Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 14, 2023PLoS ONEOpen Access

An XGBoost machine learning model effectively predicted coronary artery disease with an AUROC of 0.89, identifying age, platelet count, family history of heart disease, and total cholesterol as the top risk factors.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Can an XGBoost machine learning model accurately predict coronary artery disease and identify key risk factors using demographic, laboratory, physical exam, and lifestyle covariates?

Population

7,929 patients from the National Health and Nutrition Examination Survey who completed demographic, dietary…

Design

Cross-sectional

Key result

An XGBoost machine learning model effectively predicted coronary artery disease with an AUROC of 0.89, identifying age, platelet count, family history of heart disease, and total cholesterol as the top risk factors.

Authors

AHAlexander A. HuangSHSamuel Y. Huang

Discussion

Loading...

Member takes

Overview

Machine learning CAD prediction with routine data remains hypothesis-generating; prospective validation required before any practice change.

Study Design

Type

Cross-Sectional (n=7,929)

Structured PICO

Can an XGBoost machine learning model accurately predict coronary artery disease and identify key risk factors using demographic, laboratory, physical exam, and lifestyle covariates?

P
Population
7,929 adult participants from the US NHANES dataset with complete demographic, clinical, and lifestyle data, of whom 4.5% had coronary artery disease.
E
Exposure
XGBoost machine learning model using demographic, laboratory, physical exam, and lifestyle covariates
O
Outcome
Coronary artery disease (CAD)

Main Result

Effect estimate: AUROC 0.89

A machine learning model using routine clinical, demographic, and lifestyle data can accurately predict coronary artery disease and identify key risk factors such as age and platelet count.

Limitations

  • Retrospective nature of the cohort
  • Reliance on self-reported surveys to obtain the outcome of interest (CAD) as well as dietary and lifestyle information
  • Voluntary nature of the cohort, with participants choosing to opt into the study instead of being randomly selected

Cite This Study

Huang et al. (2023) conducted a cross-sectional in Coronary artery disease (n=7,929). Demographic, laboratory, physical exam, and lifestyle covariates was evaluated on Prediction of coronary artery disease (AUROC 0.89). An XGBoost machine learning model effectively predicted coronary artery disease with an AUROC of 0.89, identifying age, platelet count, family history of heart disease, and total cholesterol as the top risk factors.

synapsesocial.com/papers/6aacfedec9a6fdb0ab1e6245https://doi.org/10.1371/journal.pone.0284103
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Machine Learning Model for Predicting Coronary Heart Disease Risk: Development and Validation Using Insights From a Japanese Population–Based Study2025 · 32 citations
  2. 2Explainable Machine Learning Prognosis of Coronary Artery Disease Using Lifestyle and Medical History Data2026
  3. 3Abstract TH961: Beyond Traditional Risk Factors: A Data-Driven Approach to Coronary Artery Disease (CAD) Prediction2026
  4. 4Use machine learning models to identify and assess risk factors for coronary artery disease2024 · 14 citations
  5. 5Study on the risk of coronary heart disease in middle-aged and young people based on machine learning methods: a retrospective cohort study2022 · 10 citations