Individualised variable-interval risk-based screening for sight-threatening diabetic retinopathy: the Liverpool Risk Calculation Engine

Initial Retinal Nerve Fiber Layer Loss and Risk of Diabetic Retinopathy Over a Four-Year Period

Purpose

The purpose of this study was to investigate whether the rapid rate of peripapillary retinal nerve fiber layer (pRNFL) thinning in short-term is associated with the future risk of developing diabetic retinopathy (DR).

Methods

This prospective cohort study utilized 4-year follow-up data from the Guangzhou Diabetic Eye Study. The pRNFL thickness was measured by optical coherence tomography (OCT). DR was graded by seven-field fundus photography after dilation of the pupil. Correlations between pRNFL thinning rate and DR were analyzed using logistic regression. The additive predictive value of the prediction model was assessed using the C-index, net reclassification index (NRI), and integrated discriminant improvement index (IDI).

Results

A total of 1012 patients with diabetes (1012 eyes) without DR at both baseline and 1-year follow-up were included in this study. Over the 4-year follow-up, 132 eyes (13%) developed DR. After adjusting for confounding factors, a faster rate of initial pRNFL thinning was significantly associated with the risk of DR (odds ratio per standard deviation [SD] decrease = 1.15, 95% confidence interval [CI] = 1.08 to 1.23, P < 0.001). Incorporating either the baseline pRNFL thickness or its thinning rate into conventional prediction models significantly improved the discriminatory power. Adding the rate of pRNFL thinning further enhanced the discriminative power compared with models with only baseline pRNFL thickness (C-index increased from 0.685 to 0.731, P = 0.040). The IDI and NRI were 0.114 and 0.463, respectively (P < 0.001).

Conclusions

The rate of initial pRNFL thinning was associated with DR occurrence and improved discriminatory power of traditional predictive models. This provides new insights into the management and screening of DR.

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.

Referable Diabetic Retinopathy Prediction Algorithm Applied to a Population of 120,389 Type 2 Diabetics over 11 Years Follow-Up

(1) Background: Although DR screening is effective, one of its most significant problems is a lack of attendance. The aim of the present study was to demonstrate the effectiveness of our algorithm in predicting the development of any type of DR and referable DR. (2) Methods: A retrospective study with an 11-year follow-up of a population of 120,389 T2DM patients was undertaken. (3) Results: Applying the results of the algorithm showed an AUC of 0.93 (95% CI, 0.92-0.94) for any DR and 0.90 (95% CI, 0.89-0.91) for referable DR. Therefore, we achieved a promising level of agreement when applying our algorithm. (4) Conclusions: The algorithm is useful for predicting which patients may develop referable forms of DR and also any type of DR. This would allow a personalized screening plan to be drawn up for each patient.

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.

Comprehensive Factors for Predicting the Complications of DiabetesMellitus: A Systematic Review

BACKGROUND

This article focuses on extracting a standard feature set for predicting the complications of diabetes mellitus by systematically reviewing the literature. It is conducted and reported by following the guidelines of PRISMA, a well-known systematic review and meta-analysis method. The research articles included in this study are extracted using the search engine "Web of Science" over eight years. The most common complications of diabetes, diabetic neuropathy, retinopathy, nephropathy, and cardiovascular diseases are considered in the study.

METHOD

The features used to predict the complications are identified and categorised by scrutinising the standards of electronic health records.

RESULT

Overall, 102 research articles have been reviewed, resulting in 59 frequent features being identified. Nineteen attributes are recognised as a standard in all four considered complications, which are age, gender, ethnicity, weight, height, BMI, smoking history, HbA1c, SBP, eGFR, DBP, HDL, LDL, total cholesterol, triglyceride, use of insulin, duration of diabetes, family history of CVD, and diabetes. The existence of a well-accepted and updated feature set for health analytics models to predict the complications of diabetes mellitus is a vital and contemporary requirement. A widely accepted feature set is beneficial for benchmarking the risk factors of complications of diabetes.

CONCLUSION

This study is a thorough literature review to provide a clear state of the art for academicians, clinicians, and other stakeholders regarding the risk factors and their importance.

A systematic review of diabetic retinopathy screening intervals

The current evidence on whether annual diabetic retinopathy (DR) screening intervals can be extended was reviewed. A systematic review protocol was followed (PROSPERO ID: CRD42022359590). Original longitudinal articles that specifically assessed DR screening intervals were in English and collected data after 2000 were included. Two reviewers independently conducted the search and reviewed the articles for quality and relevant information. The heterogeneity of the data meant that a meta-analysis was not appropriate. Twelve publications were included. Studies were of good quality and many used data from DR screening programs. Studies fit into three categories; those that assessed specific DR screening intervals, those that determined optimal DR screening intervals and those that developed/assessed DR screening risk equations. For those with type 2 diabetes, extending screening intervals to 3- to 4-yearly in those with no baseline DR appeared safe. DR risk equations considered clinical factors and allocated those at lower risk of DR progression screening intervals of up to five years. Those with baseline DR or type 1 diabetes appeared to have a higher risk of progression to STDR and needed more frequent screening. DR screening intervals can be extended to 3-5 yearly in certain circumstances. These include patients with type 2 diabetes and no current DR, and those who have optimal management of other risk factors such as glucose and blood pressure.

