Related Experiment Videos
Clinical Positioning and Implementation of a Deep-Learning Retinal Biomarker (Reti-CVD) for Cardiovascular Risk
Junseung Rho1, Sung-Goo Kang1, Se-Hong Kim1
1Department of Family Medicine, St. Vincent's Hospital, College of Medicine, The Catholic University of Korea, Seoul 16247, Republic of Korea.
Insights
Retinal imaging AI (Reti-CVD) shows promise for cardiovascular disease (CVD) risk stratification, especially in borderline cases. However, more outcome-based studies are needed to confirm its clinical utility and guide integration.
Area of Science:
- Ophthalmology
- Cardiology
- Artificial Intelligence
Background:
- Cardiovascular disease (CVD) prevention relies on accurate risk stratification, but standard tools have limitations, particularly for borderline-risk individuals.
- Retinal imaging offers a non-invasive window into systemic microvasculature, with deep-learning oculomics potentially providing complementary CVD risk information.
- Reti-CVD, a retinal AI tool, generates a three-tier classification from retinal photographs and is among the more validated retinal AI tools for CVD risk assessment.
Purpose of the Study:
- To evaluate the clinical positioning and implementation of Reti-CVD as an exemplar of retinal AI in CVD risk stratification.
- To compare Reti-CVD's performance with established CVD risk scores and subclinical atherosclerosis markers.
- To consider the practical aspects of Reti-CVD implementation, including regulation and equity.
Main Methods:
- A narrative review of existing evidence on Reti-CVD, organized by cohort studies.
- Comparison of Reti-CVD's discriminative ability (Harrell C-index) with traditional risk scores.
- Analysis of Reti-CVD's reclassification improvement, particularly in borderline-risk populations.
Main Results:
- Reti-CVD demonstrated a discrimination of approximately 0.75 (Harrell C-index) with modest reclassification improvement, notably in borderline-risk groups.
- The tool has received marketing authorization in Korea (MFDS) and CE certification (EU MDR) as the commercial product DrNoon, but lacks US FDA authorization.
- Evidence primarily stems from a single research group and algorithm; no randomized or outcome-based trials confirm improved clinical outcomes with Reti-CVD-guided care.
Conclusions:
- Reti-CVD shows potential as a non-invasive risk enhancer for borderline/intermediate CVD risk reclassification.
- Current evidence is observational and hypothesis-generating, indicating a need for independent validation and intervention trials.
- Broad integration of Reti-CVD requires further evidence on clinical utility, cost-effectiveness, reimbursement, and demonstrated improvement in patient outcomes.
Abstract:
Cardiovascular disease (CVD) prevention depends on accurate risk stratification before symptoms develop. Standard tools such as the Pooled Cohort Equations, QRISK3, and SCORE2 require laboratory data and are less informative in borderline-risk individuals, creating a role for accessible adjuncts. Retinal imaging directly visualizes the systemic microvasculature, and deep-learning oculomics may provide complementary risk information. Reti-CVD generates a three-tier classification from a retinal photograph and is among the more extensively validated retinal-AI tools. This narrative review evaluates its clinical positioning and implementation as an exemplar rather than a product endorsement, organizing evidence by cohort, comparing the approach with established scores and subclinical atherosclerosis markers, and considering implementation, regulation, and equity. RetiCAC was trained using coronary artery calcium as a surrogate label; subsequent Reti-CVD studies included UK Biobank, Singapore SEED, and CMERC-HI. Reported discrimination was approximately 0.75 by the Harrell C-index, with modest reclassification improvement, particularly in borderline-risk groups. As the commercial product DrNoon for CVD, the tool holds marketing authorization from Korea's Ministry of Food and Drug Safety (MFDS) and, according to the manufacturer, CE certification under the EU Medical Device Regulation (MDR); in Korea it entered outpatient practice through a time-limited non-covered (out-of-pocket) assessment-deferral pathway, and it has not yet received US FDA authorization. Most evidence originates from one research group and one commercial algorithm, and no randomized or outcome-based study has shown that Reti-CVD-guided care improves clinical outcomes. These observational findings remain hypothesis-generating rather than evidence of established clinical utility. Reti-CVD is therefore best regarded as a non-invasive risk enhancer for borderline/intermediate-risk reclassification, not as a tool of established clinical utility; independent validation, intervention trials, and cost-effectiveness and reimbursement evidence are needed before broad integration.