Prediction models for development of retinopathy in people with type 2 diabetes: systematic review and external validation in a Dutch primary care setting

Role of Systemic Factors in Improving the Prognosis of Diabetic Retinal Disease and Predicting Response to Diabetic Retinopathy Treatment

Topic

To review clinical evidence on systemic factors that might be relevant to update diabetic retinal disease (DRD) staging systems, including prediction of DRD onset, progression, and response to treatment.

Clinical relevance

Systemic factors may improve new staging systems for DRD to better assess risk of disease worsening and predict response to therapy.

Methods

The Systemic Health Working Group of the Mary Tyler Moore Vision Initiative reviewed systemic factors individually and in multivariate models for prediction of DRD onset or progression (i.e., prognosis) or response to treatments (prediction).

Results

There was consistent evidence for associations of longer diabetes duration, higher glycosylated hemoglobin (HbA1c), and male sex with DRD onset and progression. There is strong trial evidence for the effect of reducing HbA1c and reducing DRD progression. There is strong evidence that higher blood pressure (BP) is a risk factor for DRD incidence and for progression. Pregnancy has been consistently reported to be associated with worsening of DRD but recent studies reflecting modern care standards are lacking. In studies examining multivariate prognostic models of DRD onset, HbA1c and diabetes duration were consistently retained as significant predictors of DRD onset. There was evidence of associations of BP and sex with DRD onset. In multivariate prognostic models examining DRD progression, retinal measures were consistently found to be a significant predictor of DRD with little evidence of any useful marginal increment in prognostic information with the inclusion of systemic risk factor data apart from retinal image data in multivariate models. For predicting the impact of treatment, although there are small studies that quantify prognostic information based on imaging data alone or systemic factors alone, there are currently no large studies that quantify marginal prognostic information within a multivariate model, including both imaging and systemic factors.

Conclusion

With standard imaging techniques and ways of processing images rapidly evolving, an international network of centers is needed to routinely capture systemic health factors simultaneously to retinal images so that gains in prediction increment may be precisely quantified to determine the usefulness of various health factors in the prognosis of DRD and prediction of response to treatment.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Prediction of retinopathy progression using deep learning on retinal images within the Scottish screening programme

BACKGROUND/AIMS

National guidelines of many countries set screening intervals for diabetic retinopathy (DR) based on grading of the last screening retinal images. We explore the potential of deep learning (DL) on images to predict progression to referable DR beyond DR grading, and the potential impact on assigned screening intervals, within the Scottish screening programme.

METHODS

We consider 21 346 and 247 233 people with type 1 diabetes mellitus (T1DM) and type 2 diabetes mellitus (T2DM), respectively, each contributing on average 4.8 and 4.4 screening intervals of which 1339 and 4675 intervals concluded with a referable screening episode. Information extracted from fundus images using DL was used to predict referable status at the end of interval and its predictive value in comparison to screening-assigned DR grade was assessed.

RESULTS

The DL predictor increased the area under the receiver operating characteristic curve in comparison to a predictor using current DR grades from 0.809 to 0.87 for T1DM and from 0.825 to 0.87 for T2DM. Expected sojourn time-the time from becoming referable to being rescreened-was found to be 3.4 (T1DM) and 2.7 (T2DM) weeks less for a DL-derived policy compared with the current recall policy.

CONCLUSIONS

We showed that, compared with using the current retinopathy grade, DL of fundus images significantly improves the prediction of incident referable retinopathy before the next screening episode. This can impact screening recall interval policy positively, for example, by reducing the expected time with referable disease for a fixed workload-which we show as an exemplar. Additionally, it could be used to optimise workload for a fixed sojourn time.

Machine Learning Models for Prediction of Diabetic Microvascular Complications

IMPORTANCE AND AIMS

Diabetic microvascular complications significantly impact morbidity and mortality. This review focuses on machine learning/artificial intelligence (ML/AI) in predicting diabetic retinopathy (DR), diabetic kidney disease (DKD), and diabetic neuropathy (DN).

METHODS

A comprehensive PubMed search from 1990 to 2023 identified studies on ML/AI models for diabetic microvascular complications. The review analyzed study design, cohorts, predictors, ML techniques, prediction horizon, and performance metrics.

RESULTS

Among the 74 identified studies, 256 featured internally validated ML models and 124 had externally validated models, with about half being retrospective. Since 2010, there has been a rise in the use of ML for predicting microvascular complications, mainly driven by DKD research across 27 countries. A more modest increase in ML research on DR and DN was observed, with publications from fewer countries. For all microvascular complications, predictive models achieved a mean (standard deviation) c-statistic of 0.79 (0.09) on internal validation and 0.72 (0.12) on external validation. Diabetic kidney disease models had the highest discrimination, with c-statistics of 0.81 (0.09) on internal validation and 0.74 (0.13) on external validation, respectively. Few studies externally validated prediction of DN. The prediction horizon, outcome definitions, number and type of predictors, and ML technique significantly influenced model performance.

