Cargando…

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

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 exam...

Descripción completa

Detalles Bibliográficos
Autores principales: Dogan, Meeshanthini V., Beach, Steven R. H., Simons, Ronald L., Lendasse, Amaury, Penaluna, Brandan, Philibert, Robert A.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6315411/
https://www.ncbi.nlm.nih.gov/pubmed/30567402
http://dx.doi.org/10.3390/genes9120641
_version_ 1783384288061816832
author Dogan, Meeshanthini V.
Beach, Steven R. H.
Simons, Ronald L.
Lendasse, Amaury
Penaluna, Brandan
Philibert, Robert A.
author_facet Dogan, Meeshanthini V.
Beach, Steven R. H.
Simons, Ronald L.
Lendasse, Amaury
Penaluna, Brandan
Philibert, Robert A.
author_sort Dogan, Meeshanthini V.
collection PubMed
description 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.
format Online
Article
Text
id pubmed-6315411
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-63154112019-01-09 Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning Dogan, Meeshanthini V. Beach, Steven R. H. Simons, Ronald L. Lendasse, Amaury Penaluna, Brandan Philibert, Robert A. Genes (Basel) Article 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. MDPI 2018-12-18 /pmc/articles/PMC6315411/ /pubmed/30567402 http://dx.doi.org/10.3390/genes9120641 Text en © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Dogan, Meeshanthini V.
Beach, Steven R. H.
Simons, Ronald L.
Lendasse, Amaury
Penaluna, Brandan
Philibert, Robert A.
Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning
title Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning
title_full Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning
title_fullStr Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning
title_full_unstemmed Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning
title_short Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning
title_sort blood-based biomarkers for predicting the risk for five-year incident coronary heart disease in the framingham heart study via machine learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6315411/
https://www.ncbi.nlm.nih.gov/pubmed/30567402
http://dx.doi.org/10.3390/genes9120641
work_keys_str_mv AT doganmeeshanthiniv bloodbasedbiomarkersforpredictingtheriskforfiveyearincidentcoronaryheartdiseaseintheframinghamheartstudyviamachinelearning
AT beachstevenrh bloodbasedbiomarkersforpredictingtheriskforfiveyearincidentcoronaryheartdiseaseintheframinghamheartstudyviamachinelearning
AT simonsronaldl bloodbasedbiomarkersforpredictingtheriskforfiveyearincidentcoronaryheartdiseaseintheframinghamheartstudyviamachinelearning
AT lendasseamaury bloodbasedbiomarkersforpredictingtheriskforfiveyearincidentcoronaryheartdiseaseintheframinghamheartstudyviamachinelearning
AT penalunabrandan bloodbasedbiomarkersforpredictingtheriskforfiveyearincidentcoronaryheartdiseaseintheframinghamheartstudyviamachinelearning
AT philibertroberta bloodbasedbiomarkersforpredictingtheriskforfiveyearincidentcoronaryheartdiseaseintheframinghamheartstudyviamachinelearning