Is cardiovascular risk profiling from UK Biobank retinal images using explicit deep learning estimates of traditional risk factors equivalent to actual risk measurements? A prospective cohort study design

• Published in: BMJ open 2024-10, Vol.14 (10), p.e078609
• Main Authors: Qian, Yiming, Li, Liangzhi, Nakashima, Yuta, Nagahara, Hajime, Nishida, Kohji, Kawasaki, Ryo
• Format: Article
• Language: English
• Subjects: Adult; Aged; Algorithms; Biobanks; Biological Specimen Banks; Biomarkers; biotechnology & bioinformatics; Blood pressure; Body mass index; Cardiovascular disease; Cardiovascular Diseases - diagnostic imaging; Cardiovascular Diseases - epidemiology; Cholesterol; Datasets; Deep Learning; Diabetes; Female; Gender; health informatics; Heart Disease Risk Factors; Hemoglobin; High density lipoprotein; Humans; Hypertension; Lipoproteins; Male; Middle Aged; Ophthalmology; Original Research; Prospective Studies; Retina - diagnostic imaging; Retina - pathology; Risk assessment; Risk Assessment - methods; Risk Factors; ROC Curve; Triglycerides; UK Biobank; United Kingdom - epidemiology
• ISSN: 2044-6055; 2044-6055
• DOI: 10.1136/bmjopen-2023-078609

ObjectiveDespite extensive exploration of potential biomarkers of cardiovascular diseases (CVDs) derived from retinal images, it remains unclear how retinal images contribute to CVD risk profiling and how the results can inform lifestyle modifications. Therefore, we aimed to determine the performance of cardiovascular risk prediction model from retinal images via explicitly estimating 10 traditional CVD risk factors and compared with the model based on actual risk measurements.DesignA prospective cohort study design.SettingThe UK Biobank (UKBB), a prospective cohort study, following the health conditions including CVD outcomes of adults recruited between 2006 and 2010.ParticipantsA subset of data from the UKBB which contains 52 297 entries with retinal images and 5-year cumulative incidence of major adverse cardiovascular events (MACE) was used. Our dataset is split into 3:1:1 as training set (n=31 403), validation set (n=10 420) and testing set (n=10 474). We developed a deep learning (DL) model to predict 5-year MACE using a two-stage DL neural network.Primary and secondary outcome measuresWe computed accuracy, area under the receiver operating characteristic curve (AUC) and compared variations in the risk prediction models combining CVD risk factors and retinal images.ResultsThe first-stage DL model demonstrated that the 10 CVD risk factors can be estimated from a given retinal image with an accuracy ranging between 65.2% and 89.8% (overall AUC of 0.738 with 95% CI: 0.710 to 0.766). In MACE prediction, our model outperformed the traditional score-based models, with 8.2% higher AUC than Systematic COronary Risk Evaluation (SCORE), 3.5% for SCORE 2 and 7.1% for the Framingham Risk Score (with p value