Personalized risk-based screening for diabetic retinopathy: A multivariate approach versus the use of stratification rules

Predicting 1, 2 and 3 year emergent referable diabetic retinopathy and maculopathy using deep learning

BACKGROUND

Predicting diabetic retinopathy (DR) progression could enable individualised screening with prompt referral for high-risk individuals for sight-saving treatment, whilst reducing screening burden for low-risk individuals. We developed and validated deep learning systems (DLS) that predict 1, 2 and 3 year emergent referable DR and maculopathy using risk factor characteristics (tabular DLS), colour fundal photographs (image DLS) or both (multimodal DLS).

METHODS

From 162,339 development-set eyes from south-east London (UK) diabetic eye screening programme (DESP), 110,837 had eligible longitudinal data, with the remaining 51,502 used for pretraining. Internal and external (Birmingham DESP, UK) test datasets included 27,996, and 6928 eyes respectively.

RESULTS

Internal multimodal DLS emergent referable DR, maculopathy or either area-under-the receiver operating characteristic (AUROC) were 0.95 (95% CI: 0.92-0.98), 0.84 (0.82-0.86), 0.85 (0.83-0.87) for 1 year, 0.92 (0.87-0.96), 0.84 (0.82-0.87), 0.85 (0.82-0.87) for 2 years, and 0.85 (0.80-0.90), 0.79 (0.76-0.82), 0.79 (0.76-0.82) for 3 years. External multimodal DLS emergent referable DR, maculopathy or either AUROC were 0.93 (0.88-0.97), 0.85 (0.80-0.89), 0.85 (0.76-0.85) for 1 year, 0.93 (0.89-0.97), 0.79 (0.74-0.84), 0.80 (0.76-0.85) for 2 years, and 0.91 (0.84-0.98), 0.79 (0.74-0.83), 0.79 (0.74-0.84) for 3 years.

CONCLUSIONS

Multimodal and image DLS performance is significantly better than tabular DLS at all intervals. DLS accurately predict 1, 2 and 3 year emergent referable DR and referable maculopathy using colour fundal photographs, with additional risk factor characteristics conferring improvements in prognostic performance. Proposed DLS are a step towards individualised risk-based screening, whereby AI-assistance allows high-risk individuals to be closely monitored while reducing screening burden for low-risk individuals.

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.

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.

Development and validation of a risk prediction model for diabetic retinopathy in type 2 diabetic patients

To establish a risk prediction model and make individualized assessment for the susceptible diabetic retinopathy (DR) population in type 2 diabetic mellitus (T2DM) patients. According to the retrieval strategy, inclusion and exclusion criteria, the relevant meta-analyses on DR risk factors were searched and evaluated. The pooled odds ratio (OR) or relative risk (RR) of each risk factor was obtained and calculated for β coefficients using logistic regression (LR) model. Besides, an electronic patient-reported outcome questionnaire was developed and 60 cases of DR and non-DR T2DM patients were investigated to validate the developed model. Receiver operating characteristic curve (ROC) was drawn to verify the prediction accuracy of the model. After retrieving, eight meta-analyses with a total of 15,654 cases and 12 risk factors associated with the onset of DR in T2DM, including weight loss surgery, myopia, lipid-lowing drugs, intensive glucose control, course of T2DM, glycated hemoglobin (HbA1c), fasting plasma glucose, hypertension, gender, insulin treatment, residence, and smoking were included for LR modeling. These factors, followed by the respective β coefficient was bariatric surgery (− 0.942), myopia (− 0.357), lipid-lowering drug follow-up < 3y (− 0.994), lipid-lowering drug follow-up > 3y (− 0.223), course of T2DM (0.174), HbA1c (0.372), fasting plasma glucose (0.223), insulin therapy (0.688), rural residence (0.199), smoking (− 0.083), hypertension (0.405), male (0.548), intensive glycemic control (− 0.400) with constant term α (− 0.949) in the constructed model. The area under receiver operating characteristic curve (AUC) of the model in the external validation was 0.912. An application was presented as an example of use. In conclusion, the risk prediction model of DR is developed, which makes individualized assessment for the susceptible DR population feasible and needs to be further verified with large sample size application.

Predictive model for diabetic retinopathy under limited medical resources: A multicenter diagnostic study

Background

Comprehensive eye examinations for diabetic retinopathy is poorly implemented in medically underserved areas. There is a critical need for a widely available and economical tool to aid patient selection for priority retinal screening. We investigated the possibility of a predictive model for retinopathy identification using simple parameters.