CONCLUSIONS AND RELEVANCE

There is growing global interest in using ML for predicting diabetic microvascular complications. Research on DKD is the most advanced in terms of publication volume and overall prediction performance. Both DR and DN require more research. External validation and adherence to recommended guidelines are crucial.

A literature review of quality assessment and applicability to HTA of risk prediction models of coronary heart disease in patients with diabetes

This literature review had two objectives: to identify models for predicting the risk of coronary heart diseases in patients with diabetes (DM); and to assess model quality in terms of risk of bias (RoB) and applicability for the purpose of health technology assessment (HTA). We undertook a targeted review of journal articles published in English, Dutch, Chinese, or Spanish in 5 databases from 1st January 2016 to 18th December 2022, and searched three systematic reviews for the models published after 2012. We used PROBAST (Prediction model Risk Of Bias Assessment Tool) to assess RoB, and used findings from Betts et al. 2019, which summarized recommendations and criticisms of HTA agencies on cardiovascular risk prediction models, to assess model applicability for the purpose of HTA. As a result, 71 % and 67 % models reporting C-index showed good discrimination abilities (C-index >= 0.7). Of the 26 model studies and 30 models identified, only one model study showed low RoB in all domains, and no model was fully applicable for HTA. Since the major cause of high RoB is inappropriate use of analysis method, we advise clinicians to carefully examine the model performance declared by model developers, and to trust a model if all PROBAST domains except analysis show low RoB and at least one validation study conducted in the same setting (e.g. country) is available. Moreover, since general model applicability is not informative for HTA, novel adapted tools may need to be developed.

Retinal age gap as a predictive biomarker for future risk of clinically significant diabetic retinopathy

AIMS

Retinal age derived from fundus images has been verified as a novel ageing biomarker. We aim to explore the association between retinal age gap (retinal age minus chronological age) and incident diabetic retinopathy (DR).

METHODS

Retinal age prediction was performed by a deep learning model, trained and validated based on 19,200 fundus images of 11,052 disease-free participants. Retinal age gaps were determined for 2311 patients with diabetes who had no history of diabetic retinopathy at baseline. DR events were ascertained by data linkage to hospital admissions. Cox proportional hazards regression models were performed to evaluate the association between retinal age gaps and incident DR.

RESULTS

During the median follow-up period of 11.0 (interquartile range: 10.8-11.1) years, 183 of 2311 participants with diabetes developed incident DR. Each additional year of the retinal age gap was associated with a 7% increase in the risk of incident DR (hazard ratio [HR] = 1.07, 95% confidence interval [CI] 1.02-1.12, P = 0.004), after adjusting for confounding factors. Participants with retinal age gaps in the fourth quartile had a significantly higher DR risk compared to participants with retinal age gaps in the lowest quartile (HR = 2.88, 95% CI 1.61-5.15, P < 0.001).

CONCLUSIONS

We found that higher retinal age gap was associated with an increased risk of incident DR. As an easy and non-invasive biomarker, the retinal age gap may serve as an informative tool to facilitate the individualized risk assessment and personalized screening protocol for DR.

A Prediction Model for Sight-Threatening Diabetic Retinopathy Based on Plasma Adipokines among Patients with Mild Diabetic Retinopathy

Background

Accumulating evidence has suggested a link between adipokines and diabetic retinopathy (DR). This study is aimed at investigating the risk factors for sight-threatening DR (STDR) and establishing a prognostic model for predicting STDR among a high-risk population of patients with type 2 diabetes mellitus (T2DM).

Methods

Plasma concentrations of adipokines were determined by enzyme-linked immunosorbent assay. In the case-control set, principal component analysis (PCA) was performed to select optimal predictive cytokines for STDR, involving severe nonproliferative DR (NPDR) and proliferative DR. Support vector machine (SVM) was used to examine the possible combination of baseline plasma adipokines to discriminate the patients with mild NPDR who will later develop STDR. An individual prospective cohort with a follow-up period of 3 years was used for the external validation.

Results

In both training and testing sets, involving 306 patients with T2DM, median levels of plasma adiponectin (APN), leptin, and fatty acid-binding protein 4 (FABP4) were significantly higher in the STDR group than those in mild NPDR. Except for adipsin, the other three adipokines, FABP4, APN, and leptin, were selected by PCA and integrated into SVM. The accuracy of the multivariate SVM classification model was acceptable in both the training set (AUC = 0.81, sensitivity = 71%, and specificity = 91%) and the testing set (AUC = 0.77, sensitivity = 61%, and specificity = 92%). 110 T2DM patients with mild NPDR, the high-risk population of STDR, were enrolled for external validation. Based on the SVM, the risk of each patient was calculated. More STDR occurred in the high-risk group than in the low-risk group, which were grouped by the median value of APN, FABP4, and leptin, respectively. The model was validated in an individual cohort using SVM with the AUC, sensitivity, and specificity reaching 0.77, 64%, and 91%, respectively.