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.

Quantification of risk factors for diabetic retinopathy progression

AIMS

To determine the importance of blood sugar control, blood pressure, and other key systemic factors on the risk of progression from no retinopathy to various stages of diabetic retinopathy.

METHODS

Restrospective cohort analysis of patients (N = 99, 280) in the Kaiser Permanente Northern California healthcare system with a baseline retina photographic screening showing no evidence of retinopathy and a minimum follow-up surveillance period of 3 years from 2008 to 2019. We gathered longitudinal data on diabetic retinopathy progression provided by subsequent screening fundus photographs and data captured in the electronic medical record over a mean surveillance of 7.3 ± 2.2 (mean ± SD) years. Progression from an initial state of no diabetic retinopathy to any of four outcomes was determined: (1) any incident retinopathy, (2) referable (moderate or worse) retinopathy, (3) diabetic macular edema, and (4) proliferative diabetic retinopathy. Multiple predictors, including age, race, gender, glycosylated hemoglobin (HbA1c), systolic blood pressure (SBP), cholesterol, chronic renal disease, and type of diabetes were investigated.

RESULTS

Among modifiable risk factors, the average HbA1c had the strongest impact on the progression of diabetic retinopathy, followed by average SBP control and total cholesterol. Patients with an average HbA1c of 10.0% or greater (≥ 97 mmol/mol) had a risk ratio of 5.72 (95% CI 5.44-6.02) for progression to any retinopathy, 18.84 (95% CI 17.25-20.57) for referable retinopathy, 22.85 (95% CI 18.87-27.68) for diabetic macular edema, and 25.96 (95% CI 18.75-36.93) for proliferative diabetic retinopathy compared to those with an average HbA1c of 7.0% (53 mmol/mol) or less. Non-white patients generally had a higher risk of progression to all forms of diabetic retinopathy, while Asian patients were less likely to develop diabetic macular edema (HR 0.76, 95% CI 0.66-0.87).

CONCLUSIONS

We confirm the critical importance of glucose control as measured by HbA1c on the risk of development of diabetic retinopathy.

Prognostic factors for the development and progression of proliferative diabetic retinopathy in people with diabetic retinopathy

BACKGROUND

Diabetic retinopathy (DR) is characterised by neurovascular degeneration as a result of chronic hyperglycaemia. Proliferative diabetic retinopathy (PDR) is the most serious complication of DR and can lead to total (central and peripheral) visual loss. PDR is characterised by the presence of abnormal new blood vessels, so-called "new vessels," at the optic disc (NVD) or elsewhere in the retina (NVE). PDR can progress to high-risk characteristics (HRC) PDR (HRC-PDR), which is defined by the presence of NVD more than one-fourth to one-third disc area in size plus vitreous haemorrhage or pre-retinal haemorrhage, or vitreous haemorrhage or pre-retinal haemorrhage obscuring more than one disc area. In severe cases, fibrovascular membranes grow over the retinal surface and tractional retinal detachment with sight loss can occur, despite treatment. Although most, if not all, individuals with diabetes will develop DR if they live long enough, only some progress to the sight-threatening PDR stage.  OBJECTIVES: To determine risk factors for the development of PDR and HRC-PDR in people with diabetes and DR.