Methods

Clinical data were retrospectively collected from 4, 159 patients with diabetes admitted to five tertiary hospitals. Independent predictors were identified by univariate analysis and least absolute shrinkage and selection operator (LASSO) regression, and a nomogram was developed based on a multivariate logistic regression model. The validity and clinical practicality of this nomogram were assessed using concordance index (C-index), area under the receiver operating characteristic curve (AUROC), calibration curves, decision curve analysis (DCA), and clinical impact curves (CIC).

Results

The predictive factors in the multivariate model included the duration of diabetes, history of hypertension, and cardiovascular disease. The three-variable model displayed medium prediction ability with an AUROC of 0.722 (95%CI 0.696-0.748) in the training set, 0.715 (95%CI 0.670-0.754) in the internal set, and 0.703 (95%CI 0.552-0.853) in the external dataset. DCA showed that the threshold probability of DR in diabetic patients was 17-55% according to the nomogram, and CIC also showed that the nomogram could be applied clinically if the risk threshold exceeded 30%. An operation interface on a webpage (https://cqmuxss.shinyapps.io/dr_tjj/) was built to improve the clinical utility of the nomogram.

Conclusions

The predictive model developed based on a minimal amount of clinical data available to diabetic patients with restricted medical resources could help primary healthcare practitioners promptly identify potential retinopathy.

Fast approximate inference for multivariate longitudinal data

Collecting information on multiple longitudinal outcomes is increasingly common in many clinical settings. In many cases, it is desirable to model these outcomes jointly. However, in large data sets, with many outcomes, computational burden often prevents the simultaneous modeling of multiple outcomes within a single model. We develop a mean field variational Bayes algorithm, to jointly model multiple Gaussian, Poisson, or binary longitudinal markers within a multivariate generalized linear mixed model. Through simulation studies and clinical applications (in the fields of sight threatening diabetic retinopathy and primary biliary cirrhosis), we demonstrate substantial computational savings of our approximate approach when compared to a standard Markov Chain Monte Carlo, while maintaining good levels of accuracy of model parameters.

Optimal Frequency of Retinopathy Screening in Adolescents With Type 1 Diabetes: Markov Modeling Approach Based on 30 Years of Data

OBJECTIVE

Current guidelines recommend biennial diabetic retinopathy (DR) screening commencing at the age of 11 years and after 2-5 years' duration of type 1 diabetes. Growing evidence suggests less frequent screening may be feasible.

RESEARCH DESIGN AND METHODS

Prospective data were collected from 2,063 youth with type 1 diabetes who were screened two or more times between 1990 and 2019. Baseline (mean ± SD) age was 13.3 ± 1.8 years, HbA1c was 8.6 ± 1.3% (70.1 ± 14.7 mmol/mol), diabetes duration was 5.6 ± 2.8 years, and follow-up time was 4.8 ± 2.8 years. DR was manually graded from 7-field retinal photographs using the Early Treatment Diabetic Retinopathy Study (ETDRS) scale. Markov chain was used to calculate probabilities of DR change over time and hazard ratio (HR) of DR stage transition.

RESULTS

The incidence of moderate nonproliferative DR (MNPDR) or worse was 8.6 per 1,000 patient-years. Probabilities of transition to this state after a 3-year interval were from no DR, 1.3%; from minimal DR, 5.1%; and from mild DR, 22.2%, respectively. HRs (95% CIs) for transition per 1% current HbA1c increase were 1.23 (1.16-1.31) from no DR to minimal NPDR, 1.12 (1.03-1.23) from minimal to mild NPDR, and 1.28 (1.13-1.46) from mild to MNPDR or worse. HbA1c alone explained 27% of the transitions between no retinopathy and MNPDR or worse. The addition of diabetes duration into the model increased this value to 31% (P = 0.03). Risk was also increased by female sex and higher attained age.

CONCLUSIONS

These results support less frequent DR screening in youth with type 1 diabetes without DR and short duration. Although DR progression to advanced stages is generally slow, higher HbA1c greatly accelerates it.

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.

