Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

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

Summary

This summary is machine-generated.

Related Concept Videos

Mechanistic Models: Compartment Models in Individual and Population Analysis

Mechanistic Models: Compartment Models in Individual and Population Analysis

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...

Blood Studies for Cardiovascular System I: Cardiac Biomarkers

Blood Studies for Cardiovascular System I: Cardiac Biomarkers

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...

You might also read

Related Articles

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

Sort by

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

Same author

Accurate detection of tumor clonality and ongoing expansion mode from genomic data.

bioRxiv : the preprint server for biology·2026

Same author

Efficacy of extracorporeal shock wave therapy combined with conventional physical therapy for chronic low back pain: a systematic review and network meta-analysis of randomized controlled trials.

Frontiers in physiology·2026

Same author

Skin characteristics of photoaging and intrinsic aging in Southwest Chinese population: a reflectance confocal microscopy and histopathological study.

Frontiers in physiology·2026

Same author

Integrated E-nose, GC-MS/GC-IMS, untargeted metabolomics, and high-throughput sequencing reveal mechanisms underlying grade-dependent flavour differentiation in Xuanwei ham.

International journal of food microbiology·2026

Same journal

Editorial: Epigenetic and genetic mechanisms underlying cardiovascular diseases and neurodevelopmental disorders, volume II.

Frontiers in molecular biosciences·2026

Same journal

Integrated transcriptomic profiling reveals oncogenic pathways and chimeric transcripts in equine sarcoid lesions with predominant BPV1 detection.

Frontiers in molecular biosciences·2026

Same journal

Mesenchymal stem cells-derived extracellular vesicles as a novel drug delivery carrier: engineering strategies and clinical safety estimation.

Frontiers in molecular biosciences·2026

Same journal

Preparation and analysis of tobacco glycosides, and the relationship between glycoside aglycones and pyrolysis products: a review.

Frontiers in molecular biosciences·2026

Same journal

Peritoneal metastasis in pancreatic cancer: molecular mechanisms, microenvironmental remodeling, and emerging intraperitoneal interventions.

Frontiers in molecular biosciences·2026

Same journal

Insights from LC-MS-based cerebrospinal fluid metabolomics in tuberculous meningitis.

Frontiers in molecular biosciences·2026

See all related articles

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:

SHAP classifier heart disease interpretability stacking 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.