Conclusions

Adiponectin, leptin, and FABP4 were demonstrated to be associated with the severity of DR and maybe good predictors for STDR, suggesting that adipokines may play an important role in the pathophysiology of DR development.

Cardiovascular risk in diabetes mellitus: epidemiology, assessment and prevention

Cardiovascular diseases (CVDs) are the leading causes of morbidity and mortality in individuals with type 2 diabetes mellitus (T2DM). Secular changes in CVD outcomes have occurred over the past few decades, mainly due to a decline in the incidence of ischaemic heart disease. The onset of T2DM at a young age (<40 years), leading to a greater number of life-years lost, has also become increasingly common. Researchers are now looking beyond established risk factors in patients with T2DM towards the role of ectopic fat and, potentially, haemodynamic abnormalities in mediating important outcomes (such as heart failure). T2DM confers a wide spectrum of risk and is not necessarily a CVD risk equivalent, indicating the importance of risk assessment strategies (such as global risk scoring, consideration of risk-enhancing factors and assessment of subclinical atherosclerosis) to inform treatment. Data from epidemiological studies and clinical trials demonstrate that successful control of multiple risk factors can reduce the risk of CVD events by ≥50%; however, only ≤20% of patients achieve targets for risk factor reduction (plasma lipid levels, blood pressure, glycaemic control, body weight and non-smoking status). Improvements in composite risk factor control with lifestyle management (including a greater emphasis on weight loss interventions) and evidence-based generic and novel pharmacological therapies are therefore needed when the risk of CVD is high.

Choriocapillaris flow deficit and the risk of referable diabetic retinopathy: a longitudinal SS-OCTA study

AIMS

To investigate the association between the choriocapillaris flow deficit percentage (CC FD%) and the 1-year incidence of referable diabetic retinopathy (RDR) in participants with type 2 diabetes mellitus (DM).

METHODS

This prospective cohort study included participants with type 2 DM. The DR status was graded based on the ETDRS-7 photography. The CC FD% in the central 1 mm area, inner circle (1.5 mm to 2.5 mm), outer circle (2.5 mm to 5.0 mm) and the entire area in the macular region were measured using swept-source optical coherence tomography angiography (SS-OCTA). Logistic regression analysis was used to examine the association between baseline CC FD% and 1-year incident RDR.

RESULTS

A total of 1222 patients (1222 eyes, mean age: 65.1±7.4 years) with complete baseline and 1-year follow-up data were included. Each 1% increase in baseline CC FD% was significantly associated with a 1.69 times (relative risk 2.69; 95% CI 1.53 to 4.71; p=0.001) higher odds for development of RDR after 1-year follow-up, after adjusting for other confounding factors.

CONCLUSIONS

A greater baseline CC FD% detected by SS-OCTA reliably predicted higher risks of RDR in participants with type 2 DM. Thus, CC FD% may act as a novel biomarker for predicting the onset and progression of DR.

A systematic literature review of machine learning based risk prediction models for diabetic retinopathy progression

Diabetic Retinopathy (DR) is the most popular debilitating impairment of diabetes and it progresses symptom-free until a sudden loss of vision occurs. Understanding the progression of DR is a pressing issue in clinical research and practice. In this systematic review of articles on Machine Learning (ML) based risk prediction models for DR progression, ever since the use of Artificial Intelligence (AI) for DR detection, there have been more cross-sectional studies with different algorithms of use of AI, there haven't been many longitudinal studies for the AI based risk prediction models. This paper proposes a novel review to fill in the gaps identified in current reviews and facilitate other researchers with current research solutions for developing AI-based risk prediction models for DR progression and closely related problems; synthesize the current results from these studies and identify research challenges, limitations and gaps to inform the selection of machine learning techniques and predictors to build novel prediction models. Additionally, this paper suggested six (6) deep AI-related technical and critical discussion of the adopted strategies and approaches. The Systematic Literature Review (SLR) methodology was employed to gather relevant studies. We searched IEEE Xplore, PubMed, Springer Link, Google Scholar, and Science Direct electronic databases for papers published from January 2017 to 30th April 2023. Thirteen (13) studies were chosen on the basis of their relevance to the review questions and satisfying the selection criteria. However, findings from the literature review exposed some critical research gaps that need to be addressed in future research to improve on the performance of risk prediction models for DR progression.

