A multimodal approach to cardiovascular risk stratification in patients with type 2 diabetes incorporating retinal, genomic and clinical features

Ahmed E Fetit, Alexander S Doney, Stephen Hogg, Ruixuan Wang, Tom MacGillivray, Joanna M Wardlaw, Fergus N Doubal, Gareth J McKay, Stephen McKenna, Emanuele Trucco

Research output: Contribution to journalArticle

Abstract

Cardiovascular diseases are a public health concern; they remain the leading cause of morbidity and mortality in patients with type 2 diabetes. Phenotypic information available from retinal fundus images and clinical measurements, in addition to genomic data, can identify relevant biomarkers of cardiovascular health. In this study, we assessed whether such biomarkers stratified risks of major adverse cardiac events (MACE). A retrospective analysis was carried out on an extract from the Tayside GoDARTS bioresource of participants with type 2 diabetes (n = 3,891). A total of 519 features were incorporated, summarising morphometric properties of the retinal vasculature, various single nucleotide polymorphisms (SNPs), as well as routine clinical measurements. After imputing missing features, a predictive model was developed on a randomly sampled set (n = 2,918) using L1-regularised logistic regression (lasso). The model was evaluated on an independent set (n = 973) and its performance associated with overall hazard rate after censoring (log-rank p < 0.0001), suggesting that multimodal features were able to capture important knowledge for MACE risk assessment. We further showed through a bootstrap analysis that all three sources of information (retinal, genetic, routine clinical) offer robust signal. Particularly robust features included: tortuousity, width gradient, and branching point retinal groupings; SNPs known to be associated with blood pressure and cardiovascular phenotypic traits; age at imaging; clinical measurements such as blood pressure and high density lipoprotein. This novel approach could be used for fast and sensitive determination of future risks associated with MACE.

LanguageEnglish
Article number3591
Number of pages10
JournalScientific Reports
Volume9
DOIs
Publication statusPublished - 05 Mar 2019

Fingerprint

Type 2 Diabetes Mellitus
Single Nucleotide Polymorphism
Biomarkers
Blood Pressure
HDL Lipoproteins
Cardiovascular Diseases
Public Health
Logistic Models
Morbidity
Mortality
Health
alachlor

Cite this

Fetit, Ahmed E ; Doney, Alexander S ; Hogg, Stephen ; Wang, Ruixuan ; MacGillivray, Tom ; Wardlaw, Joanna M ; Doubal, Fergus N ; McKay, Gareth J ; McKenna, Stephen ; Trucco, Emanuele. / A multimodal approach to cardiovascular risk stratification in patients with type 2 diabetes incorporating retinal, genomic and clinical features. In: Scientific Reports. 2019 ; Vol. 9.
@article{bebdcc95bc47402e90f9504dd9826f23,
title = "A multimodal approach to cardiovascular risk stratification in patients with type 2 diabetes incorporating retinal, genomic and clinical features",
abstract = "Cardiovascular diseases are a public health concern; they remain the leading cause of morbidity and mortality in patients with type 2 diabetes. Phenotypic information available from retinal fundus images and clinical measurements, in addition to genomic data, can identify relevant biomarkers of cardiovascular health. In this study, we assessed whether such biomarkers stratified risks of major adverse cardiac events (MACE). A retrospective analysis was carried out on an extract from the Tayside GoDARTS bioresource of participants with type 2 diabetes (n = 3,891). A total of 519 features were incorporated, summarising morphometric properties of the retinal vasculature, various single nucleotide polymorphisms (SNPs), as well as routine clinical measurements. After imputing missing features, a predictive model was developed on a randomly sampled set (n = 2,918) using L1-regularised logistic regression (lasso). The model was evaluated on an independent set (n = 973) and its performance associated with overall hazard rate after censoring (log-rank p < 0.0001), suggesting that multimodal features were able to capture important knowledge for MACE risk assessment. We further showed through a bootstrap analysis that all three sources of information (retinal, genetic, routine clinical) offer robust signal. Particularly robust features included: tortuousity, width gradient, and branching point retinal groupings; SNPs known to be associated with blood pressure and cardiovascular phenotypic traits; age at imaging; clinical measurements such as blood pressure and high density lipoprotein. This novel approach could be used for fast and sensitive determination of future risks associated with MACE.",
author = "Fetit, {Ahmed E} and Doney, {Alexander S} and Stephen Hogg and Ruixuan Wang and Tom MacGillivray and Wardlaw, {Joanna M} and Doubal, {Fergus N} and McKay, {Gareth J} and Stephen McKenna and Emanuele Trucco",
year = "2019",
month = "3",
day = "5",
doi = "10.1038/s41598-019-40403-1",
language = "English",
volume = "9",
journal = "Nature Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",

