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

455
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...
455
End Point Prediction: Gran Plot01:07

End Point Prediction: Gran Plot

586
A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...
586

You might also read

Related Articles

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

Sort by
Same author

Prediction of Anthracycline Benefit in Hormone Receptor-Positive, Human Epidermal Growth Factor Receptor 2-Negative Early-Stage Breast Cancer by the MammaPrint 70-Gene Signature for Patients Enrolled in the FLEX Study.

JCO precision oncology·2026
Same author

Phase II Study of Adavosertib in Patients With Tumors Containing BRCA1 and BRCA2 Mutations: Results From the NCI-MATCH ECOG-ACRIN Cancer Research Group (EAY131) Subprotocol Z1I.

JCO precision oncology·2026
Same author

Multi-modal AI for comprehensive breast cancer prognostication.

Nature communications·2026
Same author

Real-world treatment durations, subsequent treatments, and switching of CDK4/6 inhibitors among patients with HR+/HER2- metastatic breast cancer.

The oncologist·2026
Same author

Efficacy and Genomic Analysis of HER2-Mutant Metastatic Triple-Negative Breast Cancer Treated with Neratinib Alone or with Trastuzumab in the SUMMIT Basket Trial.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same author

Comparative effectiveness of CDK4/6 inhibitors in metastatic breast cancer: using the target trial emulation framework to investigate overall survival in routine care.

Breast cancer research and treatment·2026

Related Experiment Video

Updated: Sep 11, 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

6.9K

Leveraging Deep Learning, Grid Search, and Bayesian Networks to Predict Distant Recurrence of Breast Cancer.

Xia Jiang1, Yijun Zhou1, Alan Wells2,3

  • 1Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA 15206, USA.

Cancers
|August 14, 2025
PubMed
Summary

This study introduces a novel machine learning approach to predict long-term breast cancer recurrence risk, significantly improving accuracy for early-stage patients. The interpretable pipeline enhances clinical decision-making for follow-up and treatment strategies.

Keywords:
Bayesian networksEHRbreast cancerbreast cancer metastasisclinicaldeep learninggrid searchmachine learningmetastasisneural networksprediction

More Related Videos

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

8.3K
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

194

Related Experiment Videos

Last Updated: Sep 11, 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

6.9K
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

8.3K
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

194

Area of Science:

  • Oncology
  • Biomedical Informatics
  • Machine Learning

Background:

  • Breast cancer recurrence risk persists years after treatment, challenging long-term patient stratification.
  • Current prediction tools are inadequate for identifying late metastatic events, especially in early-stage disease.
  • Accurate prediction of distant recurrence is crucial for optimizing patient management.

Purpose of the Study:

  • To develop and validate an interpretable machine learning pipeline for predicting distant recurrence-free survival at 5, 10, and 15 years.
  • To integrate causal feature selection and deep neural networks for enhanced prediction accuracy.
  • To improve the transparency and clinical utility of breast cancer recurrence risk models.

Main Methods:

  • Utilized electronic health record (EHR) data from over 6000 patients.
  • Employed Bayesian network-based causal feature selection (Markov Blanket and Interactive Risk Factor Learner - MBIL) to identify key predictors.
  • Trained deep feed-forward neural network models (DNMs) with hyperparameters optimized via grid search.
  • Interpreted model predictions using SHAP (SHapley Additive exPlanations) values.

Main Results:

  • Achieved high area under the curve (AUC) scores: 0.79 (5-year), 0.83 (10-year), and 0.89 (15-year), outperforming baseline models.
  • MBIL reduced input dimensionality by over 80% without compromising predictive accuracy.
  • Identified key predictors like nodal status, hormone receptor expression, and tumor size, aligning with SHAP interpretations.
  • Demonstrated strong calibration between predicted probabilities and observed recurrence rates.

Conclusions:

  • The combined approach of causal selection, deep learning, and grid search significantly enhances prediction accuracy, transparency, and calibration for long-term breast cancer recurrence risk.
  • The developed framework offers a robust and interpretable tool for clinical application.
  • This methodology can guide long-term follow-up and therapeutic decisions, particularly for early-stage breast cancer patients.