Retinal Information is Independently Associated with Cardiovascular Disease in Patients with Type 2 diabetes

Enhancing stroke risk and prognostic timeframe assessment with deep learning and a broad range of retinal biomarkers

Stroke stands as a major global health issue, causing high death and disability rates and significant social and economic burdens. The effectiveness of existing stroke risk assessment methods is questionable due to their use of inconsistent and varying biomarkers, which may lead to unpredictable risk evaluations. This study introduces an automatic deep learning-based system for predicting stroke risk (both ischemic and hemorrhagic) and estimating the time frame of its occurrence, utilizing a comprehensive set of known retinal biomarkers from fundus images. Our system, tested on the UK Biobank and DRSSW datasets, achieved AUROC scores of 0.83 (95% CI: 0.79-0.85) and 0.93 (95% CI: 0.9-0.95), respectively. These results not only highlight our system's advantage over established benchmarks but also underscore the predictive power of retinal biomarkers in assessing stroke risk and the unique effectiveness of each biomarker. Additionally, the correlation between retinal biomarkers and cardiovascular diseases broadens the potential application of our system, making it a versatile tool for predicting a wide range of cardiovascular conditions.

Automated Retinal Vessel Analysis Based on Fundus Photographs as a Predictor for Non-Ophthalmic Diseases-Evolution and Perspectives

The study of retinal vessels in relation to cardiovascular risk has a long history. The advent of a dedicated tool based on digital imaging, i.e., the retinal vessel analyzer, and also other software such as Integrative Vessel Analysis (IVAN), Singapore I Vessel Assessment (SIVA), and Vascular Assessment and Measurement Platform for Images of the Retina (VAMPIRE), has led to the accumulation of a formidable body of evidence regarding the prognostic value of retinal vessel analysis (RVA) for cardiovascular and cerebrovascular disease (including arterial hypertension in children). There is also the potential to monitor the response of retinal vessels to therapies such as physical activity or bariatric surgery. The dynamic vessel analyzer (DVA) remains a unique way of studying neurovascular coupling, helping to understand the pathogenesis of cerebrovascular and neurodegenerative conditions and also being complementary to techniques that measure macrovascular dysfunction. Beyond cardiovascular disease, retinal vessel analysis has shown associations with and prognostic value for neurological conditions, inflammation, kidney function, and respiratory disease. Artificial intelligence (AI) (represented by algorithms such as QUantitative Analysis of Retinal vessel Topology and siZe (QUARTZ), SIVA-DLS (SIVA-deep learning system), and many others) seems efficient in extracting information from fundus photographs, providing prognoses of various general conditions with unprecedented predictive value. The future challenges will be integrating RVA and other qualitative and quantitative risk factors in a unique, comprehensive prediction tool, certainly powered by AI, while building the much-needed acceptance for such an approach inside the medical community and reducing the "black box" effect, possibly by means of saliency maps.

Association of retinopathy with risk of all-cause and specific-cause mortality in the National Health and Nutrition Examination Survey, 2005 to 2008

Objective

This study aimed to elucidate the relationship between retinopathy status or severity and the all-cause and specific-cause mortality risk based on the updated National Health and Nutrition Examination Survey (NHANES) database and 2019 Public Access Link mortality file.

Methods

In this prospective cohort study, a total of 6,797 participants aged over 40 years based on NHANES 2005-2008 were analyzed. The severity of retinopathy was classified into 4 grades-no retinopathy, mild non-proliferative retinopathy (NPR), moderate to severe NPR, and proliferative retinopathy (PR). Multiple covariate-adjusted Cox proportional hazards regression models and Fine and Gray competing risk regression models were used to assess the all-cause and cause-specific mortality risks, respectively. The propensity score matching (PSM) approach was also applied additionally to adequately balance between-group covariates to validate our findings.

Results

A final total of 4,808 participants representing 18,282,772 United States (US) non-hospitalized participants were included for analysis, 50.27% were male (n = 2,417), 55.32% were non-hispanic white (n = 2,660), and mean [SE] age, 56.10 [0.40] years. After a median follow-up of 12.24 years (interquartile range, 11.16-13.49 years), 1,164 participants died of all-cause mortality, of which 941 (80.84%) died without retinopathy and 223 (19.16%) died with retinopathy at baseline. The presence of retinopathy was associated with increased all-cause mortality, cardiovascular disease (CVD), and diabetes mellitus (DM)-specific mortality, and the results remain consistent after PSM. Severity analysis showed that only mild NPR was associated with an increased all-cause mortality risk (hazard ratio (HR) = 2.01; 95% confidence interval (CI), 1.00-4.03), while increased CVD and DM-specific mortality risk were associated with all grades of retinopathy and were exponentially greater with increasing retinopathy severity, and the trend test was also significant (P for trend 0.004 and 0.04, respectively).

Discussion

Our findings suggest that the diagnosis of retinopathy is an independent risk factor for all-cause mortality in people over 40 years old. Retinopathy grading is significantly associated with the survival risk of patients with CVD or DM, it can be a valuable predictor in the stratified management and risk warning of CVD or DM patients, as well as in the monitoring of systemic vasculopathy status.

An efficient approach to estimate the risk of coronary artery disease for people living with HIV using machine-learning-based retinal image analysis

BACKGROUND

People living with HIV (PLWH) have increased risks of non-communicable diseases, especially cardiovascular diseases. Current HIV clinical management guidelines recommend regular cardiovascular risk screening, but the risk equation models are not specific for PLWH. Better tools are needed to assess cardiovascular risk among PLWH accurately.

METHODS

We performed a prospective study to determine the performance of automatic retinal image analysis in assessing coronary artery disease (CAD) in PLWH. We enrolled PLWH with ≥1 cardiovascular risk factor. All participants had computerized tomography (CT) coronary angiogram and digital fundus photographs. The primary outcome was coronary atherosclerosis; secondary outcomes included obstructive CAD. In addition, we compared the performances of three models (traditional cardiovascular risk factors alone; retinal characteristics alone; and both traditional and retinal characteristics) by comparing the area under the curve (AUC) of receiver operating characteristic curves.

RESULTS

Among the 115 participants included in the analyses, with a mean age of 54 years, 89% were male, 95% had undetectable HIV RNA, 45% had hypertension, 40% had diabetes, 45% had dyslipidemia, and 55% had obesity, 71 (61.7%) had coronary atherosclerosis, and 23 (20.0%) had obstructive CAD. The machine-learning models, including retinal characteristics with and without traditional cardiovascular risk factors, had AUC of 0.987 and 0.979, respectively and had significantly better performance than the model including traditional cardiovascular risk factors alone (AUC 0.746) in assessing coronary artery disease atherosclerosis. The sensitivity and specificity for risk of coronary atherosclerosis in the combined model were 93.0% and 93.2%, respectively. For the assessment of obstructive CAD, models using retinal characteristics alone (AUC 0.986) or in combination with traditional risk factors (AUC 0.991) performed significantly better than traditional risk factors alone (AUC 0.777). The sensitivity and specificity for risk of obstructive CAD in the combined model were 95.7% and 97.8%, respectively.

CONCLUSION

In this cohort of Asian PLWH at risk of cardiovascular diseases, retinal characteristics, either alone or combined with traditional risk factors, had superior performance in assessing coronary atherosclerosis and obstructive CAD.

SUMMARY

People living with HIV in an Asian cohort with risk factors for cardiovascular disease had a high prevalence of coronary artery disease (CAD). A machine-learning-based retinal image analysis could increase the accuracy in assessing the risk of coronary atherosclerosis and obstructive CAD.

Assessment of image quality on color fundus retinal images using the automatic retinal image analysis

Image quality assessment is essential for retinopathy detection on color fundus retinal image. However, most studies focused on the classification of good and poor quality without considering the different types of poor quality. This study developed an automatic retinal image analysis (ARIA) method, incorporating transfer net ResNet50 deep network with the automatic features generation approach to automatically assess image quality, and distinguish eye-abnormality-associated-poor-quality from artefact-associated-poor-quality on color fundus retinal images. A total of 2434 retinal images, including 1439 good quality and 995 poor quality (483 eye-abnormality-associated-poor-quality and 512 artefact-associated-poor-quality), were used for training, testing, and 10-ford cross-validation. We also analyzed the external validation with the clinical diagnosis of eye abnormality as the reference standard to evaluate the performance of the method. The sensitivity, specificity, and accuracy for testing good quality against poor quality were 98.0%, 99.1%, and 98.6%, and for differentiating between eye-abnormality-associated-poor-quality and artefact-associated-poor-quality were 92.2%, 93.8%, and 93.0%, respectively. In external validation, our method achieved an area under the ROC curve of 0.997 for the overall quality classification and 0.915 for the classification of two types of poor quality. The proposed approach, ARIA, showed good performance in testing, 10-fold cross validation and external validation. This study provides a novel angle for image quality screening based on the different poor quality types and corresponding dealing methods. It suggested that the ARIA can be used as a screening tool in the preliminary stage of retinopathy grading by telemedicine or artificial intelligence analysis.

Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning

Cardiovascular diseases (CVD) are the leading cause of death worldwide. People affected by CVDs may go undiagnosed until the occurrence of a serious heart failure event such as stroke, heart attack, and myocardial infraction. In Qatar, there is a lack of studies focusing on CVD diagnosis based on non-invasive methods such as retinal image or dual-energy X-ray absorptiometry (DXA). In this study, we aimed at diagnosing CVD using a novel approach integrating information from retinal images and DXA data. We considered an adult Qatari cohort of 500 participants from Qatar Biobank (QBB) with an equal number of participants from the CVD and the control groups. We designed a case-control study with a novel multi-modal (combining data from multiple modalities-DXA and retinal images)-to propose a deep learning (DL)-based technique to distinguish the CVD group from the control group. Uni-modal models based on retinal images and DXA data achieved 75.6% and 77.4% accuracy, respectively. The multi-modal model showed an improved accuracy of 78.3% in classifying CVD group and the control group. We used gradient class activation map (GradCAM) to highlight the areas of interest in the retinal images that influenced the decisions of the proposed DL model most. It was observed that the model focused mostly on the centre of the retinal images where signs of CVD such as hemorrhages were present. This indicates that our model can identify and make use of certain prognosis markers for hypertension and ischemic heart disease. From DXA data, we found higher values for bone mineral density, fat content, muscle mass and bone area across majority of the body parts in CVD group compared to the control group indicating better bone health in the Qatari CVD cohort. This seminal method based on DXA scans and retinal images demonstrate major potentials for the early detection of CVD in a fast and relatively non-invasive manner.

Risk Assessment of CHD Using Retinal Images with Machine Learning Approaches for People with Cardiometabolic Disorders

BACKGROUND

Coronary heart disease (CHD) is the leading cause of death worldwide, constituting a growing health and social burden. People with cardiometabolic disorders are more likely to develop CHD. Retinal image analysis is a novel and noninvasive method to assess microvascular function. We aim to investigate whether retinal images can be used for CHD risk estimation for people with cardiometabolic disorders.

METHODS

We have conducted a case-control study at Shenzhen Traditional Chinese Medicine Hospital, where 188 CHD patients and 128 controls with cardiometabolic disorders were recruited. Retinal images were captured within two weeks of admission. The retinal characteristics were estimated by the automatic retinal imaging analysis (ARIA) algorithm. Risk estimation models were established for CHD patients using machine learning approaches. We divided CHD patients into a diabetes group and a non-diabetes group for sensitivity analysis. A ten-fold cross-validation method was used to validate the results.

RESULTS

The sensitivity and specificity were 81.3% and 88.3%, respectively, with an accuracy of 85.4% for CHD risk estimation. The risk estimation model for CHD with diabetes performed better than the model for CHD without diabetes.

CONCLUSIONS

The ARIA algorithm can be used as a risk assessment tool for CHD for people with cardiometabolic disorders.

Retinal arteriolar tortuosity and fractal dimension are associated with long-term cardiovascular outcomes in people with type 2 diabetes

AIMS/HYPOTHESIS

Our aim was to determine whether quantitative retinal traits in people with type 2 diabetes are independently associated with incident major cardiovascular events including CHD and stroke.

METHODS

A total of 1066 men and women with type 2 diabetes, aged 65-74 years, were followed up over 8 years in the population-based Edinburgh Type 2 Diabetes Study. Using retinal photographs taken at baseline and specialist software, a number of quantitative retinal traits were measured, including arteriolar and venular widths and tortuosity as well as fractal dimension (a measure of the branching pattern complexity of the retinal vasculature network). Incident CHD events occurring during follow-up included fatal and non-fatal myocardial infarction, first episodes of angina and coronary interventions for CHD. Incident cerebrovascular events included fatal and non-fatal stroke or transient ischaemic attack. Cox proportional hazard regression analyses were performed to identify the association of the retinal traits with cardiovascular events in the population with retinal data available (n = 1028).

RESULTS

A total of 200 participants had an incident cardiovascular event (139 CHD and 61 cerebrovascular events). Following adjustment for age and sex, arteriolar tortuosity and fractal dimension were associated with cerebrovascular events (HR 1.27 [95% CI 1.02, 1.58] and HR 0.74 [95% CI 0.57, 0.95], respectively), including with stroke alone (HR 1.30 [95% CI 1.01, 1.66] and HR 0.73 [95% CI 0.56, 0.97], respectively). These associations persisted after further adjustment for established cardiovascular risk factors (HR 1.26 [95% CI 1.01, 1.58] and HR 0.73 [95% CI 0.56, 0.94], respectively). Associations generally reduced in strength after a final adjustment for the presence of diabetic retinopathy, but the association of fractal dimension with incident cerebrovascular events and stroke retained statistical significance (HR 0.73 [95% CI 0.57, 0.95] and HR 0.72 [95% CI 0.54, 0.97], respectively). Associations of retinal traits with CHD were generally weak and showed no evidence of statistical significance.

CONCLUSIONS/INTERPRETATION

Arteriolar tortuosity and fractal dimension were associated with incident cerebrovascular events, independent of a wide range of traditional cardiovascular risk factors including diabetic retinopathy. These findings suggest potential for measurements of early retinal vasculature change to aid in the identification of people with type 2 diabetes who are at increased risk from stroke.

Comparison of Static Retinal Vessel Caliber Measurements by Different Commercially Available Platforms

SIGNIFICANCE

Commercially available platforms show good agreement in clinical outcomes for retinal vessel caliber measurements, despite differing absolute values. Tighter agreement is observed when right and left eye data are averaged, suggesting an approach suitable for clinical practice.

PURPOSE

The purpose of this study was to compare the retinal vessel caliber measurements generated by different commercially available platforms and their associations with systemic blood pressure and age.

METHODS

A total of 209 participants were recruited from a UK optometric practice. After a routine eye examination, participants had disc-centered retinal photographs and systemic blood pressure taken. Retinal vessel calibers (central retinal artery equivalent, central retinal vein equivalent, and arteriovenous ratio) were calculated using both MONA REVA and VesselMap.

RESULTS

An inverse Pearson correlation was observed between central retinal artery equivalent and mean arterial blood pressure on both platforms (r = -0.275 [P ≤ .001] and r = -0.388 [P ≤ .001] for MONA REVA and VesselMap, respectively); this correlation was also observed with arteriovenous ratio and blood pressure. An inverse correlation was observed between central retinal artery equivalent and age (r = -0.362 [P ≤ .001] and r = -0.404 [P ≤ .001] for MONA REVA and VesselMap, respectively); this was also seen between central retinal vein equivalent and age (r = -0.322 [P ≤ .001] and r = -0.369 [P ≤ .001]). Arteriovenous ratio remained independent from age for both platforms. Bland-Altman plots demonstrated good agreement between the platforms for all three variables.

CONCLUSIONS

Although absolute caliber measurements differed between the platforms, the correlations observed were of similar magnitudes, with good agreement between the two platforms. Tighter spaced limits of agreement were observed when right and left eye data were averaged for each subject. In the absence of localized ocular pathology, this approach should be used.

Machine-learning method for localization of cerebral white matter hyperintensities in healthy adults based on retinal images

Retinal vessels are known to be associated with various cardiovascular and cerebrovascular disease outcomes. Recent research has shown significant correlations between retinal characteristics and the presence of cerebral small vessel disease as measured by white matter hyperintensities from cerebral magnetic resonance imaging. Early detection of age-related white matter changes using retinal images is potentially helpful for population screening and allow early behavioural and lifestyle intervention. This study investigates the ability of the machine-learning method for the localization of brain white matter hyperintensities. All subjects were age 65 or above without any history of stroke and dementia and recruited from local community centres and community networks. Subjects with known retinal disease or disease influencing vessel structure in colour retina images were excluded. All subjects received MRI on the brain, and age-related white matter changes grading was determined from MRI as the primary endpoint. The presence of age-related white matter changes on each of the six brain regions was also studied. Retinal images were captured using a fundus camera, and the analysis was done based on a machine-learning approach. A total of 240 subjects are included in the study. The analysis of various brain regions included the left and right sides of frontal lobes, parietal–occipital lobes and basal ganglia. Our results suggested that data from both eyes are essential for detecting age-related white matter changes in the brain regions, but the retinal parameters useful for estimation of the probability of age-related white matter changes in each of the brain regions may differ for different locations. Using a classification and regression tree approach, we also found that at least three significant heterogeneous subgroups of subjects were identified to be essential for the localization of age-related white matter changes. Namely those with age-related white matter changes in the right frontal lobe, those without age-related white matter changes in the right frontal lobe but with age-related white matter changes in the left parietal–occipital lobe, and the rest of the subjects. Outcomes such as risks of severe grading of age-related white matter changes and the proportion of hypertension were significantly related to these subgroups. Our study showed that automatic retinal image analysis is a convenient and non-invasive screening tool for detecting age-related white matter changes and cerebral small vessel disease with good overall performance. The localization analysis for various brain regions shows that the classification models on each of the six brain regions can be done, and it opens up potential future clinical application.

Effect of ECG-gating Retinal Photographs on Retinal Vessel Caliber Measurements in Subjects with and without Type 2 Diabetes

Purpose/Aim of this study: Retinal vessel caliber is an independent risk marker of cardiovascular disease risk. However, variable mechanical delays in capturing retinal photographs and cardiac cycle-induced retinal vascular changes have been shown to reduce the accuracy of retinal vessel caliber measurements, but this has only ever been investigated in healthy subjects. This cross-sectional study is the first study to investigate this issue in type 2 diabetes. The aim of this study was to determine whether ECG-gating retinal photographs reduce the variability in retinal arteriolar and venular caliber measurements in controls and type 2 diabetes.Materials and Methods: Fifteen controls and 15 patients with type 2 diabetes were arbitrarily recruited from Westmead Hospital, Sydney, Australia. A mydriatic fundoscope connected to our novel ECG synchronization unit captured 10 ECG-gated (at the QRS) and 10 ungated digital retinal photographs of the left eye in a randomized fashion, blinded to study participants. Two independent reviewers used an in-house semi-automated software to grade single cross-sectional vessel diameters across photographs, between 900 and 1800 microns from the optic disc edge. The coefficient of variation compared caliber variability between retinal arterioles and venules.Results: Our ECG synchronization unit reported the smallest time delay (33.1 ± 48.4 ms) in image capture known in the literature. All 30 participants demonstrated a higher reduction in retinal arteriolar (ungated: 1.02, 95%CI 0.88-1.17% vs ECG-gated: 0.39, 95%CI 0.29-0.49%, p < .0001) than venular (ungated 0.62, 95%CI 0.53-0.73% vs ECG-gated: 0.26, 95%CI 0.19-0.35%, p < .0001) coefficient of variation by ECG-gating photographs. Intra-observer repeatability and inter-observer reproducibility analysis reported high interclass correlation coefficients ranging from 0.80 to 0.86 and 0.80 to 0.93 respectively.Conclusion: ECG-gating photographs at the QRS are recommended for retinal vessel caliber analysis in controls and patients with type 2 diabetes as they refine measurements.

Severity of Diabetic Retinopathy and the Risk of Future Cerebrovascular Disease, Cardiovascular Disease, and All-Cause Mortality

PURPOSE

To determine the relationship between the severity of diabetic retinopathy and the future risk of cerebrovascular accident (CVA), myocardial infarction (MI), congestive heart failure (CHF), and all-cause mortality in patients with type 2 diabetes mellitus.

DESIGN

Retrospective cohort study.

PARTICIPANTS

Patients with type 2 diabetes who underwent diabetic retinopathy screening via fundus photography.

METHODS

The relationship between retinopathy status and the 5-year risk of first-time CVA, MI, CHF, and all-cause mortality was investigated using multivariate Cox proportional hazards regressions that controlled for age, gender, race or ethnicity, hemoglobin A1c, duration of diabetes, high-density lipoprotein level, low-density lipoprotein level, history of hypertension, systolic blood pressure, diastolic blood pressure, tobacco use, statin use, body mass index, urine microalbumin-to-creatinine ratio, and estimated glomerular filtration rate.

MAIN OUTCOME MEASURES

Five-year risk of first-time CVA, MI, CHF, and all-cause mortality.

RESULTS

Seventy-seven thousand three hundred seventy-six patients were included in this study. The average age was 59.8 years with 53.6% male, 31.2% non-Hispanic White, and 41.4% Hispanic patients. Diabetic retinopathy was significantly associated with all outcomes on multivariate analysis. Compared with patients with no retinopathy, those with minimal nonproliferative diabetic retinopathy (NPDR) had a higher risk of CVA (hazard ratio [HR], 1.31; 95% confidence interval [CI], 1.18-1.46), MI (HR, 1.30; 95% CI, 1.15-1.46), CHF (HR, 1.29; 95% CI, 1.19-1.40), and death (HR, 1.15; 95% CI, 1.05-1.25). Similarly, patients with moderate to severe NPDR had a higher risk of each outcome (CVA: HR, 1.56; 95% CI, 1.29-1.89; MI: HR, 1.92; 95% CI, 1.57-2.34; CHF: HR, 1.90; 95% CI, 1.66-2.18, and death: HR, 1.55; 95% CI, 1.32-1.82), as did patients with proliferative diabetic retinopathy (CVA: HR, 2.53; 95% CI, 1.84-3.48; MI: HR, 1.89; 95% CI, 1.26-2.83; CHF: HR, 1.96; 95% CI, 1.47-2.59; and death: HR, 1.87; 95% CI, 1.36-2.56).

CONCLUSIONS

Diabetic retinopathy is significantly associated with future risk of CVA, MI, CHF, and death, with higher degrees of retinopathy appearing to carry a heightened risk for each outcome. Retinal information may provide valuable insights into patients' risk of future vascular disease and death.

A machine learning approach for retinal images analysis as an objective screening method for children with autism spectrum disorder

BACKGROUND

Autism spectrum disorder (ASD) is characterised by many of features including problem in social interactions, different ways of learning, some children showing a keen interest in specific subjects, inclination to routines, challenges in typical communication, and particular ways of processing sensory information. Early intervention and suitable supports for these children may make a significant contribution to their development. However, considerable difficulties have been encountered in the screening and diagnosis of ASD. The literature has indicated that certain retinal features are significantly associated with ASD. In this study, we investigated the use of machine learning approaches on retinal images to further enhance the classification accuracy.

METHODS

Forty-six ASD participants were recruited from three special needs schools and 24 normal control were recruited from the community. Among them, 23 age-gender matched ASD and normal control participant-pairs were constructed for the primary analysis. All retinal images were captured using a nonmydriatic fundus camera. Automatic retinal image analysis (ARIA) methodology applying machine-learning technology was used to optimise the information of the retina to develop a classification model for ASD. The model's validity was then assessed using a 10-fold cross-validation approach to assess its validity.

FINDINGS

The sensitivity and specificity were 95.7% (95% CI 76.0%, 99.8%) and 91.3% (95% CI 70.5%, 98.5%) respectively. The area under the ROC curve was 0.974 (95% CI 0.934, 1.000); however, it was noted that the specificity for female participants might not be as high as that for male participants.

INTERPRETATION

Because ARIA is a fully automatic cloud-based algorithm and relies only on retinal images, it can be used as a risk assessment tool for ASD screening. Further diagnosis and confirmation can then be made by professionals, and potential treatment may be provided at a relatively early stage.

Structural analysis of retinal blood vessels in patients with COPD during a pulmonary rehabilitation program

Cardiovascular diseases are frequently present in chronic obstructive pulmonary disease (COPD). Population-based studies found associations between retinal vessel diameters and cardiovascular health, but it is unknown whether this also applies to COPD patients. Therefore, we measured retinal vessel diameters in COPD patients and aimed to determine the association with cardiovascular risk factors, lung function, and functional outcomes. In addition, we investigated whether an exercise-based pulmonary rehabilitation (PR) program would change retinal vessel diameters, as a proxy for improved microvascular health. Demographics and clinical characteristics, including pulmonary function, exercise capacity, blood pressure, blood measurements and level of systemic inflammation were obtained from 246 patients during routine assessment before and after PR. Retinal vessel diameters were measured from digital retinal images. Older age and higher systolic blood pressure were associated with narrower retinal arterioles (β: -0.224; p = 0.042 and β: -0.136; p < 0.001, respectively). Older age, higher systolic blood pressure and lower level of systemic inflammation were associated with narrower retinal venules (β: -0.654; -0.229; and -13.767, respectively; p < 0.05). No associations were found between retinal vessel diameters and lung function parameters or functional outcomes. After PR, no significant changes in retinal venular or arteriolar diameter were found. To conclude, retinal vessel diameters of COPD patients were significantly associated with systolic blood pressure and systemic inflammation, whilst there was no evidence for an association with lung function parameters, functional outcomes or other cardiovascular risk factors. Furthermore, an exercise-based PR program did not affect retinal vessel diameter.

Age-related changes of the retinal microvasculature

Purpose

Blood vessels of the retina provide an easily-accessible, representative window into the condition of microvasculature. We investigated how retinal vessel structure captured in fundus photographs changes with age, and how this may reflect features related to patient health, including blood pressure.

Results

We used two approaches. In the first approach, we segmented the retinal vasculature from fundus photographs and then we correlated 25 parameterized aspects ("traits")—comprising 15 measures of tortuosity, 7 fractal ranges of self-similarity, and 3 measures of junction numbers—with participant age and blood pressure. In the second approach, we examined entire fundus photographs with a set of algorithmic CHARM features. We studied 2,280 Sardinians, ages 20–28, and an U.S. based population from the AREDS study in 1,178 participants, ages 59–84. Three traits (relating to tortuosity, vessel bifurcation number, and vessel endpoint number) showed significant changes with age in both cohorts, and one additional trait (relating to fractal number) showed a correlation in the Sardinian cohort only. When using second approach, we found significant correlations of particular CHARM features with age and blood pressure, which were stronger than those detected when using parameterized traits, reflecting a greater signal from the entire photographs than was captured in the segmented microvasculature.

Conclusions

These findings demonstrate that automated quantitative image analysis of fundus images can reveal general measures of patient health status.

Retinal image analytics detects white matter hyperintensities in healthy adults

Objective

We investigated whether an automatic retinal image analysis (ARIA) incorporating machine learning approach can identify asymptomatic older adults harboring high burden of white matter hyperintensities (WMH) using MRI as gold standard.

Methods

In this cross-sectional study, we evaluated 180 community-dwelling, stroke-, and dementia-free healthy subjects and performed ARIA by acquiring a nonmydriatic retinal fundus image. The primary outcome was the diagnostic performance of ARIA in detecting significant WMH on MRI brain, defined as age-related white matter changes (ARWMC) grade ≥2. We analyzed both clinical variables and retinal characteristics using logistic regression analysis. We developed a machine learning network model with ARIA to estimate WMH and its classification.

Results

All 180 subjects completed MRI and ARIA. The mean age was 70.3 ± 4.5 years, 70 (39%) were male. Risk factor profiles were: 106 (59%) hypertension, 31 (17%) diabetes, and 47 (26%) hyperlipidemia. Severe WMH (global ARWMC grade ≥2) was found in 56 (31%) subjects. The performance for detecting severe WMH with sensitivity (SN) 0.929 (95% CI from 0.819 to 0.977) and specificity (SP) 0.984 (95% CI from 0.937 to 0.997) was excellent. There was a good correlation between WMH volume (log-transformed) obtained from MRI versus those estimated from retinal images using ARIA with a correlation coefficient of 0.897 (95% CI from 0.864 to 0.922).

Interpretation

We developed a robust algorithm to automatically evaluate retinal fundus image that can identify subjects with high WMH burden. Further community-based prospective studies should be performed for early screening of population at risk of cerebral small vessel disease.

Corydalis edulis Maxim. Promotes Insulin Secretion via the Activation of Protein Kinase Cs (PKCs) in Mice and Pancreatic β Cells

Corydalis edulis Maxim., a widely grown plant in China, had been proposed for the treatment for type 2 diabetes mellitus. In this study, we found that C. edulis extract (CE) is protective against diabetes in mice. The treatment of hyperglycemic and hyperlipidemic apolipoprotein E (ApoE)−/− mice with a high dose of CE reduced serum glucose by 28.84% and serum total cholesterol by 17.34% and increased insulin release. We also found that CE significantly enhanced insulin secretion in a glucose-independent manner in hamster pancreatic β cell (HIT-T15). Further investigation revealed that CE stimulated insulin exocytosis by a protein kinase C (PKC)-dependent signaling pathway and that CE selectively activated novel protein kinase Cs (nPKCs) and atypical PKCs (aPKCs) but not conventional PKCs (cPKCs) in HIT-T15 cells. To the best of our knowledge, our study is the first to identify the PKC pathway as a direct target and one of the major mechanisms underlying the antidiabetic effect of CE. Given the good insulinotropic effect of this herbal medicine, CE is a promising agent for the development of new drugs for treating diabetes.