A Systematic Review and Meta-Analysis of Applying Deep Learning in the Prediction of the Risk of Cardiovascular Diseases From Retinal Images

Abstract

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.

Prediction of Cardiovascular Markers and Diseases Using Retinal Fundus Images and Deep Learning: A Systematic Scoping Review

“…Another six records were identified in citations and references of the included studies and previous reviews on similar topics. 9,18 In total, 24 studies were included in this scoping review, all of which were published after 2018.…”

Development and validation of a deep-learning model to predict 10-year atherosclerotic cardiovascular disease risk from retinal images using the UK Biobank and EyePACS 10K datasets

“…25 , 26 The application of DL algorithms to predict ASCVD risk-related outcomes from retinal images has been comprehensively reviewed by Hu and colleagues. 27 This review revealed that, to date, a heterogeneous array of models have been developed using a variety of different inputs: retinal images only, retinal images + various biodata, and reporting against different cardiac-related outcomes. To date, only 2 other groups have reported the results of a DL model trained and then externally validated to predict the ASCVD 10-year risk from retinal photographs.…”

Development and validation of a deep-learning model to predict 10-year ASCVD risk from retinal images using the UK Biobank and EyePACS 10K datasets

“…Regardless of diabetes type and status, the PCE equation currently treats all people living with diabetes as a uniform group and it effectively adds a modifier to the regression equation which serves to elevate their risk score compared to non-diabetics. Recently it has been suggested that the traditional regression-based equations, like the PCE, may overestimate ASCVD risk in many people living with diabetes 32,33 The application of DL algorithms to predict ASCVD risk-related outcomes from retinal images has been comprehensively reviewed by Hu et al 35 . This review revealed that to date a heterogeneous array of models have been developed using a variety of different inputs: retinal images only, retinal images + various biodata, and reporting against different cardiac-related outcomes.…”