Predicting myocardial infarction through retinal scans and minimal personal information

• Published in: Nature machine intelligence Vol. 4; no. 1; pp. 55 - 61
• Main Authors: Diaz-Pinto, Andres, Ravikumar, Nishant, Attar, Rahman, Suinesiaputra, Avan, Zhao, Yitian, Levelt, Eylem, Dall’Armellina, Erica, Lorenzi, Marco, Chen, Qingyu, Keenan, Tiarnan D. L., Agrón, Elvira, Chew, Emily Y., Lu, Zhiyong, Gale, Chris P., Gale, Richard P., Plein, Sven, Frangi, Alejandro F.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 01-01-2022; Nature Publishing Group
• Subjects: 639/705/117; 692/699/75; 692/700/1421; Age; Biobanks; Biomarkers; Blood pressure; Blood vessels; Cardiovascular disease; Cataracts; Coronary artery disease; Deep learning; Demographics; Diabetes; Diabetic retinopathy; Engineering; Eye diseases; Heart attacks; Macular degeneration; Medical imaging; Myocardial infarction; Retinal images; Risk; Risk factors; Tortuosity; United Kingdom > UK
• ISSN: 2522-5839; 2522-5839
• DOI: 10.1038/s42256-021-00427-7

In ophthalmologic practice, retinal images are routinely obtained to diagnose and monitor primary eye diseases and systemic conditions affecting the eye, such as diabetic retinopathy. Recent studies have shown that biomarkers on retinal images, for example, retinal blood vessel density or tortuosity, are associated with cardiac function and may identify patients at risk of coronary artery disease. In this work we investigate the use of retinal images, alongside relevant patient metadata, to estimate left ventricular mass and left ventricular end-diastolic volume, and subsequently, predict incident myocardial infarction. We trained a multichannel variational autoencoder and a deep regressor model to estimate left ventricular mass (4.4 (–32.30, 41.1) g) and left ventricular end-diastolic volume (3.02 (–53.45, 59.49) ml) and predict risk of myocardial infarction (AUC = 0.80 ± 0.02, sensitivity = 0.74 ± 0.02, specificity = 0.71 ± 0.03) using just the retinal images and demographic data. Our results indicate that one could identify patients at high risk of future myocardial infarction from retinal imaging available in every optician and eye clinic.
Routine eye clinic imaging could help screen patients with cardiovascular risk as studies indicate strong associations between biomarkers in the retina and the heart. This potential is supported by a multimodal study, employing a deep learning model, that can infer cardiac functional indices based on retinal images and demographic data.