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

Kaplan-Meier Approach01:24

Kaplan-Meier Approach

111
The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...
111
Actuarial Approach01:20

Actuarial Approach

68
The actuarial approach, a statistical method originally developed for life insurance risk assessment, is widely used to calculate survival rates in clinical and population studies. This method accounts for participants lost to follow-up or those who die from causes unrelated to the study, ensuring a more accurate representation of survival probabilities.
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
68
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

45
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
45

You might also read

Related Articles

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

Sort by
Same author

Disease-Site Specific Peer Review Implementation: From Chart Rounds to the Treatment Couch.

Advances in radiation oncology·2026
Same author

Advancing radiation oncology care in Ukraine during the war: impact of international observerships on professional development and clinical practice.

Frontiers in oncology·2026
Same author

Prevalence, risk factors, and interventions for female sexual dysfunction after radiotherapy for anal cancer: a systematic review.

British journal of cancer·2026
Same author

Prospective operational feasibility, safety, and workflow of magnetic resonance-guided tracking technology for interstitial gynecologic brachytherapy.

Brachytherapy·2026
Same author

Cumulative gastrointestinal adverse events in EMBRACE-I: comparative evaluation of CTCAE vs. MOSES methods in predicting the impact of incident vs. persistent adverse events on quality of life.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2026
Same author

AAPM task group 317 report: A joint AAPM and ESTRO report on brachytherapy catheter, needle, and applicator tracking technology.

Medical physics·2026

Related Experiment Video

Updated: Jun 13, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

983

A simulated annealing-based Bayesian network structure optimization framework for late morbidity prediction with a

Kailyn Stenhouse1,2, Philip McGeachy1,2,3, Sofia Spampinato4

  • 1Department of Physics and Astronomy, University of Calgary, Calgary, Alberta, Canada.

Medical Physics
|May 22, 2025
PubMed
Summary

A new simulated annealing framework creates interpretable Bayesian networks for predicting cervical cancer late morbidity. This approach offers comparable or better predictive performance than standard methods, enhancing clinical decision-making.

Keywords:
Bayesian networkscervical brachytherapyhigh‐dose‐rate brachytherapymachine learningtoxicity prediction

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.6K
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

7.5K

Related Experiment Videos

Last Updated: Jun 13, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

983
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.6K
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

7.5K

Area of Science:

  • Computational biology and bioinformatics
  • Machine learning in healthcare
  • Medical informatics

Background:

  • Bayesian networks are increasingly used in healthcare for their interpretability and ability to model complex decisions under uncertainty.
  • Traditional optimization techniques for Bayesian networks may yield networks that lack clinical coherence or prioritize information metrics over predictive performance.
  • Developing interpretable models for complex, multifactorial outcomes like late morbidity in cancer patients requires customizable optimization.

Purpose of the Study:

  • To develop a simulated annealing-based framework for constructing Bayesian network structures tailored for late morbidity prediction in cervical cancer.
  • To address the limitations of existing optimization methods by prioritizing both predictive accuracy and clinical interpretability.
  • To create a framework that generates logically coherent and clinically relevant Bayesian networks.

Main Methods:

  • Utilized the EMBRACE I cervical cancer dataset (n=1153) for developing Bayesian networks to predict moderate-to-severe late-grade cystitis.
  • Implemented a simulated annealing optimization method incorporating information-theoretic, predictive performance, and complexity measures.
  • Compared the developed Bayesian network structures against out-of-box PyAgrum methods (Greedy Hill Climbing, TAN, Chow-Liu) and conventional classifiers using 10x5-fold cross-validation.

Main Results:

  • The simulated annealing framework produced Bayesian networks with predictive performance comparable or superior to out-of-box methods (Cochran's Q-test, p=0.03).
  • Simulated annealing models achieved a balanced accuracy of 64.1%, F1 macro score of 55.9%, and ROC-AUC of 0.66 on a bootstrapped test set.
  • These networks featured fewer arcs and nodes, enhancing interpretability without sacrificing predictive performance.

Conclusions:

  • The proposed simulated annealing framework offers a novel approach for automated Bayesian network generation in cervical cancer late morbidity modeling.
  • Simulated annealing-based Bayesian networks demonstrate superior interpretability and comparable or better predictive performance than existing optimization techniques.
  • The developed framework facilitates the creation of clinically useful, interpretable predictive models for complex health outcomes.