Artificial intelligence-enabled screening for diabetic retinopathy: a real-world, multicenter and prospective study

Transforming Non-Digital, Clinical Workflows to Detect and Track Vision-Threatening Diabetic Retinopathy via a Digital Platform Integrating Artificial Intelligence: Implementation Research

INTRODUCTION

Screening diabetic retinopathy (DR) for timely management can reduce global blindness. Many existing DR screening programs worldwide are non-digital, standalone, and deployed with grading retinal photographs by trained personnel. To integrate the screening programs, with or without artificial intelligence (AI), into hospital information systems to improve their effectiveness, the non-digital workflow must be transformed into digital. We developed a cloud-based digital platform and implemented it in an existing DR screening program.

METHODS

We conducted the following processes in the platform for prospective DR screening at a community hospital: capturing patients' retinal photographs, uploading them for grading by AI or trained personnel on alternate weeks for 32 weeks, and referring vision-threatening DR to a referral center. At this center, the platform was applied for the assessment of potential missed referrals via remote over-reading by a retinal specialist and tracking referrals. Implementational outcomes, such as detecting positive cases, agreement between AI and over-reading, and referral adherence were assessed.

RESULTS

Of 645 patients screened by AI, 201 (31.2%) were referrals, 129 (64.2%) of which were true positives agreeable by over-reading; 115 of these true positives (89.1%) had referral adherence. False negatives judged by over-reading were 1.1% (5/444). Of 730 patients in manual screening, 175 (24.0%) were potential referrals, 11 (6.3%) of which were referred at the point-of-screening; eight of these (72.7%) adhered to referral. The remaining 164 cases were appointed for later examination by a visiting general ophthalmologist; 11 of these 116 examined (9.5%) were referred for non-DR-related eye conditions with 81.8% (9/11) referral adherence. No system failure or interruption was found.

CONCLUSIONS

The digital platform can be practically integrated into the existing non-digital DR screening programs to implement AI and monitor previously unknown but important indicators, such as referral adherence, to improve the effectiveness of the programs.

TRIAL REGISTRATION

ClinicalTrials.gov. (registration number: NCT05166122).

The Relationship Between Age at Diabetes Onset and Clinical Outcomes in Newly Diagnosed Type 2 Diabetes: A Real-World Two-Center Study

Purpose

This study was developed with the goal of clarifying whether there is any relationship between type 2 diabetes mellitus (T2DM) age of onset and clinical outcomes for patients in National Metabolic Management Centers (MMC).

Patients and Methods

From September 2017 - June 2022, 864 total T2DM patients were recruited in MMC and assigned to those with early-onset and late-onset diabetes (EOD and LOD) based on whether their age at disease onset was ≤ 40 or > 40 years. All patients received standardized management. Baseline and 1-year follow-up data from these two groups of patients were assessed. Associations between onset age and other factors were evaluated with a multivariate linear regression approach, adjusting for appropriate covariates. Outcomes in particular subgroups were also assessed in stratified analyses.

Results

Markers of dysregulated glucose metabolism and BMI values were significantly higher among EOD patients as compared to LOD patients. Subjects in both groups exhibited significant improvements in several disease-related parameters on 1-year follow-up after undergoing metabolic management. EOD patients exhibited significantly greater percentage reductions in HbA1c levels (-28.49 (-44.26, -6.45)% vs -13.70 (-30.15,-1.60)%, P =0.017) relative to LOD patients following adjustment for confounders. Significant differences were also detected between these groups when focused on subgroups of patients who were male, exhibited a BMI ≥ 25, an HbA1c ≥ 9, or had a follow-up frequency < 2.

Conclusion

Data from a 1-year follow-up time point suggest that a standardized metabolic disease management model can promote effective metabolic control in newly diagnosed T2DM patients, particularly among individuals with EOD.

Screening chronic kidney disease through deep learning utilizing ultra-wide-field fundus images

To address challenges in screening for chronic kidney disease (CKD), we devised a deep learning-based CKD screening model named UWF-CKDS. It utilizes ultra-wide-field (UWF) fundus images to predict the presence of CKD. We validated the model with data from 23 tertiary hospitals across China. Retinal vessels and retinal microvascular parameters (RMPs) were extracted to enhance model interpretability, which revealed a significant correlation between renal function and RMPs. UWF-CKDS, utilizing UWF images, RMPs, and relevant medical history, can accurately determine CKD status. Importantly, UWF-CKDS exhibited superior performance compared to CTR-CKDS, a model developed using the central region (CTR) cropped from UWF images, underscoring the contribution of the peripheral retina in predicting renal function. The study presents UWF-CKDS as a highly implementable method for large-scale and accurate CKD screening at the population level.

Discriminative, generative artificial intelligence, and foundation models in retina imaging

Recent advances of artificial intelligence (AI) in retinal imaging found its application in two major categories: discriminative and generative AI. For discriminative tasks, conventional convolutional neural networks (CNNs) are still major AI techniques. Vision transformers (ViT), inspired by the transformer architecture in natural language processing, has emerged as useful techniques for discriminating retinal images. ViT can attain excellent results when pretrained at sufficient scale and transferred to specific tasks with fewer images, compared to conventional CNN. Many studies found better performance of ViT, compared to CNN, for common tasks such as diabetic retinopathy screening on color fundus photographs (CFP) and segmentation of retinal fluid on optical coherence tomography (OCT) images. Generative Adversarial Network (GAN) is the main AI technique in generative AI in retinal imaging. Novel images generated by GAN can be applied for training AI models in imbalanced or inadequate datasets. Foundation models are also recent advances in retinal imaging. They are pretrained with huge datasets, such as millions of CFP and OCT images and fine-tuned for downstream tasks with much smaller datasets. A foundation model, RETFound, which was self-supervised and found to discriminate many eye and systemic diseases better than supervised models. Large language models are foundation models that may be applied for text-related tasks, like reports of retinal angiography. Whereas AI technology moves forward fast, real-world use of AI models moves slowly, making the gap between development and deployment even wider. Strong evidence showing AI models can prevent visual loss may be required to close this gap.

Advancing healthcare with artificial intelligence: diagnostic accuracy of machine learning algorithm in diagnosis of diabetic retinopathy in the Brazilian population

BACKGROUND

In healthcare systems in general, access to diabetic retinopathy (DR) screening is limited. Artificial intelligence has the potential to increase care delivery. Therefore, we trained and evaluated the diagnostic accuracy of a machine learning algorithm for automated detection of DR.

METHODS

We included color fundus photographs from individuals from 4 databases (primary and specialized care settings), excluding uninterpretable images. The datasets consist of images from Brazilian patients, which differs from previous work. This modification allows for a more tailored application of the model to Brazilian patients, ensuring that the nuances and characteristics of this specific population are adequately captured. The sample was fractionated in training (70%) and testing (30%) samples. A convolutional neural network was trained for image classification. The reference test was the combined decision from three ophthalmologists. The sensitivity, specificity, and area under the ROC curve of the algorithm for detecting referable DR (moderate non-proliferative DR; severe non-proliferative DR; proliferative DR and/or clinically significant macular edema) were estimated.

RESULTS

A total of 15,816 images (4590 patients) were included. The overall prevalence of any degree of DR was 26.5%. Compared with human evaluators (manual method of diagnosing DR performed by an ophthalmologist), the deep learning algorithm achieved an area under the ROC curve of 0.98 (95% CI 0.97-0.98), with a specificity of 94.6% (95% CI 93.8-95.3) and a sensitivity of 93.5% (95% CI 92.2-94.9) at the point of greatest efficiency to detect referable DR.

CONCLUSIONS

A large database showed that this deep learning algorithm was accurate in detecting referable DR. This finding aids to universal healthcare systems like Brazil, optimizing screening processes and can serve as a tool for improving DR screening, making it more agile and expanding care access.

Impact of Gold-Standard Label Errors on Evaluating Performance of Deep Learning Models in Diabetic Retinopathy Screening: Nationwide Real-World Validation Study

BACKGROUND

For medical artificial intelligence (AI) training and validation, human expert labels are considered the gold standard that represents the correct answers or desired outputs for a given data set. These labels serve as a reference or benchmark against which the model's predictions are compared.

OBJECTIVE

This study aimed to assess the accuracy of a custom deep learning (DL) algorithm on classifying diabetic retinopathy (DR) and further demonstrate how label errors may contribute to this assessment in a nationwide DR-screening program.

METHODS

Fundus photographs from the Lifeline Express, a nationwide DR-screening program, were analyzed to identify the presence of referable DR using both (1) manual grading by National Health Service England-certificated graders and (2) a DL-based DR-screening algorithm with validated good lab performance. To assess the accuracy of labels, a random sample of images with disagreement between the DL algorithm and the labels was adjudicated by ophthalmologists who were masked to the previous grading results. The error rates of labels in this sample were then used to correct the number of negative and positive cases in the entire data set, serving as postcorrection labels. The DL algorithm's performance was evaluated against both pre- and postcorrection labels.

RESULTS

The analysis included 736,083 images from 237,824 participants. The DL algorithm exhibited a gap between the real-world performance and the lab-reported performance in this nationwide data set, with a sensitivity increase of 12.5% (from 79.6% to 92.5%, P<.001) and a specificity increase of 6.9% (from 91.6% to 98.5%, P<.001). In the random sample, 63.6% (560/880) of negative images and 5.2% (140/2710) of positive images were misclassified in the precorrection human labels. High myopia was the primary reason for misclassifying non-DR images as referable DR images, while laser spots were predominantly responsible for misclassified referable cases. The estimated label error rate for the entire data set was 1.2%. The label correction was estimated to bring about a 12.5% enhancement in the estimated sensitivity of the DL algorithm (P<.001).