SEARCH METHODS

We searched the Cochrane Central Register of Controlled Trials (CENTRAL; which contains the Cochrane Eyes and Vision Trials Register; 2022, Issue 5), Ovid MEDLINE, and Ovid Embase. The date of the search was 27 May 2022. Additionally, the search was supplemented by screening reference lists of eligible articles. There were no restrictions to language or year of publication.  SELECTION CRITERIA: We included prospective or retrospective cohort studies and case-control longitudinal studies evaluating prognostic factors for the development and progression of PDR, in people who have not had previous treatment for DR. The target population consisted of adults (≥18 years of age) of any gender, sexual orientation, ethnicity, socioeconomic status, and geographical location, with non-proliferative diabetic retinopathy (NPDR) or PDR with less than HRC-PDR, diagnosed as per standard clinical practice. Two review authors independently screened titles and abstracts, and full-text articles, to determine eligibility; discrepancies were resolved through discussion. We considered prognostic factors measured at baseline and any other time points during the study and in any clinical setting. Outcomes were evaluated at three and eight years (± two years) or lifelong.  DATA COLLECTION AND ANALYSIS: Two review authors independently extracted data from included studies using a data extraction form that we developed and piloted prior to the data collection stage. We resolved any discrepancies through discussion. We used the Quality in Prognosis Studies (QUIPS) tool to assess risk of bias. We conducted meta-analyses in clinically relevant groups using a random-effects approach. We reported hazard ratios (HR), odds ratios (OR), and risk ratios (RR) separately for each available prognostic factor and outcome, stratified by different time points. Where possible, we meta-analysed adjusted prognostic factors. We evaluated the certainty of the evidence with an adapted version of the GRADE framework.   MAIN RESULTS: We screened 6391 records. From these, we identified 59 studies (87 articles) as eligible for inclusion. Thirty-five were prospective cohort studies, 22 were retrospective studies, 18 of which were cohort and six were based on data from electronic registers, and two were retrospective case-control studies. Twenty-three studies evaluated participants with type 1 diabetes (T1D), 19 with type 2 diabetes (T2D), and 17 included mixed populations (T1D and T2D). Studies on T1D included between 39 and 3250 participants at baseline, followed up for one to 45 years. Studies on T2D included between 100 and 71,817 participants at baseline, followed up for one to 20 years. The studies on mixed populations of T1D and T2D ranged from 76 to 32,553 participants at baseline, followed up for four to 25 years.  We found evidence indicating that higher glycated haemoglobin (haemoglobin A1c (HbA1c)) levels (adjusted OR ranged from 1.11 (95% confidence interval (CI) 0.93 to 1.32) to 2.10 (95% CI 1.64 to 2.69) and more advanced stages of retinopathy (adjusted OR ranged from 1.38 (95% CI 1.29 to 1.48) to 12.40 (95% CI 5.31 to 28.98) are independent risk factors for the development of PDR in people with T1D and T2D. We rated the evidence for these factors as of moderate certainty because of moderate to high risk of bias in the studies.  There was also some evidence suggesting several markers for renal disease (for example, nephropathy (adjusted OR ranged from 1.58 (95% CI not reported) to 2.68 (2.09 to 3.42), and creatinine (adjusted meta-analysis HR 1.61 (95% CI 0.77 to 3.36)), and, in people with T1D, age at diagnosis of diabetes (< 12 years of age) (standardised regression estimate 1.62, 95% CI 1.06 to 2.48), increased triglyceride levels (adjusted RR 1.55, 95% CI 1.06 to 1.95), and larger retinal venular diameters (RR 4.28, 95% CI 1.50 to 12.19) may increase the risk of progression to PDR. The certainty of evidence for these factors, however, was low to very low, due to risk of bias in the included studies, inconsistency (lack of studies preventing the grading of consistency or variable outcomes), and imprecision (wide CIs). There was no substantial and consistent evidence to support duration of diabetes, systolic or diastolic blood pressure, total cholesterol, low- (LDL) and high- (HDL) density lipoproteins, gender, ethnicity, body mass index (BMI), socioeconomic status, or tobacco and alcohol consumption as being associated with incidence of PDR. There was insufficient evidence to evaluate prognostic factors associated with progression of PDR to HRC-PDR.  AUTHORS' CONCLUSIONS: Increased HbA1c is likely to be associated with progression to PDR; therefore, maintaining adequate glucose control throughout life, irrespective of stage of DR severity, may help to prevent progression to PDR and risk of its sight-threatening complications. Renal impairment in people with T1D or T2D, as well as younger age at diagnosis of diabetes mellitus (DM), increased triglyceride levels, and increased retinal venular diameters in people with T1D may also be associated with increased risk of progression to PDR. Given that more advanced DR severity is associated with higher risk of progression to PDR, the earlier the disease is identified, and the above systemic risk factors are controlled, the greater the chance of reducing the risk of PDR and saving sight.

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.

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.

Real-world outcomes of a clinical decision support system for diabetic retinopathy in Spain

Objective

The aim of present study was to evaluate our clinical decision support system (CDSS) for predicting risk of diabetic retinopathy (DR). We selected randomly a real population of patients with type 2 diabetes (T2DM) who were attending our screening programme.

Methods and analysis

The sample size was 602 patients with T2DM randomly selected from those who attended the DR screening programme. The algorithm developed uses nine risk factors: current age, sex, body mass index (BMI), duration and treatment of diabetes mellitus (DM), arterial hypertension, Glicated hemoglobine (HbA1c), urine–albumin ratio and glomerular filtration.

Results

The mean current age of 67.03±10.91, and 272 were male (53.2%), and DM duration was 10.12±6.4 years, 222 had DR (35.8%). The CDSS was employed for 1 year. The prediction algorithm that the CDSS uses included nine risk factors: current age, sex, BMI, DM duration and treatment, arterial hypertension, HbA1c, urine–albumin ratio and glomerular filtration. The area under the curve (AUC) for predicting the presence of any DR achieved a value of 0.9884, the sensitivity of 98.21%, specificity of 99.21%, positive predictive value of 98.65%, negative predictive value of 98.95%, α error of 0.0079 and β error of 0.0179.

Conclusion

Our CDSS for predicting DR was successful when applied to a real population.