Multi-cohort and longitudinal Bayesian clustering study of stage and subtype in Alzheimer's disease

Understanding Alzheimer's disease (AD) heterogeneity is important for understanding the underlying pathophysiological mechanisms of AD. However, AD atrophy subtypes may reflect different disease stages or biologically distinct subtypes. Here we use longitudinal magnetic resonance imaging data (891 participants with AD dementia, 305 healthy control participants) from four international cohorts, and longitudinal clustering to estimate differential atrophy trajectories from the age of clinical disease onset. Our findings (in amyloid-β positive AD patients) show five distinct longitudinal patterns of atrophy with different demographical and cognitive characteristics. Some previously reported atrophy subtypes may reflect disease stages rather than distinct subtypes. The heterogeneity in atrophy rates and cognitive decline within the five longitudinal atrophy patterns, potentially expresses a complex combination of protective/risk factors and concomitant non-AD pathologies. By alternating between the cross-sectional and longitudinal understanding of AD subtypes these analyses may allow better understanding of disease heterogeneity.

Prediction models of diabetes complications: a scoping review

BACKGROUND

Diabetes often places a large burden on people with diabetes (hereafter 'patients') and the society, that is, in part attributable to its complications. However, evidence from models predicting diabetes complications in patients remains unclear. With the collaboration of patient partners, we aimed to describe existing prediction models of physical and mental health complications of diabetes.

METHODS

Building on existing frameworks, we systematically searched for studies in Ovid-Medline and Embase. We included studies describing prognostic prediction models that used data from patients with pre-diabetes or any type of diabetes, published between 2000 and 2020. Independent reviewers screened articles, extracted data and narratively synthesised findings using established reporting standards.

RESULTS

Overall, 78 studies reported 260 risk prediction models of cardiovascular complications (n=42 studies), mortality (n=16), kidney complications (n=14), eye complications (n=10), hypoglycaemia (n=8), nerve complications (n=3), cancer (n=2), fracture (n=2) and dementia (n=1). Prevalent complications deemed important by patients such as amputation and mental health were poorly or not at all represented. Studies primarily analysed data from older people with type 2 diabetes (n=54), with little focus on pre-diabetes (n=0), type 1 diabetes (n=8), younger (n=1) and racialised people (n=10). Per complication, predictors vary substantially between models. Studies with details of calibration and discrimination mostly exhibited good model performance.

CONCLUSION

This rigorous knowledge synthesis provides evidence of gaps in the landscape of diabetes complication prediction models. Future studies should address unmet needs for analyses of complications n> and among patient groups currently under-represented in the literature and should consistently report relevant statistics. SCOPING REVIEW REGISTRATION: https://osf.io/fjubt/.

Prognostic models of diabetic microvascular complications: a systematic review and meta-analysis

BACKGROUND

Many prognostic models of diabetic microvascular complications have been developed, but their performances still varies. Therefore, we conducted a systematic review and meta-analysis to summarise the performances of the existing models.

METHODS

Prognostic models of diabetic microvascular complications were retrieved from PubMed and Scopus up to 31 December 2020. Studies were selected, if they developed or internally/externally validated models of any microvascular complication in type 2 diabetes (T2D).

RESULTS

In total, 71 studies were eligible, of which 32, 30 and 18 studies initially developed prognostic model for diabetic retinopathy (DR), chronic kidney disease (CKD) and end stage renal disease (ESRD) with the number of derived equations of 84, 96 and 51, respectively. Most models were derived-phases, some were internal and external validations. Common predictors were age, sex, HbA1c, diabetic duration, SBP and BMI. Traditional statistical models (i.e. Cox and logit regression) were mostly applied, otherwise machine learning. In cohorts, the discriminative performance in derived-logit was pooled with C statistics of 0.82 (0.73‑0.92) for DR and 0.78 (0.74‑0.83) for CKD. Pooled Cox regression yielded 0.75 (0.74‑0.77), 0.78 (0.74‑0.82) and 0.87 (0.84‑0.89) for DR, CKD and ESRD, respectively. External validation performances were sufficiently pooled with 0.81 (0.78‑0.83), 0.75 (0.67‑0.84) and 0.87 (0.85‑0.88) for DR, CKD and ESRD, respectively.

CONCLUSIONS

Several prognostic models were developed, but less were externally validated. A few studies derived the models by using appropriate methods and were satisfactory reported. More external validations and impact analyses are required before applying these models in clinical practice.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO CRD42018105287.

Trends in diabetic retinopathy screening attendance and associations with vision impairment attributable to diabetes in a large nationwide cohort

AIMS

To investigate diabetic retinopathy screening attendance and trends in certified vision impairment caused by diabetic eye disease.

METHODS

This was a retrospective study of attendance in three urban UK diabetic eye screening programmes in England. A survival analysis was performed to investigate time from diagnosis to first screen by age and sex. Logistic regression analysis of factors influencing screening attendance during a 15-month reporting period was conducted, as well as analysis of new vision impairment certifications (Certificate of Vision Impairment) in England and Wales from 2009 to 2019.

