Exploring Associations Between Cardiac Structure and Retinal Vascular Geometry

Correlation between retinal vascular geometric parameters and pathologically diagnosed type 2 diabetic nephropathy

Background

Diabetic nephropathy (DN) and diabetic retinopathy (DR) are common microvascular complications of diabetes. The purpose of this study was to investigate the correlation between retinal vascular geometric parameters and pathologically diagnosed type 2 DN and to determine the capacity of retinal vascular geometric parameters in differentiating DN from non-diabetic renal disease (NDRD).

Methods

The study participants were adult patients with type 2 diabetes mellitus (T2DM) and chronic kidney disease who underwent a renal biopsy. Univariate and multivariable regression analyses were performed to evaluate associations between retinal vessel geometry parameters and pathologically diagnosed DN. Multivariate binary logistic regression analyses were performed to establish a differential diagnostic model for DN.

Results

In total, 403 patients were examined in this cross-sectional study, including 152 (37.7%) with DN, 157 (39.0%) with NDRD and 94 (23.3%) with DN combined with NDRD. After univariate logistic regression, total vessel fractal dimension, arteriolar fractal dimension and venular fractal dimension were all found to be associated with DN. In multivariate analyses adjusting for age, sex, blood pressure, diabetes, DR and other factors, smaller retinal vascular fractal dimensions were significantly associated with DN (P < .05). We developed a differential diagnostic model for DN combining traditional clinical indicators and retinal vascular geometric parameters. The area under the curve of the model established by multivariate logistic regression was 0.930.

Conclusions

Retinal vessel fractal dimension is of great significance for the rapid and non-invasive differentiation of DN. Incorporating retinal vessel fractal dimension into the diagnostic model for DN and NDRD can improve the diagnostic efficiency.

Standardization and clinical applications of retinal imaging biomarkers for cardiovascular disease: a Roadmap from an NHLBI workshop

The accessibility of the retina with the use of non-invasive and relatively low-cost ophthalmic imaging techniques and analytics provides a unique opportunity to improve the detection, diagnosis and monitoring of systemic diseases. The National Heart, Lung, and Blood Institute conducted a workshop in October 2022 to examine this concept. On the basis of the discussions at that workshop, this Roadmap describes current knowledge gaps and new research opportunities to evaluate the relationships between the eye (in particular, retinal biomarkers) and the risk of cardiovascular diseases, including coronary artery disease, heart failure, stroke, hypertension and vascular dementia. Identified gaps include the need to simplify and standardize the capture of high-quality images of the eye by non-ophthalmic health workers and to conduct longitudinal studies using multidisciplinary networks of diverse at-risk populations with improved implementation and methods to protect participant and dataset privacy. Other gaps include improving the measurement of structural and functional retinal biomarkers, determining the relationship between microvascular and macrovascular risk factors, improving multimodal imaging 'pipelines', and integrating advanced imaging with 'omics', lifestyle factors, primary care data and radiological reports, by using artificial intelligence technology to improve the identification of individual-level risk. Future research on retinal microvascular disease and retinal biomarkers might additionally provide insights into the temporal development of microvascular disease across other systemic vascular beds.

A Multi-Stage Approach for Cardiovascular Risk Assessment from Retinal Images Using an Amalgamation of Deep Learning and Computer Vision Techniques

Cardiovascular diseases (CVDs) are a leading cause of mortality worldwide. Early detection and effective risk assessment are crucial for implementing preventive measures and improving patient outcomes for CVDs. This work presents a novel approach to CVD risk assessment using fundus images, leveraging the inherent connection between retinal microvascular changes and systemic vascular health. This study aims to develop a predictive model for the early detection of CVDs by evaluating retinal vascular parameters. This methodology integrates both handcrafted features derived through mathematical computation and retinal vascular patterns extracted by artificial intelligence (AI) models. By combining these approaches, we seek to enhance the accuracy and reliability of CVD risk prediction in individuals. The methodology integrates state-of-the-art computer vision algorithms and AI techniques in a multi-stage architecture to extract relevant features from retinal fundus images. These features encompass a range of vascular parameters, including vessel caliber, tortuosity, and branching patterns. Additionally, a deep learning (DL)-based binary classification model is incorporated to enhance predictive accuracy. A dataset comprising fundus images and comprehensive metadata from the clinical trials conducted is utilized for training and validation. The proposed approach demonstrates promising results in the early prediction of CVD risk factors. The interpretability of the approach is enhanced through visualization techniques that highlight the regions of interest within the fundus images that are contributing to the risk predictions. Furthermore, the validation conducted in the clinical trials and the performance analysis of the proposed approach shows the potential to provide early and accurate predictions. The proposed system not only aids in risk stratification but also serves as a valuable tool for identifying vascular abnormalities that may precede overt cardiovascular events. The approach has achieved an accuracy of 85% and the findings of this study underscore the feasibility and efficacy of leveraging fundus images for cardiovascular risk assessment. As a non-invasive and cost-effective modality, fundus image analysis presents a scalable solution for population-wide screening programs. This research contributes to the evolving landscape of precision medicine by providing an innovative tool for proactive cardiovascular health management. Future work will focus on refining the solution's robustness, exploring additional risk factors, and validating its performance in additional and diverse clinical settings.

