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

An interpretability heart disease prediction model based on stacking ensemble with SHAP.

Yanjie Chen1, Liqiang Chong2, Zhenghao Bao1

  • 1Department of Abdominal Ultrasound, The Affiliated Hospital of Qingdao University, Qingdao, China.

Frontiers in Molecular Biosciences
|March 9, 2026
PubMed
Summary

Related Concept Videos

Mechanistic Models: Compartment Models in Individual and Population Analysis01:23

Mechanistic Models: Compartment Models in Individual and Population Analysis

314
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
314
Blood Studies for Cardiovascular System I: Cardiac Biomarkers01:20

Blood Studies for Cardiovascular System I: Cardiac Biomarkers

1.0K
Cardiac biomarkers are enzymes, proteins, and hormones released into the blood when cardiac cells are injured. They are powerful tools for triaging.
The essential diagnostic tools for detecting myocardial necrosis and monitoring individuals suspected of having acute coronary syndrome (ACS) include:
Troponins
Troponins, particularly cardiac troponins I and T, are the most precise and sensitive markers of myocardial injury. They are detectable within 4-6 hours of myocardial injury and remain...
1.0K

You might also read

Related Articles

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

Sort by
Same author

Higher-Order Dynamic Disentangled Intent Sensing and Bidirectional Joint Updating Framework for NcRNA-Drug Resistance Association Prediction.

Journal of chemical information and modeling·2026
Same author

Metabolic reprogramming of cancer associated fibroblasts informs stromal heterogeneity and therapeutic targeting.

Discover oncology·2026
Same author

Plasma-state metasurfaces for ultra-intensive field manipulation.

Light, science & applications·2026
Same author

Association of induced abortion with bipolar disorder and major depression from the UK Biobank: a propensity score matching and weighting analysis.

Social psychiatry and psychiatric epidemiology·2026
Same author

The causal relationship between the palmitoylation gene ZDHHC13 and ulcerative colitis: A Mendelian randomization study implicating CD62L-monocyte AC.

Medicine·2026
Same author

Tricholoma matsutake polysaccharides promote physiological germination and metabolic reactivation of Bacillus cereus spores: Mechanisms and application in milk preservation.

International journal of food microbiology·2026

Ensemble learning effectively predicts heart disease risk by analyzing health indicators. Maintaining 7-8 hours of sleep daily is key to reducing risk, while age and health status are critical factors.

Area of Science:

  • Cardiovascular research
  • Machine learning in healthcare
  • Big data analytics

Background:

  • Exponential growth in healthcare data offers opportunities for understanding heart disease pathogenesis.
  • Identifying correlations between health indicators and heart disease is vital for early prevention strategies.

Purpose of the Study:

  • To employ ensemble learning for identifying key factors influencing heart disease.
  • To enhance prediction strategies for cardiovascular risk assessment.

Main Methods:

  • A two-layer stacking ensemble model was developed, integrating Naive Bayes, Decision Trees, CatBoost, and Gradient Boosting Trees.
  • The SHAP (SHapley Additive exPlanations) technique was utilized for visualizing the ensemble model's decision-making logic and interpretability.
Keywords:
SHAPclassifierheart diseaseinterpretabilitystacking ensemble

Related Experiment Videos

Main Results:

  • The stacking model achieved 86.69% accuracy, balancing precision and recall.
  • Global interpretive analysis identified age, sleep duration (7-8 hours optimal), self-rated health, and BMI as critical cardiovascular risk factors.
  • Local analysis assessed individual feature contributions to predictions.

Conclusions:

  • Ensemble learning models outperform single learners in predicting heart disease.
  • Personalized prevention strategies can be informed by identified key predictive factors like sleep duration and age.