Availability and variability in guidelines on diabetic retinopathy screening in Asian countries

Multiplatform tear proteomic profiling reveals novel non-invasive biomarkers for diabetic retinopathy

OBJECTIVES

To investigate a comprehensive proteomic profile of the tear fluid in patients with diabetic retinopathy (DR) and further define non-invasive biomarkers.

METHODS

A cross-sectional, multicentre study that includes 46 patients with DR, 28 patients with diabetes mellitus (DM), and 30 healthy controls (HC). Tear samples were collected with Schirmer strips. As for the discovery set, data-independent acquisition mass spectrometry was used to characterize the tear proteomic profile. Differentially expressed proteins between groups were identified, with gene ontology enrichment analysis and Kyoto Encyclopedia of Genes and Genomes enrichment analysis further developed. Classifying performance of biomarkers for distinguishing DR from DM was compared by the combination of three machine-learning algorithms. The selected biomarker panel was tested in the validation cohort using parallel reaction monitoring mass spectrometry.

RESULTS

Among 3364 proteins quantified, 235 and 88 differentially expressed proteins were identified for DR when compared to HC and DM, respectively, which were fundamentally related to retina homeostasis, inflammation and immunity, oxidative stress, angiogenesis and coagulation, metabolism, and cellular adhesion processes. The biomarker panel consisting of NAD-dependent protein deacetylase sirtuin-2 (SIR2), amine oxidase [flavin-containing] B (AOFB), and U8 snoRNA-decapping enzyme (NUD16) exhibited the best diagnostic performance in discriminating DR from DM, with AUCs of 0.933 and 0.881 in the discovery and validation set, respectively.

CONCLUSIONS

Tear protein dysregulation is comprehensively revealed to be associated with DR onset. The combination of tear SIR2, AOFB, and NUD16 can be a novel potential approach for non-invasive detection or pre-screening of DR.

CLINICAL TRIAL REGISTRATION

Chinese Clinical Trial Registry Identifier: ChiCTR2100054263. https://www.chictr.org.cn/showproj.html?proj=143177 . Date of registration: 2021/12/12.

Extending the diabetic retinopathy screening intervals in Singapore: methodology and preliminary findings of a cohort study

BACKGROUND

The Diabetic Retinopathy Extended Screening Study (DRESS) aims to develop and validate a new DR/diabetic macular edema (DME) risk stratification model in patients with Type 2 diabetes (DM) to identify low-risk groups who can be safely assigned to biennial or triennial screening intervals. We describe the study methodology, participants' baseline characteristics, and preliminary DR progression rates at the first annual follow-up.

METHODS

DRESS is a 3-year ongoing longitudinal study of patients with T2DM and no or mild non-proliferative DR (NPDR, non-referable) who underwent teleophthalmic screening under the Singapore integrated Diabetic Retinopathy Programme (SiDRP) at four SingHealth Polyclinics. Patients with referable DR/DME (> mild NPDR) or ungradable fundus images were excluded. Sociodemographic, lifestyle, medical and clinical information was obtained from medical records and interviewer-administered questionnaires at baseline. These data are extracted from medical records at 12, 24 and 36 months post-enrollment. Baseline descriptive characteristics stratified by DR severity at baseline and rates of progression to referable DR at 12-month follow-up were calculated.

RESULTS

Of 5,840 eligible patients, 78.3% (n = 4,570, median [interquartile range [IQR] age 61.0 [55-67] years; 54.7% male; 68.0% Chinese) completed the baseline assessment. At baseline, 97.4% and 2.6% had none and mild NPDR (worse eye), respectively. Most participants had hypertension (79.2%) and dyslipidemia (92.8%); and almost half were obese (43.4%, BMI ≥ 27.5 kg/m2). Participants without DR (vs mild DR) reported shorter DM duration, and had lower haemoglobin A1c, triglycerides and urine albumin/creatinine ratio (all p < 0.05). To date, we have extracted 41.8% (n = 1909) of the 12-month follow-up data. Of these, 99.7% (n = 1,904) did not progress to referable DR. Those who progressed to referable DR status (0.3%) had no DR at baseline.

CONCLUSIONS

In our prospective study of patients with T2DM and non-referable DR attending polyclinics, we found extremely low annual DR progression rates. These preliminary results suggest that extending screening intervals beyond 12 months may be viable and safe for most participants, although our 3-year follow up data are needed to substantiate this claim and develop the risk stratification model to identify low-risk patients with T2DM who can be assigned biennial or triennial screening intervals.

DRAC 2022: A public benchmark for diabetic retinopathy analysis on ultra-wide optical coherence tomography angiography images

We described a challenge named "DRAC - Diabetic Retinopathy Analysis Challenge" in conjunction with the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2022). Within this challenge, we provided the DRAC datset, an ultra-wide optical coherence tomography angiography (UW-OCTA) dataset (1,103 images), addressing three primary clinical tasks: diabetic retinopathy (DR) lesion segmentation, image quality assessment, and DR grading. The scientific community responded positively to the challenge, with 11, 12, and 13 teams submitting different solutions for these three tasks, respectively. This paper presents a concise summary and analysis of the top-performing solutions and results across all challenge tasks. These solutions could provide practical guidance for developing accurate classification and segmentation models for image quality assessment and DR diagnosis using UW-OCTA images, potentially improving the diagnostic capabilities of healthcare professionals. The dataset has been released to support the development of computer-aided diagnostic systems for DR evaluation.

Performance of Artificial Intelligence in Detecting Diabetic Macular Edema From Fundus Photography and Optical Coherence Tomography Images: A Systematic Review and Meta-analysis

BACKGROUND

Diabetic macular edema (DME) is the leading cause of vision loss in people with diabetes. Application of artificial intelligence (AI) in interpreting fundus photography (FP) and optical coherence tomography (OCT) images allows prompt detection and intervention.

PURPOSE

To evaluate the performance of AI in detecting DME from FP or OCT images and identify potential factors affecting model performances.

DATA SOURCES

We searched seven electronic libraries up to 12 February 2023.

STUDY SELECTION

We included studies using AI to detect DME from FP or OCT images.

DATA EXTRACTION

We extracted study characteristics and performance parameters.

DATA SYNTHESIS

Fifty-three studies were included in the meta-analysis. FP-based algorithms of 25 studies yielded pooled area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity of 0.964, 92.6%, and 91.1%, respectively. OCT-based algorithms of 28 studies yielded pooled AUROC, sensitivity, and specificity of 0.985, 95.9%, and 97.9%, respectively. Potential factors improving model performance included deep learning techniques, larger size, and more diversity in training data sets. Models demonstrated better performance when validated internally than externally, and those trained with multiple data sets showed better results upon external validation.

LIMITATIONS

Analyses were limited by unstandardized algorithm outcomes and insufficient data in patient demographics, OCT volumetric scans, and external validation.

CONCLUSIONS

This meta-analysis demonstrates satisfactory performance of AI in detecting DME from FP or OCT images. External validation is warranted for future studies to evaluate model generalizability. Further investigations may estimate optimal sample size, effect of class balance, patient demographics, and additional benefits of OCT volumetric scans.

A deep learning system for predicting time to progression of diabetic retinopathy

Diabetic retinopathy (DR) is the leading cause of preventable blindness worldwide. The risk of DR progression is highly variable among different individuals, making it difficult to predict risk and personalize screening intervals. We developed and validated a deep learning system (DeepDR Plus) to predict time to DR progression within 5 years solely from fundus images. First, we used 717,308 fundus images from 179,327 participants with diabetes to pretrain the system. Subsequently, we trained and validated the system with a multiethnic dataset comprising 118,868 images from 29,868 participants with diabetes. For predicting time to DR progression, the system achieved concordance indexes of 0.754-0.846 and integrated Brier scores of 0.153-0.241 for all times up to 5 years. Furthermore, we validated the system in real-world cohorts of participants with diabetes. The integration with clinical workflow could potentially extend the mean screening interval from 12 months to 31.97 months, and the percentage of participants recommended to be screened at 1-5 years was 30.62%, 20.00%, 19.63%, 11.85% and 17.89%, respectively, while delayed detection of progression to vision-threatening DR was 0.18%. Altogether, the DeepDR Plus system could predict individualized risk and time to DR progression over 5 years, potentially allowing personalized screening intervals.