Cost-effectiveness of artificial intelligence screening for diabetic retinopathy in rural China

BACKGROUND

Diabetic retinopathy (DR) has become a leading cause of global blindness as a microvascular complication of diabetes. Regular screening of diabetic retinopathy is strongly recommended for people with diabetes so that timely treatment can be provided to reduce the incidence of visual impairment. However, DR screening is not well carried out due to lack of eye care facilities, especially in the rural areas of China. Artificial intelligence (AI) based DR screening has emerged as a novel strategy and show promising diagnostic performance in sensitivity and specificity, relieving the pressure of the shortage of facilities and ophthalmologists because of its quick and accurate diagnosis. In this study, we estimated the cost-effectiveness of AI screening for DR in rural China based on Markov model, providing evidence for extending use of AI screening for DR.

METHODS

We estimated the cost-effectiveness of AI screening and compared it with ophthalmologist screening in which fundus images are evaluated by ophthalmologists. We developed a Markov model-based hybrid decision tree to analyze the costs, effectiveness and incremental cost-effectiveness ratio (ICER) of AI screening strategies relative to no screening strategies and ophthalmologist screening strategies (dominated) over 35 years (mean life expectancy of diabetes patients in rural China). The analysis was conducted from the health system perspective (included direct medical costs) and societal perspective (included medical and nonmedical costs). Effectiveness was analyzed with quality-adjusted life years (QALYs). The robustness of results was estimated by performing one-way sensitivity analysis and probabilistic analysis.

RESULTS

From the health system perspective, AI screening and ophthalmologist screening had incremental costs of $180.19 and $215.05 but more quality-adjusted life years (QALYs) compared with no screening. AI screening had an ICER of $1,107.63. From the societal perspective which considers all direct and indirect costs, AI screening had an ICER of $10,347.12 compared with no screening, below the cost-effective threshold (1-3 times per capita GDP of Chinese in 2019).

CONCLUSIONS

Our analysis demonstrates that AI-based screening is more cost-effective compared with conventional ophthalmologist screening and holds great promise to be an alternative approach for DR screening in the rural area of China.

Identification of risk factors for targeted diabetic retinopathy screening to urgently decrease the rate of blindness in people with diabetes in India

PURPOSE

There is an exponential rise in the prevalence of diabetes mellitus (DM) in India. Ideally all people with DM should be periodically screening for diabetic retinopathy (DR) but is not practical with current infrastructure. An alternate strategy is to identify high-risk individuals with vision-threatening diabetic retinopathy (VTDR) for priority screening and treatment.

METHODS

We reanalyzed four population-based studies, conducted in South India between 2001 and 2010, and reclassified individuals above 40 years into known and newly diagnosed diabetes. Multiple regression analysis was done to identify risk factors in people with known and new DM.

RESULTS

The prevalence of DR in 44,599 subjects aged ≥40 years was 14.8% (18.4 and 4.7% in known and new DM, respectively), and the prevalence of VTDR was 5.1%. Higher risk factors of VTDR were older age >50 years, diabetes duration >5 years, and systolic blood pressure >140 mm Hg. Targeted screening of people with diabetes using high-risk criteria obtained from this study was able to detect 93.5% of all individuals with VTDR.

CONCLUSION

In a limited resource country like India, a high-risk group-based targeted screening of individuals with DM could be prioritized while continuing the current opportunistic screening till India adopts universal screening of all people with DM.

Incidence of sight-threatening diabetic retinopathy in an established urban screening programme: An 11-year cohort study

AIMS

Systematic annual screening to detect sight-threatening diabetic retinopathy (STDR) is established in the United Kingdom. We designed an observational cohort study to provide up-to-date data for policy makers and clinical researchers on incidence of key screening endpoints in people with diabetes attending one screening programme running for over 30 years.

METHODS

All people with diabetes aged ≥12 years registered with general practices in the Liverpool health district were offered inclusion. Data sources comprised: primary care (demographics, systemic risk factors), Liverpool Diabetes Eye Screening Programme (retinopathy grading), Hospital Eye Services (slit lamp biomicroscopy assessment of screen positives).

RESULTS

133,366 screening episodes occurred in 28,384 people over 11 years. Overall incidences were: screen positive 6.7% (95% CI 6.5-6.8), screen positive for retinopathy 3.1% (3.0-3.1), unassessable images 2.6% (2.5-2.7), other significant eye diseases 1.0% (1.0-1.1). 1.6% (1.6-1.7) had sight-threatening retinopathy confirmed by slit lamp biomicroscopy. The annual incidence of screen positive and screen positive for retinopathy showed consistent declines from 8.8%-10.6% and 4.4%-4.6% in 2007/09 to 4.4%-6.8% and 2.3%-2.9% in 2013/17, respectively. Rates of STDR (true positive) were consistently below 2% after 2008/09. Screen positive rates were higher in first time attenders (9.9% [9.4-10.2] vs. 6.1% [6.0-6.2]) in part due to ungradeable images (4.1% vs. 2.3%) and other eye disease (2.4% vs. 0.8%). 4.5% (3.9-5.2) of previous non-attenders had sight-threatening retinopathy. Compared with people with type 2 diabetes, those with type 1 disease demonstrated higher rates of screen positive (11.9% vs. 6.0%) and STDR (6.4% vs. 1.2%). Overall prevalence of any retinopathy was 27.2% (27.0-27.4).

