Validation of the Prognostic Impact of a Retinal Photograph-based Cardiovascular Disease Risk Stratification System in de Novo HFrEF

Recruiting

• Conditions: Heart Failure; Cardiomyopathies; Retinal Photograph; Deep Learning; Reti-CVD

• Registration Number: NCT06978998
• Lead Sponsor: Yonsei University

Brief Summary

"Despite significant advances in pharmacologic and device-based therapies, heart failure (HF) remains a major public health burden, with persistently high rates of hospitalization, impaired quality of life, and excess mortality-often exceeding those of leading malignancies. Prognosis in HF is shaped by its underlying etiology: ischemic HF often responds to revascularization strategies, whereas non-ischemic HF, particularly due to idiopathic or genetic cardiomyopathies, demonstrates highly variable outcomes and limited responsiveness to guideline-directed medical therapy (GDMT). Although left ventricular reverse remodeling (LVRR) is associated with favorable outcomes, only 40-50% of non-ischemic HF patients achieve meaningful LVRR with GDMT alone.

In this context of therapeutic uncertainty and prognostic heterogeneity, there is a critical need for novel, non-invasive risk stratification tools. Retinal imaging offers a unique advantage, enabling direct, in vivo visualization of systemic microvascular and neurovascular integrity. Prior work from our group has demonstrated that deep learning algorithms applied to retinal fundus photographs can estimate physiologic and metabolic markers-including CAC scores-and predict future cardiovascular events. The Reti-CVD scoring system, derived from these models, has been externally validated in independent populations.

In the present study, we aim to evaluate the prognostic utility of the Reti-CVD model in a cohort of patients with newly diagnosed HF and reduced ejection fraction. Specifically, we will assess whether retinal-derived risk scores at baseline are associated with adverse clinical outcomes, including cardiovascular events and all-cause mortality, and whether prognostic performance varies according to HF etiology."

Detailed Description

"Study Methods

1. Eligible participants will be approached during outpatient visits or hospitalization. The purpose and procedures of the study will be explained in detail, and informed consent will be obtained prior to data collection. Even after initial enrollment, participants will undergo continuous re-confirmation of consent at each subsequent visit.

2. All data will be collected in accordance with clinical guideline of heart failure in Korea (published from KHFS). This includes demographic characteristics, clinical history, echocardiographic parameters, laboratory findings, and cardiovascular outcomes. These data will be documented in a dedicated case report form.

3. Participants will undergo assessments during the first year following enrollment, with a target total follow-up duration of at least five years to evaluate long-term clinical outcomes.

4. All study data will be stored on password-protected computers with restricted access. No personal identifiers will be included and only de-identified, coded data will be used for analysis to ensure data confidentiality. This study will not involve development or modification of a deep learning algorithm. Instead, we will apply a pre-existing, validated retinal-based cardiovascular risk classification algorithm to newly diagnosed heart failure patients. Prognostic analyses will be conducted to determine whether algorithm-derived risk stratification is associated with differences in clinical outcomes during follow-up."

Study Timeline

• Study Start: 2024-12-10
• Status Verified: 2025-05
• Study First Submitted: 2025-05-11
• Study First Submitted QC: 2025-05-11
• Last Update Submitted: 2025-05-11
• Study First Posted: 2025-05-18
• Last Update Posted: 2025-05-18
• Primary Completion: 2030-12-10
• Study Completion: 2030-12-10

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 100

Inclusion Criteria

• Patients aged between 20 and 79 years with a left ventricular ejection fraction of 40% or less (assessed by transthoracic echocardiography), who have provided written consent for participation, have the capability to consent voluntarily

Exclusion Criteria

• Inability to obtain high-quality fundus photographs due to severe ophthalmologic conditions
• Presence of extensive retinal diseases that significantly impair visualization of the retinal vasculature
• Decline to provide informed consent for study participation, including:
• Pregnant individuals
• Individuals lacking decision-making capacity

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Occurrence of adjudicated cardiovascular event	From enrollment to completion of follow up, up to 5 years	Clinical events were defined to encompass cardiovascular-related death, myocardial infarction, rehospitalization due to heart failure, malignant ventricular arrhythmias, and other major adverse cardiac events.; Patients without a specific endpoint event were censored at the last date the patient was known to be free of the event or at the end of the planned follow up period, whichever was earlier

Secondary Outcome Measures

Name	Time	Method
Prevalence of Left Ventricular Reverse Remodeling	At 6months and 12 months after GDMT initiation	Left Ventricular Reverse Remodeling is characterized by an increase in left ventricular ejection fraction (LVEF) of more than 10% in heart failure patients with a baseline LVEF of 40% or less, or an increase in LVEF of more than 40% during follow-up, which is classified as heart failure with improved EF (HFimpEF).

Trial Locations

Locations (1)

Severance hospital; 🇰🇷 Seoul, Korea, Republic of