The role of cadre in the community on diabetic retinopathy management and its challenges in low-middle income countries: a scoping review

INTRODUCTION

Diabetes is a serious public health problem, with low- and middle-income countries (LMICs) bearing over 80% of the burden. Diabetic retinopathy (DR) is one of the most prevalent diabetic microvascular problems, and early diagnosis through eye screening programs for people with diabetes is critical to prevent vision impairment and blindness. Community-based treatments, including non-physician cadres have been recommended to enhance DR care.

METHODS

The review protocol was determined and scoping review was conducted.The population, concept, and context were "cadre", "role of cadre in the management of DR", and LMICs". Data were collected from databases and searches, including grey literature.

RESULTS

Cadre can motivate people to attend a diabetic eye screening event when the rate of eye examinations is about six times higher than before the start of the intervention. Health education is a possible area for task sharing, and the cadre reported could also perform the task of vision testing. The cadre could be a good supporter and a good reminder for society. However, several challenges have been faced in this study and inadequate infrastructure is the foremost challenge found in this study. Other challenges encountered in the studies include poverty, lack of community awareness, trust issues, and low education levels contributing to poor health.

CONCLUSION

The current study highlighted significant gaps in the literature, which focus on the role of cadre as a community-based intervention in managing DR in LMICs. Further research is needed to develop evidence to support cost-effective screening services and cadre-related policy development in LMICs.

Optical coherence tomography in the management of diabetic macular oedema

Diabetic macular oedema (DMO) is the major cause of visual impairment in people with diabetes. Optical coherence tomography (OCT) is now the most widely used modality to assess presence and severity of DMO. DMO is currently broadly classified based on the involvement to the central 1 mm of the macula into non-centre or centre involved DMO (CI-DMO) and DMO can occur with or without visual acuity (VA) loss. This classification forms the basis of management strategies of DMO. Despite years of research on quantitative and qualitative DMO related features assessed by OCT, these do not fully inform physicians of the prognosis and severity of DMO relative to visual function. Having said that, recent research on novel OCT biomarkers development and re-defined classification of DMO show better correlation with visual function and treatment response. This review summarises the current evidence of the association of OCT biomarkers in DMO management and its potential clinical importance in predicting VA and anatomical treatment response. The review also discusses some future directions in this field, such as the use of artificial intelligence to quantify and monitor OCT biomarkers and retinal fluid and identify phenotypes of DMO, and the need for standardisation and classification of OCT biomarkers to use in future clinical trials and clinical practice settings as prognostic markers and secondary treatment outcome measures in the management of DMO.

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.

Where Art Thou O treatment for diabetic neuropathy: the sequel

INTRODUCTION

Having lived through a pandemic and witnessed how regulatory approval processes can evolve rapidly; it is lamentable how we continue to rely on symptoms/signs and nerve conduction as primary endpoints for clinical trials in DPN.

AREAS COVERED

Small (Aδ and C) fibers are key to the genesis of pain, regulate skin blood flow, and play an integral role in the development of diabetic foot ulceration but continue to be ignored. This article challenges the rationale for the FDA insisting on symptoms/signs and nerve conduction as primary endpoints for clinical trials in DPN.

EXPERT OPINION

Quantitative sensory testing, intraepidermal nerve fiber density, and especially corneal confocal microscopy remain an after-thought, demoted at best to exploratory secondary endpoints in clinical trials of diabetic neuropathy. If pharma are to be given a fighting chance to secure approval for a new therapy for diabetic neuropathy, the FDA needs to reassess the evidence rather than rely on 'opinion' for the most suitable endpoint(s) in clinical trials of diabetic neuropathy.

Diabetic retinopathy is a predictor of chronic respiratory failure: A nationwide register-based cohort study

Purpose

Diabetic retinopathy (DR) is a hypoxic retinal disease, but so far, the association with systemic hypoxia is poorly understood. Hence, the aim of this study was to evaluate cross-sectional and longitudinal associations between DR and chronic respiratory failure (CRF) in a national cohort.

Design

Cross-sectional and 5-year longitudinal register-based cohort study.

Methods

Between 2013 and 2018, we included patients with diabetes from the Danish Registry of Diabetic Retinopathy, who were each age and sex matched with five controls without diabetes. At index date, the prevalence of CRF was compared between cases and controls, and the longitudinal relationship between DR and CRF was assessed in a five-year follow-up.

Results

At baseline, we identified 1,980 and 9,990 patients with CRF among 205,970 cases and 1,003,170 controls. The prevalence of CRF was higher among cases than controls (OR 1.75, 95% CI 1.65-1.86), but no difference between cases with and without DR was found.During follow-up, we identified 1,726 and 5,177 events of CRF among cases and controls, respectively. The incidence of CRF was higher among both cases with and without DR compared to controls (DR level 0: HR 1.24, 95% CI 1.16-1.33, DR level 1-4: HR 1.86, 95% CI 1.63-2.12), and higher among cases with DR compared to cases without DR (HR 1.54, 95% CI 1.38-1.72).

Conclusion

In this study based on nationwide data, we found an increased risk of present and incident CRF in patients with diabetes with or without DR, and we identified DR as a predictor of future CRF.

Diabetic retinopathy as the leading cause of blindness and early predictor of cascading complications-risks and mitigation

Proliferative diabetic retinopathy (PDR) the sequel of diabetic retinopathy (DR), a frequent complication of diabetes mellitus (DM), is the leading cause of blindness in the working-age population. The current screening process for the DR risk is not sufficiently effective such that often the disease is undetected until irreversible damage occurs. Diabetes-associated small vessel disease and neuroretinal changes create a vicious cycle resulting in the conversion of DR into PDR with characteristic ocular attributes including excessive mitochondrial and retinal cell damage, chronic inflammation, neovascularisation, and reduced visual field. PDR is considered an independent predictor of other severe diabetic complications such as ischemic stroke. A "domino effect" is highly characteristic for the cascading DM complications in which DR is an early indicator of impaired molecular and visual signaling. Mitochondrial health control is clinically relevant in DR management, and multi-omic tear fluid analysis can be instrumental for DR prognosis and PDR prediction. Altered metabolic pathways and bioenergetics, microvascular deficits and small vessel disease, chronic inflammation, and excessive tissue remodelling are in focus of this article as evidence-based targets for a predictive approach to develop diagnosis and treatment algorithms tailored to the individual for a cost-effective early prevention by implementing the paradigm shift from reactive medicine to predictive, preventive, and personalized medicine (PPPM) in primary and secondary DR care management.

Automated machine learning-based classification of proliferative and non-proliferative diabetic retinopathy using optical coherence tomography angiography vascular density maps

PURPOSE

The study aims to classify the eyes with proliferative diabetic retinopathy (PDR) and non-proliferative diabetic retinopathy (NPDR) based on the optical coherence tomography angiography (OCTA) vascular density maps using a supervised machine learning algorithm.

METHODS

OCTA vascular density maps (at superficial capillary plexus (SCP), deep capillary plexus (DCP), and total retina (R) levels) of 148 eyes from 78 patients with diabetic retinopathy (45 PDR and 103 NPDR) was used to classify the images to NPDR and PDR groups based on a supervised machine learning algorithm known as the support vector machine (SVM) classifier optimized by a genetic evolutionary algorithm.

