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

Patient-specific guides and osteosynthesis versus CAD/CAM occlusal splints in orthognathic surgery: a systematic review and meta-analysis of accuracy, operative time, and complications.

BMC oral health·2026
Same author

Bi-layer photonic random meta-composite for cryogenic thermal control by ultra-broadband scattering matched reflectance.

Light, science & applications·2026
Same author

Inotodiol ameliorates oxidative stress and apoptosis by regulating PI3K/Akt/GSK-3β signaling pathways in diabetic nephropathy.

Renal failure·2026
Same author

Mechanistic Insights and Therapeutic Advances of Anti-Inflammatory Biologics in Immune-Mediated Glomerulonephritis: A Narrative Review.

Journal of inflammation research·2026
Same author

Corrigendum to "Dynamic regulation of neuronal vault trafficking and RNA cargo by the noncoding RNA, Vaultrc5" [Neurobiol. Learn. Memory 225 (2026) 108161].

Neurobiology of learning and memory·2026
Same author

Pd/TiO<sub>2</sub> and Surface Hydrogen: A Dual Driver for <i>n</i>-Butyraldehyde Aldol Condensation and Selective Hydrogenation of the Condensation Product.

Langmuir : the ACS journal of surfaces and colloids·2026

Related Experiment Video

Updated: Aug 14, 2025

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

7.6K

Using Bayesian network model with MMHC algorithm to detect risk factors for stroke.

Wenzhu Song1, Lixia Qiu1, Jianbo Qing2

  • 1School of Public Health, Shanxi Medical University, Taiyuan, China.

Mathematical Biosciences and Engineering : MBE
|January 19, 2023
PubMed
Summary
This summary is machine-generated.

This study identified key stroke risk factors using a Bayesian Network (BN) model. Age, blood glucose, blood pressure, and family history are direct risks, while sex and cholesterol are indirect risks.

Keywords:
Bayesian networklogistic regressionmodel constructionrisk factorsstroke

More Related Videos

Author Spotlight: Establishing a Reliable Distal MCA Occlusion Model in Mice for Stroke Research
07:34

Author Spotlight: Establishing a Reliable Distal MCA Occlusion Model in Mice for Stroke Research

Published on: December 15, 2023

2.3K
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

15.7K

Related Experiment Videos

Last Updated: Aug 14, 2025

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

7.6K
Author Spotlight: Establishing a Reliable Distal MCA Occlusion Model in Mice for Stroke Research
07:34

Author Spotlight: Establishing a Reliable Distal MCA Occlusion Model in Mice for Stroke Research

Published on: December 15, 2023

2.3K
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

15.7K

Area of Science:

  • Neurology
  • Medical Informatics
  • Public Health

Background:

  • Stroke is a leading cause of death and disability globally.
  • Understanding stroke risk factors is crucial for prevention and management.
  • Traditional statistical models may not fully capture complex risk factor interactions.

Purpose of the Study:

  • To explore stroke risk factors using a Bayesian Network (BN) model with the Max-Min Hill-Climbing (MMHC) algorithm.
  • To identify direct and indirect risk factors contributing to stroke incidence.
  • To evaluate the efficacy of the BN-MMHC model in stroke risk prediction.

Main Methods:

  • Propensity score matching (PSM) was used for class balancing.
  • Chi-square testing and Logistic regression identified initial risk factors.
  • Bayesian Network (BN) structure learning employed the MMHC algorithm.
  • Parameter learning utilized Maximum Likelihood Estimation.

Main Results:

  • The study included 748 stroke and 748 non-stroke cases after PSM.
  • A BN model with 10 nodes and 12 directed edges was constructed.
  • Direct risk factors: age, fasting plasma glucose, systolic blood pressure, family history.
  • Indirect risk factors: sex, educational level, HDL cholesterol, diastolic blood pressure, urinary albumin-to-creatinine ratio.

Conclusions:

  • The BN-MMHC model effectively reveals complex relationships between stroke risk factors.
  • Bayesian reasoning with BN models offers superior stroke risk prediction compared to Logistic regression.
  • BN models show significant potential for stroke risk factor detection and prediction.