Identification of a blood-based 12-gene signature that predicts the severity of coronary artery stenosis: An integrative approach based on gene network construction, Support Vector Machine algorithm, and multi-cohort validation.
Aged
China
Coronary Stenosis
/ blood
Decision Support Techniques
Female
Gene Expression Profiling
Gene Regulatory Networks
Genetic Predisposition to Disease
Humans
Male
Middle Aged
Nomograms
Phenotype
Predictive Value of Tests
Reproducibility of Results
Retrospective Studies
Risk Factors
Severity of Illness Index
Support Vector Machine
Transcriptome
Coronary artery stenosis
Gene coexpression network
Gene expression score
Prediction model
Journal
Atherosclerosis
ISSN: 1879-1484
Titre abrégé: Atherosclerosis
Pays: Ireland
ID NLM: 0242543
Informations de publication
Date de publication:
12 2019
12 2019
Historique:
received:
01
08
2019
revised:
25
09
2019
accepted:
08
10
2019
pubmed:
7
11
2019
medline:
4
8
2020
entrez:
6
11
2019
Statut:
ppublish
Résumé
We aimed to identify a blood-based gene expression score (GES) to predict the severity of coronary artery stenosis in patients with known or suspected coronary artery disease (CAD) by integrative use of gene network construction, Support Vector Machine (SVM) algorithm, and multi-cohort validation. In the discovery phase, a public blood-based microarray dataset of 110 patients with known CAD was analyzed by weighted gene coexpression network analysis and protein-protein interaction network analysis to identify candidate hub genes. In the training set with 151 CAD patients, bioinformatically identified hub genes were experimentally verified by real-time polymerase chain reaction, and statistically filtered with the SVM algorithm to develop a GES. Internal and external validation of GES was performed in patients with suspected CAD from two validation cohorts (n = 209 and 206). The discovery phase screened 15 network-centric hub genes significantly correlated with the Duke CAD Severity Index. In the training cohort, 12 of 15 hub genes were filtered to construct a blood-based GES12, which showed good discrimination for higher modified Gensini scores (AUC: 0.798 and 0.812), higher Sullivan Extent scores (AUC: 0.776 and 0.778), and the presence of obstructive CAD (AUC: 0.834 and 0.792) in two validation cohorts. A nomogram comprising GES12, smoking status, hypertension status, low density lipoprotein cholesterol level, and body mass index further improved performance, with respect to discrimination, risk classification, and clinical utility, for prediction of coronary stenosis severity. GES12 is useful in predicting the severity of coronary artery stenosis in patients with known or suspected CAD.
Sections du résumé
BACKGROUND AND AIMS
We aimed to identify a blood-based gene expression score (GES) to predict the severity of coronary artery stenosis in patients with known or suspected coronary artery disease (CAD) by integrative use of gene network construction, Support Vector Machine (SVM) algorithm, and multi-cohort validation.
METHODS
In the discovery phase, a public blood-based microarray dataset of 110 patients with known CAD was analyzed by weighted gene coexpression network analysis and protein-protein interaction network analysis to identify candidate hub genes. In the training set with 151 CAD patients, bioinformatically identified hub genes were experimentally verified by real-time polymerase chain reaction, and statistically filtered with the SVM algorithm to develop a GES. Internal and external validation of GES was performed in patients with suspected CAD from two validation cohorts (n = 209 and 206).
RESULTS
The discovery phase screened 15 network-centric hub genes significantly correlated with the Duke CAD Severity Index. In the training cohort, 12 of 15 hub genes were filtered to construct a blood-based GES12, which showed good discrimination for higher modified Gensini scores (AUC: 0.798 and 0.812), higher Sullivan Extent scores (AUC: 0.776 and 0.778), and the presence of obstructive CAD (AUC: 0.834 and 0.792) in two validation cohorts. A nomogram comprising GES12, smoking status, hypertension status, low density lipoprotein cholesterol level, and body mass index further improved performance, with respect to discrimination, risk classification, and clinical utility, for prediction of coronary stenosis severity.
CONCLUSIONS
GES12 is useful in predicting the severity of coronary artery stenosis in patients with known or suspected CAD.
Identifiants
pubmed: 31689620
pii: S0021-9150(19)31518-7
doi: 10.1016/j.atherosclerosis.2019.10.001
pii:
doi:
Types de publication
Journal Article
Multicenter Study
Research Support, Non-U.S. Gov't
Validation Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
34-43Informations de copyright
Copyright © 2019 Elsevier B.V. All rights reserved.