RESULTS

The implemented algorithm in three different models reached up to 85% accuracy in classifying PDR and NPDR in all three levels of vascular density maps. The deep retinal layer vascular density map demonstrated the best performance with a 90% accuracy in discriminating between PDR and NPDR.

CONCLUSIONS

The current study on a limited number of patients with diabetic retinopathy demonstrated that a supervised machine learning-based method known as SVM can be used to differentiate PDR and NPDR patients using OCTA vascular density maps.

Associations between psycho-behavioral risk factors and diabetic retinopathy: NHANES (2005-2018)

Introduction

Diabetes mellitus (DM) and diabetic retinopathy (DR) increase the global burden. Since their pathogenesis is complex, it is necessary to use the biopsychosocial model to discover the most effective strategies. The study is aimed to investigate the psycho-behavioral factors of DR and confirm the discrepancies from previous studies.

Research design and methods

The study comprised seven cycles of cross-sectional data of the National Health and Nutrition Examination Survey (NHANES) from 2005-2006 to 2017-2018. Samples of DM were selected from this complex multi-stage probability sample and divided into the non-DR and DR groups, where 4,426 samples represented 18,990,825 individuals after weighting. This study comprehensively explored the biological, social, and psychological risk factors of DR, among which the biological factors included blood pressure, blood routine, HbA1c%, blood glucose, the duration of DM, family history, comorbidities, and treatment methods. Social aspects include gender, education, income, insurance, smoking, drinking, sleep habits, and recreational activities. The Patient Health Questionnaire-9 (PHQ-9) was used to assess the psychological state. Taylor series regression was used to examine the connection between factors and DR.

Results

Men accounted for 55.5% of the DR group (P = 0.0174). Lymphocyte count, insulin treatment, heart failure, stroke, liver condition, and renal failure showed significant differences in DR (P < 0.05). The incidence of depression in DR was 40.5%. Mild to moderate depression [odds ratio was associated with DR [(OR) = 1.37, 95% confidence interval (CI): 1.06-1.79], but there was no statistical difference in severe depression (OR = 1.34, 95% CI: 0.83-2.17). Although ≤ 6 h of sleep was associated with DR (OR = 1.38, 95% CI: 1.01-1.88), we found no statistical differences in alcohol consumption, recreational activities, or sedentary time between the two groups in our current study (P > 0.05).

Conclusions

The biological risk factors of DR are significant. It showed that stroke is associated with DR, and retinal exams have the potential value as a screening tool for the brain. Besides, psycho-behavioral risk factors of DR should also be paid attention. Our study highlights that mild and moderate depression and ≤6 h of sleep are distinguishably associated with DM complicated with DR. It indicates that psycho-behavioral risk factors confer a vital influence on diabetic health care and DR.

Diabetic retinopathy screening in the emerging era of artificial intelligence

Diabetic retinopathy is a frequent complication in diabetes and a leading cause of visual impairment. Regular eye screening is imperative to detect sight-threatening stages of diabetic retinopathy such as proliferative diabetic retinopathy and diabetic macular oedema in order to treat these before irreversible visual loss occurs. Screening is cost-effective and has been implemented in various countries in Europe and elsewhere. Along with optimised diabetes care, this has substantially reduced the risk of visual loss. Nevertheless, the growing number of patients with diabetes poses an increasing burden on healthcare systems and automated solutions are needed to alleviate the task of screening and improve diagnostic accuracy. Deep learning by convolutional neural networks is an optimised branch of artificial intelligence that is particularly well suited to automated image analysis. Pivotal studies have demonstrated high sensitivity and specificity for classifying advanced stages of diabetic retinopathy and identifying diabetic macular oedema in optical coherence tomography scans. Based on this, different algorithms have obtained regulatory approval for clinical use and have recently been implemented to some extent in a few countries. Handheld mobile devices are another promising option for self-monitoring, but so far they have not demonstrated comparable image quality to that of fundus photography using non-portable retinal cameras, which is the gold standard for diabetic retinopathy screening. Such technology has the potential to be integrated in telemedicine-based screening programmes, enabling self-captured retinal images to be transferred virtually to reading centres for analysis and planning of further steps. While emerging technologies have shown a lot of promise, clinical implementation has been sparse. Legal obstacles and difficulties in software integration may partly explain this, but it may also indicate that existing algorithms may not necessarily integrate well with national screening initiatives, which often differ substantially between countries.

Automated multidimensional deep learning platform for referable diabetic retinopathy detection: a multicentre, retrospective study

OBJECTIVE

To develop and validate a real-world screening, guideline-based deep learning (DL) system for referable diabetic retinopathy (DR) detection.

DESIGN

This is a multicentre platform development study based on retrospective, cross-sectional data sets. Images were labelled by two-level certificated graders as the ground truth. According to the UK DR screening guideline, a DL model based on colour retinal images with five-dimensional classifiers, namely image quality, retinopathy, maculopathy gradability, maculopathy and photocoagulation, was developed. Referable decisions were generated by integrating the output of all classifiers and reported at the image, eye and patient level. The performance of the DL was compared with DR experts.

SETTING

DR screening programmes from three hospitals and the Lifeline Express Diabetic Retinopathy Screening Program in China.

PARTICIPANTS

83 465 images of 39 836 eyes from 21 716 patients were annotated, of which 53 211 images were used as the development set and 30 254 images were used as the external validation set, split based on centre and period.

MAIN OUTCOMES

Accuracy, F1 score, sensitivity, specificity, area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), Cohen's unweighted κ and Gwet's AC1 were calculated to evaluate the performance of the DL algorithm.

RESULTS

In the external validation set, the five classifiers achieved an accuracy of 0.915-0.980, F1 score of 0.682-0.966, sensitivity of 0.917-0.978, specificity of 0.907-0.981, AUROC of 0.9639-0.9944 and AUPRC of 0.7504-0.9949. Referable DR at three levels was detected with an accuracy of 0.918-0.967, F1 score of 0.822-0.918, sensitivity of 0.970-0.971, specificity of 0.905-0.967, AUROC of 0.9848-0.9931 and AUPRC of 0.9527-0.9760. With reference to the ground truth, the DL system showed comparable performance (Cohen's κ: 0.86-0.93; Gwet's AC1: 0.89-0.94) with three DR experts (Cohen's κ: 0.89-0.96; Gwet's AC1: 0.91-0.97) in detecting referable lesions.

CONCLUSIONS

The automatic DL system for detection of referable DR based on the UK guideline could achieve high accuracy in multidimensional classifications. It is suitable for large-scale, real-world DR screening.

International collaboration for the development of clinical guidelines in low and middle-income countries: case study on the development of a national framework and clinical guidelines for diabetic retinopathy in Ghana

Background

Diabetic retinopathy is a leading cause of blindness in many countries across the world. Ghana has seen a rise in diabetic retinopathy and is working on various strategies to prevent blindness. Clinical guidelines are seen as a promising strategy for improving quality and reducing cost of care. Little is known about the processes of collaborative guideline development in the African context.

Methods

This case study discusses the process of developing clinical guidelines for diabetic retinopathy in Ghana via a collaboration with the Kenya team that had previously developed guidelines for Kenya.

Results

The main lesson learnt was the ability to overcome challenges. The main output achieved was the draft national framework, guidelines and training slides on the guidelines.

Conclusion

Horizontal international collaboration can aid development of clinical guidelines.