Diabetic retinopathy progression in patients under monitoring for treatment or vision loss: external validation and update of a multivariable prediction model

INTRODUCTION

The number of people with diabetes mellitus is increasing globally and consequently so too is diabetic retinopathy (DR). Most patients with diabetes are monitored through the diabetic eye screening programme (DESP) until they have signs of retinopathy and these changes progress, requiring referral into hospital eye services (HES). Here, they continue to be monitored until they require treatment. Due to current pressures on HES, delays can occur, leading to harm. There is a need to triage patients based on their individual risk. At present, patients are stratified according to retinopathy stage alone, yet other risk factors like glycated haemoglobin (HbA1c) may be useful. Therefore, a prediction model that combines multiple prognostic factors to predict progression will be useful for triage in this setting to improve care.We previously developed a Diabetic Retinopathy Progression model to Treatment or Vision Loss (DRPTVL-UK) using a large primary care database. The aim of the present study is to externally validate the DRPTVL-UK model in a secondary care setting, specifically in a population under care by HES. This study will also provide an opportunity to update the model by considering additional predictors not previously available.

METHODS AND ANALYSIS

We will use a retrospective cohort of 2400 patients with diabetes aged 12 years and over, referred from DESP to the NHS hospital trusts with referable DR between 2013 and 2016, with follow-up information recorded until December 2021.We will evaluate the external validity of the DRPTVL-UK model using measures of discrimination, calibration and net benefit. In addition, consensus meetings will be held to agree on acceptable risk thresholds for triage within the HES system.

ETHICS AND DISSEMINATION

This study was approved by REC (ref 22/SC/0425, 05/12/2022, Hampshire A Research Ethics Committee). The results of the study will be published in a peer-reviewed journal, presented at clinical conferences.

TRIAL REGISTRATION NUMBER

ISRCTN 10956293.

Evaluation of Machine Learning Methods Developed for Prediction of Diabetes Complications: A Systematic Review

BACKGROUND

With the rising prevalence of diabetes, machine learning (ML) models have been increasingly used for prediction of diabetes and its complications, due to their ability to handle large complex data sets. This study aims to evaluate the quality and performance of ML models developed to predict microvascular and macrovascular diabetes complications in an adult Type 2 diabetes population.

METHODS

A systematic review was conducted in MEDLINE®, Embase®, the Cochrane® Library, Web of Science®, and DBLP Computer Science Bibliography databases according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist. Studies that developed or validated ML prediction models for microvascular or macrovascular complications in people with Type 2 diabetes were included. Prediction performance was evaluated using area under the receiver operating characteristic curve (AUC). An AUC >0.75 indicates clearly useful discrimination performance, while a positive mean relative AUC difference indicates better comparative model performance.

RESULTS

Of 13 606 articles screened, 32 studies comprising 87 ML models were included. Neural networks (n = 15) were the most frequently utilized. Age, duration of diabetes, and body mass index were common predictors in ML models. Across predicted outcomes, 36% of the models demonstrated clearly useful discrimination. Most ML models reported positive mean relative AUC compared with non-ML methods, with random forest showing the best overall performance for microvascular and macrovascular outcomes. Majority (n = 31) of studies had high risk of bias.

CONCLUSIONS

Random forest was found to have the overall best prediction performance. Current ML prediction models remain largely exploratory, and external validation studies are required before their clinical implementation.

PROTOCOL REGISTRATION

Open Science Framework (registration number: 10.17605/OSF.IO/UP49X).

A Nomogram for Predicting Vision-Threatening Diabetic Retinopathy Among Mild Diabetic Retinopathy Patients: A Case-Control and Prospective Study of Type 2 Diabetes

AIM

This study aims to develop a nomogram for predicting vision-threatening diabetic retinopathy (VTDR) in type 2 diabetes mellitus (T2DM) with mild non-proliferative diabetic retinopathy (NPDR) patients.

MATERIALS AND METHODS

In case-control analysis, 440 patients with mild NPDR or VTDR were enrolled to identify predictors and develop a nomogram. In the prospective cohort, 120 T2DM patients with mild NPDR were enrolled for external validation. Sensitivity, specificity, and area under the receiver operating characteristic (AUC) were calculated to evaluate the predictive performance of the nomogram.

RESULTS

In case-control analysis, 2-h C-peptide (OR = 0.85, 95% CI: 0.75 to 0.95, p = 0.006), sural nerve conduction impaired (SNCI) (mildly: OR = 2.18, 95% CI: 1.10 to 4.33, p = 0.026; moderately/severely: 3.66, 95% CI: 1.74 to 7.70, p < 0.001) and UACR (microalbuminuria: OR = 2.37, 95% CI: 1.25 to 4.48, p = 0.008; macroalbuminuria: 4.02, 95% CI: 1.61 to 10.06, p = 0.003) were identified as independent predictors. The concordance index of the prediction nomogram was 0.76 in the training set. In the test set, sensitivity, specificity, and AUC were 84.8%, 60.6%, and 0.73, respectively. In the prospective cohort, median follow-up period was 42 months, and 15 patients (12.5%) developed VTDR. Sensitivity, specificity, and AUC of prediction were 66.7%, 89.5%, and 0.75, respectively.

CONCLUSION

Introducing 2-h C-peptide, UACR, and SNCI, the nomogram demonstrated a good discriminatory power for predicting risk of VTDR in mild NPDR individuals.