CONCLUSIONS

Label errors based on human image grading, although in a small percentage, can significantly affect the performance evaluation of DL algorithms in real-world DR screening.

Development and external validation of a predictive model for type 2 diabetic retinopathy

Diabetes retinopathy (DR) is a critical clinical disease with that causes irreversible visual damage in adults, and may even lead to permanent blindness in serious cases. Early identification and treatment of DR is critical. Our aim was to train and externally validate a prediction nomogram for early prediction of DR. 2381 patients with type 2 diabetes mellitus (T2DM) were retrospective study from the First Affiliated Hospital of Xinjiang Medical University in Xinjiang, China, hospitalised between Jan 1, 2019 and Jun 30, 2022. 962 patients with T2DM from the Suzhou BenQ Hospital in Jiangsu, China hospitalised between Jul 1, 2020 to Jun 30, 2022 were considered for external validation. The least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression was performed to identify independent predictors and establish a nomogram to predict the occurrence of DR. The performance of the nomogram was evaluated using a receiver operating characteristic curve (ROC), a calibration curve, and decision curve analysis (DCA). Neutrophil, 25-hydroxyvitamin D3 [25(OH)D3], Duration of T2DM, hemoglobin A1c (HbA1c), and Apolipoprotein A1 (ApoA1) were used to establish a nomogram model for predicting the risk of DR. In the development and external validation groups, the areas under the curve of the nomogram constructed from the above five factors were 0.834 (95%CI 0.820-0.849) and 0.851 (95%CI 0.829-0.874), respectively. The nomogram demonstrated excellent performance in the calibration curve and DCA. This research has developed and externally verified that the nomograph model shows a good predictive ability in assessing DR risk in people with type 2 diabetes. The application of this model will help clinicians to intervene early, thus effectively reducing the incidence rate and mortality of DR in the future, and has far-reaching significance in improving the long-term health prognosis of diabetes patients.

Transparency in Artificial Intelligence Reporting in Ophthalmology-A Scoping Review

Topic

This scoping review summarizes artificial intelligence (AI) reporting in ophthalmology literature in respect to model development and validation. We characterize the state of transparency in reporting of studies prospectively validating models for disease classification.

Clinical Relevance

Understanding what elements authors currently describe regarding their AI models may aid in the future standardization of reporting. This review highlights the need for transparency to facilitate the critical appraisal of models prior to clinical implementation, to minimize bias and inappropriate use. Transparent reporting can improve effective and equitable use in clinical settings.

Methods

Eligible articles (as of January 2022) from PubMed, Embase, Web of Science, and CINAHL were independently screened by 2 reviewers. All observational and clinical trial studies evaluating the performance of an AI model for disease classification of ophthalmic conditions were included. Studies were evaluated for reporting of parameters derived from reporting guidelines (CONSORT-AI, MI-CLAIM) and our previously published editorial on model cards. The reporting of these factors, which included basic model and dataset details (source, demographics), and prospective validation outcomes, were summarized.

Results

Thirty-seven prospective validation studies were included in the scoping review. Eleven additional associated training and/or retrospective validation studies were included if this information could not be determined from the primary articles. These 37 studies validated 27 unique AI models; multiple studies evaluated the same algorithms (EyeArt, IDx-DR, and Medios AI). Details of model development were variably reported; 18 of 27 models described training dataset annotation and 10 of 27 studies reported training data distribution. Demographic information of training data was rarely reported; 7 of the 27 unique models reported age and gender and only 2 reported race and/or ethnicity. At the level of prospective clinical validation, age and gender of populations was more consistently reported (29 and 28 of 37 studies, respectively), but only 9 studies reported race and/or ethnicity data. Scope of use was difficult to discern for the majority of models. Fifteen studies did not state or imply primary users.

Conclusion

Our scoping review demonstrates variable reporting of information related to both model development and validation. The intention of our study was not to assess the quality of the factors we examined, but to characterize what information is, and is not, regularly reported. Our results suggest the need for greater transparency in the reporting of information necessary to determine the appropriateness and fairness of these tools prior to clinical use.

Financial Disclosures

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

Effectiveness of artificial intelligence for diabetic retinopathy screening in community in Binh Dinh Province, Vietnam

PURPOSE

The objective of this study is to evaluate the sensitivity, specificity, and accuracy of artificial intelligence (AI) for diabetic retinopathy (DR) screening in community in Binh Dinh Province in Vietnam.

MATERIALS AND METHODS

This retrospective, descriptive, cross-sectional study assessed the DR screening efficacy of EyeArt system v2.0 by analyzing 2332 nonmydriatic digital fundus pictures of 583 diabetic patients from hospitals and health centers in Binh Dinh province. First, we selected thirty patients with 120 digital fundus pictures to perform the Kappa index by two eye doctors who would be responsible for the DR clinical feature evaluation and DR severity scale classification. Second, all digital fundus pictures were coded and then sent to the two above-mentioned eye doctors for the evaluation and classifications according to the International Committee of Ophthalmology's guidelines. Finally, DR severity scales with EyeArt were compared with those by eye doctors as a reference standard for EyeArt's effectiveness. All the data were analyzed using the SPSS software version 20.0. Values (with confidence interval 95%) of sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were calculated according to DR state, referable or not and vision-threatening DR state or not. P < 0.05 was considered statistically significant.

RESULTS

The sensitivity and specificity of EyeArt for DR screening were 94.1% and 87.2%. The sensitivity and specificity for referable DR and vision-threatening DR were 96.6%, 90.1%, and 100.0%, 92.2%. Accuracy for DR screening, referable DR, and vision-threatening DR were 88.9%, 91.4%, and 93.0%, respectively.

CONCLUSION

EyeArt AI was effective for DR screening in community.

Diabetes management in the era of artificial intelligence

Artificial intelligence is growing quickly, and its application in the global diabetes pandemic has the potential to completely change the way this chronic illness is identified and treated. Machine learning methods have been used to construct algorithms supporting predictive models for the risk of getting diabetes or its complications. Social media and Internet forums also increase patient participation in diabetes care. Diabetes resource usage optimisation has benefited from technological improvements. As a lifestyle therapy intervention, digital therapies have made a name for themselves in the treatment of diabetes. Artificial intelligence will cause a paradigm shift in diabetes care, moving away from current methods and toward the creation of focused, data-driven precision treatment.

Deep learning detection of diabetic retinopathy in Scotland's diabetic eye screening programme

BACKGROUND/AIMS

Support vector machine-based automated grading (known as iGradingM) has been shown to be safe, cost-effective and robust in the diabetic retinopathy (DR) screening (DES) programme in Scotland. It triages screening episodes as gradable with no DR versus manual grading required. The study aim was to develop a deep learning-based autograder using images and gradings from DES and to compare its performance with that of iGradingM.

METHODS

Retinal images, quality assurance (QA) data and routine DR grades were obtained from national datasets in 179 944 patients for years 2006-2016. QA grades were available for 744 images. We developed a deep learning-based algorithm to detect whether either eye contained ungradable images or any DR. The sensitivity and specificity were evaluated against consensus QA grades and routine grades.

RESULTS

Images used in QA which were ungradable or with DR were detected by deep learning with better specificity compared with manual graders (p<0.001) and with iGradingM (p<0.001) at the same sensitivities. Any DR according to the DES final grade was detected with 89.19% (270 392/303 154) sensitivity and 77.41% (500 945/647 158) specificity. Observable disease and referable disease were detected with sensitivities of 96.58% (16 613/17 201) and 98.48% (22 600/22 948), respectively. Overall, 43.84% of screening episodes would require manual grading.

CONCLUSION

A deep learning-based system for DR grading was evaluated in QA data and images from 11 years in 50% of people attending a national DR screening programme. The system could reduce the manual grading workload at the same sensitivity compared with the current automated grading system.

Ferric particle-assisted LDI-MS platform for metabolic fingerprinting of diabetic retinopathy

OBJECTIVES

To explore the metabolic fingerprints of diabetic retinopathy (DR) in individuals with type 2 diabetes using a newly-developed laser desorption/ionization mass spectrometry (LDI-MS) platform assisted by ferric particles.

METHODS

Metabolic fingerprinting was performed using a ferric particle-assisted LDI-MS platform. A nested population-based case-control study was performed on 216 DR cases and 216 control individuals with type 2 diabetes.

RESULTS

DR cases and control individuals with type 2 diabetes were comparable for a list of clinical factors. The newly-developed LDI-MS platform allowed us to draw the blueprint of plasma metabolic fingerprints from participants with and without DR. The neural network afforded diagnostic performance with an average area under curve value of 0.928 for discovery cohort and 0.905 for validation cohort (95 % confidence interval: 0.902-0.954 and 0.845-0.965, respectively). Tandem MS and Fourier transform ion cyclotron resonance MS with ultrahigh resolution identified seven specific metabolites that were significantly associated with DR in fully adjusted models. Of these metabolites, dihydrobiopterin, phosphoserine, N-arachidonoylglycine, and 3-methylhistamine levels in plasma were first reported to show the associations.

CONCLUSIONS

This work advances the design of metabolic analysis for DR and holds the potential to promise as an efficient tool for clinical management of DR.