Review of the management of sight-threatening diabetic retinopathy during pregnancy

Diabetes mellitus (DM) is a noncommunicable disease reaching epidemic proportions around the world. It affects younger individuals, including women of childbearing age. Diabetes can cause diabetic retinopathy (DR), which is potentially sight threatening when severe nonproliferative DR (NPDR), proliferative DR (PDR), or sight-threatening diabetic macular oedema (STDME) develops. Pregnancy is an independent risk factor for the progression of DR. Baseline DR at the onset of pregnancy is an important indicator of progression, with up to 10% of women with baseline NPDR progressing to PDR. Progression to sight-threatening DR (STDR) during pregnancy causes distress to the patient and often necessitates ocular treatment, which may have a systemic effect. Management includes prepregnancy counselling and, when possible, conventional treatment prior to pregnancy. During pregnancy, closer follow-up is required for those with a long duration of DM, poor baseline control of blood sugar and blood pressure, and worse DR, as these are risk factors for progression to STDR. Conventional treatment with anti-vascular endothelial growth factor agents for STDME can potentially lead to foetal loss. Treatment with laser photocoagulation may be preferred, and surgery under general anaesthesia should be avoided. This review provides a management plan for STDR from the perspective of practising ophthalmologists. A review of strategies for maintaining the eyesight of diabetic women with STDR with emphasis on prepregnancy counselling and planning, monitoring and safe treatment during pregnancy, and management of complications is presented.

A Multitask Deep-Learning System to Classify Diabetic Macular Edema for Different Optical Coherence Tomography Devices: A Multicenter Analysis

OBJECTIVE

Diabetic macular edema (DME) is the primary cause of vision loss among individuals with diabetes mellitus (DM). We developed, validated, and tested a deep learning (DL) system for classifying DME using images from three common commercially available optical coherence tomography (OCT) devices.

RESEARCH DESIGN AND METHODS

We trained and validated two versions of a multitask convolution neural network (CNN) to classify DME (center-involved DME [CI-DME], non-CI-DME, or absence of DME) using three-dimensional (3D) volume scans and 2D B-scans, respectively. For both 3D and 2D CNNs, we used the residual network (ResNet) as the backbone. For the 3D CNN, we used a 3D version of ResNet-34 with the last fully connected layer removed as the feature extraction module. A total of 73,746 OCT images were used for training and primary validation. External testing was performed using 26,981 images across seven independent data sets from Singapore, Hong Kong, the U.S., China, and Australia.

RESULTS

In classifying the presence or absence of DME, the DL system achieved area under the receiver operating characteristic curves (AUROCs) of 0.937 (95% CI 0.920-0.954), 0.958 (0.930-0.977), and 0.965 (0.948-0.977) for the primary data set obtained from CIRRUS, SPECTRALIS, and Triton OCTs, respectively, in addition to AUROCs >0.906 for the external data sets. For further classification of the CI-DME and non-CI-DME subgroups, the AUROCs were 0.968 (0.940-0.995), 0.951 (0.898-0.982), and 0.975 (0.947-0.991) for the primary data set and >0.894 for the external data sets.

CONCLUSIONS

We demonstrated excellent performance with a DL system for the automated classification of DME, highlighting its potential as a promising second-line screening tool for patients with DM, which may potentially create a more effective triaging mechanism to eye clinics.

Blue Widefield Images of Scanning Laser Ophthalmoscope Can Detect Retinal Ischemic Areas in Eyes With Diabetic Retinopathy

PURPOSE

To determine whether the hyporeflective areas in the blue images obtained by widefield scanning laser ophthalmoscopy (SLO) correspond to the non-perfused areas (NPAs) in the fluorescein angiograms (FA) in eyes with diabetic retinopathy (DR).

DESIGN

Retrospective observational case series.

METHODS

Ninety patients with diabetes mellitus (DM) were studied. All had undergone multicolor widefield SLO imaging. The NPAs in the FA images and hyporeflective areas in the blue widefield SLO images were examined. The morphology of the retina was determined by optical coherence tomography.

RESULTS

Hyporeflective areas in the blue SLO images were found with a rate of 76.6% in eyes with proliferative DR eyes. In a comparison of the hyporeflective areas of the blue SLO images to the non-perfused areas in the FA images, the appearance and the correspondence in the locations of these two types of images were found, and the rate was highly concordant with a Cohen's kappa value of 0.675.

CONCLUSIONS

The high concordance between the hyporeflective areas in the widefield blue SLO and the NPAs in the FA indicates that widefield blue SLO can be used to identify ischemic retinal areas in eyes with DR without the intravenous injection of any dye.

Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks

Retinal fundus diseases can lead to irreversible visual impairment without timely diagnoses and appropriate treatments. Single disease-based deep learning algorithms had been developed for the detection of diabetic retinopathy, age-related macular degeneration, and glaucoma. Here, we developed a deep learning platform (DLP) capable of detecting multiple common referable fundus diseases and conditions (39 classes) by using 249,620 fundus images marked with 275,543 labels from heterogenous sources. Our DLP achieved a frequency-weighted average F1 score of 0.923, sensitivity of 0.978, specificity of 0.996 and area under the receiver operating characteristic curve (AUC) of 0.9984 for multi-label classification in the primary test dataset and reached the average level of retina specialists. External multihospital test, public data test and tele-reading application also showed high efficiency for multiple retinal diseases and conditions detection. These results indicate that our DLP can be applied for retinal fundus disease triage, especially in remote areas around the world.

Detection of Diabetic Eye Disease from Retinal Images Using a Deep Learning Based CenterNet Model

Diabetic retinopathy (DR) is an eye disease that alters the blood vessels of a person suffering from diabetes. Diabetic macular edema (DME) occurs when DR affects the macula, which causes fluid accumulation in the macula. Efficient screening systems require experts to manually analyze images to recognize diseases. However, due to the challenging nature of the screening method and lack of trained human resources, devising effective screening-oriented treatment is an expensive task. Automated systems are trying to cope with these challenges; however, these methods do not generalize well to multiple diseases and real-world scenarios. To solve the aforementioned issues, we propose a new method comprising two main steps. The first involves dataset preparation and feature extraction and the other relates to improving a custom deep learning based CenterNet model trained for eye disease classification. Initially, we generate annotations for suspected samples to locate the precise region of interest, while the other part of the proposed solution trains the Center Net model over annotated images. Specifically, we use DenseNet-100 as a feature extraction method on which the one-stage detector, CenterNet, is employed to localize and classify the disease lesions. We evaluated our method over challenging datasets, namely, APTOS-2019 and IDRiD, and attained average accuracy of 97.93% and 98.10%, respectively. We also performed cross-dataset validation with benchmark EYEPACS and Diaretdb1 datasets. Both qualitative and quantitative results demonstrate that our proposed approach outperforms state-of-the-art methods due to more effective localization power of CenterNet, as it can easily recognize small lesions and deal with over-fitted training data. Our proposed framework is proficient in correctly locating and classifying disease lesions. In comparison to existing DR and DME classification approaches, our method can extract representative key points from low-intensity and noisy images and accurately classify them. Hence our approach can play an important role in automated detection and recognition of DR and DME lesions.

A deep learning system for detecting diabetic retinopathy across the disease spectrum

Retinal screening contributes to early detection of diabetic retinopathy and timely treatment. To facilitate the screening process, we develop a deep learning system, named DeepDR, that can detect early-to-late stages of diabetic retinopathy. DeepDR is trained for real-time image quality assessment, lesion detection and grading using 466,247 fundus images from 121,342 patients with diabetes. Evaluation is performed on a local dataset with 200,136 fundus images from 52,004 patients and three external datasets with a total of 209,322 images. The area under the receiver operating characteristic curves for detecting microaneurysms, cotton-wool spots, hard exudates and hemorrhages are 0.901, 0.941, 0.954 and 0.967, respectively. The grading of diabetic retinopathy as mild, moderate, severe and proliferative achieves area under the curves of 0.943, 0.955, 0.960 and 0.972, respectively. In external validations, the area under the curves for grading range from 0.916 to 0.970, which further supports the system is efficient for diabetic retinopathy grading.

