Related Experiment Video
Updated: Jan 31, 2026
Author Spotlight: Innovative Technique for Coronary Angiography in Marginal Donors
Published on: July 12, 2024
Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart
Meeshanthini V Dogan1,2,3, Steven R H Beach4, Ronald L Simons5
1Department of Biomedical Engineering, University of Iowa, Iowa City, IA 52242, USA. meeshanthini-vijayendran@uiowa.edu.
Insights
A new DNA-based tool using machine learning improves prediction of incident coronary heart disease (CHD) risk. This genetic-epigenetic model outperforms traditional risk scores, offering a precision medicine approach for cardiovascular health.
Area of Science:
- Cardiovascular Medicine
- Genetics
- Bioinformatics
Background:
- Conventional risk factors have limitations in predicting coronary heart disease (CHD) incidence.
- Genetic and epigenetic factors show promise for more sensitive CHD risk prediction.
- Machine learning approaches can analyze complex biological data for predictive modeling.
Purpose of the Study:
- To develop and evaluate a machine learning-based panel for predicting incident CHD risk.
- To compare the performance of a novel genetic-epigenetic model against established risk scores.
- To identify a DNA-based precision medicine tool for CHD risk stratification.
Main Methods:
- Utilized data mining and Random Forest ensemble models on training (1180 individuals) and test (524 individuals) sets.
- Developed a predictive panel integrating four genetic and four epigenetic loci.
- Evaluated model performance using sensitivity and specificity metrics.
Main Results:
- The integrated genetic-epigenetic model achieved test sensitivity of 0.70 and specificity of 0.74.
- Outperformed Framingham Risk Score (sensitivity 0.20) and ASCVD risk estimator (sensitivity 0.38).
- Demonstrated superior prediction across genders and within a three-year risk window.
Conclusions:
- A novel DNA-based precision medicine tool effectively predicts incident CHD risk.
- The model captures complex genetic-environmental interactions contributing to CHD.
- This approach offers actionable insights for cardiovascular risk modification efforts.
Abstract:
An improved approach for predicting the risk for incident coronary heart disease (CHD) could lead to substantial improvements in cardiovascular health. Previously, we have shown that genetic and epigenetic loci could predict CHD status more sensitively than conventional risk factors. Herein, we examine whether similar machine learning approaches could be used to develop a similar panel for predicting incident CHD. Training and test sets consisted of 1180 and 524 individuals, respectively. Data mining techniques were employed to mine for predictive biosignatures in the training set. An ensemble of Random Forest models consisting of four genetic and four epigenetic loci was trained on the training set and subsequently evaluated on the test set. The test sensitivity and specificity were 0.70 and 0.74, respectively. In contrast, the Framingham risk score and atherosclerotic cardiovascular disease (ASCVD) risk estimator performed with test sensitivities of 0.20 and 0.38, respectively. Notably, the integrated genetic-epigenetic model predicted risk better for both genders and very well in the three-year risk prediction window. We describe a novel DNA-based precision medicine tool capable of capturing the complex genetic and environmental relationships that contribute to the risk of CHD, and being mapped to actionable risk factors that may be leveraged to guide risk modification efforts.
Related Concept Videos
01:27Anatomy of the Heart
01:20Anatomy of the Heart
The heart has three layers: the innermost endocardium, the muscular myocardium, and the outer epicardium, all working together for optimal cardiac function.
Chambers of the Heart
The heart is made up of four...
01:22Rheumatic Heart Disease II: Clinical Manifestations and Diagnostic Studies
01:23Rheumatic Heart Disease I: Introduction
01:17Ischemic Heart Disease: Overview
Atherosclerosis, the primary malefactor, orchestrates this dangerous condition. It manifests as the accumulation of fatty deposits, akin to insidious plaques, within arterial walls. As time elapses, these plaques metamorphose, hardening and...
01:20Blood Studies for Cardiovascular System I: Cardiac Biomarkers
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...