RESULTS

Of those newly registered in the Routine Digital Screening pathway (n = 97 048), 80% attended screening within the first 12 months and 88% by 36 months. Time from registration to first eye screening was longer for people aged 18-34 years, and 20% were unscreened after 3 years. Delay in first screen was associated with increased risk of referable retinopathy. Although 95% of participants (n = 291 296) attended during the 15-month reporting period, uptake varied considerably. Younger age, social deprivation, ethnicity and duration of diabetes were independent predictors of non-attendance and referable retinopathy. Although the last 10 years has seen an overall reduction in vision impairment certification attributable to diabetic eye disease, the incidence of vision impairment in those aged <35 years was unchanged.

CONCLUSIONS

Whilst the majority of participants are screened in a timely manner, there is considerable variation in uptake. Young adults, have sub-optimal attendance, and levels of vision impairment in this population have not changed over the last 10 years. There is an urgent need to explore barriers to/enablers of attendance in this group to inform policy initiatives and tailored interventions to address this issue.

Safety and cost-effectiveness of individualised screening for diabetic retinopathy: the ISDR open-label, equivalence RCT

AIMS/HYPOTHESIS

Using variable diabetic retinopathy screening intervals, informed by personal risk levels, offers improved engagement of people with diabetes and reallocation of resources to high-risk groups, while addressing the increasing prevalence of diabetes. However, safety data on extending screening intervals are minimal. The aim of this study was to evaluate the safety and cost-effectiveness of individualised, variable-interval, risk-based population screening compared with usual care, with wide-ranging input from individuals with diabetes.

METHODS

This was a two-arm, parallel-assignment, equivalence RCT (minimum 2 year follow-up) in individuals with diabetes aged 12 years or older registered with a single English screening programme. Participants were randomly allocated 1:1 at baseline to individualised screening at 6, 12 or 24 months for those at high, medium and low risk, respectively, as determined at each screening episode by a risk-calculation engine using local demographic, screening and clinical data, or to annual screening (control group). Screening staff and investigators were observer-masked to allocation and interval. Data were collected within the screening programme. The primary outcome was attendance (safety). A secondary safety outcome was the development of sight-threatening diabetic retinopathy. Cost-effectiveness was evaluated within a 2 year time horizon from National Health Service and societal perspectives.

RESULTS

A total of 4534 participants were randomised. After withdrawals, there were 2097 participants in the individualised screening arm and 2224 in the control arm. Attendance rates at first follow-up were equivalent between the two arms (individualised screening 83.6%; control arm 84.7%; difference -1.0 [95% CI -3.2, 1.2]), while sight-threatening diabetic retinopathy detection rates were non-inferior in the individualised screening arm (individualised screening 1.4%, control arm 1.7%; difference -0.3 [95% CI -1.1, 0.5]). Sensitivity analyses confirmed these findings. No important adverse events were observed. Mean differences in complete case quality-adjusted life-years (EuroQol Five-Dimension Questionnaire, Health Utilities Index Mark 3) did not significantly differ from zero; multiple imputation supported the dominance of individualised screening. Incremental cost savings per person with individualised screening were £17.34 (95% CI 17.02, 17.67) from the National Health Service perspective and £23.11 (95% CI 22.73, 23.53) from the societal perspective, representing a 21% reduction in overall programme costs. Overall, 43.2% fewer screening appointments were required in the individualised arm.

CONCLUSIONS/INTERPRETATION

Stakeholders involved in diabetes care can be reassured by this study, which is the largest ophthalmic RCT in diabetic retinopathy screening to date, that extended and individualised, variable-interval, risk-based screening is feasible and can be safely and cost-effectively introduced in established systematic programmes. Because of the 2 year time horizon of the trial and the long time frame of the disease, robust monitoring of attendance and retinopathy rates should be included in any future implementation.

TRIAL REGISTRATION

ISRCTN 87561257 FUNDING: The study was funded by the UK National Institute for Health Research. Graphical abstract.

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.

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

AIMS/HYPOTHESIS

The aims of this study were to identify all published prognostic models predicting retinopathy risk applicable to people with type 2 diabetes, to assess their quality and accuracy, and to validate their predictive accuracy in a head-to-head comparison using an independent type 2 diabetes cohort.