The Clinical Influence after Implementation of Convolutional Neural Network-Based Software for Diabetic Retinopathy Detection in the Primary Care Setting

Deep learning-based software is developed to assist physicians in terms of diagnosis; however, its clinical application is still under investigation. We integrated deep-learning-based software for diabetic retinopathy (DR) grading into the clinical workflow of an endocrinology department where endocrinologists grade for retinal images and evaluated the influence of its implementation. A total of 1432 images from 716 patients and 1400 images from 700 patients were collected before and after implementation, respectively. Using the grading by ophthalmologists as the reference standard, the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) to detect referable DR (RDR) were 0.91 (0.87-0.96), 0.90 (0.87-0.92), and 0.90 (0.87-0.93) at the image level; and 0.91 (0.81-0.97), 0.84 (0.80-0.87), and 0.87 (0.83-0.91) at the patient level. The monthly RDR rate dropped from 55.1% to 43.0% after implementation. The monthly percentage of finishing grading within the allotted time increased from 66.8% to 77.6%. There was a wide range of agreement values between the software and endocrinologists after implementation (kappa values of 0.17-0.65). In conclusion, we observed the clinical influence of deep-learning-based software on graders without the retinal subspecialty. However, the validation using images from local datasets is recommended before clinical implementation.

Inverse Cross-sectional and Longitudinal Relationships between Diabetic Retinopathy and Obstructive Sleep Apnea in Type 2 Diabetes

Purpose

Design

Participants

Methods

Main Outcome Measures

Results

Conclusions

Plasma Metabolomics Reveals Metabolic Profiling For Diabetic Retinopathy and Disease Progression

BACKGROUNDS

Diabetic retinopathy (DR), the main retinal vascular complication of DM, is the leading cause of visual impairment and blindness among working-age people worldwide. The aim of this study was to investigate the difference of plasma metabolic profiles in patients with DR to better understand the mechanism of this disease and disease progression.

METHODS

We used ultrahigh-performance liquid Q-Exactive mass spectrometry and multivariate statistical analyses to conduct a comprehensive analysis of plasma metabolites in a population with DR and proliferative DR (PDR). A risk score based on the level of the selected metabolite was established and evaluated using the least absolute shrinkage and selection operator regularization logistic regression (LASSO-LR) based machine learning model.

RESULTS

22 differentially expressed metabolites which belonged to different metabolic pathway were identified and confirmed to be associated with the occurrence of DR. A risk score based on the level of the selected metabolite pseudouridine was established and evaluated to strongly associated with the occurrence of DR. Four circulating plasma metabolites (pseudouridine, glutamate, leucylleucine and N-acetyltryptophan) were identified to be differentially expressed between patients with PDR and other patients, and a risk score formula based on these plasma metabolites was developed and assessed to be significantly related to PDR.

CONCLUSIONS

Our work highlights the possible use of the risk score assessment based on the plasma metabolites not only reveal in the early diagnosis of DR and PDR but also assist in enhancing current therapeutic strategies in the clinic.

Prevalence and causes of avoidable blindness and visual impairment, including the prevalence of diabetic retinopathy in Siwan district of Bihar, India: A population-based survey

Purpose:

The aim of this study was to estimate the prevalence and causes of visual impairment (VI) and blindness and diabetic retinopathy (DR) in Siwan district, Bihar.

Methods:

A population-based cross-sectional study was done from January to March 2016 using the Rapid Assessment of Avoidable Blindness 6 (RAAB 6, incorporating DR module) methodology. All individuals aged ≥50 years were examined in 57 randomly selected clusters within the district.

Results:

A total of 3476 individuals were enumerated and 3189 (92%) completed examination. The overall prevalence of blindness and severe VI was 2.2% (95% confidence interval (CI): 1.6–2.8) and 3.4% (95% CI: 2.6–4.3), respectively. Untreated cataract was the leading cause of blindness (73%) and severe VI (93%). The cataract surgical coverage (CSC) at <3/60 was 71.5% for eyes and 89.3% for persons in this sample and the CSC was similar between the genders. Refractive error (71%) was the primary cause of early VI. The overall prevalence of known and newly diagnosed diabetes was 6.3% (95% CI, 5.4–7.2%). Prevalence of any DR, maculopathy, and sight-threatening DR was 15, 12.4, and 6%, respectively.

Conclusion:

To conclude, as compared to previous reports, the prevalence of blindness and DR in Siwan district of Bihar was found to be lower and the CSC was higher. However, the problem of avoidable blindness remains a major problem in this region.

Multiplatform Metabolomics Reveals Novel Serum Metabolite Biomarkers in Diabetic Retinopathy Subjects

Diabetic retinopathy (DR) is the main cause of vision loss or blindness in working age adults worldwide. The lack of effective diagnostic biomarkers for DR leads to unsatisfactory curative treatments. To define potential metabolite biomarkers for DR diagnosis, a multiplatform-based metabolomics study is performed. In this study, a total of 905 subjects with diabetes without DR (NDR) and with DR at different clinical stages are recruited. Multiplatform metabolomics methods are used to characterize the serum metabolic profiles and to screen and validate the DR biomarkers. Based on the criteria p < 0.05 and false-discovery rate < 0.05, 348 and 290 metabolites are significantly associated with the pathogenesis of DR and early-stage DR, respectively. The biomarker panel consisting of 12-hydroxyeicosatetraenoic acid (12-HETE) and 2-piperidone exhibited better diagnostic performance than hemoglobin A1c (HbA1c) in differentiating DR from diabetes, with AUCs of 0.946 versus 0.691 and 0.928 versus 0.648 in the discovery and validation sets, respectively. In addition, this panel showed higher sensitivity in early-stage DR detection than HbA1c. In conclusion, this multiplatform-based metabolomics study comprehensively revealed the metabolic dysregulation associated with DR onset and progression. The defined biomarker panel can be used for detection of DR and early-stage DR.

Can subthreshold micropulse yellow laser treatment change the anti-vascular endothelial growth factor algorithm in diabetic macular edema? A randomized clinical trial

Purpose

To compare the efficacy of subthreshold micropulse yellow laser (SMYL) and intravitreal aflibercept injection (IAI) combination therapy with IAI monotherapy in the treatment of diabetic macular edema (DME) and to evaluate the number of injections and SMYL sessions required.

Methods

This prospective study compared a group of 28 patients treated with a combination of SMYL and IAI with a group of 28 patients treated only with IAI. All patients initially received 3 monthly IAIs, and the monotherapy group was given additional injections as needed. The combination therapy patients additionally received SMYL after the loading phase. The primary outcome measures were the change in the best-corrected visual acuity (BCVA) and central macular thickness (CMT) from baseline to month 12; the secondary outcomes were the mean number of required injections and SMYL sessions.

Results

In the monotherapy group, the BCVA improved from 0.38 ± 0.10 to 0.20 ± 0.10 logMAR; in the combination group, BCVA improved from 0.40 ± 0.09 to 0.17 ± 0.06 logMAR at the end of the 12^th month. The CMT was reduced from 451.28 ± 44.85 to 328.8 ± 49.69 μm in the monotherapy group and from 466.07 ± 71.79 to 312.0 ± 39.29 μm in the combination group. Improvement of the mean BCVA and reduction of the mean CMT were similar in each group. The combination group required significantly fewer injections (3.21 ± 0.41 vs 5.39 ± 1.54; P < 0.001). By month 12, 75% of patients in the monotherapy group had required additional IAIs when compared with 16% in the combination group (P < 0.001).

Conclusion

SMYL combination therapy demonstrated significant visual improvements in patients with DME. In the combination group, the retreatment rate and number of required injections were significantly lower compared with the IAI monotherapy group.

