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 Videos

Bayesian neural networks for bivariate binary data: an application to prostate cancer study.

Sounak Chakraborty1, Malay Ghosh, Tapabrata Maiti

  • 1Department of Statistics, University of Florida, 103 Griffin/Floyd Hall, Gainesville, FL 32611-8545, USA. schakrab@stat.ufl.edu

Statistics in Medicine
|September 3, 2005
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

Reproducibility of MRI Radiomics Measurements in Men with Prostate Cancer Undergoing Active Surveillance.

Cancers·2026
Same author

Benchmarking Sparse Variable Selection Methods for Genomic Data Analyses.

Statistics in medicine·2026
Same author

Happening in the Prostate Tumor Microenvironment: Ion Channels and Extrachromosomal DNA Driving Phenotypic Plasticity.

The Prostate·2026
Same author

A Systematic Review of Longitudinal Studies on Youth Internet Behavior Using the Positive Youth Development Frameworks.

Journal of adolescence·2026
Same author

Diagnostic Utility of 18F-DCFPyL PSMA PET/CT-Ultrasound Fusion Biopsies Across the Prostate Cancer Spectrum.

The Prostate·2025
Same author

Scalable Survival Analysis: Equivalence of Cox and Log-Linear Models for Big Data.

Chest·2025

Predicting prostate cancer spread is crucial for treatment. A new Bayesian neural network method accurately forecasts margin positivity and seminal vesicle positivity, outperforming existing models for better patient outcomes.

Area of Science:

  • Computational biology
  • Medical informatics
  • Oncology

Background:

  • Prostate cancer is a common malignancy in men, with outcomes depending on whether it is organ-confined or has spread.
  • Accurate prediction of non-organ confined disease pre-surgery is vital for effective treatment planning.
  • Features like margin positivity (MP) and seminal vesicle (SV) positivity indicate cancer spread.

Purpose of the Study:

  • To develop and evaluate a hierarchical Bayesian neural network for predicting non-organ confined prostate cancer.
  • To jointly predict the probabilities of margin positivity (MP) and seminal vesicle (SV) positivity.
  • To compare the proposed method against existing statistical and machine learning models.

Main Methods:

  • Utilized a hierarchical Bayesian neural network approach.

Related Experiment Videos

  • Employed Markov chain Monte Carlo (MCMC) for Bayesian inference.
  • Incorporated covariates such as prostate-specific antigen (PSA), Gleason score, and cancer laterality.
  • Applied leave-one-out cross-validation for microarray data analysis.

    • Main Results:

    • The Bayesian bivariate neural network demonstrated superior performance in predicting joint MP and SV positivity compared to classical neural networks, Radford Neal's Bayesian neural network, and bivariate logistic models.
    • The method showed strong predictive accuracy on both clinical and gene expression microarray datasets.
    • A simulation study confirmed the superiority of the proposed Bayesian approach.

    Conclusions:

    • The hierarchical Bayesian neural network provides a robust and accurate method for predicting key indicators of non-organ confined prostate cancer.
    • This approach offers improved prediction accuracy over traditional methods, potentially aiding in more precise treatment strategies.
    • The findings highlight the utility of advanced Bayesian modeling in cancer prognostics.