An Economic Analysis for the Use of Artificial Intelligence in Screening for Diabetic Retinopathy in Trinidad and Tobago

This is a systematic review of 25 publications on the topics of the prevalence and cost of diabetic retinopathy (DR) in Trinidad and Tobago, the cost of traditional methods of screening for DR, and the use and cost of artificial intelligence (AI) in screening for DR. Analysis of these publications was used to identify and make estimates for how resources allocated to ophthalmology in public health systems in Trinidad and Tobago can be more efficiently utilized by employing AI in diagnosing treatable DR. DR screening was found to be an effective method of detecting the disease. Screening was found to be a universally cost-effective method of disease prevention and for altering the natural history of the disease in the spectrum of low-middle to high-income economies, such as Rwanda, Thailand, China, South Korea, and Singapore. AI and deep learning systems were found to be clinically superior to, or as effective as, human graders in areas where they were deployed, indicating that the systems are clinically safe. They have been shown to improve access to diabetic retinal screening, improve compliance with screening appointments, and prove to be cost-effective, especially in rural areas. Trinidad and Tobago, which is estimated to be disproportionately more affected by the burden of DR when projected out to the mid-21st century, stands to save as much as US$60 million annually from the implementation of an AI-based system to screen for DR versus conventional manual grading.

Application of non-mydriatic fundus photography-assisted telemedicine in diabetic retinopathy screening

BACKGROUND

Early screening and accurate staging of diabetic retinopathy (DR) can reduce blindness risk in type 2 diabetes patients. DR's complex pathogenesis involves many factors, making ophthalmologist screening alone insufficient for prevention and treatment. Often, endocrinologists are the first to see diabetic patients and thus should screen for retinopathy for early intervention.

AIM

To explore the efficacy of non-mydriatic fundus photography (NMFP)-enhanced telemedicine in assessing DR and its various stages.

METHODS

This retrospective study incorporated findings from an analysis of 93 diabetic patients, examining both NMFP-assisted telemedicine and fundus fluorescein angiography (FFA). It focused on assessing the concordance in DR detection between these two methodologies. Additionally, receiver operating characteristic (ROC) curves were generated to determine the optimal sensitivity and specificity of NMFP-assisted telemedicine, using FFA outcomes as the standard benchmark.

RESULTS

In the context of DR diagnosis and staging, the kappa coefficients for NMFP-assisted telemedicine and FFA were recorded at 0.775 and 0.689 respectively, indicating substantial intermethod agreement. Moreover, the NMFP-assisted telemedicine's predictive accuracy for positive FFA outcomes, as denoted by the area under the ROC curve, was remarkably high at 0.955, within a confidence interval of 0.914 to 0.995 and a statistically significant P-value of less than 0.001. This predictive model exhibited a specificity of 100%, a sensitivity of 90.9%, and a Youden index of 0.909.

CONCLUSION

NMFP-assisted telemedicine represents a pragmatic, objective, and precise modality for fundus examination, particularly applicable in the context of endocrinology inpatient care and primary healthcare settings for diabetic patients. Its implementation in these scenarios is of paramount significance, enhancing the clinical accuracy in the diagnosis and therapeutic management of DR. This methodology not only streamlines patient evaluation but also contributes substantially to the optimization of clinical outcomes in DR management.

Implementing and evaluating a fully functional AI-enabled model for chronic eye disease screening in a real clinical environment

BACKGROUND

Artificial intelligence (AI) has the potential to increase the affordability and accessibility of eye disease screening, especially with the recent approval of AI-based diabetic retinopathy (DR) screening programs in several countries.

METHODS

This study investigated the performance, feasibility, and user experience of a seamless hardware and software solution for screening chronic eye diseases in a real-world clinical environment in Germany. The solution integrated AI grading for DR, age-related macular degeneration (AMD), and glaucoma, along with specialist auditing and patient referral decision. The study comprised several components: (1) evaluating the entire system solution from recruitment to eye image capture and AI grading for DR, AMD, and glaucoma; (2) comparing specialist's grading results with AI grading results; (3) gathering user feedback on the solution.

RESULTS

A total of 231 patients were recruited, and their consent forms were obtained. The sensitivity, specificity, and area under the curve for DR grading were 100.00%, 80.10%, and 90.00%, respectively. For AMD grading, the values were 90.91%, 78.79%, and 85.00%, and for glaucoma grading, the values were 93.26%, 76.76%, and 85.00%. The analysis of all false positive cases across the three diseases and their comparison with the final referral decisions revealed that only 17 patients were falsely referred among the 231 patients. The efficacy analysis of the system demonstrated the effectiveness of the AI grading process in the study's testing environment. Clinical staff involved in using the system provided positive feedback on the disease screening process, particularly praising the seamless workflow from patient registration to image transmission and obtaining the final result. Results from a questionnaire completed by 12 participants indicated that most found the system easy, quick, and highly satisfactory. The study also revealed room for improvement in the AMD model, suggesting the need to enhance its training data. Furthermore, the performance of the glaucoma model grading could be improved by incorporating additional measures such as intraocular pressure.

CONCLUSIONS

The implementation of the AI-based approach for screening three chronic eye diseases proved effective in real-world settings, earning positive feedback on the usability of the integrated platform from both the screening staff and auditors. The auditing function has proven valuable for obtaining efficient second opinions from experts, pointing to its potential for enhancing remote screening capabilities.

TRIAL REGISTRATION

Institutional Review Board of the Hamburg Medical Chamber (Ethik-Kommission der Ärztekammer Hamburg): 2021-10574-BO-ff.

How Can Artificial Intelligence Be Implemented Effectively in Diabetic Retinopathy Screening in Japan?

Diabetic retinopathy (DR) is a major microvascular complication of diabetes, affecting a substantial portion of diabetic patients worldwide. Timely intervention is pivotal in mitigating the risk of blindness associated with DR, yet early detection remains a challenge due to the absence of early symptoms. Screening programs have emerged as a strategy to address this burden, and this paper delves into the role of artificial intelligence (AI) in advancing DR screening in Japan. There are two pathways for DR screening in Japan: a health screening pathway and a clinical referral path from physicians to ophthalmologists. AI technologies that realize automated image classification by applying deep learning are emerging. These technologies have exhibited substantial promise, achieving sensitivity and specificity levels exceeding 90% in prospective studies. Moreover, we introduce the potential of Generative AI and large language models (LLMs) to transform healthcare delivery, particularly in patient engagement, medical records, and decision support. Considering the use of AI in DR screening in Japan, we propose to follow a seven-step framework for systematic screening and emphasize the importance of integrating AI into a well-designed screening program. Automated scoring systems with AI enhance screening quality, but their effectiveness depends on their integration into the broader screening ecosystem. LLMs emerge as an important tool to fill gaps in the screening process, from personalized invitations to reporting results, facilitating a seamless and efficient system. However, it is essential to address concerns surrounding technical accuracy and governance before full-scale integration into the healthcare system. In conclusion, this review highlights the challenges in the current screening pathway and the potential for AI, particularly LLM, to revolutionize DR screening in Japan. The future direction will depend on leadership from ophthalmologists and stakeholders to address long-standing challenges in DR screening so that all people have access to accessible and effective screening.

The effects of economic status on metabolic control in type 2 diabetes mellitus at 10 metabolic management centers in China

OBJECTIVE

This study investigated the association of economic status with metabolic index control in type 2 diabetes mellitus (T2DM) patients.

METHODS

In total, 37 454 T2DM patients from 10 National Metabolic Management Centers in China were recruited and categorized into two groups: a high-gross domestic product (GDP) group (n = 23 993) and a low-GDP group (n = 13 461). Sociodemographic characteristics, medical histories, and lifestyle factors were recorded. Logistic regression and interaction analysis were performed to evaluate the association of economic status and healthy lifestyle with metabolic control.

RESULTS

Compared to the low-GDP group, there were fewer patients with glycated hemoglobin (HbA1c) levels ≥7% in the high-GDP group. Fewer patients with a high GDP had an abnormal metabolic state (HbA1c ≥ 7%, blood pressure [BP] ≥130/80 mm Hg, total cholesterol [TCH] ≥4.5 mmol/L or body mass index [BMI] ≥24 kg/m2 ). The risks of developing HbA1c ≥ 7% (odds ratios [OR] = 0.545 [95% CI: 0.515-0.577], p < .001), BP ≥ 130/80 mm Hg (OR = 0.808 [95% CI: 0.770-0.849], p < .001), BMI ≥ 24 kg/m2 (OR = 0.840 [95% CI: 0.799-0.884], p < .001), and an abnormal metabolic state (OR = 0.533 [95% CI: 0.444-0.636], p < .001) were significantly lower in the high-GDP group even after adjustment for confounding factors. Younger participants; those with a family history of diabetes, normal weight, and a physical activity level up to standard; and those who did not drink alcohol in the high-GDP group were predisposed to better glycemic levels.

CONCLUSIONS

T2DM patients in economically developed regions had better metabolic control, especially glycemic control. A healthy lifestyle had an additive effect on achieving glycemic goals, even among high-GDP patients.

Population impact and cost-effectiveness of artificial intelligence-based diabetic retinopathy screening in people living with diabetes in Australia: a cost effectiveness analysis

Background

We aimed to evaluate the cost-effectiveness of an artificial intelligence-(AI) based diabetic retinopathy (DR) screening system in the primary care setting for both non-Indigenous and Indigenous people living with diabetes in Australia.