Detection of Diabetic Retinopathy Using Bichannel Convolutional Neural Network

Deep learning of fundus photograph has emerged as a practical and cost-effective technique for automatic screening and diagnosis of severer diabetic retinopathy (DR). The entropy image of luminance of fundus photograph has been demonstrated to increase the detection performance for referable DR using a convolutional neural network- (CNN-) based system. In this paper, the entropy image computed by using the green component of fundus photograph is proposed. In addition, image enhancement by unsharp masking (UM) is utilized for preprocessing before calculating the entropy images. The bichannel CNN incorporating the features of both the entropy images of the gray level and the green component preprocessed by UM is also proposed to improve the detection performance of referable DR by deep learning.

Perception Among Diabetic Patients of Telescreening for Diabetic Retinopathy

Purpose: To evaluate the satisfaction of diabetic patients and its determinants of telescreening for diabetic retinopathy (DR) in Saudi Arabia. Methods: This cross-sectional survey was conducted in December 2018 in a diabetes center of Riyadh, Saudi Arabia. Ten questions were asked by the interviewer. A 5-point Likert scale was used to grade patient responses for each question. Rasch analysis was conducted to evaluate the response of the participants. The main outcome variable was the sum of the Logit values of the responses. The Rasch score was also compared among subgroups. Results: Two hundred (n = 200) diabetic patients were interviewed. The median Rasch score of client-perceived benefit of DR telescreening was +14.6 (25% quartile +3.09, minimum; -23.2, maximum; +35.7). A positive attitude of patients regarding DR telescreening was recorded in 159 (79.5%) participants. The perception of telescreening was better in younger diabetic patients than in older diabetic patients (Friedman p < 0.001). The perception was similar in both genders (Mann-Whitney p = 0.3). Diabetic patients from Riyadh and the southern region of Saudi Arabia had significantly more positive perception than those from north and eastern regions (Freedman p < 0.001). Conclusion: Diabetic patients have positive attitude toward tele-DR screening. Their cooperation is likely to be high if large scale tele-DR screening is implemented in the Kingdom.

When to perform renal biopsy in patients with type2 diabetes mellitus? Predictive model of non-diabetic renal disease

INTRODUCTION

Diabetic nephropathy (DN) is one of the most frequent complications in patients with diabetes mellitus (DM) and its diagnosis is usually established on clinical grounds. However, kidney involvement in some diabetic patients can be due to other causes, and renal biopsy might be needed to exclude them. The aim of our study was to establish the clinical and analytical data that predict DN and no-diabetic renal disease (NDRD), and to develop a predictive model (score) to confirm or dismiss DN.

MATERIAL AND METHODS

We conducted a transversal, observational and retrospective study, including renal biopsies performed in type2 DM patients, between 2000 and 2018.

RESULTS

Two hundred seven DM patients were included in our study. The mean age was 64.5±10.6 years and 74% were male. DN was found in 126 (61%) of the biopsies and NDRD in 81 (39%). Diabetic retinopathy was presented in 58% of DN patients, but only in 6% of NDRD patients (P<.001). Patients with NDRD were diagnosed of primary glomerulopathies (52%), nephroangiosclerosis (16%), inmunoallergic interstitial nephritis (15%) and vasculitis (8.5%). In the multivariate analysis, retinopathy (OR26.7; 95%CI: 6.8-104.5), chronic ischaemia of lower limbs (OR4,37; 95%CI: 1.33-14.3), insulin therapy (OR3.05; 95%CI: 1.13-8.25), time course of DM ≥10years (OR2.71; 95%CI: 1.1-6.62) and nephrotic range proteinuria (OR2.91; 95%CI: 1.2-7.1) were independent predictors for DN. Microhaematuria defined as ≥10 red blood cells per high-power field (OR0.032; 95%CI: 0.01-0.11) and overweight (OR0.21; 95%CI: 0.08-0.5) were independent predictors of NDRD. According to the predictive model based on the multivariate analysis, all patients with a score >3 had DN and 94% of cases with a score ≤1 had NDRD (score ranked from -6 to 8points).

CONCLUSIONS

NDRD is common in DM patients (39%), being primary glomerulonephritis the most frequent ethology. The absence of retinopathy and the presence of microhematuria are highly suggestive of NDRD. The use of our predictive model could facilitate the indication of performing a renal biopsy in DM patients.

The War on Diabetic Retinopathy: Where Are We Now?

Diabetic retinopathy (DR), a major cause of blindness in working-age adults, is emerging as a major public health issue worldwide, in particular in low- and middle-income countries (LMIC). Traditionally, the management of DR has been on tertiary-level treatment (eg, laser, anti-VEGF injections and surgery) in specialized settings by highly trained ophthalmologists on individual patients. To win the war on DR, a paradigm shift in strategic focus and resources must be made from such tertiary treatment toward primary and secondary prevention, which are broader, more impactful, and cost-effective for the larger population. These include improving education and awareness of risk of DR among people initially diagnosed with diabetes, promoting behavioral modifications such as physical activity and medication adherence for improving glycemic and blood pressure control, setting up systematic screening programs for DR to detect the onset or progression of the disease, and implementing cost-effective, evidence-based policies and guidelines for managing DR. Additionally, there is a need to leverage on novel technology including the application of digital big data to predict people at risk of diabetes and DR, the use of wearable devices and smart phone apps, behavioral techniques including social media for self-management of diabetes, and telemedicine-based DR screening incorporating artificial intelligence (AI) to broaden access to screening in all settings. To turn the tide on the war on DR, we must reframe DR not only as a specific condition that can be managed by ophthalmologists, but fundamentally, as a preventable condition by shifting the weight of strategies from tertiary to secondary and primary battlegrounds.

Deep learning in estimating prevalence and systemic risk factors for diabetic retinopathy: a multi-ethnic study

In any community, the key to understanding the burden of a specific condition is to conduct an epidemiological study. The deep learning system (DLS) recently showed promising diagnostic performance for diabetic retinopathy (DR). This study aims to use DLS as the grading tool, instead of human assessors, to determine the prevalence and the systemic cardiovascular risk factors for DR on fundus photographs, in patients with diabetes. This is a multi-ethnic (5 races), multi-site (8 datasets from Singapore, USA, Hong Kong, China and Australia), cross-sectional study involving 18,912 patients (n = 93,293 images). We compared these results and the time taken for DR assessment by DLS versus 17 human assessors - 10 retinal specialists/ophthalmologists and 7 professional graders). The estimation of DR prevalence between DLS and human assessors is comparable for any DR, referable DR and vision-threatening DR (VTDR) (Human assessors: 15.9, 6.5% and 4.1%; DLS: 16.1%, 6.4%, 3.7%). Both assessment methods identified similar risk factors (with comparable AUCs), including younger age, longer diabetes duration, increased HbA1c and systolic blood pressure, for any DR, referable DR and VTDR (p > 0.05). The total time taken for DLS to evaluate DR from 93,293 fundus photographs was ~1 month compared to 2 years for human assessors. In conclusion, the prevalence and systemic risk factors for DR in multi-ethnic population could be determined accurately using a DLS, in significantly less time than human assessors. This study highlights the potential use of AI for future epidemiology or clinical trials for DR grading in the global communities.

Prevalence of diabetic retinopathy, proliferative diabetic retinopathy and non-proliferative diabetic retinopathy in Asian T2DM patients: a systematic review and Meta-analysis

AIM

To investigate the pooled prevalence of diabetic retinopathy (DR), proliferative DR (PDR) and nonproliferative DR (NPDR) in Asian type 2 diabetes mellitus (T2DM) patients.

METHODS

We performed a systematic search online search using PubMed, EMBASE, Web of Science, the Cochrane Library, and China WeiPu Library to identify eligible studies that reported the prevalence of DR, PDR and NPDR in Asian T2DM patients. Effect size (ES) with 95% confidence interval (CI) was used to evaluate the prevalence of DR, PDR and NPDR in Asian T2DM patients, respectively.