METHODS

A systematic search was performed in PubMed and Embase in December 2019. Studies that met the following criteria were included: (1) the model was applicable in type 2 diabetes; (2) the outcome was retinopathy; and (3) follow-up was more than 1 year. Screening, data extraction (using the checklist for critical appraisal and data extraction for systemic reviews of prediction modelling studies [CHARMS]) and risk of bias assessment (by prediction model risk of bias assessment tool [PROBAST]) were performed independently by two reviewers. Selected models were externally validated in the large Hoorn Diabetes Care System (DCS) cohort in the Netherlands. Retinopathy risk was calculated using baseline data and compared with retinopathy incidence over 5 years. Calibration after intercept adjustment and discrimination (Harrell's C statistic) were assessed.

RESULTS

Twelve studies were included in the systematic review, reporting on 16 models. Outcomes ranged from referable retinopathy to blindness. Discrimination was reported in seven studies with C statistics ranging from 0.55 (95% CI 0.54, 0.56) to 0.84 (95% CI 0.78, 0.88). Five studies reported on calibration. Eight models could be compared head-to-head in the DCS cohort (N = 10,715). Most of the models underestimated retinopathy risk. Validating the models against different severities of retinopathy, C statistics ranged from 0.51 (95% CI 0.49, 0.53) to 0.89 (95% CI 0.88, 0.91).

CONCLUSIONS/INTERPRETATION

Several prognostic models can accurately predict retinopathy risk in a population-based type 2 diabetes cohort. Most of the models include easy-to-measure predictors enhancing their applicability. Tailoring retinopathy screening frequency based on accurate risk predictions may increase the efficiency and cost-effectiveness of diabetic retinopathy care.

REGISTRATION

PROSPERO registration ID CRD42018089122.

Advances in the treatment of diabetic retinopathy

As the diabetes epidemic in the United States continues to worsen, so too does the prevalence of diabetic retinopathy (DR). DR is divided broadly into nonproliferative and proliferative stages, with or without vision-threatening macular edema. Progression to proliferative DR is associated with vision loss that is often irreparable, and a rapid decline in health-related quality of life. Vascular endothelial growth factor (VEGF)-A is upregulated in the diabetic eye, and has been identified as a key driver of DR pathogenesis. With this perspective, we review the published phase III clinical trial data of anti-VEGF therapies approved for the treatment of DR in the United States. Using the Early Treatment Diabetic Retinopathy Study Diabetic Retinopathy Severity Scale, in which an improvement of ≥2 steps is considered clinically significant, approximately one-third of patients with DR and macular edema experience this level of improvement after 1 year of treatment with either ranibizumab or aflibercept. The rates of clinically significant DR improvement with ranibizumab could be twice that in the subgroup of patients with moderately severe or severe nonproliferative DR and macular edema. These clinical trial data indicate that intraocular inhibition of VEGF is a rational approach for the management of DR.

Personalized risk-based screening for diabetic retinopathy: A multivariate approach versus the use of stratification rules

AIMS

To evaluate our proposed multivariate approach to identify patients who will develop sight-threatening diabetic retinopathy (STDR) within a 1-year screen interval, and explore the impact of simple stratification rules on prediction.

MATERIALS AND METHODS

A 7-year dataset (2009-2016) from people with diabetes (PWD) was analysed using a novel multivariate longitudinal discriminant approach. Level of diabetic retinopathy, assessed from routine digital screening photographs of both eyes, was jointly modelled using clinical data collected over time. Simple stratification rules based on retinopathy level were also applied and compared with the multivariate discriminant approach.

RESULTS

Data from 13 103 PWD (49 520 screening episodes) were analysed. The multivariate approach accurately predicted whether patients developed STDR or not within 1 year from the time of prediction in 84.0% of patients (95% confidence interval [CI] 80.4-89.7), compared with 56.7% (95% CI 55.5-58.0) and 79.7% (95% CI 78.8-80.6) achieved by the two stratification rules. While the stratification rules detected up to 95.2% (95% CI 92.2-97.6) of the STDR cases (sensitivity) only 55.6% (95% CI 54.5-56.7) of patients who did not develop STDR were correctly identified (specificity), compared with 85.4% (95% CI 80.4-89.7%) and 84.0% (95% CI 80.7-87.6%), respectively, achieved by the multivariate risk model.

CONCLUSIONS

Accurate prediction of progression to STDR in PWD can be achieved using a multivariate risk model whilst also maintaining desirable specificity. While simple stratification rules can achieve good levels of sensitivity, the present study indicates that their lower specificity (high false-positive rate) would therefore necessitate a greater frequency of eye examinations.