Methods

We performed a cost-effectiveness analysis between January 01, 2022 and August 01, 2023. A decision-analytic Markov model was constructed to simulate DR progression in a population of 1,197,818 non-Indigenous and 65,160 Indigenous Australians living with diabetes aged ≥20 years over 40 years. From a healthcare provider's perspective, we compared current practice to three primary care AI-based screening scenarios-(A) substitution of current manual grading, (B) scaling up to patient acceptance level, and (C) achieving universal screening. Study results were presented as incremental cost-effectiveness ratio (ICER), benefit-cost ratio (BCR), and net monetary benefits (NMB). A Willingness-to-pay (WTP) threshold of AU$50,000 per quality-adjusted life year (QALY) and a discount rate of 3.5% were adopted in this study.

Findings

With the status quo, the non-Indigenous diabetic population was projected to develop 96,269 blindness cases, resulting in AU$13,039.6 m spending on DR screening and treatment during 2020-2060. In comparison, all three intervention scenarios were effective and cost-saving. In particular, if a universal screening program was to be implemented (Scenario C), it would prevent 38,347 blindness cases, gain 172,090 QALYs and save AU$595.8 m, leading to a BCR of 3.96 and NMB of AU$9,200 m. Similar findings were also reported in the Indigenous population. With the status quo, 3,396 Indigenous individuals would develop blindness, which would cost the health system AU$796.0 m during 2020-2060. All three intervention scenarios were cost-saving for the Indigenous population. Notably, universal AI-based DR screening (Scenario C) would prevent 1,211 blindness cases and gain 9,800 QALYs in the Indigenous population, leading to a saving of AU$19.2 m with a BCR of 1.62 and NMB of AU$509 m.

Interpretation

Our findings suggest that implementing AI-based DR screening in primary care is highly effective and cost-saving in both Indigenous and non-Indigenous populations.

Funding

This project received grant funding from the Australian Government: the National Critical Research Infrastructure Initiative, Medical Research Future Fund (MRFAI00035) and the NHMRC Investigator Grant (APP1175405). The contents of the published material are solely the responsibility of the Administering Institution, a participating institution or individual authors and do not reflect the views of the NHMRC. This work was supported by the Global STEM Professorship Scheme (P0046113), the Fundamental Research Funds of the State Key Laboratory of Ophthalmology, Project of Investigation on Health Status of Employees in Financial Industry in Guangzhou, China (Z012014075). The Centre for Eye Research Australia receives Operational Infrastructure Support from the Victorian State Government. W.H. is supported by the Melbourne Research Scholarship established by the University of Melbourne. The funding source had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication.

Effects of sleep duration and changes in body mass index on diabetic kidney disease: a prospective cohort study

Aims

To examine the associations of sleep duration and changes in BMI with the onset of diabetic kidney disease (DKD).

Materials and methods

2,959 participants with type 2 diabetes were divided into three groups based on sleep duration: short (<7 h/day), intermediate (7-9 h/day), or long (>9 h/day). Changes in BMI during follow-up were trisected into loss, stable, or gain groups. DKD was defined as either the urinary albumin/creatinine ratio (UACR) ≥ 3.39 mg/mmol or the estimated glomerular filtration rate (eGFR) < 60 mL/min/1.73m², or both. Cox regression models were used to assess hazard ratios (HRs) and 95% confidence intervals (CIs).

Results

During a mean follow-up of 2.3 years, DKD occurred in 613 participants (20.7%). A J-shaped curve was observed between sleep duration and DKD. Compared to intermediate sleep duration, long sleep duration was associated with higher risks of DKD (HR 1.47; 95% CI: 1.19-1.81). In the joint analyses, compared to participants with intermediate sleep duration and stable BMI, long sleep duration with BMI gain had the highest risks of DKD (HR 2.04; 95% CI: 1.48-2.83). In contrast, short or intermediate sleep duration accompanied by decrease in BMI was associated with a reduced risk of DKD, with HRs of 0.50 (95% CI: 0.31-0.82) and 0.61 (95% CI:0.47-0.80), respectively.

Conclusions

Long sleep duration is significantly associated with an increased risk of DKD, which is further amplified by obesity or BMI gain. These findings suggest that both proper sleep duration and weight control are essential to preventing DKD.

CHILDSTAR: CHIldren Living With Diabetes See and Thrive with AI Review

Background

Artificial intelligence (AI) appears capable of detecting diabetic retinopathy (DR) with a high degree of accuracy in adults; however, there are few studies in children and young adults.

Methods

Children and young adults (3-26 years) with type 1 diabetes mellitus (T1DM) or type 2 diabetes mellitus (T2DM) were screened at the Dhaka BIRDEM-2 hospital, Bangladesh. All gradable fundus images were uploaded to Cybersight AI for interpretation. Two main outcomes were considered at a patient level: 1) Any DR, defined as mild non-proliferative diabetic retinopathy (NPDR or more severe; and 2) Referable DR, defined as moderate NPDR or more severe. Diagnostic test performance comparing Orbis International's Cybersight AI with the reference standard, a fully qualified optometrist certified in DR grading, was assessed using the Matthews correlation coefficient (MCC), area under the receiver operating characteristic curve (AUC-ROC), area under the precision-recall curve (AUC-PR), sensitivity, specificity, positive and negative predictive values.

Results

Among 1274 participants (53.1% female, mean age 16.7 years), 19.4% (n = 247) had any DR according to AI. For referable DR, 2.35% (n = 30) were detected by AI. The sensitivity and specificity of AI for any DR were 75.5% (CI 69.7-81.3%) and 91.8% (CI 90.2-93.5%) respectively, and for referable DR, these values were 84.2% (CI 67.8-100%) and 98.9% (CI 98.3%-99.5%). The MCC, AUC-ROC and the AUC-PR for referable DR were 63.4, 91.2 and 76.2% respectively. AI was most successful in accurately classifying younger children with shorter duration of diabetes.

Conclusions

Cybersight AI accurately detected any DR and referable DR among children and young adults, despite its algorithms having been trained on adults. The observed high specificity is particularly important to avoid over-referral in low-resource settings. AI may be an effective tool to reduce demands on scarce physician resources for the care of children with diabetes in low-resource settings.

Artificial Intelligence and Diabetic Retinopathy: AI Framework, Prospective Studies, Head-to-head Validation, and Cost-effectiveness

Current guidelines recommend that individuals with diabetes receive yearly eye exams for detection of referable diabetic retinopathy (DR), one of the leading causes of new-onset blindness. For addressing the immense screening burden, artificial intelligence (AI) algorithms have been developed to autonomously screen for DR from fundus photography without human input. Over the last 10 years, many AI algorithms have achieved good sensitivity and specificity (>85%) for detection of referable DR compared with human graders; however, many questions still remain. In this narrative review on AI in DR screening, we discuss key concepts in AI algorithm development as a background for understanding the algorithms. We present the AI algorithms that have been prospectively validated against human graders and demonstrate the variability of reference standards and cohort demographics. We review the limited head-to-head validation studies where investigators attempt to directly compare the available algorithms. Next, we discuss the literature regarding cost-effectiveness, equity and bias, and medicolegal considerations, all of which play a role in the implementation of these AI algorithms in clinical practice. Lastly, we highlight ongoing efforts to bridge gaps in AI model data sets to pursue equitable development and delivery.

Watching intense movies increase IOP of primary open angle glaucoma patients: A prospective study

PURPOSE

To investigate intraocular pressure (IOP) changes while viewing smartphone movies under artificial intelligence (AI) monitoring.

METHODS

In all, 48 subjects were recruited from the glaucoma clinic of Xianyou maternal and child health hospital from January 2018 to March 2020. The research consisted of three parts. In part 1, movies rated by the Motion Picture Association of America (MPAA) were viewed via smartphones of various screen sizes under AI supervision for 90minutes, at a distance of 40cm. IOP and biological parameters including anterior chamber angle, Schlemm's canal (SC) cross-sectional area, heart rate, systolic and diastolic blood pressures (SBP and DBP) were measured and analyzed. In part 2, blue-blocking glasses (BB glasses) were worn to repeat the above experiments. In part 3, the efficacy of AI in decreasing attention loss was analyzed. In addition, results were analyzed to determine whether interval breaks, prompted by AI, prevented IOP from rising.

RESULTS

In part 1, the mean IOP of primary open angle glaucoma (POAG) subjects' right eyes significantly increased by 4.828 and 4.974mmHg after watching R and NC-17 movies, respectively. In their left eyes, it increased by 2.876 and 5.767 after watching R and NC-17 movies, respectively. The maximum IOP difference was also increased by 4.782 and 4.510 on right and left eyes, respectively, after viewing NC-17 movies on a 6.1-inch screen. Furthermore, the SC became narrower, whereas heart rate, DBP and SBP increased in the POAG group. In addition, maximum IOP difference was significantly correlated with SC cross-sectional area, DBP and SBP in the POAG group. In part 2, symptom scores were improved by BB glasses; however, IOP was not decreased. In part 3, attention loss was significantly decreased by AI monitoring. On the contrary, AI also prevented IOP from rising via promoting interval rest.

CONCLUSION

Watching adult movies (NC-17) can significantly increase the IOP of POAG patients. AI can prevent IOP from rising by promoting interval rest when viewing NC-17 movies.

