Are Cardiovascular Risk Scores from Genome and Retinal Image Complementary? A Deep Learning Investigation in a Diabetic Cohort

Mohammad Ghouse Syed (Lead / Corresponding author), Alexander Doney, Gittu George, Ify Mordi, Emanuele Trucco

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Risk of cardiovascular diseases (CVD) is driven by both genetic and environmental factors. Deep learning (DL) has shown that retinal images contain latent information indicating CVD risk. At the same time, genome-wide polygenic risk scores have demonstrated CVD risk prediction accuracy similar to conventional clinical factor-based risk scores. We speculated that information conveying CVD risk in retinal images may predominantly indicate environment factors rather than genetic factors, i.e., provide complementary information. Hence, we developed a DL model applied to diabetes retinal screening photographs from patients with type 2 diabetes based on EfficientNetB2 for predicting clinical atherosclerotic cardiovascular disease (ASCVD) risk score and a genome-wide polygenic risk score (PRS) for CVD. Results from 6656 photographs suggest a correlation between the actual and predicted ASCVD risk score (R2 = 0.534, 95% CI [0.504, 0.563]; MAE = 0.109 [0.105, 0.112]), but not so for actual and predicted PRS (R2 = −0.005 [−0.02, 0.01]; MAE = 0.484 [0.467, 0.5]. This suggests that retinal and genetic information are potentially complementary within an individual’s cardiovascular risk, hence their combination may provide an efficient and powerful approach to screening for CVD risk. To our best knowledge, this is the first time that DL is used to investigate the complementarity of retinal and genetic information for CVD risk.

Original languageEnglish
Title of host publicationOphthalmic Medical Image Analysis
Subtitle of host publication8th International Workshop, OMIA 2021, Held in Conjunction with MICCAI 2021, Proceedings
EditorsHuazhu Fu, Mona K. Garvin, Tom MacGillivray, Yanwu Xu, Yalin Zheng
Place of PublicationSwitzerland
PublisherSpringer
Pages109-118
Number of pages10
Edition1
ISBN (Electronic)9783030870003
ISBN (Print)9783030869991
DOIs
Publication statusPublished - 2021
Event8th International Workshop on Ophthalmic Medical Image Analysis, OMIA 2021 held in conjunction with 24th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2021 - Virtual, Online
Duration: 27 Sep 202127 Sep 2021

Publication series

NameLecture Notes in Computer Science
Volume12970
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference8th International Workshop on Ophthalmic Medical Image Analysis, OMIA 2021 held in conjunction with 24th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2021
CityVirtual, Online
Period27/09/2127/09/21

Keywords

  • CVD risk
  • EfficientNet
  • Genetic risk
  • Retinal fundus imaging

Fingerprint

Dive into the research topics of 'Are Cardiovascular Risk Scores from Genome and Retinal Image Complementary? A Deep Learning Investigation in a Diabetic Cohort'. Together they form a unique fingerprint.

Cite this