Precision prognostics for the development of complications in diabetes

Individuals with diabetes face higher risks for macro- and microvascular complications than their non-diabetic counterparts. The concept of precision medicine in diabetes aims to optimise treatment decisions for individual patients to reduce the risk of major diabetic complications, including cardiovascular outcomes, retinopathy, nephropathy, neuropathy and overall mortality. In this context, prognostic models can be used to estimate an individual's risk for relevant complications based on individual risk profiles. This review aims to place the concept of prediction modelling into the context of precision prognostics. As opposed to identification of diabetes subsets, the development of prediction models, including the selection of predictors based on their longitudinal association with the outcome of interest and their discriminatory ability, allows estimation of an individual's absolute risk of complications. As a consequence, such models provide information about potential patient subgroups and their treatment needs. This review provides insight into the methodological issues specifically related to the development and validation of prediction models for diabetes complications. We summarise existing prediction models for macro- and microvascular complications, commonly included predictors, and examples of available validation studies. The review also discusses the potential of non-classical risk markers and omics-based predictors. Finally, it gives insight into the requirements and challenges related to the clinical applications and implementation of developed predictions models to optimise medical decision making.

Development and validation of predictive risk models for sight threatening diabetic retinopathy in patients with type 2 diabetes to be applied as triage tools in resource limited settings

Background

Delayed diagnosis and treatment of sight threatening diabetic retinopathy (STDR) is a common cause of visual impairment in people with Type 2 diabetes. Therefore, systematic regular retinal screening is recommended, but global coverage of such services is challenging. We aimed to develop and validate predictive models for STDR to identify 'at-risk' population for retinal screening.

Methods

Models were developed using datasets obtained from general practices in inner London, United Kingdom (UK) on adults with type 2 Diabetes during the period 2007-2017. Three models were developed using Cox regression and model performance was assessed using C statistic, calibration slope and observed to expected ratio measures. Models were externally validated in cohorts from Wales, UK and India.

Findings

A total of 40,334 people were included in the model development phase of which 1427 (3·54%) people developed STDR. Age, gender, diabetes duration, antidiabetic medication history, glycated haemoglobin (HbA1c), and history of retinopathy were included as predictors in the Model 1, Model 2 excluded retinopathy status, and Model 3 further excluded HbA1c. All three models attained strong discrimination performance in the model development dataset with C statistics ranging from 0·778 to 0·832, and in the external validation datasets (C statistic 0·685 - 0·823) with calibration slopes closer to 1 following re-calibration of the baseline survival.

Interpretation

We have developed new risk prediction equations to identify those at risk of STDR in people with type 2 diabetes in any resource-setting so that they can be screened and treated early. Future testing, and piloting is required before implementation.

Funding

This study was funded by the GCRF UKRI (MR/P207881/1) and supported by the NIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology.

Clinical scoring systems for the risk of cardiovascular autonomic neuropathy in type 1 and type 2 diabetes: a simple tool

BACKGROUND AND AIMS

This study was aimed at developing a clinical risk score for cardiovascular autonomic neuropathy (CAN) for type 1 and type 2 diabetes.

METHODS

In a retrospective cross-sectional one-centre study in an unselected population, 115 participants with type 1 diabetes (age 41.1±12.2 years), and 161 with type 2 diabetes (age 63.1±8.9 years), well-characterised for clinical variables, underwent standard cardiovascular reflex tests (CARTs). Strength of associations of confirmed CAN (based on 2 abnormal CARTs) with clinical variables was used to build a CAN risk score.

RESULTS

CAN risk score was based on resting heart rate, HbA1c, retinopathy, nephropathy, cardiovascular disease in both type 1 and type 2 diabetes, and on HDL cholesterol, systolic blood pressure, and smoking in type 1 diabetes or insulin treatment and physical activity in type 2 diabetes (range 0-10). In type 1 diabetes, CAN risk score showed an area under the ROC curve (AUC) of 0.890±0.034, and at cut-off of 4 sensitivity of 88%, specificity of 74.4%, and negative predictive value (NPV) of 95.7% for confirmed CAN. In type 2 diabetes, CAN risk score showed an AUC of 0.830±0.051 and at the cut-off of 4 sensitivity and specificity of 78.6% and 73.5%, respectively, and NPV of 97.3% for confirmed CAN.

INTERPRETATION

These newly developed CAN risk scores are accessible in clinical practice and, if confirmed in a validation study, they might identify asymptomatic individuals with diabetes at greater risk of CAN to be referred to CARTs, thus limiting the burden of a universal screening. This article is protected by copyright. All rights reserved.

Improving the screening of risk factors in diabetic retinopathy

INTRODUCTION

In 2002, Diabetic Retinopathy was reported as the leading cause of blindness in the working age group. The introduction of systematic screening programs in the UK has reduced visual loss and blindness due to diabetic retinopathy, but it does still occur with catastrophic consequences for the individual.

