Purpose The purpose of this study was to perform a systematic review and meta-analysis to synthesize evidence from studies using deep learning (DL) to predict cardiovascular disease (CVD) risk from retinal images. Methods A systematic literature search was performed in MEDLINE, Scopus, and Web of Science up to June 2022. We extracted data pertaining to predicted outcomes, model development, and validation and model performance metrics. Included studies were graded using the Quality Assessment of Diagnostic Accuracies Studies 2 tool. Model performance was pooled across eligible studies using a random-effects meta-analysis model. Results A total of 26 studies were included in the analysis. There were 42 CVD risk-related outcomes predicted from retinal images were identified, including 33 CVD risk factors, 4 cardiac imaging biomarkers, 2 CVD risk scores, the presence of CVD, and incident CVD. Three studies that aimed to predict the development of future CVD events reported an area under the receiver operating curve (AUROC) between 0.68 and 0.81. Models that used retinal images as input data had a pooled mean absolute error of 3.19 years (95% confidence interval [CI] = 2.95–3.43) for age prediction; a pooled AUROC of 0.96 (95% CI = 0.95–0.97) for gender classification; a pooled AUROC of 0.80 (95% CI = 0.73–0.86) for diabetes detection; and a pooled AUROC of 0.86 (95% CI = 0.81–0.92) for the detection of chronic kidney disease. We observed a high level of heterogeneity and variation in study designs. Conclusions Although DL models appear to have reasonably good performance when it comes to predicting CVD risk, further work is necessary to evaluate the real-world applicability and predictive accuracy. Translational Relevance DL-based CVD risk assessment from retinal images holds great promise to be translated to clinical practice as a novel approach for CVD risk assessment, given its simple, quick, and noninvasive nature.
Assuming the robustness of a deep learning model to suboptimal images is a key consideration, we asked if there was any value in including training images of poor quality. In particular, should we treat the (quality) threshold at which a training image is either included or excluded as a tunable hyperparameter? To that end, we systematically examined the effect of including training images of varying quality on the test performance of a DL model in classifying the severity of diabetic retinopathy. We found that there was a unique combination of (categorical) quality labels or a Goldilocks (continuous) quality score that gave rise to optimal test performance on either high-quality or suboptimal images. The model trained exclusively on high-quality images yielded worse performance in all test scenarios than that trained on the optimally tuned training set which included images with some level of degradation.
PurposeTo compare axial length (AL) growth curves in East Asian (EA) and non‐EA emmetropes.MethodsA meta‐regression of 28 studies with emmetrope‐specific AL data (measured with optical biometry) was performed. Emmetropia was defined as spherical equivalent refraction (SER) between −0.50 and +1.25 D, determined under cycloplegia if the mean age was ≤20 years. The AL growth curve (mean AL vs. mean age) was first fitted to the full dataset using a weighted nonlinear mixed‐effects model, before refitting the model with ethnicity as a two‐level grouping variable (EA vs. non‐EA). Ethnic differences in growth curve parameters were tested using the Wald test.ResultsA total of 3331 EA and 1071 non‐EA emmetropes (mean age: 6.5–23.1 years) were included. There was no evidence of an ethnic difference in either final AL (difference: 0.15 mm, 95% CI: −0.04 to 0.35 mm, p = 0.15) or initial AL, as represented by the amount that the final AL needed to be offset to obtain the y‐intercept (difference: −2.77 mm, 95% CI: −10.97 to 5.44, p = 0.51). Likewise, AL growth rate (curve steepness) did not differ between ethnic groups (difference: 0.09, 95% CI: −0.13 to 0.31, p = 0.43). Collectively, AL growth rate decreased from 0.24 mm/year at 6 years of age to around 0.05 mm/year at 11 years of age, after which it dipped below the repeatability of optical biometry (±0.04 mm) and practically plateaued around 16 years of age (final AL: 23.60 mm).ConclusionsEA and non‐EA emmetropes have comparable AL growth curves.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.