An innovative model for predicting coronary heart disease using triglyceride-glucose index: a machine learning-based cohort study
Main finding · CHDResult — go to the resultFully adjusted HR 2.32 CI 1.16–4.68Authors' conclusion
We recommend using the TyG-index in clinical practice and predictive models to identify individuals at risk of developing CHD and to aid in its prevention.
Study context
- Population
- Community-based Iranian population aged 20–74 years; mean follow-up 9.9 years (range: 7.6–12.2)
- Participants
- 2,000 participants
- Exposure
- Triglyceride-glucose index (TyG-index) quartiles (Q4 vs Q1); TyG-index-based vs diabetes-based coronary heart disease (CHD) prediction models
- Outcome
- Incident CHD
- Follow-up
- Mean 9.9 years
Methodological detailscommunity-based, machine learning prediction models, multivariate Cox proportional hazard models
- Community-based
- Machine learning prediction models
- Multivariate Cox proportional hazard models
Main finding
CHD
Fully adjusted HR
2.32
CI 1.16–4.68
p-trend 0.04
TyG-index Q4vs TyG-index Q1
fully adjusted HR 2.32 (CI 1.16–4.68); p-trend 0.04
As reported in the abstract
- Incidence of CHD
- 14.5%
Observational data: associations, not effects.
Further findings
Prediction of CHD by TyG-index
- TyG-index cut-off with highest NPV for CHD
- > 8.42
- TyG-index-based support vector machine (SVM) performed significantly better than diabetes-based SVM for predicting CHD
- TyG-index more important than diabetes; most important factor after age in machine learning models
Original publication
An innovative model for predicting coronary heart disease using triglyceride-glucose index: a machine learning-based cohort study. Cardiovasc Diabetol. Published 4 August 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →