Diabetic Retinopathy Environment-Wide Association Study (EWAS) in NHANES 2005-2008

An enhanced machine learning algorithm for type 2 diabetes prognosis with a detailed examination of Key correlates

This study aimed to construct a high-performance prediction and diagnosis model for type 2 diabetic retinopathy (DR) and identify key correlates of DR. This study utilized a cross-sectional dataset of 3,000 patients from the People's Liberation Army General Hospital in 2021. Logistic regression was used as the baseline model to compare the prediction performance of the machine learning model and the related factors. The recursive feature elimination cross-validation (RFECV) algorithm was used to select features. Four machine learning models, support vector machine (SVM), decision tree (DT), random forest (RF), and gradient boost decision tree (GBDT), were developed to predict DR. The models were optimized using grid search to determine hyperparameters, and the model with superior performance was selected. Shapley-additive explanations (SHAP) were used to analyze the important correlation factors of DR. Among the four machine learning models, the optimal model was GBDT, with predicted accuracy, precision, recall, F1-measure, and AUC values of 0.7883, 0.8299, 0.7539, 0.7901, and 0.8672, respectively. Six key correlates of DR were identified, including rapid micronutrient protein/creatinine measurement, 24-h micronutrient protein, fasting C-peptide, glycosylated hemoglobin, blood urea, and creatinine. The logistic model had 27 risk factors, with an AUC value of 0.8341. A superior prediction model was constructed that identified easily explainable key factors. The number of correlation factors was significantly lower compared to traditional statistical methods, leading to a more accurate prediction performance than the latter.

Association between HDL cholesterol with diabetic retinopathy in diabetic patients: a cross-sectional retrospective study

OBJECTIVE

Diabetic patients are often comorbid with dyslipidemia, however, the relationship between high-density lipoprotein cholesterol(HDL-C) and diabetic retinopathy (DR) in the adult diabetic population remains to be fully elucidated.The aim of this study is to evaluate the associations between HDL-C and DR in the United States adults with diabetes.

METHODS

A total of 1708 participants from the National Health and Nutrition Examination Survey (NHANES) 2005-2008 were enrolled in the present study. Fundus images of all study subjects were captured and evaluated using a digital camera and an ophthalmic digital imaging system, and the diagnosis of DR was made by the severity scale of the Early Treatment Diabetic Retinopathy Study (ETDRS).Roche Diagnostics were used to measure serum HDL-C concentration. The relationship of DR with HDL-C was investigated using multivariable logistic regression. The potential non-line correlation was explored with smooth curve fitting approach.

RESULTS

The fully-adjusted model showed that HDL-C positively correlated with DR(OR:1.69, 95%CI: 1.25-2.31).However, an inverted U-shaped association between them was observed by applying the smooth curve fitted method. The inflection point of HDL-C(1.99mmol/l) was calculated by utilizing the two-piecewise logistic regression model. In the subgroup analysis, the inverted U-shaped nonlinear correlation between HDL-C and DR was also found in female, Non-Hispanic White, and lower age groups.

CONCLUSION

Our study revealed an inverted U-shaped positive relationship between HDL-C and DR.The findings may provide us with a more comprehensive understanding of the association between HDL-C and DR.

Applications of artificial intelligence and bioinformatics methodologies in the analysis of ocular biofluid markers: a scoping review

PURPOSE

This scoping review summarizes the applications of artificial intelligence (AI) and bioinformatics methodologies in analysis of ocular biofluid markers. The secondary objective was to explore supervised and unsupervised AI techniques and their predictive accuracies. We also evaluate the integration of bioinformatics with AI tools.

METHODS

This scoping review was conducted across five electronic databases including EMBASE, Medline, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, and Web of Science from inception to July 14, 2021. Studies pertaining to biofluid marker analysis using AI or bioinformatics were included.

RESULTS

A total of 10,262 articles were retrieved from all databases and 177 studies met the inclusion criteria. The most commonly studied ocular diseases were diabetic eye diseases, with 50 papers (28%), while glaucoma was explored in 25 studies (14%), age-related macular degeneration in 20 (11%), dry eye disease in 10 (6%), and uveitis in 9 (5%). Supervised learning was used in 91 papers (51%), unsupervised AI in 83 (46%), and bioinformatics in 85 (48%). Ninety-eight papers (55%) used more than one class of AI (e.g. > 1 of supervised, unsupervised, bioinformatics, or statistical techniques), while 79 (45%) used only one. Supervised learning techniques were often used to predict disease status or prognosis, and demonstrated strong accuracy. Unsupervised AI algorithms were used to bolster the accuracy of other algorithms, identify molecularly distinct subgroups, or cluster cases into distinct subgroups that are useful for prediction of the disease course. Finally, bioinformatic tools were used to translate complex biomarker profiles or findings into interpretable data.

CONCLUSION

AI analysis of biofluid markers displayed diagnostic accuracy, provided insight into mechanisms of molecular etiologies, and had the ability to provide individualized targeted therapeutic treatment for patients. Given the progression of AI towards use in both research and the clinic, ophthalmologists should be broadly aware of the commonly used algorithms and their applications. Future research may be aimed at validating algorithms and integrating them in clinical practice.

Association of different obesity patterns with hypertension in US male adults: a cross-sectional study

Obesity is an important risk factor for hypertension. We aimed to investigate the association between different obesity patterns and hypertension risk in a large male population in the US. Male participants from the National Health and Nutrition Examination Survey (NHANES) (2007-2018) were enrolled in this cross-sectional study. Social demographic information, lifestyle factors, anthropometric measurements and biochemical measurements were collected. Three obesity patterns were classified according to the body mass index (BMI) and waist circumference (WC), including overweight and general obesity, abdominal obesity, and compound obesity. We adopted multivariate logistic regression to investigate the associations between hypertension and different obesity patterns after adjusting for cofounding factors. Subgroup analysis, stratified by age, smoking, drinking and estimated glomerular filtration rate (eGFR), was also conducted to explore the associations between obesity patterns and hypertension risk among different populations. Moreover, the association between WC and hypertension among male individuals was also explored using restricted cubic spline (RCS) analysis. Receiver operating characteristic (ROC) was used to evaluate the discriminatory power of WC for screening hypertension risk. 13,859 male participants from NHANES survey (2007-2018) were enrolled. Comparing with the normal-weight group, the odds ratios (ORs) [95% confidence interval (CI)] for hypertension in individuals with overweight and general obesity, abdominal obesity and compound obesity were 1.41 [1.17-1.70], 1.97 [1.53-2.54] and 3.28 [2.70-3.99], respectively. Subgroup analysis showed that the effect of different obesity patterns on hypertension risk was highly stable among individuals with different clinical conditions. In addition, WC had a positive correlation with the risk of hypertension (OR: 1.43; 95% CI 1.37-1.52; P < 0.001) in fully adjusted multivariate logistic regression model. RCS analysis showed that the association between WC and hypertension risk was in a nonlinear pattern, and WC had a good discriminatory power for hypertension in ROC analysis. Different patterns of obesity have a great impact on the risk of hypertension among male individuals. Increment of WC significantly increased the hypertension risk. More attention should be paid to the prevention of obesity, especially abdominal obesity and compound obesity in male individuals.

Development and validation of medical record-based logistic regression and machine learning models to diagnose diabetic retinopathy

PURPOSES

Many factors were reported to be associated with diabetic retinopathy (DR); however, their contributions remained unclear. We aimed to evaluate the prognostic and diagnostic accuracy of logistic regression and three machine learning models based on various medical records.

METHODS

This was a cross-sectional study. We investigated the prevalence and associations of DR among 757 participants aged 40 years or older in the 2005-2006 National Health and Nutrition Examination Survey (NHANES). We trained the models to predict if the participants had DR with 15 predictor variables. Area under the receiver operating characteristic (AUROC) and mean squared error (MSE) of each algorithm were compared in the external validation dataset using a replicate cohort from NHANES 2007-2008.

RESULTS

Among the 757 participants, 53 (7.00%) subjects had DR, the mean (standard deviation, SD) age was 57.7 (13.04), and 78.0% were male (n = 42). Logistic regression revealed that female gender (OR = 4.130, 95% CI: 1.820-9.380; P < 0.05), HbA1c (OR = 1.665, 95% CI: 1.197-2.317; P < 0.05), serum creatine level (OR = 2.952, 95% CI: 1.274-6.851; P < 0.05), and eGFR level (OR = 1.009, 95% CI: 1.000-1.014, P < 0.05) increased the risk of DR. The average performance obtained from internal validation was similar in all models (AUROC ≥ 0.945), and k-nearest neighbors (KNN) had the highest value with an AUROC of 0.984. In external validation, they remained robust or with modest reductions in discrimination with AUROC still ≥ 0.902, and KNN also performed the best with an AUROC of 0.982. Both logistic regression and machine learning models had good performance in the clinical diagnosis of DR.

CONCLUSIONS

This study highlights the utility of comparing traditional logistic regression to machine learning models. We found that logistic regression performed as well as optimized machine learning methods when classifying DR patients.

Putative Biomarkers in Tears for Diabetic Retinopathy Diagnosis

Purpose

Tear fluid biomarkers may offer a non-invasive strategy for detecting diabetic patients with increased risk of developing diabetic retinopathy (DR) or increased disease progression, thus helping both improving diagnostic accuracy and understanding the pathophysiology of the disease. Here, we assessed the tear fluid of nondiabetic individuals, diabetic patients with no DR, and diabetic patients with nonproliferative DR (NPDR) or with proliferative DR (PDR) to find putative biomarkers for the diagnosis and staging of DR.

Methods

Tear fluid samples were collected using Schirmer test strips from a cohort with 12 controls and 54 Type 2 Diabetes (T2D) patients, and then analyzed using mass spectrometry (MS)-based shotgun proteomics and bead-based multiplex assay. Tear fluid-derived small extracellular vesicles (EVs) were analyzed by transmission electron microscopy, Western Blotting, and nano tracking.

Results

Proteomics analysis revealed that among the 682 reliably quantified proteins in tear fluid, 42 and 26 were differentially expressed in NPDR and PDR, respectively, comparing to the control group. Data are available via ProteomeXchange with identifier PXD033101. By multicomparison analyses, we also found significant changes in 32 proteins. Gene ontology (GO) annotations showed that most of these proteins are associated with oxidative stress and small EVs. Indeed, we also found that tear fluid is particularly enriched in small EVs. T2D patients with NPDR have higher IL-2/-5/-18, TNF, MMP-2/-3/-9 concentrations than the controls. In the PDR group, IL-5/-18 and MMP-3/-9 concentrations were significantly higher, whereas IL-13 was lower, compared to the controls.

Conclusions

Overall, the results show alterations in tear fluid proteins profile in diabetic patients with retinopathy. Promising candidate biomarkers identified need to be validated in a large sample cohort.

Lab-on-a-chip technologies for minimally invasive molecular sensing of diabetic retinopathy

Diabetic retinopathy (DR) is the most common diabetic eye disease and the worldwide leading cause of vision loss in working-age adults. It progresses from mild to severe non-proliferative or proliferative DR based on several pathological features including the magnitude of blood-retinal barrier breakdown and neovascularization. Available pharmacological and retinal laser photocoagulation interventions are mostly applied in the advanced stages of DR and are inefficient in halting disease progression in a significantly high percentage of patients. Yet, recent evidence has shown that some therapies could potentially limit DR progression if applied at early stages, highlighting the importance of early disease diagnostics. In the past few decades, different imaging modalities have proved their utility for examining retinal and optic nerve changes in patients with retinal diseases. However, imaging based-methodologies solely rely on morphological examination of the retinal vascularization and are not suitable for recurrent and personalized patient evaluation. This raises the need for new technologies to enable accurate and early diagnosis of DR. In this review, we critically discuss the potential clinical benefit of minimally-invasive molecular biomarker identification and profiling of diabetic patients who are at risk of developing DR. We provide a comparative overview of conventional and recently developed lab-on-a-chip technologies for quantitative assessment of potential DR molecular biomarkers and discuss their advantages, current limitations and challenges for future practical implementation and continuous patient monitoring at the point-of-care.