AREAS COVERED

The author conducted an ongoing search for articles relating to diabetic retinopathy since 2000 utilizing Zetoc Alert with keywords and contents page lists from relevant journals. This review covers the risk factors for loss of vision due to diabetic retinopathy and discusses ways in which the awareness of these risk factors can be used to further reduce visual loss. Some risk factors such as glycemic and B/P control are well known from landmark trials. This review has included these factors but concentrated more on the evidence behind those risk factors that are not so clearly defined or so well known.

EXPERT OPINION

The major risk factors are well known, but one continues to find that people with diabetes lose vision in situations in which a better awareness of the risks by both the individual with diabetes and the health workers involved may have prevented the visual loss.

Longitudinal associations of ocular biometric parameters with onset and progression of diabetic retinopathy in Chinese adults with type 2 diabetes mellitus

AIMS

To investigate the associations of ocular biometric parameters with incident diabetic retinopathy (DR), incident vision-threatening DR (VTDR) and DR progression.

METHODS

This community-based prospective cohort study recruited participants with type 2 diabetes aged 35-80 years from 2017 to 2019 in Guangzhou, China. Refractive error and ocular biometric parameters were measured at baseline, including axial length (AL), axial length-to-corneal radius (AL/CR) ratio, corneal curvature (CC), lens thickness (LT), anterior chamber depth (ACD), lens power and corneal diameter (CD).

RESULTS

A total of 1370 participants with a mean age of 64.3±8.1 years were followed up for two consecutive years. During the follow-up period, 342 out of 1195 (28.6%) participants without DR at baseline had incident DR, 15 out of 175 (8.57%) participants with baseline DR had DR progression and 11 of them progressed to VTDR. After multiple adjustments, a longer AL (OR=0.76; 95% CI, 0.66 to 0.86; p<0.001) and a larger AL/CR ratio (OR=0.20; 95% CI, 0.07 to 0.55; p=0.002) were associated with significantly reduced risks of incident DR but were not associated with incident VTDR or DR progression. Refractive status and other ocular biometric parameters investigated, including ACD, CC, CD, lens power and LT were not associated with any of the DR outcomes (all p>0.05).

CONCLUSIONS

A longer AL and a larger AL/CR ratio are protective against incident DR. These parameters may be incorporated into future DR risk prediction models to individualise the frequency of DR screening and prevention measures.

Retinal oxygen saturation is associated with HbA1c but not with short-term diabetes control, internal environment, smoking and mild retinopathy - ROXINEGLYD study

PURPOSE

Purpose of this prospective uncontrolled single-centre pilot study was to find an association of retinal oxygen saturation (SatO₂ ) with acid-base balance (ABB), carboxyhaemoglobin concentration, current plasma glucose concentration (PG), mean PG and PG variability over the last 72 hr, haemoglobin A1c (HbA1c), and other conditions.

METHODS

Forty-one adults (17 men) with type 1 (N = 14) or type 2 (N = 27) diabetes mellitus, age 48.6 ± 13.5 years, diabetes duration 9 (0.1-36) years, BMI 29.4 ± 6.3 kg/m² , and HbA1c 52 ± 12.7 mmol/mol completed the study. The 4-day study comprised two visits (Day l, Day 4) including 72 hr of continuous glucose monitoring (CGM) by iPro^® 2 Professional CGM (Medtronic, MiniMed, Inc., Northridge, CA, USA). Retinal oximeter Oxymap T1 (Oxymap ehf., Reykjavik, Iceland) was used to assess SatO₂ .

RESULTS

Wilcoxon signed-rank test showed no SatO₂ difference between eyes and visits. Spearman's correlation analysis revealed a significant correlation between arterial SatO₂ and PG variability in type 2 diabetes mellitus, a positive correlation of venous SatO₂ with HbA1c and with finger pulse oximetry. However, no correlation of SatO₂ with ABB, carboxyhaemoglobin, current PG, mean PG over the 72 hr, age, diabetes duration, BMI, lipoproteinaemia, body temperature, systolic and diastolic blood pressure, heart rate, central retinal thickness and retinal nerve fibre layer thickness was found.

CONCLUSION

This study confirmed the association of venous SatO₂ with long-term but not with short-term diabetes control, ABB and other conditions. The increased SatO₂ and questionable impact of PG variability on retinal SatO₂ is a research challenge.

Ethnic Disparities in the Development of Sight-Threatening Diabetic Retinopathy in a UK Multi-Ethnic Population with Diabetes: An Observational Cohort Study

There is little data on ethnic differences in incidence of DR and sight threatening DR (STDR) in the United Kingdom. We aimed to determine ethnic differences in the development of DR and STDR and to identify risk factors of DR and STDR in people with incident or prevalent type II diabetes (T2DM). We used electronic primary care medical records of people registered with 134 general practices in East London during the period from January 2007-January 2017. There were 58,216 people with T2DM eligible to be included in the study. Among people with newly diagnosed T2DM, Indian, Pakistani and African ethnic groups showed an increased risk of DR with Africans having highest risk of STDR compared to White ethnic groups (HR: 1.36 95% CI 1.02-1.83). Among those with prevalent T2DM, Indian, Pakistani, Bangladeshi and Caribbean ethnic groups showed increased risk of DR and STDR with Indian having the highest risk of any DR (HR: 1.24 95% CI 1.16-1.32) and STDR (HR: 1.38 95% CI 1.17-1.63) compared with Whites after adjusting for all covariates considered. It is important to optimise prevention, screening and treatment options in these ethnic minority groups to avoid health inequalities in diabetes eye care.

