A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre

Nat Biomed Eng. 2021 Jun;5(6):498-508. doi: 10.1038/s41551-020-00626-4. Epub 2020 Oct 12.

Abstract

Retinal blood vessels provide information on the risk of cardiovascular disease (CVD). Here, we report the development and validation of deep-learning models for the automated measurement of retinal-vessel calibre in retinal photographs, using diverse multiethnic multicountry datasets that comprise more than 70,000 images. Retinal-vessel calibre measured by the models and by expert human graders showed high agreement, with overall intraclass correlation coefficients of between 0.82 and 0.95. The models performed comparably to or better than expert graders in associations between measurements of retinal-vessel calibre and CVD risk factors, including blood pressure, body-mass index, total cholesterol and glycated-haemoglobin levels. In retrospectively measured prospective datasets from a population-based study, baseline measurements performed by the deep-learning system were associated with incident CVD. Our findings motivate the development of clinically applicable explainable end-to-end deep-learning systems for the prediction of CVD on the basis of the features of retinal vessels in retinal photographs.

Publication types

  • Research Support, Non-U.S. Gov't
  • Validation Study

MeSH terms

  • Adult
  • Aged
  • Aged, 80 and over
  • Blood Pressure
  • Body Mass Index
  • Cholesterol / blood
  • Coronary Disease / blood
  • Coronary Disease / diagnostic imaging*
  • Coronary Disease / etiology
  • Coronary Disease / pathology
  • Datasets as Topic
  • Deep Learning / statistics & numerical data*
  • Female
  • Glycated Hemoglobin A / metabolism
  • Humans
  • Hypertensive Retinopathy / blood
  • Hypertensive Retinopathy / complications
  • Hypertensive Retinopathy / diagnostic imaging*
  • Hypertensive Retinopathy / pathology
  • Image Interpretation, Computer-Assisted
  • Male
  • Middle Aged
  • Myocardial Infarction / blood
  • Myocardial Infarction / diagnostic imaging*
  • Myocardial Infarction / etiology
  • Myocardial Infarction / pathology
  • Photography
  • Retina / diagnostic imaging
  • Retina / metabolism
  • Retina / pathology
  • Retinal Vessels / diagnostic imaging*
  • Retinal Vessels / metabolism
  • Retinal Vessels / pathology
  • Retrospective Studies
  • Risk Assessment
  • Risk Factors
  • Stroke / blood
  • Stroke / diagnostic imaging*
  • Stroke / etiology
  • Stroke / pathology

Substances

  • Glycated Hemoglobin A
  • hemoglobin A1c protein, human
  • Cholesterol