CONCLUSIONS

In an established screening programme with a stable population screen, positive rates show a consistent fall over time to a low level. Of those who are screen positive, fewer than 50% are screen positive for diabetic retinopathy. Most are due to sight threatening maculopathy. The annual incidence of STDR is under 2% suggesting future work on redefining screen positive and supporting extended intervals for people at low risk. Higher rates of screen positive and STDR are seen in first time attenders. Those who have never attended for screening should be specifically targeted.

Associations with sight-threatening diabetic macular oedema among Indigenous adults with type 2 diabetes attending an Indigenous primary care clinic in remote Australia: a Centre of Research Excellence in Diabetic Retinopathy and Telehealth Eye and Associated Medical Services Network study

Objective

To identify factors associated with sight-threatening diabetic macular oedema (STDM) in Indigenous Australians attending an Indigenous primary care clinic in remote Australia.

Methods and analysis

A cross-sectional study design of retinopathy screening data and routinely-collected clinical data among 236 adult Indigenous participants with type 2 diabetes (35.6% men) set in one Indigenous primary care clinic in remote Australia. The primary outcome variable was STDM assessed from retinal images.

Results

Age (median (range)) was 48 (21–86) years, and known diabetes duration (median (range)) was 8.0 (0–24) years. Prevalence of STDM was high (14.8%) and similar in men and women. STDM was associated with longer diabetes duration (11.7 vs 7.9 years, respectively; p<0.001) and markers of renal impairment: abnormal estimated Glomerular Filtration Rate (eGFR) (62.9 vs 38.3%, respectively; p=0.007), severe macroalbuminuria (>300 mg/mmol) (20.6 vs 5.7%, respectively; p=0.014) and chronic kidney disease (25.7 vs 12.2%, respectively; p=0.035). Some clinical factors differed by sex: anaemia was more prevalent in women. A higher proportion of men were smokers, prescribed statins and had increased albuminuria. Men had higher blood pressure, but lower glycated Haemoglobin A1c (HbA1c) levels and body mass index, than women.

Conclusion

STDM prevalence was high and similar in men and women. Markers of renal impairment and longer diabetes duration were associated with STDM in this Indigenous primary care population. Embedded teleretinal screening, known diabetes duration-based risk stratification and targeted interventions may lower the prevalence of STDM in remote Indigenous primary care services.

Trial registration number

Australia and New Zealand Clinical Trials Register: ACTRN 12616000370404.

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.

Screening for Diabetic Retinopathy with Extended Intervals, Safe and Without Compromising Adherence: A Retrospective Cohort Study

INTRODUCTION

Screening for diabetic retinopathy (DR) prevents blindness through the early detection of sight-threatening retinal microvascular lesions that respond to timely local treatment. However, the provision of easy and regular access to DR screening programs is currently being challenged by the increasing prevalence of diabetes. One proposed solution is to extend the screening interval for patients at low risk for progression of retinopathy. To date, most providers of screening programs have hesitated to implement a strategy of extended intervals due to the lack of data on whether adherence and safety are compromised when retinal examinations occur less frequently. In the study reported here, we investigated adherence to the screening program and progression of retinopathy in patients with type 2 diabetes participating in a DR screening program with extended intervals.

METHODS

This was a retrospective study that included 1000 patients with type 2 diabetes mellitus who attended a screening program for DR. The patients were consecutively placed into a low-risk patient cohort with no retinopathy or into an intermediate-risk patient cohort with mild retinopathy (each cohort n = 500). Screening intervals were 36 months for the low-risk cohort and 18 months for the intermediate-risk cohort.

RESULTS

The 1000 subjects enrolled in the study had a median age of 68 (interquartile range 12) years and 60.4% were men. At the follow-up screening visit, data on 102 subjects were not included in the analysis of adherence rate due to death, severe systemic illness, other concurrent eye disease or migration. Among the 898 remaining subjects, adherence to the screening program was 93.7% (413/443) in the 36-month group and 98.3% (449/455) in the 18-month group (p < 0.0001). Non-adherence decreased with increasing age (odds ratio 0.92, 95% confidence interval 0.888-0.954, p = 0.0005). At follow-up, 65 subjects showed progression of retinopathy; none had worse than moderate retinopathy. Risk factors for DR and treatment for hyperglycemia, hypertension and hyperlipidemia were compared among subjects in the low-risk cohort: non-adherent subjects did not differ from their adherent counterparts without progression of DR, but the former had a shorter duration of diabetes and higher diastolic blood pressure than adherent subjects with progression of DR (4.5 vs. 7.5 years, p = 0.007; and 80 vs. 75 mmHg, p = 0.02, respectively).