Testing the performance of risk prediction models to determine progression to referable diabetic retinopathy in an Irish type 2 diabetes cohort

Background /Aims

To evaluate the performance of existing prediction models to determine risk of progression to referable diabetic retinopathy (RDR) using data from a prospective Irish cohort of people with type 2 diabetes (T2D).

Methods

A cohort of 939 people with T2D followed prospectively was used to test the performance of risk prediction models developed in Gloucester, UK, and Iceland. Observed risk of progression to RDR in the Irish cohort was compared with that derived from each of the prediction models evaluated. Receiver operating characteristic curves assessed models’ performance.

Results

The cohort was followed for a total of 2929 person years during which 2906 screening episodes occurred. Among 939 individuals followed, there were 40 referrals (4%) for diabetic maculopathy, pre-proliferative DR and proliferative DR. The original Gloucester model, which includes results of two consecutive retinal screenings; a model incorporating, in addition, systemic biomarkers (HbA1c and serum cholesterol); and a model including results of one retinopathy screening, HbA1c, total cholesterol and duration of diabetes, had acceptable discriminatory power (area under the curve (AUC) of 0.69, 0.76 and 0.77, respectively). The Icelandic model, which combined retinopathy grading, duration and type of diabetes, HbA1c and systolic blood pressure, performed very similarly (AUC of 0.74).

Conclusion

In an Irish cohort of people with T2D, the prediction models tested had an acceptable performance identifying those at risk of progression to RDR. These risk models would be useful in establishing more personalised screening intervals for people with T2D.

Therapeutic Potential of Peptides Derived from Animal Venoms: Current Views and Emerging Drugs for Diabetes

The therapeutic potential of venom-derived drugs is evident today. Currently, several significant drugs are FDA approved for human use that descend directly from animal venom products, with others having undergone, or progressing through, clinical trials. In addition, there is growing awareness of the important cosmeceutical application of venom-derived products. The success of venom-derived compounds is linked to their increased bioactivity, specificity and stability when compared to synthetically engineered compounds. This review highlights advancements in venom-derived compounds for the treatment of diabetes and related disorders. Exendin-4, originating from the saliva of Gila monster lizard, represents proof-of-concept for this drug discovery pathway in diabetes. More recent evidence emphasises the potential of venom-derived compounds from bees, cone snails, sea anemones, scorpions, snakes and spiders to effectively manage glycaemic control. Such compounds could represent exciting exploitable scaffolds for future drug discovery in diabetes, as well as providing tools to allow for a better understanding of cell signalling pathways linked to insulin secretion and metabolism.

Apocynin ameliorates NADPH oxidase 4 (NOX4) induced oxidative damage in the hypoxic human retinal Müller cells and diabetic rat retina

NADPH oxidase (NOX) is a main producers of reactive oxygen species (ROS) that may contribute to the early pathogenesis of diabetic retinopathy (DR). ROS has harmful effects on endogenous neuro-survival factors brain-derived neurotrophic factor (BDNF) and sirtuin 1 (SIRT1) are necessary for the growth and survival of the retina. The role of NOX isoforms NOX4 in triggering ROS in DR is not clear. Here we determine the protective effects of a plant-derived NOX inhibitor apocynin (APO) on NOX4-induced ROS production which may contribute to the depletion of survival factors BDNF/SIRT1 or cell death in the diabetic retinas. Human retinal Müller glial cells (MGCs) were treated with hypoxia mimetic agent cobalt chloride (CoCl₂) in the absence or presence of APO. Molecular analysis demonstrates that NOX4 is upregulated in CoCl₂-treated MGCs and in the diabetic retinas. Increased NOX4 was accompanied by the downregulation of BDNF/SIRT1 expression or in the activation of apoptotic marker caspase-3. Whereas, APO treatment downregulates NOX4 and subsequently upregulates BDNF/SIRT1 or alleviate caspase-3 expression. Accordingly, in the diabetic retina we found a positive correlation in NOX4 vs ROS (p = 0.025; R² = 0.488) and caspase-3 vs ROS (p = 0.04; R² = 0.428); whereas a negative correlation in BDNF vs ROS (p = 0.009; R² = 0.596) and SIRT1 vs ROS (p = 0.0003; R² = 0.817) respectively. Taken together, NOX4-derived ROS could be a main contributor in downregulating BDNF/SIRT1 expression or in the activation of caspase-3. Whereas, APO treatment may minimize the deleterious effects occurring due to hyperglycemia and/or diabetic mimic hypoxic condition in early pathogenesis of DR.