RESULTS

There were 41 references and 48 995 T2DM patients involved in this study. The prevalence of DR, PDR, and NPDR was 28%, 6%, and 27% in T2DM patients, respectively; while the prevalence of PDR and NPDR in DR patients was 17% and 83%, respectively. Subgroup analysis showed that prevalence of DR in T2DM patients from Singaporean, Indian, South Korean, Malaysian, Asian, and Chinese was 33%, 42%, 16%, 35%, 21% and 25%, respectively. In T2DM patients with NPDR from Indian, South Korean, Malaysian, Asian, Chinese, higher prevalence was found than that in PDR patients (45% vs 17%, 13% vs 3%, 30% vs 5%, 23% vs 2% and 22% vs 3%), as well as in DR patients (74% vs 26%, 81% vs 19%, 86% vs 14%, 92% vs 8% and 85% vs 15%). The prevalence of PDR in T2DM from India was higher than patients from other locations of Asia, and the same results were also observed in NPDR patients.

CONCLUSION

In either T2DM Asian patients or DR patients, NPDR is more common than PDR. Based on our results, we should pay more attention to NPDR screening and management in T2DM patients, and we also recommend suitable interventions to prevent its progression.

An Automated Grading System for Detection of Vision-Threatening Referable Diabetic Retinopathy on the Basis of Color Fundus Photographs

OBJECTIVE

The goal of this study was to describe the development and validation of an artificial intelligence-based, deep learning algorithm (DLA) for the detection of referable diabetic retinopathy (DR).

RESEARCH DESIGN AND METHODS

A DLA using a convolutional neural network was developed for automated detection of vision-threatening referable DR (preproliferative DR or worse, diabetic macular edema, or both). The DLA was tested by using a set of 106,244 nonstereoscopic retinal images. A panel of ophthalmologists graded DR severity in retinal photographs included in the development and internal validation data sets (n = 71,043); a reference standard grading was assigned once three graders achieved consistent grading outcomes. For external validation, we tested our DLA using 35,201 images of 14,520 eyes (904 eyes with any DR; 401 eyes with vision-threatening referable DR) from population-based cohorts of Malays, Caucasian Australians, and Indigenous Australians.

RESULTS

Among the 71,043 retinal images in the training and validation data sets, 12,329 showed vision-threatening referable DR. In the internal validation data set, the area under the curve (AUC), sensitivity, and specificity of the DLA for vision-threatening referable DR were 0.989, 97.0%, and 91.4%, respectively. Testing against the independent, multiethnic data set achieved an AUC, sensitivity, and specificity of 0.955, 92.5%, and 98.5%, respectively. Among false-positive cases, 85.6% were due to a misclassification of mild or moderate DR. Undetected intraretinal microvascular abnormalities accounted for 77.3% of all false-negative cases.

CONCLUSIONS

This artificial intelligence-based DLA can be used with high accuracy in the detection of vision-threatening referable DR in retinal images. This technology offers potential to increase the efficiency and accessibility of DR screening programs.

Non-mydriatic ultrawide field scanning laser ophthalmoscopy compared with dilated fundal examination for assessment of diabetic retinopathy and diabetic macular oedema in Chinese individuals with diabetes mellitus

AIMS

To evaluate the performance of ultrawide field scanning laser ophthalmoscopy (UWF-SLO) for assessing diabetic retinopathy (DR) and diabetic macular oedema (DME) in a Chinese population, compared with clinical examination.

METHODS

This is a retrospective cohort study. A series of 322 eyes from 164 patients with DM were included. Each patient underwent both dilated fundal examination with DR and DME grading by retina specialist and non-mydriatic 200° UWF-SLO (Daytona, Optos, Dunfermline, UK). The severity of DR and DME from UWF-SLO images was further graded by ophthalmologists, according to both international clinical DR and DME disease severity scales and the standard 7-field Early Treatment Diabetic Retinopathy Study (ETDRS) scale. Any DR, DME and vision-threatening DR (VTDR) were treated as endpoints for this study.

RESULTS

23 out of 322 images (7.14%), including all four cases with proliferative DR on clinical examinations, were determined as ungradable. When the international scale was used for grading UWF-SLO images, the sensitivity of any DR, DME and VTDR was 67.7%, 67.4% and 72.6%, respectively; the specificity of any DR, DME and VTDR was 97.8%, 97.3% and 97.8%, respectively. The agreement with clinical grading in picking up any DR, DME and VTDR was substantial, with κ-values of 0.634, 0.694 and 0.707, respectively. The performance of UWF-SLO was shown to be lower when ETDRS scale was used for grading the images.

CONCLUSION

The performance of non-mydriatic UWF-SLO is comparable in identifying DR with that of clinical examination in a Chinese cohort. However, whether UWF-SLO can be considered as tool for screening DR is still undetermined.

Transforming Retinal Photographs to Entropy Images in Deep Learning to Improve Automated Detection for Diabetic Retinopathy

Entropy images, representing the complexity of original fundus photographs, may strengthen the contrast between diabetic retinopathy (DR) lesions and unaffected areas. The aim of this study is to compare the detection performance for severe DR between original fundus photographs and entropy images by deep learning. A sample of 21,123 interpretable fundus photographs obtained from a publicly available data set was expanded to 33,000 images by rotating and flipping. All photographs were transformed into entropy images using block size 9 and downsized to a standard resolution of 100 × 100 pixels. The stages of DR are classified into 5 grades based on the International Clinical Diabetic Retinopathy Disease Severity Scale: Grade 0 (no DR), Grade 1 (mild nonproliferative DR), Grade 2 (moderate nonproliferative DR), Grade 3 (severe nonproliferative DR), and Grade 4 (proliferative DR). Of these 33,000 photographs, 30,000 images were randomly selected as the training set, and the remaining 3,000 images were used as the testing set. Both the original fundus photographs and the entropy images were used as the inputs of convolutional neural network (CNN), and the results of detecting referable DR (Grades 2–4) as the outputs from the two data sets were compared. The detection accuracy, sensitivity, and specificity of using the original fundus photographs data set were 81.80%, 68.36%, 89.87%, respectively, for the entropy images data set, and the figures significantly increased to 86.10%, 73.24%, and 93.81%, respectively (all p values <0.001). The entropy image quantifies the amount of information in the fundus photograph and efficiently accelerates the generating of feature maps in the CNN. The research results draw the conclusion that transformed entropy imaging of fundus photographs can increase the machinery detection accuracy, sensitivity, and specificity of referable DR for the deep learning-based system.

Prevalence and association of clinical characteristics and biochemical factors with complications of diabetes mellitus in Palestinians treated in primary healthcare practice

AIMS

The current study was carried out to examine prevalence of complications related to diabetes mellitus (DM) and to investigate association between clinical variables and biochemical factors with complications of DM in patients treated in primary healthcare settings in the West Bank of Palestine.

MATERIALS AND METHODS

Sociodemographic, clinical, and biochemical variables were collected from 385 patients visiting 17 primary healthcare settings in the West Bank. Patients provided blood and urine samples, responded to a questionnaire interview, and were subjected to ophthalmic examination.

RESULTS

HbA_1c levels were predicted by duration of DM (p < 0.001), HDL (p = 0.011), alkaline phosphatase (p = 0.001), blood urea (p = 0.006), and LDL (p = 0.008). Triglycerides levels were predicted by blood urea (p = 0.002), HDL (p < 0.001), and total cholesterol (p < 0.001). GOT levels were predicted by LDL (p = 0.002) and GPT (p < 0.001). GPT levels were predicted by HDL (p = 0.003) and blood urea (p = 0.025). Urine albumin were predicted by total cholesterol (p = 0.001), LDL (p = 0.005), and blood urea (p = 0.036). CD ratio was predicted by the IOP and the IOP was predicted by the CD ratio (p = 0.001).