Characterization of retinal microvasculature and structure in atrial fibrillation

Background and objective

Quantitative changes in retinal microvasculature are associated with subclinical cardiac alterations and clinical cardiovascular diseases (i.e., heart failure and coronary artery disease). Nonetheless, very little is known about the retinal vascular and structural changes in patients with atrial fibrillation (AF). Our study aims to characterize the microvasculature and structure of the retina in AF patients and explore their differences in different types of AF (paroxysmal and sustained AF).

Methods

This cross-sectional study was conducted at the Departments of Neurology and Cardiology in West China Hospital, Chengdu, China. Individuals aged 40 years or older with a diagnosis of AF were eligible for inclusion and underwent an evaluation and diagnosis confirmation before enrollment. Control individuals aged 40 years or older and without a history of AF, ocular abnormalities/disease, or any significant systemic illness were recruited. The retinal vascular and structural parameters were assessed using swept-source optical coherence tomography (SS-OCT)/SS-OCT angiography. Echocardiographic data of left atrium (LA) diameter were collected in patients with AF at the time of inclusion.

Results

A total of 242 eyes of 125 participants [71 men (56.8%); mean (SD) age, 61.98 (8.73) years] with AF and 219 eyes of 111 control participants [53 men (47.7%); mean (SD) age, 62.31 (6.47) years] were analyzed. In our AF cohort, 71 patients with paroxysmal AF and 54 patients with sustained AF (i.e., persistent/permanent AF) were included. Decreased retinal microvascular perfusion (β coefficient = -0.08; 95% CI, -0.14 to -0.03) and densities (β coefficient = -1.86; 95% CI, -3.11 to -0.60) in superficial vascular plexus (SVC) were found in the eyes of the participants with AF. In regard to retinal structures, thinner ganglion cell-inner plexiform layer (GCIPL; β coefficient = -2.34; 95% CI, -4.32 to -0.36) and retinal nerve fiber layer (RNFL) thicknesses (β coefficient = -0.63; 95% CI, -2.09 to -0.18) were observed in the eyes of the participants with AF. The retinal parameters did not significantly differ between paroxysmal and sustained AF (all P > 0.05). However, significant interactions were observed between LA diameter and AF subtypes with the perfusion and densities in SVC (P < 0.05).

Conclusion

This study found that individuals with AF had decreased retinal vascular densities and perfusion in SVC, as well as thinner GCIPL and RNFL thickness compared with age- and sex-matched control participants. The differences of the retinal microvasculature in SVC between paroxysmal and sustained AF depend on the LA diameter. Given our findings, further longitudinal studies with our participants are of interest to investigate the natural history of retinal microvascular and structural changes in individuals across the clinical process of AF and AF subtypes.

Computer-assisted evaluation of retinal vessel tortuosity in moderate-to-late preterm children

PURPOSE

Since very preterm children often have increased retinal tortuosity that may indicate decisive architectural changes in the systemic microvascular network, we used a new semi-automatic software to measure retinal vessel tortuosity on fundus digital images of moderate-to-late preterm (MLP) children.

METHODS

In this observational case-control study, the global and local tortuosity parameters of retinal vessels were evaluated on fundus photographs of 36 MLP children and 36 age- and sex-matched controls. The associations between birth parameters and parameters reflecting retinal vessel tortuosity were evaluated using correlation analysis.

RESULTS

Even after incorporation of anatomical factors, the global and local tortuosity parameters were not significantly different between groups. The MLP group showed a smaller arteriolar caliber (0.53  ±  0.2) than the controls (0.56  ±  0.2; p  =  0.013). Other local tortuosity parameters, such as vessel length, distance to fovea, and distance to optic disc, were not significantly different between arteries and veins. Tortuosity in both groups was higher among vessels closer to the fovea (r  =  -0.077, p < 0.001) and the optic disc (r  =  -0.0544, p  =  0.009). Global tortuosity showed a weakly positive correlation with gestational age and a weakly negative correlation with birth weight in both groups.

CONCLUSION

MLP patients did not display increased vessel tortuosity in comparison with the controls; however, the arteriolar caliber in the MLP group was smaller than that in children born full-term. Larger studies should confirm this finding and explore associations between cardiovascular and metabolic status and retinal vessel geometry in MLP children.

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

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.

RETINAL VASCULAR DENSITY CHANGE IN PATIENTS WITH HEART FAILURE

PURPOSE

The aim of this study is to assess choroid thickness, retinal vessel density in the superficial capillary plexus layer and deep capillary plexus layer in heart failure (HF) using optical coherence tomography angiography (OCT-A).

METHODS

36 healthy participants (group 1), 33 patients with HF were assessed for this study. HF patients had a left ventricular ejection fraction (LVEF) <50%. HF patients were divided into 2 groups according to the New York Heart Association (NYHA). 15 patients were evaluated as group 2 according to NYHA and 18 patients as group 3 according to NYHA. Choroid thickness, superficial and deep capillary plexus perfusion were analyzed between groups using OCT-A.

