Prediction of cardiovascular risk factors from retinal fundus photographs: Validation of a deep learning algorithm in a prospective non‐interventional study in Kenya
Open Access
- 15 April 2024
- journal article
- research article
- Published by Wiley in Diabetes, Obesity and Metabolism
- Vol. 26 (7) , 2722-2731
Abstract
Aim: Hypertension and diabetes mellitus (DM) are major causes of morbidity and mortality, with growing burdens in low‐income countries where they are underdiagnosed and undertreated. Advances in machine learning may provide opportunities to enhance diagnostics in settings with limited medical infrastructure. Materials and Methods: A non‐interventional study was conducted to develop and validate a machine learning algorithm to estimate cardiovascular clinical and laboratory parameters. At two sites in Kenya, digital retinal fundus photographs were collected alongside blood pressure (BP), laboratory measures and medical history. The performance of machine learning models, originally trained using data from the UK Biobank, were evaluated for their ability to estimate BP, glycated haemoglobin, estimated glomerular filtration rate and diagnoses from fundus images. Results: In total, 301 participants were enrolled. Compared with the UK Biobank population used for algorithm development, participants from Kenya were younger and would probably report Black/African ethnicity, with a higher body mass index and prevalence of DM and hypertension. The mean absolute error was comparable or slightly greater for systolic BP, diastolic BP, glycated haemoglobin and estimated glomerular filtration rate. The model trained to identify DM had an area under the receiver operating curve of 0.762 (0.818 in the UK Biobank) and the hypertension model had an area under the receiver operating curve of 0.765 (0.738 in the UK Biobank). Conclusions: In a Kenyan population, machine learning models estimated cardiovascular parameters with comparable or slightly lower accuracy than in the population where they were trained, suggesting model recalibration may be appropriate. This study represents an incremental step toward leveraging machine learning to make early cardiovascular screening more accessible, particularly in resource‐limited settings.Keywords
Funding Information
- AstraZeneca
This publication has 18 references indexed in Scilit:
- DiaNet: A Deep Learning Based Architecture to Diagnose Diabetes Using Retinal Images OnlyIEEE Access, 2021
- A Human-Centered Evaluation of a Deep Learning System Deployed in Clinics for the Detection of Diabetic Retinopathy2020
- Implementing Machine Learning in Health Care — Addressing Ethical ChallengesNew England Journal of Medicine, 2018
- Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus PhotographsJAMA, 2016
- Rethinking the Inception Architecture for Computer Vision2016
- Racial Differences in Hypertension: Implications for High Blood Pressure ManagementThe American Journal of the Medical Sciences, 2014
- Global Supply of Health ProfessionalsNew England Journal of Medicine, 2014
- Diurnal blood pressure variation and related behavioral factorsHypertension Research, 2010
- Receiver Operating Characteristic Curve in Diagnostic Test AssessmentJournal of Thoracic Oncology, 2010
- ImageNet: A large-scale hierarchical image database2009