CONCLUSION

The results suggest that screening DR at extended intervals can be achieved with high adherence rates without compromising patient safety. However, younger subjects and those at higher risk of progression may require extra attention.

Predictors for diabetic retinopathy progression-findings from nominal group technique and Evidence review

Objectives

Risk stratification is needed for patients referred to hospital eye services by Diabetic Eye Screening Programme UK. This requires a set of candidate predictors. The literature contains a large number of predictors. The objective of this research was to arrive at a small set of clinically important predictors for the outcome of the progression of diabetic retinopathy (DR). They need to be evidence based and readily available during the clinical consultation.

Methods and analysis

Initial list of predictors was obtained from a systematic review of prediction models. We sought the clinical expert opinion using a formal qualitative study design. A series of nominal group technique meetings to shorten the list and to rank the predictors for importance by voting were held with National Health Service hospital-based clinicians involved in caring for patients with DR in the UK. We then evaluated the evidence base for the selected predictors by critically appraising the evidence.

Results

The source list was presented at nominal group meetings (n=4), attended by 44 clinicians. Twenty-five predictors from the original list were ranked as important predictors and eight new predictors were proposed. Two additional predictors were retained after evidence check. Of these 35, 21 had robust supporting evidence in the literature condensed into a set of 19 predictors by categorising DR.

Conclusion

We identified a set of 19 clinically meaningful predictors of DR progression that can help stratify higher-risk patients referred to hospital eye services and should be considered in the development of an individual risk stratification model.

Study design

A qualitative study and evidence review.

Setting

Secondary eye care centres in North East, Midlands and South of England.

Cost-effectiveness of biennial screening for diabetes related retinopathy in people with type 1 and type 2 diabetes compared to annual screening

OBJECTIVE

Examine the health and economic impact of extending screening intervals in people with Type 2 diabetes (T2DM) and Type 1 diabetes (T1DM) without diabetes-related retinopathy (DR).

SETTING

Diabetic Eye Screening Wales (DESW).

STUDY DESIGN

Retrospective observational study with cost-utility analysis (CUA) and Decremental Cost-Effectiveness Ratios (DCER) study.

INTERVENTION

Biennial screening versus usual care (annual screening).

INPUTS

Anonymised data from DESW were linked to primary care data for people with two prior screening events with no DR. Transition probabilities for progression to DR were estimated based on a subset of 26,812 and 1232 people with T2DM and T1DM, respectively. DCER above £20,000 per QALY was considered cost-effective.

RESULTS

The base case analysis DCER results of £71,243 and £23,446 per QALY for T2DM and T1DM respectively at a 3.5% discount rate and £56,822 and £14,221 respectively when discounted at 1.5%. Diabetes management represented by the mean HbA_1c was 7.5% for those with T2DM and 8.7% for T1DM.

SENSITIVITY ANALYSIS

Extending screening to biennial based on HbA_1c, being the strongest predictor of progression of DR, at three levels of HbA_1c 6.5%, 8.0% and 9.5% lost one QALY saving the NHS £106,075; £58,653 and £31,626 respectively for T2DM and £94,696, £37,646 and £11,089 respectively for T1DM. In addition, extending screening to biennial based on the duration of diabetes > 6 years for T2DM per QALY lost, saving the NHS £54,106 and for 6-12 and > 12 years for T1DM saving £83,856, £23,446 and £13,340 respectively.

CONCLUSIONS

Base case and sensitivity analyses indicate biennial screening to be cost-effective for T2DM irrespective of HbA_1c and duration of diabetes. However, the uncertainty around the DCER indicates that annual screening should be maintained for those with T1DM especially when the HbA_1c exceeds 80 mmol/mol (9.5%) and duration of diabetes is greater than 12 years.

Personalising screening of sight-threatening diabetic retinopathy - qualitative evidence to inform effective implementation

BACKGROUND

Internationally, systematic screening for sight-threatening diabetic retinopathy (STDR) usually includes annual recall. Researchers and policy-makers support extending screening intervals, citing evidence from observational studies with low incidence rates. However, there is little research around the acceptability to people with diabetes (PWD) and health care professionals (HCP) about changing eye screening intervals.

METHODS

We conducted a qualitative study to explore issues surrounding acceptability and the barriers and enablers for changing from annual screening, using in-depth, semistructured interviews analysed using the constant comparative method. PWD were recruited from general practices and HCP from eye screening networks and related specialties in North West England using purposive sampling. Interviews were conducted prior to the commencement of and during a randomised controlled trial (RCT) comparing fixed annual with variable (6, 12 or 24 month) interval risk-based screening.