RESULTS

Choroid thicknesses were found to be significantly decrease in the HF groups. Superficial capillary plexus density was compared with the control group, no statistically significant difference was found between the HF groups. But among the HF groups, a statistically significant decrease was found in group 3 patients. Deep capillary plexus density was compared with the control group, a statistically significant decrease was found in group 3. In addition, deep capillary plexus density a statistically significant difference was found between the groups HF.

CONCLUSIONS

Patients with HF showed decreased flow density compared with healthy controls. In addition, significant changes were found in flow densities among the HF groups. Retinal perfusion measured using OCT-A may give an idea about the hemodynamic status and microperfusion of HF patients.

Unhealthy Lifestyles and Retinal Vessel Calibers among Children and Adolescents: A Systematic Review and Meta-Analysis

The retinal vessel caliber (RVC) is an important biomarker of cardiovascular diseases, which can be semi-automatically measured by fundus photography. This review investigated the associations between the RVCs and the life styles of early life, such as physical activity (PA), sedentary behavior (SB), dietary and sleep, by summarizing the findings from studies on children and adolescents. Two databases (Medline and Embase) were searched from their inception to 30 June 2022. The selected studies were literatures on observational designs, fundus photographs, retinal vessels and lifestyles of children or adolescents. Correlation coefficients of unhealthy life styles and RVCs were transformed to Fisher's z-scores, and the random-effects model was applied to pool data. A total of 18 observational studies were selected; the lifestyles accessed include 9 studies for PA and SB, 8 studies for dietary and 1 study for sleep. The meta-analysis on the correlation coefficients of regression models found the high level of SB (qualified by screen time, ST) was associated the narrower central retinal arteriolar equivalent (CRAE) among children (r = -0.043, 95% confidence intervals [CI] -0.078 to -0.009). By comparing the first and fourth quartiles of PA, the meta-analysis showed that more indoor PA was associated with smaller venular calibers and more outdoor PA was associated with wider CRAE (r = 0.88, 95%CI -3.33 to 0). Unhealthy lifestyles might be harmful on the retinal microcirculation among children and adolescents but their health effect seems not to be as significant as those in adults.

Associations between cardiac function and retinal microvascular geometry among Chinese adults

Abnormal retinal microvascular geometry has been associated with cardiac remodeling and heart failure. However, its relation to cardiac function, prior to clinical disease has not been explored. In this cross-sectional study, 50 participants (mean age 62.5 ± 11.7 years) without cardiovascular disease (CVD) were recruited from the Cardiac Ageing Study. Transthoracic echocardiography imaging was performed to measure cardiac function indices, and retinal imaging was used to measure retinal vascular caliber and retinal vascular geometric indices. Multiple linear regressions were applied to examine associations between indices of cardiac function and retinal microvasculature, adjusting for age, sex, body mass index, mean blood pressure and comorbidity (i.e. hypertension, diabetes and dyslipidemia). After adjusting for confounders, each unit decrease in peak systolic septal mitral annular velocity (Septal S′) indicating poorer left function was associated with smaller retinal venular branching angle (β: − 2.69°; 95% CI − 4.92, − 0.46). Furthermore, each unit increase in peak velocity flow in late diastole by atrial contraction (MV A Peak) indicating poorer left atrial function was associated with lower retinal venular fractal dimension (− 0.13Df; − 0.25, − 0.004). Our findings suggested a relationship between poorer cardiac function and suboptimal retinal microvascular geometry, among Chinese without CVD.

Exploring Associations Between Cardiac Structure and Retinal Vascular Geometry

Background

Retinal arteriolar narrowing and venular widening has been widely suggested to be associated with subclinical changes in cardiac structure. The novel retinal vascular geometric indices might reflect more comprehensive information on microvasculature other than vascular caliber alone. However, the association between suboptimal retinal vascular geometry and cardiac structural alteration has not been studied.

Methods and Results

We recruited 50 participants without cardiovascular disease from the Cardiac Aging Study conducted between 2014 and 2016. We performed transthoracic echocardiography imaging to measure cardiac structure indices such as left ventricular internal diameter end diastole index, left ventricular internal diameter end systole index, left ventricular mass index, and left atrial volume index, and retinal imaging to measure retinal vascular geometric indices including branching angle, curvature tortuosity, and fractal dimension. We applied multiple linear regressions to examine associations between indices of cardiac structure and retinal vascular geometry, adjusting for age, sex, body mass index, mean blood pressure, and comorbidity. The average age of all participants was 62.54 years old and slightly more than half were male (27; 54%). Each unit increase in a set of cardiac structure indices was associated with larger retinal arteriolar branching angle (β and 95% CI: for left ventricular internal diameter end systole index, 26.93°; 6.00–47.86; for left ventricular internal diameter end diastole index, 17.86°; 1.61–34.11; for left ventricular mass index, 0.39°; 0.10–0.67; for left atrial volume index, 0.91°; 0.24–1.58).

Conclusions

Adverse retinal arteriolar geometric morphology mirrored suboptimal cardiac structural alteration.