Diagnostic test accuracy of artificial intelligence in screening for referable diabetic retinopathy in real-world settings: A systematic review and meta-analysis

Retrospective studies on artificial intelligence (AI) in screening for diabetic retinopathy (DR) have shown promising results in addressing the mismatch between the capacity to implement DR screening and increasing DR incidence. This review sought to evaluate the diagnostic test accuracy (DTA) of AI in screening for referable diabetic retinopathy (RDR) in real-world settings. We searched CENTRAL, PubMed, CINAHL, Scopus, and Web of Science on 9 February 2023. We included prospective DTA studies assessing AI against trained human graders (HGs) in screening for RDR in patients with diabetes. Two reviewers independently extracted data and assessed methodological quality against QUADAS-2 criteria. We used the hierarchical summary receiver operating characteristics (HSROC) model to pool estimates of sensitivity and specificity and, forest plots and SROC plots to visually examine heterogeneity in accuracy estimates. From our initial search results of 3899 studies, we included 15 studies comprising 17 datasets. Meta-analyses revealed a sensitivity of 95.33% (95%CI: 90.60-100%) and specificity of 92.01% (95%CI: 87.61-96.42%) for patient-level analysis (10 datasets, N = 45,785) while, for the eye-level analysis, sensitivity was 91.24% (95%CI: 79.15-100%) and specificity, 93.90% (95%CI: 90.63-97.16%) (7 datasets, N = 15,390). Subgroup analyses did not provide variations in the diagnostic accuracy of country classification and DR classification criteria. However, a moderate increase was observed in diagnostic accuracy in the primary-level healthcare settings: sensitivity of 99.35% (95%CI: 96.85-100%), specificity of 93.72% (95%CI: 88.83-98.61%) and, a minimal decrease in the tertiary-level healthcare settings: sensitivity of 94.71% (95%CI: 89.00-100%), specificity of 90.88% (95%CI: 83.22-98.53%). Sensitivity analyses did not show any variations in studies that included diabetic macular edema in the RDR definition, nor studies with ≥3 HGs. This review provides evidence, for the first time from prospective studies, for the effectiveness of AI in screening for RDR in real-world settings. The results may serve to strengthen existing guidelines to improve current practices.

Artificial intelligence for diabetic retinopathy in low-income and middle-income countries: a scoping review

Diabetic retinopathy (DR) is a leading cause of blindness globally. There is growing evidence to support the use of artificial intelligence (AI) in diabetic eye care, particularly for screening populations at risk of sight loss from DR in low-income and middle-income countries (LMICs) where resources are most stretched. However, implementation into clinical practice remains limited. We conducted a scoping review to identify what AI tools have been used for DR in LMICs and to report their performance and relevant characteristics. 81 articles were included. The reported sensitivities and specificities were generally high providing evidence to support use in clinical practice. However, the majority of studies focused on sensitivity and specificity only and there was limited information on cost, regulatory approvals and whether the use of AI improved health outcomes. Further research that goes beyond reporting sensitivities and specificities is needed prior to wider implementation.

Towards population-independent, multi-disease detection in fundus photographs

Independent validation studies of automatic diabetic retinopathy screening systems have recently shown a drop of screening performance on external data. Beyond diabetic retinopathy, this study investigates the generalizability of deep learning (DL) algorithms for screening various ocular anomalies in fundus photographs, across heterogeneous populations and imaging protocols. The following datasets are considered: OPHDIAT (France, diabetic population), OphtaMaine (France, general population), RIADD (India, general population) and ODIR (China, general population). Two multi-disease DL algorithms were developed: a Single-Dataset (SD) network, trained on the largest dataset (OPHDIAT), and a Multiple-Dataset (MD) network, trained on multiple datasets simultaneously. To assess their generalizability, both algorithms were evaluated whenever training and test data originate from overlapping datasets or from disjoint datasets. The SD network achieved a mean per-disease area under the receiver operating characteristic curve (mAUC) of 0.9571 on OPHDIAT. However, it generalized poorly to the other three datasets (mAUC < 0.9). When all four datasets were involved in training, the MD network significantly outperformed the SD network (p = 0.0058), indicating improved generality. However, in leave-one-dataset-out experiments, performance of the MD network was significantly lower on populations unseen during training than on populations involved in training (p < 0.0001), indicating imperfect generalizability.

Visit-to-visit HbA1c variability is associated with aortic stiffness progression in participants with type 2 diabetes

BACKGROUND

Glycemic variability plays an important role in the development of cardiovascular disease (CVD). This study aims to determine whether long-term visit-to-visit glycemic variability is associated with aortic stiffness progression in participants with type 2 diabetes (T2D).

METHODS

Prospective data were obtained from 2115 T2D participants in the National Metabolic Management Center (MMC) from June 2017 to December 2022. Two brachial-ankle pulse wave velocity (ba-PWV) measurements were performed to assess aortic stiffness over a mean follow-up period of 2.6 years. A multivariate latent class growth mixed model was applied to identify trajectories of blood glucose. Logistic regression models were used to determine the odds ratio (OR) for aortic stiffness associated with glycemic variability evaluated by the coefficient of variation (CV), variability independent of the mean (VIM), average real variability (ARV), and successive variation (SV) of blood glucose.

RESULTS

Four distinct trajectories of glycated hemoglobin (HbA1c) or fasting blood glucose (FBG) were identified. In the U-shape class of HbA1c and FBG, the adjusted ORs were 2.17 and 1.21 for having increased/persistently high ba-PWV, respectively. Additionally, HbA1c variability (CV, VIM, SV) was significantly associated with aortic stiffness progression, with ORs ranging from 1.20 to 1.24. Cross-tabulation analysis indicated that the third tertile of the HbA1c mean and VIM conferred a 78% (95% confidence interval [CI] 1.23-2.58) higher odds of aortic stiffness progression. Sensitivity analysis demonstrated that the SD of HbA1c and the highest HbA1c variability score (HVS) were significantly associated with the adverse outcomes independent of the mean of HbA1c during the follow-up.

CONCLUSIONS

Long-term visit-to-visit HbA1c variability was independently associated with aortic stiffness progression, suggesting that HbA1c variability was a strong predictor of subclinical atherosclerosis in T2D participants.

Artificial intelligence to distinguish retinal vein occlusion patients using color fundus photographs

PURPOSE

Our aim is to establish an AI model for distinguishing color fundus photographs (CFP) of RVO patients from normal individuals.

METHODS

The training dataset included 2013 CFP from fellow eyes of RVO patients and 8536 age- and gender-matched normal CFP. Model performance was assessed in two independent testing datasets. We evaluated the performance of the AI model using the area under the receiver operating characteristic curve (AUC), accuracy, precision, specificity, sensitivity, and confusion matrices. We further explained the probable clinical relevance of the AI by extracting and comparing features of the retinal images.

RESULTS

Our model achieved an average AUC was 0.9866 (95% CI: 0.9805-0.9918), accuracy was 0.9534 (95% CI: 0.9421-0.9639), precision was 0.9123 (95% CI: 0.8784-9453), specificity was 0.9810 (95% CI: 0.9729-0.9884), and sensitivity was 0.8367 (95% CI: 0.7953-0.8756) for identifying fundus images of RVO patients in training dataset. In independent external datasets 1, the AUC of the RVO group was 0.8102 (95% CI: 0.7979-0.8226), the accuracy of 0.7752 (95% CI: 0.7633-0.7875), the precision of 0.7041 (95% CI: 0.6873-0.7211), specificity of 0.6499 (95% CI: 0.6305-0.6679) and sensitivity of 0.9124 (95% CI: 0.9004-0.9241) for RVO group. There were significant differences in retinal arteriovenous ratio, optic cup to optic disc ratio, and optic disc tilt angle (p = 0.001, p = 0.0001, and p = 0.0001, respectively) between the two groups in training dataset.

CONCLUSION

We trained an AI model to classify color fundus photographs of RVO patients with stable performance both in internal and external datasets. This may be of great importance for risk prediction in patients with retinal venous occlusion.

Performance of artificial intelligence in diabetic retinopathy screening: a systematic review and meta-analysis of prospective studies

Aims

To systematically evaluate the diagnostic value of an artificial intelligence (AI) algorithm model for various types of diabetic retinopathy (DR) in prospective studies over the previous five years, and to explore the factors affecting its diagnostic effectiveness.

Materials and methods

A search was conducted in Cochrane Library, Embase, Web of Science, PubMed, and IEEE databases to collect prospective studies on AI models for the diagnosis of DR from January 2017 to December 2022. We used QUADAS-2 to evaluate the risk of bias in the included studies. Meta-analysis was performed using MetaDiSc and STATA 14.0 software to calculate the combined sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio of various types of DR. Diagnostic odds ratios, summary receiver operating characteristic (SROC) plots, coupled forest plots, and subgroup analysis were performed according to the DR categories, patient source, region of study, and quality of literature, image, and algorithm.

Results

Finally, 21 studies were included. Meta-analysis showed that the pooled sensitivity, specificity, pooled positive likelihood ratio, pooled negative likelihood ratio, area under the curve, Cochrane Q index, and pooled diagnostic odds ratio of AI model for the diagnosis of DR were 0.880 (0.875-0.884), 0.912 (0.99-0.913), 13.021 (10.738-15.789), 0.083 (0.061-0.112), 0.9798, 0.9388, and 206.80 (124.82-342.63), respectively. The DR categories, patient source, region of study, sample size, quality of literature, image, and algorithm may affect the diagnostic efficiency of AI for DR.

Conclusion

AI model has a clear diagnostic value for DR, but it is influenced by many factors that deserve further study.

Systematic review registration

https://www.crd.york.ac.uk/prospero/, identifier CRD42023389687.