CONCLUSIONS

Prevalence of complications related to DM was high among patients with DM treated in primary healthcare practice. These complications and risk factors were predicted by certain clinical characteristics and biochemical factors. Policies and programs are needed to manage these modifiable risk factors.

Guidelines on Diabetic Eye Care: The International Council of Ophthalmology Recommendations for Screening, Follow-up, Referral, and Treatment Based on Resource Settings

Diabetes mellitus (DM) is a global epidemic and affects populations in both developing and developed countries, with differing health care and resource levels. Diabetic retinopathy (DR) is a major complication of DM and a leading cause of vision loss in working middle-aged adults. Vision loss from DR can be prevented with broad-level public health strategies, but these need to be tailored to a country's and population's resource setting. Designing DR screening programs, with appropriate and timely referral to facilities with trained eye care professionals, and using cost-effective treatment for vision-threatening levels of DR can prevent vision loss. The International Council of Ophthalmology Guidelines for Diabetic Eye Care 2017 summarize and offer a comprehensive guide for DR screening, referral and follow-up schedules for DR, and appropriate management of vision-threatening DR, including diabetic macular edema (DME) and proliferative DR, for countries with high- and low- or intermediate-resource settings. The guidelines include updated evidence on screening and referral criteria, the minimum requirements for a screening vision and retinal examination, follow-up care, and management of DR and DME, including laser photocoagulation and appropriate use of intravitreal anti-vascular endothelial growth factor inhibitors and, in specific situations, intravitreal corticosteroids. Recommendations for management of DR in patients during pregnancy and with concomitant cataract also are included. The guidelines offer suggestions for monitoring outcomes and indicators of success at a population level.

Diabetic Retinopathy in the Asia-Pacific

Diabetic retinopathy (DR), the most common complication of diabetes mellitus, is the leading cause of new cases of blindness in middle-aged and elderly in the Asia-Pacific. It has been estimated that 51% of all those with blindness due to DR globally (n = 424,400) and 56% of those with visual impairment due to DR (2.1 million) come from the Asia-Pacific. Prevalence of DR among those with diabetes ranged from 10% in India to 43% in Indonesia within the Asia-Pacific. Awareness of DR among persons with diabetes ranged from 28% to 84%. Most common modifiable risk factors for DR in the Asia-Pacific were hyperglycemia, blood pressure, dyslipidemia, and obesity. Implementation of systematic screening programs for DR and advancement in telemedicine screening methods have increased patient coverage and cost-effectiveness, though there are still numerous factors impeding screening uptake in the low-middle income regions of the Asia-Pacific. Management and treatment of DR in the Asia-Pacific is mainly limited to traditional laser retinopexy, but it is suboptimal despite new clinical approaches such as use of intravitreal anti.vascular endothelial growth factor and steroids due to limited resources. Further research and data are required to structure a more cost-effective public healthcare program and more awareness-building initiatives to increase the effectiveness of DR screening programs.

Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes

IMPORTANCE

A deep learning system (DLS) is a machine learning technology with potential for screening diabetic retinopathy and related eye diseases.

OBJECTIVE

To evaluate the performance of a DLS in detecting referable diabetic retinopathy, vision-threatening diabetic retinopathy, possible glaucoma, and age-related macular degeneration (AMD) in community and clinic-based multiethnic populations with diabetes.

DESIGN, SETTING, AND PARTICIPANTS

Diagnostic performance of a DLS for diabetic retinopathy and related eye diseases was evaluated using 494 661 retinal images. A DLS was trained for detecting diabetic retinopathy (using 76 370 images), possible glaucoma (125 189 images), and AMD (72 610 images), and performance of DLS was evaluated for detecting diabetic retinopathy (using 112 648 images), possible glaucoma (71 896 images), and AMD (35 948 images). Training of the DLS was completed in May 2016, and validation of the DLS was completed in May 2017 for detection of referable diabetic retinopathy (moderate nonproliferative diabetic retinopathy or worse) and vision-threatening diabetic retinopathy (severe nonproliferative diabetic retinopathy or worse) using a primary validation data set in the Singapore National Diabetic Retinopathy Screening Program and 10 multiethnic cohorts with diabetes.

EXPOSURES

Use of a deep learning system.

MAIN OUTCOMES AND MEASURES

Area under the receiver operating characteristic curve (AUC) and sensitivity and specificity of the DLS with professional graders (retinal specialists, general ophthalmologists, trained graders, or optometrists) as the reference standard.

RESULTS

In the primary validation dataset (n = 14 880 patients; 71 896 images; mean [SD] age, 60.2 [2.2] years; 54.6% men), the prevalence of referable diabetic retinopathy was 3.0%; vision-threatening diabetic retinopathy, 0.6%; possible glaucoma, 0.1%; and AMD, 2.5%. The AUC of the DLS for referable diabetic retinopathy was 0.936 (95% CI, 0.925-0.943), sensitivity was 90.5% (95% CI, 87.3%-93.0%), and specificity was 91.6% (95% CI, 91.0%-92.2%). For vision-threatening diabetic retinopathy, AUC was 0.958 (95% CI, 0.956-0.961), sensitivity was 100% (95% CI, 94.1%-100.0%), and specificity was 91.1% (95% CI, 90.7%-91.4%). For possible glaucoma, AUC was 0.942 (95% CI, 0.929-0.954), sensitivity was 96.4% (95% CI, 81.7%-99.9%), and specificity was 87.2% (95% CI, 86.8%-87.5%). For AMD, AUC was 0.931 (95% CI, 0.928-0.935), sensitivity was 93.2% (95% CI, 91.1%-99.8%), and specificity was 88.7% (95% CI, 88.3%-89.0%). For referable diabetic retinopathy in the 10 additional datasets, AUC range was 0.889 to 0.983 (n = 40 752 images).

CONCLUSIONS AND RELEVANCE

In this evaluation of retinal images from multiethnic cohorts of patients with diabetes, the DLS had high sensitivity and specificity for identifying diabetic retinopathy and related eye diseases. Further research is necessary to evaluate the applicability of the DLS in health care settings and the utility of the DLS to improve vision outcomes.

Clinical and Biochemical Associations with Diabetic Retinopathy in Male Patients in the Gaza Strip

BACKGROUND

There are limited data on the prevalence and risk factors for diabetic retinopathy (DR) in the Gaza Strip.

OBJECTIVE

To assesses clinical and biochemical associated with DR in males with type 2 diabetes mellitus (T2DM) in the Gaza Strip.

METHODS

One hundred and fifty males with T2DM from the Gaza Strip underwent a questionnaire interview, serum biochemical analysis, and assessment of their previous urine and blood results.

RESULTS

The prevalence of DR was 24.7%. The duration of diabetes and prevalence of neuropathy, nephropathy, cardiovascular disease, and recurrent infections were significantly higher among patients with DR compared with those without DR (p < 0.05). Serum urea, creatinine, glucose, cholesterol, and low-density lipoprotein cholesterol were significantly elevated, whilst eGFR and high-density lipoprotein cholesterol were significantly lower in patients with DR compared with patients without DR (p < 0.05). Urinary albumin concentration and albumin creatinine ratio (ACR) was higher in patients with DR. ACR correlated significantly with the duration of T2DM (r = 0.311, p < 0.001), glucose (r = 0.479, p < 0.001), urea (r = 0.337, p < 0.001), creatinine (r = 0.275, p = 0.001), and GFR (r = -0.275, p < 0.001).

CONCLUSION

These data show a high prevalence of DR in an unselected cohort of patients with T2DM and relationships to modifiable risk factors in Gaza.