  • To evaluate and compare the effectiveness of de novo ML, transfer learning from PREDICT v3, and a stacked ensemble approach for breast cancer survival prognostication.
  • To assess the ability of these methods to improve upon existing prognostic tools, particularly in scenarios with missing data.

Main Methods:

  • Trained models using data from the MA.27 trial (NCT00066573).
  • Applied transfer learning by re-estimating PREDICT v3 parameters.
  • Utilized de novo ML (random survival forests, extreme gradient boosting) and a stacked ensemble.
  • Performed internal and external validation using multiple cohorts and assessed performance via integrated calibration index, discrimination, and decision-curve analysis.
  • Employed Shapley Additive Explanations for model interpretability.

Main Results:

  • Transfer learning, de novo ML, and the ensemble significantly improved calibration (ICI ≤0.007) and maintained comparable discrimination (AUROC 0.744-0.799) versus PREDICT v3 (ICI 0.042, AUROC 0.738).
  • ML and ensemble models successfully predicted survival despite missing data, unlike PREDICT v3 which showed invalid predictions in 23.8%-25.8% of cases.
  • Key prognostic factors identified by Shapley values included age, nodal status, grade, and tumor size.
  • External validation confirmed benefits in calibration and discrimination in one cohort, but limited generalizability in another with different clinicopathological characteristics.

Conclusions:

  • Transfer learning, de novo random survival forests (RSF), and stacked ensembles offer improved breast cancer survival prognostication over PREDICT v3, especially with incomplete data.
  • Model transportability across diverse populations is limited and requires local validation.
  • Enhanced survival estimation through advanced ML techniques can significantly improve clinical guidance in breast cancer management.