Diabetic Retinopathy Screening Using Non-Mydriatic Fundus Camera in Primary Health Care Settings - A Multicenter Study from Saudi Arabia

Background

Screening of diabetic retinopathy (DR) using the current digital imaging facilities in a primary health care setting is still in its early stages in Saudi Arabia. This study aims to reduce the risk of vision impairment and blindness among known diabetic people through early identification by general practitioners (GP) in a primary health care setting in Saudi Arabia. The objective of this study was to evaluate the accuracy of diabetic retinopathy (DR) detection by general practitioners (GPs) by comparing the agreement of DR assessment between GPs and ophthalmologists' assessment as a gold standard.

Methods

A hospital-based, six-month cross-sectional study was conducted, and the participants were type 2 diabetic adults from the diabetic registries of seven rural PHCs, in Saudi Arabia. After medical examination, the participants were then evaluated by fundus photography using a non-mydriatic fundus camera without medication for mydriasis. Presence or absence of DR was graded by the trained GPs in the PHCs and then compared with the grading of an ophthalmologist which was taken as a reference or a gold standard.

Results

A total of 899 diabetic patients were included, and the mean age of the patients was 64.89 ± 11.01 years. The evaluation by the GPs had a sensitivity of 80.69 [95% CI 74.8-85.4]; specificity of 92.23 [88.7-96.3]; positive predictive value, 74.1 [70.4-77.0]; negative predictive value, 73.34 [70.6-77.9]; and an accuracy of 84.57 [81.8-89.88]. For the consensus of agreement the adjusted kappa coefficient was from 0.74 to 0.92 for the DR.

Conclusion

This study demonstrates that trained GPs in rural health centers are able to provide reliable detection results of DR from fundus photographs. The study highlights the need for early DR screening programs in the rural areas of Saudi Arabia to facilitate early identification of the condition and to lessen impact of blindness due to diabetes.

A multi-centre prospective evaluation of THEIA™ to detect diabetic retinopathy (DR) and diabetic macular oedema (DMO) in the New Zealand screening program

PURPOSE

To validate the potential application of THEIA™ as clinical decision making assistant in a national screening program.

METHODS

A total of 900 patients were recruited from either an urban large eye hospital, or a semi-rural optometrist led screening provider, as they were attending their appointment as part of New Zealand Diabetic Eye Screening Programme. The de-identified images were independently graded by three senior specialists, and final results were aggregated using New Zealand grading scheme, which was then converted to referable/non-referable and Healthy/mild/more than mild/sight threatening categories.

RESULTS

THEIA™ managed to grade all images obtained during the study. Comparing the adjudicated images from the specialist grading team, "ground truth", with the grading by the AI platform in detecting "sight threatening" disease, at the patient level THEIA™ achieved 100% imageability, 100% [98.49-100.00%] sensitivity and [97.02-99.16%] specificity, and negative predictive value of 100%. In other words, THEIA™ did not miss any patients with "more than mild" or "sight threatening" disease. The level of agreement between the clinicians and the aggregated results was (k value: 0.9881, 0.9557, and 0.9175), and the level of agreement between THEIA™ and the aggregated labels was (k value: 0.9515).

CONCLUSION

This multi-centre prospective trial showed that THEIA™ did not miss referable disease when screening for diabetic retinopathy and maculopathy. It also had a very high level of granularity in reporting the disease level. As THEIA™ has been tested on a variety of cameras, operating in a range of clinics (rural/urban, ophthalmologist-led\optometrist-led), we believe that it will be a suitable addition to a public diabetic screening program.

Cost-Utility Analysis of Deep Learning and Trained Human Graders for Diabetic Retinopathy Screening in a Nationwide Program

INTRODUCTION

Deep learning (DL) for screening diabetic retinopathy (DR) has the potential to address limited healthcare resources by enabling expanded access to healthcare. However, there is still limited health economic evaluation, particularly in low- and middle-income countries, on this subject to aid decision-making for DL adoption.

METHODS

In the context of a middle-income country (MIC), using Thailand as a model, we constructed a decision tree-Markov hybrid model to estimate lifetime costs and outcomes of Thailand's national DR screening program via DL and trained human graders (HG). We calculated the incremental cost-effectiveness ratio (ICER) between the two strategies. Sensitivity analyses were performed to probe the influence of modeling parameters.

RESULTS

From a societal perspective, screening with DL was associated with a reduction in costs of ~ US$ 2.70, similar quality-adjusted life-years (QALY) of + 0.0043, and an incremental net monetary benefit of ~ US$ 24.10 in the base case. In sensitivity analysis, DL remained cost-effective even with a price increase from US$ 1.00 to US$ 4.00 per patient at a Thai willingness-to-pay threshold of ~ US$ 4.997 per QALY gained. When further incorporating recent findings suggesting improved compliance to treatment referral with DL, our analysis models effectiveness benefits of ~ US$ 20 to US$ 50 depending on compliance.

CONCLUSION

DR screening using DL in an MIC using Thailand as a model may result in societal cost-savings and similar health outcomes compared with HG. This study may provide an economic rationale to expand DL-based DR screening in MICs as an alternative solution for limited availability of skilled human resources for primary screening, particularly in MICs with similar prevalence of diabetes and low compliance to referrals for treatment.

Artificial Intelligence for Diabetic Retinopathy Screening Using Color Retinal Photographs: From Development to Deployment

Diabetic retinopathy (DR), a leading cause of preventable blindness, is expected to remain a growing health burden worldwide. Screening to detect early sight-threatening lesions of DR can reduce the burden of vision loss; nevertheless, the process requires intensive manual labor and extensive resources to accommodate the increasing number of patients with diabetes. Artificial intelligence (AI) has been shown to be an effective tool which can potentially lower the burden of screening DR and vision loss. In this article, we review the use of AI for DR screening on color retinal photographs in different phases of application, ranging from development to deployment. Early studies of machine learning (ML)-based algorithms using feature extraction to detect DR achieved a high sensitivity but relatively lower specificity. Robust sensitivity and specificity were achieved with the application of deep learning (DL), although ML is still used in some tasks. Public datasets were utilized in retrospective validations of the developmental phases in most algorithms, which require a large number of photographs. Large prospective clinical validation studies led to the approval of DL for autonomous screening of DR although the semi-autonomous approach may be preferable in some real-world settings. There have been few reports on real-world implementations of DL for DR screening. It is possible that AI may improve some real-world indicators for eye care in DR, such as increased screening uptake and referral adherence, but this has not been proven. The challenges in deployment may include workflow issues, such as mydriasis to lower ungradable cases; technical issues, such as integration into electronic health record systems and integration into existing camera systems; ethical issues, such as data privacy and security; acceptance of personnel and patients; and health-economic issues, such as the need to conduct health economic evaluations of using AI in the context of the country. The deployment of AI for DR screening should follow the governance model for AI in healthcare which outlines four main components: fairness, transparency, trustworthiness, and accountability.

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

Background

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

Methods

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

Results

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

Conclusions

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

Association between Age at Type 2 Diabetes Onset and Diabetic Retinopathy: A Double-Center Retrospective Study

BACKGROUND

With the decreasing age of type 2 diabetes mellitus (T2DM) onset, the incidence of diabetic complications is gradually increasing. We evaluated the independent effect of age at diabetes onset on diabetic retinopathy (DR) development.

METHODS

A total of 7472 patients with T2DM were enrolled in the National Metabolic Management Center from September 2017 to May 2022. Anthropometry data, laboratory reports, and medical history were collected. The independent association of DR with age at diabetes onset was analyzed using multivariable logistic regression models. In addition, a stratified analysis was performed to determine the effect of confounding variables.

RESULTS

Of the 7472 patients recruited, 1642 (21.98%) had DR. Patients with DR had considerably younger ages of diabetes onset than those without DR (45 (38-53) years vs. 50 (43-57) years, P < 0.001). The proportion of patients with T2DM onset at a younger age was higher in the DR group than that in the non-DR group. Participants were divided into four groups according to their age at diabetes onset, namely, ≥60, <40, 40-49, and 50-59 years. Compared with patients with diabetes onset at age ≥ 60 years, those with diabetes onset at <40 years (odds ratio (OR): 5.56, 95% confidence interval (CI): 3.731-8.285, P < 0.001), 40-49 years (OR: 2.751, 95% CI: 2.047-3.695, P < 0.001), and 50-59 years (OR: 1.606, 95% CI: 1.263-2.042, P < 0.001) were at an increased risk of DR after adjusting for potential confounding factors. Furthermore, stratification analyses demonstrated that young age at diabetes onset is an independent risk factor for DR.

CONCLUSIONS

Compared with diabetes onset at an older age, diabetes onset at a younger age is associated with a significantly increased DR risk.

Impact of Artificial Intelligence Assessment of Diabetic Retinopathy on Referral Service Uptake in a Low-Resource Setting: The RAIDERS Randomized Trial

PURPOSE

This trial was designed to determine if artificial intelligence (AI)-supported diabetic retinopathy (DR) screening improved referral uptake in Rwanda.

DESIGN

The Rwanda Artificial Intelligence for Diabetic Retinopathy Screening (RAIDERS) study was an investigator-masked, parallel-group randomized controlled trial.

PARTICIPANTS

Patients ≥ 18 years of age with known diabetes who required referral for DR based on AI interpretation.

METHODS

The RAIDERS study screened for DR using retinal imaging with AI interpretation implemented at 4 facilities from March 2021 through July 2021. Eligible participants were assigned randomly (1:1) to immediate feedback of AI grading (intervention) or communication of referral advice after human grading was completed 3 to 5 days after the initial screening (control).

MAIN OUTCOME MEASURES

Difference between study groups in the rate of presentation for referral services within 30 days of being informed of the need for a referral visit.