Diagnostic circulating biomarkers to detect vision-threatening diabetic retinopathy: Potential screening tool of the future?

With the increasing prevalence of diabetes in developing and developed countries, the socio-economic burden of diabetic retinopathy (DR), the leading complication of diabetes, is growing. Diabetic retinopathy (DR) is currently one of the leading causes of blindness in working-age adults worldwide. Robust methodologies exist to detect and monitor DR; however, these rely on specialist imaging techniques and qualified practitioners. This makes detecting and monitoring DR expensive and time-consuming, which is particularly problematic in developing countries where many patients will be remote and have little contact with specialist medical centres. Diabetic retinopathy (DR) is largely asymptomatic until late in the pathology. Therefore, early identification and stratification of vision-threatening DR (VTDR) is highly desirable and will ameliorate the global impact of this disease. A simple, reliable and more cost-effective test would greatly assist in decreasing the burden of DR around the world. Here, we evaluate and review data on circulating protein biomarkers, which have been verified in the context of DR. We also discuss the challenges and developments necessary to translate these promising data into clinically useful assays, to detect VTDR, and their potential integration into simple point-of-care testing devices.

Prevalence and risk factors for diabetic retinopathy in prediabetes in Asian Indians

AIM

To assess the prevalence of diabetic retinopathy (DR) and associated risk factors in Asian Indians with prediabetes.

METHODS

In a cross-sectional study conducted at two tertiary care diabetes centres in Chennai, India, clinical and biochemical assessment and nonmydriatic ultra-wide field fundus photography was performed in individuals with prediabetes (impaired fasting glucose [IFG] and/or impaired glucose tolerance [IGT]) based on oral glucose tolerance test (OGTT) and/or glycated hemoglobin (HbA1c) between 5.7% and 6.4% in 2019. The retinal photographs were graded by certified ophthalmologists. Systemic risk factors associated with DR in prediabetes were assessed.

RESULTS

The mean age of the 192 individuals with prediabetes was 48 ± 13 years (55.2% were males). DR was present in 12 (6.3%) individuals of which nine (4.7%) had mild non-proliferative DR (NPDR) and three (1.6%) had moderate NPDR. None had severe sight-threatening DR. The Poisson multiple regression analysis showed that after adjusting for other systemic covariates, HbA1c values ≥ 6% (6-6.4%) was associated with 2 times higher relative risk of DR (Risk ratio 1.95 (95% CI 1.07-3.545, p = 0.028) in comparison to HbA1c < 6%).

CONCLUSION

DR was present in about 6% of the Asian Indians with prediabetes. Higher HbA1c values among individuals with prediabetes was associated with twice the relative risk for DR. Robust control of HbA1c should be encouraged even before the diagnosis of diabetes is established.

Galectins in the Pathogenesis of Common Retinal Disease

Diseases of the retina are major causes of visual impairment and blindness in developed countries and, due to an ageing population, their prevalence is continually rising. The lack of effective therapies and the limitations of those currently in use highlight the importance of continued research into the pathogenesis of these diseases. Vascular endothelial growth factor (VEGF) plays a major role in driving vascular dysfunction in retinal disease and has therefore become a key therapeutic target. Recent evidence also points to a potentially similarly important role of galectins, a family of β-galactoside-binding proteins. Indeed, they have been implicated in regulating fundamental processes, including vascular hyperpermeability, angiogenesis, neuroinflammation, and oxidative stress, all of which also play a prominent role in retinopathies. Here, we review direct evidence for pathological roles of galectins in retinal disease. In addition, we extrapolate potential roles of galectins in the retina from evidence in cancer, immune and neuro-biology. We conclude that there is value in increasing understanding of galectin function in retinal biology, in particular in the context of the retinal vasculature and microglia. With greater insight, recent clinical developments of galectin-targeting drugs could potentially also be of benefit to the clinical management of many blinding diseases.