RESULTS

Thirty PWD and 21 HCP participants were interviewed prior to and 30 PWD during the parallel RCT. The data suggests that a move to variable screening intervals was generally acceptable in principle, though highlighted significant concerns and challenges to successful implementation. The current annual interval was recognised as unsustainable against a backdrop of increasing diabetes prevalence. There were important caveats attached to acceptability and a need for clear safeguards around: the safety and reliability of calculating screening intervals, capturing all PWD, referral into screening of PWD with diabetic changes regardless of planned interval. For PWD the 6-month interval was perceived positively as medical reassurance, and the 12-month seen as usual treatment. Concerns were expressed by many HCP and PWD that a 2-year interval was too lengthy and was risky for detecting STDR. There were also concerns about a negative effect upon PWD care and increasing non-attendance rates. Amongst PWD, there was considerable conflation and misunderstanding about different eye-related appointments within the health care system.

CONCLUSIONS

Implementing variable-interval screening into clinical practice is generally acceptable to PWD and HCP with important caveats, and misconceptions must be addressed. Clear safeguards against increasing non-attendance, loss of diabetes control and alternative referral pathways are required. For risk calculation systems to be safe, reliable monitoring and clear communication is required.

Applications of Artificial Intelligence for the Detection, Management, and Treatment of Diabetic Retinopathy

Rates of diabetic retinopathy (DR) and diabetic macular edema (DME), a common ocular complication of diabetes mellitus, are increasing worldwide. There is a substantial burden concerning the detection and management of this condition, particularly in low-resource settings, due to limitations such as the time, cost, and labor associated with current screening and treatment methods. Artificial intelligence (AI) is a modality of pattern recognition that has the potential to combat these limitations in a reliable and cost-effective way. This review explores the various applications of AI on the screening, management, and treatment of DR and DME. AI applications for detecting referable DR and DME have been the most thoroughly researched applications for this condition. While some studies exist using AI to stratify DR patients based on the risk of progression, predict treatment outcomes to anti-VEGF therapy, and explore the utilization of AI for clinical trials to develop new treatments for DR, further validation studies on larger datasets are warranted.

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.

Use of personalised risk-based screening schedules to optimise workload and sojourn time in screening programmes for diabetic retinopathy: A retrospective cohort study

BACKGROUND

National guidelines in most countries set screening intervals for diabetic retinopathy (DR) that are insufficiently informed by contemporary incidence rates. This has unspecified implications for interval disease risks (IDs) of referable DR, disparities in ID between groups or individuals, time spent in referable state before screening (sojourn time), and workload. We explored the effect of various screening schedules on these outcomes and developed an open-access interactive policy tool informed by contemporary DR incidence rates.

METHODS AND FINDINGS

Scottish Diabetic Retinopathy Screening Programme data from 1 January 2007 to 31 December 2016 were linked to diabetes registry data. This yielded 128,606 screening examinations in people with type 1 diabetes (T1D) and 1,384,360 examinations in people with type 2 diabetes (T2D). Among those with T1D, 47% of those without and 44% of those with referable DR were female, mean diabetes duration was 21 and 23 years, respectively, and mean age was 26 and 24 years, respectively. Among those with T2D, 44% of those without and 42% of those with referable DR were female, mean diabetes duration was 9 and 14 years, respectively, and mean age was 58 and 52 years, respectively. Individual probability of developing referable DR was estimated using a generalised linear model and was used to calculate the intervals needed to achieve various IDs across prior grade strata, or at the individual level, and the resultant workload and sojourn time. The current policy in Scotland-screening people with no or mild disease annually and moderate disease every 6 months-yielded large differences in ID by prior grade (13.2%, 3.6%, and 0.6% annually for moderate, mild, and no prior DR strata, respectively, in T1D) and diabetes type (2.4% in T1D and 0.6% in T2D overall). Maintaining these overall risks but equalising risk across prior grade strata would require extremely short intervals in those with moderate DR (1-2 months) and very long intervals in those with no prior DR (35-47 months), with little change in workload or average sojourn time. Changing to intervals of 12, 9, and 3 months in T1D and to 24, 9, and 3 months in T2D for no, mild, and moderate DR strata, respectively, would substantially reduce disparity in ID across strata and between diabetes types whilst reducing workload by 26% and increasing sojourn time by 2.3 months. Including clinical risk factor data gave a small but significant increment in prediction of referable DR beyond grade (increase in C-statistic of 0.013 in T1D and 0.016 in T2D, both p < 0.001). However, using this model to derive personalised intervals did not have substantial workload or sojourn time benefits over stratum-specific intervals. The main limitation is that the results are pertinent only to countries that share broadly similar rates of retinal disease and risk factor distributions to Scotland.

CONCLUSIONS

Changing current policies could reduce disparities in ID and achieve substantial reductions in workload within the range of IDs likely to be deemed acceptable. Our tool should facilitate more rational policy setting for screening.

