Related Experiment Video
Updated: Feb 25, 2026
Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts
Published on: September 20, 2024
Cardiovascular Event Prediction by Machine Learning: The Multi-Ethnic Study of Atherosclerosis.
Bharath Ambale-Venkatesh1, Xiaoying Yang1, Colin O Wu1
1From the Department of Radiology (B.A.-V.), Bloomberg School of Public Health (E.G.), and Department of Medicine, Cardiology and Radiology (J.A.C.L.), Johns Hopkins University, Baltimore, MD; George Washington University, DC (X.Y.); Office of Biostatistics, NHLBI, NIH, Bethesda, MD (C.O.W.); Department of Preventive Medicine, Northwestern University Medical School, Chicago, IL (K.L.); Department of Cardiology, Wake Forest University Health Sciences, Winston-Salem, NC (W.G.H.); Department of Biostatistics, University of Washington, Seattle (R.M.); Department of Radiology, UCLA School of Medicine, Los Angeles, CA (A.S.G.); Division of Epidemiology and Community Health, University of Minnesota, Minneapolis (A.R.F.); Departments of Medicine and Epidemiology, Columbia University, New York, NY (S.S.); and Radiology and Imaging Sciences, NIH Clinical Center, Bethesda, MD (D.A.B.).
Machine learning accurately predicts cardiovascular events using deep phenotyping, outperforming traditional risk scores in asymptomatic individuals. This approach enhances understanding of subclinical disease markers.
Area of Science:
- Cardiovascular disease research
- Biomarker discovery
- Machine learning applications in medicine
Background:
- Cardiovascular disease risk prediction is crucial for population health.
- Machine learning (ML) offers potential for characterizing risk and identifying biomarkers.
- The Multi-Ethnic Study of Atherosclerosis (MESA) provides a rich dataset for such investigations.
Purpose of the Study:
- To evaluate the predictive capability of random survival forests (RSF), an ML technique.
- To compare RSF performance against standard cardiovascular risk scores.
- To identify novel predictors of cardiovascular outcomes using a comprehensive dataset.
Main Methods:
- Utilized data from 6814 MESA participants, initially free of cardiovascular disease.
- Employed RSF to analyze 735 variables including imaging, biomarkers, and questionnaires.
- Identified top-20 predictors for six distinct cardiovascular outcomes over 12 years.
Main Results:
- RSF demonstrated superior prediction accuracy compared to established risk scores (10%-25% decrease in Brier score).
- Key predictors varied by outcome, with imaging and biomarkers often outranking traditional factors.
- Specific predictors identified include Coronary Artery Calcium for coronary heart disease and NT-proBNP for heart failure.
Conclusions:
- ML combined with deep phenotyping significantly improves cardiovascular event prediction in asymptomatic populations.
- These advanced methods offer deeper insights into subclinical disease markers.
- The findings suggest a paradigm shift in cardiovascular risk assessment beyond traditional assumptions.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
07:25Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
Related Concept Videos
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...
01:30Coronary Artery Disease I: Introduction