Clusters of people with type 2 diabetes in the general population: unsupervised machine learning approach using national surveys in Latin America and the Caribbean

INTRODUCTION

We aimed to identify clusters of people with type 2 diabetes mellitus (T2DM) and to assess whether the frequency of these clusters was consistent across selected countries in Latin America and the Caribbean (LAC).

RESEARCH DESIGN AND METHODS

We analyzed 13 population-based national surveys in nine countries (n=8361). We used k-means to develop a clustering model; predictors were age, sex, body mass index (BMI), waist circumference (WC), systolic/diastolic blood pressure (SBP/DBP), and T2DM family history. The training data set included all surveys, and the clusters were then predicted in each country-year data set. We used Euclidean distance, elbow and silhouette plots to select the optimal number of clusters and described each cluster according to the underlying predictors (mean and proportions).

RESULTS

The optimal number of clusters was 4. Cluster 0 grouped more men and those with the highest mean SBP/DBP. Cluster 1 had the highest mean BMI and WC, as well as the largest proportion of T2DM family history. We observed the smallest values of all predictors in cluster 2. Cluster 3 had the highest mean age. When we reflected the four clusters in each country-year data set, a different distribution was observed. For example, cluster 3 was the most frequent in the training data set, and so it was in 7 out of 13 other country-year data sets.

CONCLUSIONS

Using unsupervised machine learning algorithms, it was possible to cluster people with T2DM from the general population in LAC; clusters showed unique profiles that could be used to identify the underlying characteristics of the T2DM population in LAC.

Use of Machine Learning Approaches in Clinical Epidemiological Research of Diabetes

PURPOSE OF REVIEW

Machine learning approaches-which seek to predict outcomes or classify patient features by recognizing patterns in large datasets-are increasingly applied to clinical epidemiology research on diabetes. Given its novelty and emergence in fields outside of biomedical research, machine learning terminology, techniques, and research findings may be unfamiliar to diabetes researchers. Our aim was to present the use of machine learning approaches in an approachable way, drawing from clinical epidemiological research in diabetes published from 1 Jan 2017 to 1 June 2020.

RECENT FINDINGS

Machine learning approaches using tree-based learners-which produce decision trees to help guide clinical interventions-frequently have higher sensitivity and specificity than traditional regression models for risk prediction. Machine learning approaches using neural networking and "deep learning" can be applied to medical image data, particularly for the identification and staging of diabetic retinopathy and skin ulcers. Among the machine learning approaches reviewed, researchers identified new strategies to develop standard datasets for rigorous comparisons across older and newer approaches, methods to illustrate how a machine learner was treating underlying data, and approaches to improve the transparency of the machine learning process. Machine learning approaches have the potential to improve risk stratification and outcome prediction for clinical epidemiology applications. Achieving this potential would be facilitated by use of universal open-source datasets for fair comparisons. More work remains in the application of strategies to communicate how the machine learners are generating their predictions.

A personalised screening strategy for diabetic retinopathy: a cost-effectiveness perspective

AIMS/HYPOTHESIS

In this study we examined the cost-effectiveness of three different screening strategies for diabetic retinopathy: using a personalised adaptive model, annual screening (fixed intervals), and the current Dutch guideline (stratified based on previous retinopathy grade).

METHODS

For each individual, optimal diabetic retinopathy screening intervals were determined, using a validated risk prediction model. Observational data (1998-2017) from the Hoorn Diabetes Care System cohort of people with type 2 diabetes were used (n = 5514). The missing values of retinopathy grades were imputed using two scenarios of slow and fast sight-threatening retinopathy (STR) progression. By comparing the model-based screening intervals to observed time to develop STR, the number of delayed STR diagnoses was determined. Costs were calculated using the healthcare perspective and the societal perspective. Finally, outcomes and costs were compared for the different screening strategies.

RESULTS

For the fast STR progression scenario, personalised screening resulted in 11.6% more delayed STR diagnoses and €11.4 less costs per patient compared to annual screening from a healthcare perspective. The personalised screening model performed better in terms of timely diagnosis of STR (8.8% less delayed STR diagnosis) but it was slightly more expensive (€1.8 per patient from a healthcare perspective) than the Dutch guideline strategy.

CONCLUSIONS/INTERPRETATION

The personalised diabetic retinopathy screening model is more cost-effective than the Dutch guideline screening strategy. Although the personalised screening strategy was less effective, in terms of timely diagnosis of STR patients, than annual screening, the number of delayed STR diagnoses is low and the cost saving is considerable. With around one million people with type 2 diabetes in the Netherlands, implementing this personalised model could save €11.4 million per year compared with annual screening, at the cost of 658 delayed STR diagnoses with a maximum delayed time to diagnosis of 48 months.