RESULTS

Of the 823 clinic patients who met inclusion criteria, 275 participants (33.4%) showed positive findings for referable DR based on AI screening and were randomized for inclusion in the trial. Study participants (mean age, 50.7 years; 58.2% women) were randomized to the intervention (n = 136 [49.5%]) or control (n = 139 [50.5%]) groups. No significant intergroup differences were found at baseline, and main outcome data were available for analyses for 100% of participants. Referral adherence was statistically significantly higher in the intervention group (70/136 [51.5%]) versus the control group (55/139 [39.6%]; P = 0.048), a 30.1% increase. Older age (odds ratio [OR], 1.04; 95% confidence interval [CI], 1.02-1.05; P < 0.0001), male sex (OR, 2.07; 95% CI, 1.22-3.51; P = 0.007), rural residence (OR, 1.79; 95% CI, 1.07-3.01; P = 0.027), and intervention group (OR, 1.74; 95% CI, 1.05-2.88; P = 0.031) were statistically significantly associated with acceptance of referral in multivariate analyses.

CONCLUSIONS

Immediate feedback on referral status based on AI-supported screening was associated with statistically significantly higher referral adherence compared with delayed communications of results from human graders. These results provide evidence for an important benefit of AI screening in promoting adherence to prescribed treatment for diabetic eye care in sub-Saharan Africa.

Performance of deep-learning artificial intelligence algorithms in detecting retinopathy of prematurity: A systematic review

PURPOSE

Artificial intelligence (AI) offers considerable promise for retinopathy of prematurity (ROP) screening and diagnosis. The development of deep-learning algorithms to detect the presence of disease may contribute to sufficient screening, early detection, and timely treatment for this preventable blinding disease. This review aimed to systematically examine the literature in AI algorithms in detecting ROP. Specifically, we focused on the performance of deep-learning algorithms through sensitivity, specificity, and area under the receiver operating curve (AUROC) for both the detection and grade of ROP.

METHODS

We searched Medline OVID, PubMed, Web of Science, and Embase for studies published from January 1, 2012, to September 20, 2021. Studies evaluating the diagnostic performance of deep-learning models based on retinal fundus images with expert ophthalmologists' judgment as reference standard were included. Studies which did not investigate the presence or absence of disease were excluded. Risk of bias was assessed using the QUADAS-2 tool.

RESULTS

Twelve studies out of the 175 studies identified were included. Five studies measured the performance of detecting the presence of ROP and seven studies determined the presence of plus disease. The average AUROC out of 11 studies was 0.98. The average sensitivity and specificity for detecting ROP was 95.72% and 98.15%, respectively, and for detecting plus disease was 91.13% and 95.92%, respectively.

CONCLUSION

The diagnostic performance of deep-learning algorithms in published studies was high. Few studies presented externally validated results or compared performance to expert human graders. Large scale prospective validation alongside robust study design could improve future studies.

Application and observation of artificial intelligence in clinical practice of fundus screening for diabetic retinopathy with non-mydriatic fundus photography: a retrospective observational study of T2DM patients in Tianjin, China

Objective:

To observe the consistency of a preliminary report of artificial intelligence (AI) in the clinical practice of fundus screening for diabetic retinopathy (DR) using non-mydriatic fundus photography.

Methods:

Patients who underwent DR screening in the Metabolic Disease Management Center (MMC) of our hospital were selected as research participants. The degree of coincidence of the AI preliminary report and the ophthalmic diagnosis was compared and analyzed, and the kappa value was calculated. Fundus fluorescein angiography (FFA) was performed in patients referred to the out-of-hospital ophthalmology department, and the consistency between fluorescein angiography and AI diagnosis was evaluated.

Results:

In total, 6146 patients (12,263 eyes) completed the non-mydriasis fundus examination. The positive DR screening rate was 24.3%. When considering moderate nonproliferative retinopathy as the cut-off point, the kappa coefficient was 0.75 (p < 0.001), the sensitivity was 0.973, and the precision was 0.642, which was shown in the precision–recall curve. Fifty-nine patients referred to receive FFA were compared with non-mydriatic AI diagnoses. The kappa coefficient was 0.53, and the coincidence rate was 66.9%.

Conclusion:

Non-mydriasis fundus examination combined with AI has a medium-high consistency with ophthalmologists in DR diagnosis, conducive to early DR screening. Combining diagnosis and treatment modes with the Internet can promote the development of telemedicine, alleviate the shortage of ophthalmology resources, and promote the process of blindness prevention and treatment projects.

The Validation of Deep Learning-Based Grading Model for Diabetic Retinopathy

Purpose

To evaluate the performance of a deep learning (DL)-based artificial intelligence (AI) hierarchical diagnosis software, EyeWisdom V1 for diabetic retinopathy (DR).

Materials and Methods

The prospective study was a multicenter, double-blind, and self-controlled clinical trial. Non-dilated posterior pole fundus images were evaluated by ophthalmologists and EyeWisdom V1, respectively. The diagnosis of manual grading was considered as the gold standard. Primary evaluation index (sensitivity and specificity) and secondary evaluation index like positive predictive values (PPV), negative predictive values (NPV), etc., were calculated to evaluate the performance of EyeWisdom V1.

Results

A total of 1,089 fundus images from 630 patients were included, with a mean age of (56.52 ± 11.13) years. For any DR, the sensitivity, specificity, PPV, and NPV were 98.23% (95% CI 96.93-99.08%), 74.45% (95% CI 69.95-78.60%), 86.38% (95% CI 83.76-88.72%), and 96.23% (95% CI 93.50-98.04%), respectively; For sight-threatening DR (STDR, severe non-proliferative DR or worse), the above indicators were 80.47% (95% CI 75.07-85.14%), 97.96% (95% CI 96.75-98.81%), 92.38% (95% CI 88.07-95.50%), and 94.23% (95% CI 92.46-95.68%); For referral DR (moderate non-proliferative DR or worse), the sensitivity and specificity were 92.96% (95% CI 90.66-94.84%) and 93.32% (95% CI 90.65-95.42%), with the PPV of 94.93% (95% CI 92.89-96.53%) and the NPV of 90.78% (95% CI 87.81-93.22%). The kappa score of EyeWisdom V1 was 0.860 (0.827-0.890) with the AUC of 0.958 for referral DR.

Conclusion

The EyeWisdom V1 could provide reliable DR grading and referral recommendation based on the fundus images of diabetics.

Kidney disease parameters, metabolic goal achievement, and arterial stiffness risk in Chinese adult people with type 2 diabetes

BACKGROUND

To investigate the arterial stiffness (AS) risk within urinary albumin-to-creatinine ratio (UACR) and estimated glomerular filtration rate (eGFR) categories and the joint effect between kidney disease parameters and metabolic goal achievement on AS risk in adult people with type 2 diabetes (T2D).

METHODS

A total of 27 439 Chinese participants with T2D from 10 National Metabolic Management Centers (MMC) were categorized into four albuminuria/decreased eGFR groups. The criteria for decreased eGFR and AS were eGFR <90 ml/min/1.73 m2 and brachial-ankle pulse wave velocity value >the 75th percentile (1770.0 cm/s). Three metabolic goals were defined as glycated hemoglobin <7%, BP <130/80 mmHg, andlow-density lipoprotein cholesterol <2.6 mmol/L.

RESULTS

After full adjustment, odds ratios (ORs) for AS were highest for albuminuria and decreased eGFR (2.23 [1.98-2.52]) and were higher for albuminuria and normal eGFR (1.52 [1.39-1.67]) than for those with nonalbuminuria and decreased eGFR (1.17 [1.04-1.32]). Both UACR and eGFR in the subgroup or overall population independently correlated with AS risk. The achievement of ≥2 metabolic goals counteracted the association between albuminuria and AS risk (OR: 0.93; 95% CI: 0.80-1.07; p = .311). When the metabolic goals added up to ≥2 for patients with decreased eGFR, they showed significantly lower AS risk (OR: 0.65; 95% CI: 0.56-0.74; p < .001).

CONCLUSIONS

Both higher UACR and lower eGFR are determinants of AS risk, with UACR more strongly related to AS than eGFR in adults with T2D. The correlation between albuminuria/decreased eGFR and AS was modified by the achievement of multiple metabolic elements.

A Classification Tree Model with Optical Coherence Tomography Angiography Variables to Screen Early-Stage Diabetic Retinopathy in Diabetic Patients

Aim

To establish a classification tree model in DR screening and to compare the DR screening accuracy between the classification tree model and the logistic regression model in type 2 diabetes mellitus (T2DM) patients based on OCTA variables.

Methods

Two hundred forty-one eyes of 241 T2DM patients were included and divided into two groups: the development cohort and the validation cohort. Optical coherence tomography angiography (OCTA) images were acquired in these patients. The data of foveal avascular zone area, superficial capillary plexus (SCP) density, and deep capillary plexus (DCP) density were exported after automatically analyzing the macular 6 × 6 mm OCTA images, while the data of radial peripapillary capillary plexus (RPCP) density was exported after automatically analyzing the optic nerve head 4.5 × 4.5 mm OCTA images. These OCTA variables were adopted to establish and validate the logistic regression model and the classification tree model. The area under the curve (AUC), sensitivity, specificity, and statistical power for receiver operating characteristic curves of two models were calculated.

