Retinal Biomarkers for Cardiovascular Disease Prediction: A Review Focused on CHD AHD Valvular Disorders and
Anupama B C1, Sheela N Rao1, Manjappa M2
1Department of Electronics and Instrumentation, JSS Science and Technology University, SJCE, JSS TI Campus Road, Mysuru, 570006, India.
Insights
Retinal fundus imaging, combined with artificial intelligence (AI), shows promise for non-invasively predicting cardiovascular diseases (CVDs). Advanced AI models can detect heart conditions like congenital heart disease (CHD) with high accuracy, paving the way for early diagnosis.
Area of Science:
- Ophthalmology and Cardiology Intersection
- Medical Imaging and Artificial Intelligence
- Biomarker Discovery for Systemic Disease
Background:
- Cardiovascular diseases (CVDs) are a leading cause of mortality globally.
- Congenital heart disease (CHD), acquired heart disease (AHD), valvular disorders, and cardiomyopathies contribute significantly to CVD morbidity.
- Retinal fundus imaging offers a non-invasive method to detect microvascular changes indicative of systemic cardiovascular dysfunction.
Purpose of the Study:
- To systematically review the literature on retinal fundus imaging for predicting structural heart diseases.
- To evaluate the diagnostic performance of various imaging modalities and analytical methods.
- To assess the potential of AI in analyzing retinal images for CVD detection.
Main Methods:
- Systematic literature review of studies published between 2015 and 2025.
- Searches conducted in PubMed, Scopus, and Web of Science databases.
- Evaluation of studies based on disease focus, imaging modality, analytical methods, and diagnostic performance.
Main Results:
- Deep learning and machine learning models applied to retinal images show high accuracy in detecting and classifying CVDs.
- Convolutional neural networks achieved up to 91% AUC for CHD detection.
- Hybrid multimodal approaches and automated analysis of vessel tortuosity/microhemorrhages show potential for AHD, valvular diseases, and cardiomyopathies.
Conclusions:
- Retinal imaging is a promising, scalable, non-invasive tool for cardiovascular disease prediction.
- Advanced AI architectures, including transformer-based models and SAM adaptations, can enhance diagnostic accuracy and interpretability.
- Challenges include dataset imbalance, limited longitudinal validation, and AI model interpretability.
Introduction:
Cardiovascular diseases (CVDs) remain the leading cause of global mortality, with congenital heart disease (CHD), acquired heart disease (AHD), valvular disorders, and cardiomyopathies contributing significantly to morbidity. Retinal fundus imaging has emerged as a non-invasive modality capable of capturing microvascular alterations that may serve as biomarkers for systemic cardiovascular dysfunction.
Methods:
This review systematically examined literature published between 2015 and 2025 on the use of retinal fundus imaging for predicting structural heart diseases. Databases including PubMed, Scopus, and Web of Science were searched using predefined keywords. Studies were evaluated according to disease focus, imaging modality, analytical methods, and diagnostic performance.
Results:
Findings highlight that deep learning and machine learning models applied to retinal fundus images have demonstrated promising accuracy in detecting and classifying CVDs. Convolutional neural networks achieved up to 91% AUC for CHD detection, while hybrid multimodal approaches improved sensitivity in AHD and valvular disease prediction. Cardiomyopathies were associated with vessel tortuosity and microhemorrhages, quantifiable through automated image analysis.
Discussion:
Emerging approaches, such as transformer-based models and adaptations of the Segment Anything Model (SAM) for medical imaging, offer potential for improving generalizability and interpretability. Challenges remain, including dataset imbalance, limited longitudinal validation, and the black-box nature of AI models.
Conclusion:
Retinal imaging holds strong potential as a scalable, non-invasive tool for cardiovascular disease prediction. Integrating advanced AI architectures may enhance diagnostic accuracy and accelerate translation into clinical practice.
Related Concept Videos
01:20Blood Studies for Cardiovascular System I: Cardiac Biomarkers
The essential diagnostic tools for detecting myocardial necrosis and monitoring individuals suspected of having acute coronary syndrome (ACS) include:
Troponins
Troponins, particularly cardiac troponins I and T, are the most precise and sensitive markers of myocardial injury. They are detectable within 4-6 hours of myocardial injury and remain...
01:19Blood Studies for Cardiovascular System II: CRP, Hcy, and Cardiac Natriuretic Peptide Markers
These markers indicate stress or strain on the heart muscle:
Natriuretic Peptides (BNP)
Cardiac myocytes produce these hormones in response to ventricular stretching...
01:27Diabetic Retinopathy