Bimodal learning via trilogy of skip-connection deep networks for diabetic retinopathy risk progression identification

BACKGROUND

Diabetic Retinopathy (DR) is considered a pathology of retinal vascular complications, which stays in the top causes of vision impairment and blindness. Therefore, precisely inspecting its progression enables the ophthalmologists to set up appropriate next-visit schedule and cost-effective treatment plans. In the literature, existing work only makes use of numerical attributes in Electronic Medical Records (EMR) for acquiring such kind of DR-oriented knowledge through conventional machine learning techniques, which require an exhaustive job of engineering most impactful risk factors.

OBJECTIVE

In this paper, an approach of deep bimodal learning is introduced to leverage the performance of DR risk progression identification.

METHODS

In particular, we further involve valuable clinical information of fundus photography in addition to the aforementioned systemic attributes. Accordingly, a Trilogy of Skip-connection Deep Networks, namely Tri-SDN, is proposed to exhaustively exploit underlying relationships between the baseline and follow-up information of the fundus images and EMR-based attributes. Besides that, we adopt Skip-Connection Blocks as basis components of the Tri-SDN for making the end-to-end flow of signals more efficient during feedforward and backpropagation processes.

RESULTS

Through a 10-fold cross validation strategy on a private dataset of 96 diabetic mellitus patients, the proposed method attains superior performance over the conventional EMR-modality learning approach in terms of Accuracy (90.6%), Sensitivity (96.5%), Precision (88.7%), Specificity (82.1%), and Area Under Receiver Operating Characteristics (88.8%).

CONCLUSIONS

The experimental results show that the proposed Tri-SDN can combine features of different modalities (i.e., fundus images and EMR-based numerical risk factors) smoothly and effectively during training and testing processes, respectively. As a consequence, with impressive performance of DR risk progression recognition, the proposed approach is able to help the ophthalmologists properly decide follow-up schedule and subsequent treatment plans.

Individualised screening for diabetic retinopathy: the ISDR study-rationale, design and methodology for a randomised controlled trial comparing annual and individualised risk-based variable-interval screening

INTRODUCTION

Currently, all people with diabetes (PWD) aged 12 years and over in the UK are invited for screening for diabetic retinopathy (DR) annually. Resources are not increasing despite a 5% increase in the numbers of PWD nationwide each year. We describe the rationale, design and methodology for a randomised controlled trial (RCT) evaluating the safety, acceptability and cost-effectiveness of personalised variable-interval risk-based screening for DR. This is the first randomised trial of personalised screening for DR and the largest ophthalmic RCT in the UK.

METHODS AND ANALYSIS

PWD attending seven screening clinics in the Liverpool Diabetic Eye Screening Programme were recruited into a single site RCT with a 1:1 allocation to individualised risk-based variable-interval or annual screening intervals. A risk calculation engine developed for the trial estimates the probability that an individual will develop referable disease (screen positive DR) within the next 6, 12 or 24 months using demographic, retinopathy and systemic risk factor data from primary care and screening programme records. Dynamic, secure, real-time data connections have been developed. The primary outcome is attendance for follow-up screening. We will test for equivalence in attendance rates between the two arms. Secondary outcomes are rates and severity of DR, visual outcomes, cost-effectiveness and health-related quality of life. The required sample size was 4460 PWD. Recruitment is complete, and the trial is in follow-up.

ETHICS AND DISSEMINATION

Ethical approval was obtained from National Research Ethics Service Committee North West - Preston, reference 14/NW/0034. Results will be presented at international meetings and published in peer-reviewed journals. This pragmatic RCT will inform screening policy in the UK and elsewhere.

TRIAL REGISTRATION NUMBER

ISRCTN87561257; Pre-results.

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.

Prognostic prediction models for diabetic retinopathy progression: a systematic review

With the increasing incidence of diabetic retinopathy and its improved detection, there is increased demand for diabetic retinopathy treatment services. Prognostic prediction models have been used to optimise services but these were intended for early detection of sight-threatening retinopathy and are mostly used in diabetic retinopathy screening services. We wanted to look into the predictive ability and applicability of the existing models for the higher-risk patients referred into hospitals. We searched MEDLINE, EMBASE, COCHRANE CENTRAL, conference abstracts and reference lists of included publications for studies of any design using search terms related to diabetes, diabetic retinopathy and prognostic models. Search results were screened for relevance to the review question. Included studies had data extracted on model characteristics, predictive ability and validation. They were assessed for quality using criteria specified by PROBAST and CHARMS checklists, independently by two reviewers. Twenty-two articles reporting on 14 prognostic models (including four updates) met the selection criteria. Eleven models had internal validation, eight had external validation and one had neither. Discriminative ability with c-statistics ranged from 0.57 to 0.91. Studies ranged from low to high risk of bias, mostly due to the need for external validation or missing data. Participants, outcomes, predictors handling and modelling methods varied. Most models focussed on lower-risk patients, the majority had high risk of bias and doubtful applicability, but three models had some applicability for higher-risk patients. However, these models will also need updating and external validation in multiple hospital settings before being implemented into clinical practice.