Results

In the logistic regression model, best-corrected visual acuity (BCVA) (LogMAR) and SCP density were entered (BVCA : OR= 60.30, 95% CI= [2.40, 1513.82], p = 0.013; SCP density: OR= 0.86, 95% CI= [0.78, 0.96], p = 0.006). The AUC, sensitivity, and specificity for detecting early-stage DR (mild to moderate NPDR) in the development cohort were 0.75 (95% CI: [0.66, 0.85]), 63%, and 83%, respectively. The AUC, sensitivity, and specificity in the validation cohort were 0.75 (95% CI: [0.66, 0.84]), 79%, and 72%, respectively. In the classification tree model, BVCA (LogMAR), DM duration, SCP density, and DCP density were entered. The AUC, sensitivity, and specificity for detecting early-stage DR were 0.72 (95% CI: [0.60, 0.84]), 66%, and 76%, respectively. The AUC, sensitivity, and specificity in the validation cohort were 0.74 (95% CI: [0.65, 0.83]), 74%, and 72%, respectively. The statistical power of the development and validation cohorts in two models was all more than 99%.

Conclusions

Compared to the logistic regression model, the classification tree model has similar accuracy in predicting early-stage DR. The classification tree model with OCTA variables may be a simple tool for clinical practitioners to identify early-stage DR in T2DM patients. Moreover, SCP density is significantly reduced in mild-to-moderate NPDR eyes and might be a biomarker in early-stage DR detection. Further improvement and validation of the DR diagnostic model are awaiting to be performed.

A stratified analysis of a deep learning algorithm in the diagnosis of diabetic retinopathy in a real-world study

BACKGROUND

The aim of our research was to prospectively explore the clinical value of a deep learning algorithm (DLA) to detect referable diabetic retinopathy (DR) in different subgroups stratified by types of diabetes, blood pressure, sex, BMI, age, glycosylated hemoglobin (HbA1c), diabetes duration, urine albumin-to-creatinine ratio (UACR), and estimated glomerular filtration rate (eGFR) at a real-world diabetes center in China.

METHODS

A total of 1147 diabetic patients from Shanghai General Hospital were recruited from October 2018 to August 2019. Retinal fundus images were graded by the DLA, and the detection of referable DR (moderate nonproliferative DR or worse) was compared with a reference standard generated by one certified retinal specialist with more than 12 years of experience. The performance of DLA across different subgroups stratified by types of diabetes, blood pressure, sex, BMI, age, HbA1c, diabetes duration, UACR, and eGFR was evaluated.

RESULTS

For all 1674 gradable images, the area under the receiver operating curve, sensitivity, and specificity of the DLA for referable DR were 0.942 (95% CI, 0.920-0.964), 85.1% (95% CI, 83.4%-86.8%), and 95.6% (95% CI, 94.6%-96.6%), respectively. The DLA showed consistent performance across most subgroups, while it showed superior performance in the subgroups of patients with type 1 diabetes, UACR ≥ 30 mg/g, and eGFR < 90 mL/min/1.73m² .

CONCLUSIONS

This study showed that the DLA was a reliable alternative method for the detection of referable DR and performed superior in patients with type 1 diabetes and diabetic nephropathy who were prone to DR.

Effects of basal and premixed insulin on glycemic control in type 2 diabetes patients based on multicenter prospective real-world data

BACKGROUND

To investigate the different efficacies of glycemic control between basal and premixed insulin in participants with type 2 diabetes (T2DM) when non-insulin medications fail to reach treatment targets.

METHODS

This was a prospective, large-scale, real-world study at 10 diabetes centers in China. Between June 2017 and June 2021, we enrolled 1104 T2DM participants initiated with either once-daily basal insulin or twice-daily premixed insulin when the glycosylated hemoglobin (HbA1c) control target was not met after at least two non-insulin agents were administered. A Cox proportional hazards regression model adjusting for multiple influencing factors was performed to compare the different effects of basal and premixed insulin on reaching the HbA1c control target.

RESULTS

At baseline, basal insulin (57.3%) was prescribed more frequently than premixed insulin (42.7%). Patients with a higher body mass index (BMI) or higher HbA1c levels were more likely to receive premixed insulin than basal insulin (both p < 0.001). After a median follow-up of 12.0 months, compared to those with premixed insulin, the hazard ratio for reaching the HbA1c target to those with basal insulin was 1.10 (95% CI, 0.92-1.31; p = 0.29) after adjustment, and less weight gain was observed in those with basal insulin than with premixed insulin (percentage change of BMI from baseline -0.37[5.50]% vs 3.40[6.73]%, p < 0.0001).

CONCLUSIONS

In this real-world study, once-daily basal insulin was more frequently prescribed and had similar glycemic control effects but less weight gain compared with twice-daily premixed insulin when used as initiation therapy for those in whom glycemic control with non-insulin medications failed.

Overview of global publications on machine learning in diabetic retinopathy from 2011 to 2021: Bibliometric analysis

PURPOSE

To comprehensively analyze and discuss the publications on machine learning (ML) in diabetic retinopathy (DR) following a bibliometric approach.

METHODS

The global publications on ML in DR from 2011 to 2021 were retrieved from the Web of Science Core Collection (WoSCC) database. We analyzed the publication and citation trend over time and identified highly-cited articles, prolific countries, institutions, journals and the most relevant research domains. VOSviewer and Wordcloud are used to visualize the mainstream research topics and evolution of subtopics in the form of co-occurrence maps of keywords.

RESULTS

By analyzing a total of 1147 relevant publications, this study found a rapid increase in the number of annual publications, with an average growth rate of 42.68%. India and China were the most productive countries. IEEE Access was the most productive journal in this field. In addition, some notable common points were found in the highly-cited articles. The keywords analysis showed that "diabetic retinopathy", "classification", and "fundus images" were the most frequent keywords for the entire period, as automatic diagnosis of DR was always the mainstream topic in the relevant field. The evolution of keywords highlighted some breakthroughs, including "deep learning" and "optical coherence tomography", indicating the advance in technologies and changes in the research attention.

CONCLUSIONS

As new research topics have emerged and evolved, studies are becoming increasingly diverse and extensive. Multiple modalities of medical data, new ML techniques and constantly optimized algorithms are the future trends in this multidisciplinary field.

Artificial intelligence for diabetic retinopathy

ABSTRACT

Diabetic retinopathy (DR) is an important cause of blindness globally, and its prevalence is increasing. Early detection and intervention can help change the outcomes of the disease. The rapid development of artificial intelligence (AI) in recent years has led to new possibilities for the screening and diagnosis of DR. An AI-based diagnostic system for the detection of DR has significant advantages, such as high efficiency, high accuracy, and lower demand for human resources. At the same time, there are shortcomings, such as the lack of standards for development and evaluation and the limited scope of application. This article demonstrates the current applications of AI in the field of DR, existing problems, and possible future development directions.

Profile of sight-threatening diabetic retinopathy and its awareness among patients with diabetes mellitus attending a tertiary care center in Kashmir, India

Purpose:

To study the profile of sight-threatening diabetic retinopathy (STDR), its association with various factors affecting it, and awareness of diabetic retinopathy (DR) among patients with diabetes mellitus (DM) attending a tertiary care center in Kashmir.

Methods:

In this prospective cross-sectional study, 625 consecutive patients with DM were assessed for STDR. Demographic/clinical data were obtained. Early treatment diabetic retinopathy study (ETDRS) criteria were used to grade fundus photographs. Severe nonproliferative DR, proliferative DR, and/or macular edema were classified as STDR. Optical coherence tomography was used to confirm the diagnosis of macular edema.

Results:

The mean age of patients was 56.36 ± 9.29 years. The male-to-female ratio was 0.92:1. The majority (99.36%) of patients had type 2 DM. STDR was seen in 208 (33.28%) patients. Non-sight-threatening diabetic retinopathy (NSTDR) was seen in 173 (27.68%) patients. Eye care was sought by 313 (50.08%) patients for the first time. STDR had a significant association with difficulty in accessing the health care facilities, duration of diabetes, uncontrolled diabetes, presence of other diabetes complications, use of insulin, and hypertension (P < 0.05 for all). Awareness that diabetes can affect eyes showed a significant association with age, gender, educational status, duration of diabetes, glycemic status, DR, and STDR (P < 0.001 for all).

Conclusion:

STDR is a common complication in diabetes and is duration- and glycemic control-dependent. Understanding the factors associated with STDR can help in making strategies for its prevention. Spreading awareness regarding STDR at the community level in the Kashmir valley is crucial in this regard.

Application of Surgical Decision Model for Patients With Childhood Cataract: A Study Based on Real World Data

Reliable validated methods are necessary to verify the performance of diagnosis and therapy-assisted models in clinical practice. However, some validated results have research bias and may not reflect the results of real-world application. In addition, the conduct of clinical trials has executive risks for the indeterminate effectiveness of models and it is challenging to finish validated clinical trials of rare diseases. Real world data (RWD) can probably solve this problem. In our study, we collected RWD from 251 patients with a rare disease, childhood cataract (CC) and conducted a retrospective study to validate the CC surgical decision model. The consistency of the real surgical type and recommended surgical type was 94.16%. In the cataract extraction (CE) group, the model recommended the same surgical type for 84.48% of eyes, but the model advised conducting cataract extraction and primary intraocular lens implantation (CE + IOL) surgery in 15.52% of eyes, which was different from the real-world choices. In the CE + IOL group, the model recommended the same surgical type for 100% of eyes. The real-recommended matched rates were 94.22% in the eyes of bilateral patients and 90.38% in the eyes of unilateral patients. Our study is the first to apply RWD to complete a retrospective study evaluating a clinical model, and the results indicate the availability and feasibility of applying RWD in model validation and serve guidance for intelligent model evaluation for rare diseases.