}

A multimodal approach to cardiovascular risk stratification in patients with type 2 diabetes incorporating retinal, genomic and clinical features. / Fetit, Ahmed E; Doney, Alexander S; Hogg, Stephen; Wang, Ruixuan; MacGillivray, Tom; Wardlaw, Joanna M; Doubal, Fergus N; McKay, Gareth J; McKenna, Stephen; Trucco, Emanuele.

In: Scientific Reports, Vol. 9, 3591, 05.03.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A multimodal approach to cardiovascular risk stratification in patients with type 2 diabetes incorporating retinal, genomic and clinical features

AU - Fetit, Ahmed E

AU - Doney, Alexander S

AU - Hogg, Stephen

AU - Wang, Ruixuan

AU - MacGillivray, Tom

AU - Wardlaw, Joanna M

AU - Doubal, Fergus N

AU - McKay, Gareth J

AU - McKenna, Stephen

AU - Trucco, Emanuele

PY - 2019/3/5

Y1 - 2019/3/5

N2 - Cardiovascular diseases are a public health concern; they remain the leading cause of morbidity and mortality in patients with type 2 diabetes. Phenotypic information available from retinal fundus images and clinical measurements, in addition to genomic data, can identify relevant biomarkers of cardiovascular health. In this study, we assessed whether such biomarkers stratified risks of major adverse cardiac events (MACE). A retrospective analysis was carried out on an extract from the Tayside GoDARTS bioresource of participants with type 2 diabetes (n = 3,891). A total of 519 features were incorporated, summarising morphometric properties of the retinal vasculature, various single nucleotide polymorphisms (SNPs), as well as routine clinical measurements. After imputing missing features, a predictive model was developed on a randomly sampled set (n = 2,918) using L1-regularised logistic regression (lasso). The model was evaluated on an independent set (n = 973) and its performance associated with overall hazard rate after censoring (log-rank p < 0.0001), suggesting that multimodal features were able to capture important knowledge for MACE risk assessment. We further showed through a bootstrap analysis that all three sources of information (retinal, genetic, routine clinical) offer robust signal. Particularly robust features included: tortuousity, width gradient, and branching point retinal groupings; SNPs known to be associated with blood pressure and cardiovascular phenotypic traits; age at imaging; clinical measurements such as blood pressure and high density lipoprotein. This novel approach could be used for fast and sensitive determination of future risks associated with MACE.

AB - Cardiovascular diseases are a public health concern; they remain the leading cause of morbidity and mortality in patients with type 2 diabetes. Phenotypic information available from retinal fundus images and clinical measurements, in addition to genomic data, can identify relevant biomarkers of cardiovascular health. In this study, we assessed whether such biomarkers stratified risks of major adverse cardiac events (MACE). A retrospective analysis was carried out on an extract from the Tayside GoDARTS bioresource of participants with type 2 diabetes (n = 3,891). A total of 519 features were incorporated, summarising morphometric properties of the retinal vasculature, various single nucleotide polymorphisms (SNPs), as well as routine clinical measurements. After imputing missing features, a predictive model was developed on a randomly sampled set (n = 2,918) using L1-regularised logistic regression (lasso). The model was evaluated on an independent set (n = 973) and its performance associated with overall hazard rate after censoring (log-rank p < 0.0001), suggesting that multimodal features were able to capture important knowledge for MACE risk assessment. We further showed through a bootstrap analysis that all three sources of information (retinal, genetic, routine clinical) offer robust signal. Particularly robust features included: tortuousity, width gradient, and branching point retinal groupings; SNPs known to be associated with blood pressure and cardiovascular phenotypic traits; age at imaging; clinical measurements such as blood pressure and high density lipoprotein. This novel approach could be used for fast and sensitive determination of future risks associated with MACE.

U2 - 10.1038/s41598-019-40403-1

DO - 10.1038/s41598-019-40403-1

M3 - Article

VL - 9

JO - Nature Scientific Reports

T2 - Nature Scientific Reports

JF - Nature Scientific Reports

SN - 2045-2322

M1 - 3591

ER -