Age and sex affect deep learning prediction of cardiometabolic risk factors from retinal images

• Published in: Scientific reports 2020-06, Vol.10 (1), p.9432, Article 9432
• Main Authors: Gerrits, Nele, Elen, Bart, Craenendonck, Toon Van, Triantafyllidou, Danai, Petropoulos, Ioannis N., Malik, Rayaz A., De Boever, Patrick
• Format: Article
• Language: English
• Subjects: 692/499; 692/53/2423; Adult; Age; Age Factors; Algorithms; Biomarkers - metabolism; Blood pressure; Body fat; Deep Learning; Diabetes mellitus; Diabetic retinopathy; Female; Fundus Oculi; Health risks; Hemoglobin; Hormones; Humanities and Social Sciences; Humans; Image Processing, Computer-Assisted - methods; Information processing; Male; Metabolic Diseases - diagnostic imaging; Metabolic Diseases - physiopathology; Middle Aged; multidisciplinary; Neural networks; Neural Networks, Computer; Optic Disk - diagnostic imaging; Predictions; Qatar; Retina; Retina - diagnostic imaging; Retinopathy; Risk Factors; Science; Science (multidisciplinary); Sex; Sex Factors; Steroid hormones; Testosterone
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-020-65794-4

Deep neural networks can extract clinical information, such as diabetic retinopathy status and individual characteristics (e.g. age and sex), from retinal images. Here, we report the first study to train deep learning models with retinal images from 3,000 Qatari citizens participating in the Qatar Biobank study. We investigated whether fundus images can predict cardiometabolic risk factors, such as age, sex, blood pressure, smoking status, glycaemic status, total lipid panel, sex steroid hormones and bioimpedance measurements. Additionally, the role of age and sex as mediating factors when predicting cardiometabolic risk factors from fundus images was studied. Predictions at person-level were made by combining information of an optic disc centred and a macula centred image of both eyes with deep learning models using the MobileNet-V2 architecture. An accurate prediction was obtained for age (mean absolute error (MAE): 2.78 years) and sex (area under the curve: 0.97), while an acceptable performance was achieved for systolic blood pressure (MAE: 8.96 mmHg), diastolic blood pressure (MAE: 6.84 mmHg), Haemoglobin A1c (MAE: 0.61%), relative fat mass (MAE: 5.68 units) and testosterone (MAE: 3.76 nmol/L). We discovered that age and sex were mediating factors when predicting cardiometabolic risk factors from fundus images. We have found that deep learning models indirectly predict sex when trained for testosterone. For blood pressure, Haemoglobin A1c and relative fat mass an influence of age and sex was observed. However, achieved performance cannot be fully explained by the influence of age and sex. In conclusion we confirm that age and sex can be predicted reliably from a fundus image and that unique information is stored in the retina that relates to blood pressure, Haemoglobin A1c and relative fat mass. Future research should focus on stratification when predicting person characteristics from a fundus image.