Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning

Meeshanthini V Dogan; Steven R H Beach; Ronald L Simons; Amaury Lendasse; Brandan Penaluna; Robert A Philibert

doi:10.3390/genes9120641

Back

Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning

Journal article

Open access

Peer reviewed

Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning

Meeshanthini V Dogan, Steven R H Beach, Ronald L Simons, Amaury Lendasse, Brandan Penaluna and Robert A Philibert

Genes, Vol.9(12), p.641

12/18/2018

DOI: 10.3390/genes9120641

PMCID: PMC6315411

PMID: 30567402

Files and links (1)

url

https://doi.org/10.3390/genes9120641View

Published (Version of record) Open Access

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.

risk factors

genetics

biomarkers

risk prediction

coronary heart disease

machine learning

epigenetics

Details

Title: Subtitle: Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning
Creators: Meeshanthini V Dogan - Department of Psychiatry, University of Iowa, Iowa City, IA 52242, USA. meeshanthini-vijayendran@uiowa.edu
Steven R H Beach - Department of Psychology, University of Georgia, Athens, GA 30602, USA. srhbeach@uga.edu
Ronald L Simons - Department of Sociology, University of Georgia, Athens, GA 30606, USA. rsimons@uga.edu
Amaury Lendasse - Department of Business Management and Analytics, Arcada University of Applied Sciences, 00560 Helsinki, Finland. alendass@central.uh.edu
Brandan Penaluna - Behavioral Diagnostics LLC, 2500 Crosspark Road, Coralville, IA 52241, USA. brandan-penaluna@uiowa.edu
Robert A Philibert - Behavioral Diagnostics LLC, 2500 Crosspark Road, Coralville, IA 52241, USA. robert-philibert@uiowa.edu
Resource Type: Journal article
Publication Details: Genes, Vol.9(12), p.641
DOI: 10.3390/genes9120641
PMID: 30567402
PMCID: PMC6315411
NLM abbreviation: Genes (Basel)
ISSN: 2073-4425
eISSN: 2073-4425
Publisher: Switzerland
Grant note: R01DA037648 / National Institutes of Health R44DA041014 / National Institutes of Health
Language: English
Date published: 12/18/2018
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Psychiatry; Iowa Neuroscience Institute; Industrial and Systems Engineering
Record Identifier: 9984003436402771

Metrics

30 Record Views

30 Times Cited - Web of Science