The SEE Study: Safety, Efficacy, and Equity of Implementing Autonomous Artificial Intelligence for Diagnosing Diabetic Retinopathy in Youth

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.

Artificial intelligence in paediatric endocrinology: conflict or cooperation

Artificial intelligence (AI) in medicine is transforming healthcare by automating system tasks, assisting in diagnostics, predicting patient outcomes and personalising patient care, founded on the ability to analyse vast datasets. In paediatric endocrinology, AI has been developed for diabetes, for insulin dose adjustment, detection of hypoglycaemia and retinopathy screening; bone age assessment and thyroid nodule screening; the identification of growth disorders; the diagnosis of precocious puberty; and the use of facial recognition algorithms in conditions such as Cushing syndrome, acromegaly, congenital adrenal hyperplasia and Turner syndrome. AI can also predict those most at risk from childhood obesity by stratifying future interventions to modify lifestyle. AI will facilitate personalised healthcare by integrating data from 'omics' analysis, lifestyle tracking, medical history, laboratory and imaging, therapy response and treatment adherence from multiple sources. As data acquisition and processing becomes fundamental, data privacy and protecting children's health data is crucial. Minimising algorithmic bias generated by AI analysis for rare conditions seen in paediatric endocrinology is an important determinant of AI validity in clinical practice. AI cannot create the patient-doctor relationship or assess the wider holistic determinants of care. Children have individual needs and vulnerabilities and are considered in the context of family relationships and dynamics. Importantly, whilst AI provides value through augmenting efficiency and accuracy, it must not be used to replace clinical skills.

Risk Factors for Nondiagnostic Imaging in a Real-World Deployment of Artificial Intelligence Diabetic Retinal Examinations in an Integrated Healthcare System: Maximizing Workflow Efficiency Through Predictive Dilation

OBJECTIVE

In the pivotal clinical trial that led to Food and Drug Administration De Novo "approval" of the first fully autonomous artificial intelligence (AI) diabetic retinal disease diagnostic system, a reflexive dilation protocol was used. Using real-world deployment data before implementation of reflexive dilation, we identified factors associated with nondiagnostic results. These factors allow a novel predictive dilation workflow, where patients most likely to benefit from pharmacologic dilation are dilated a priori to maximize efficiency and patient satisfaction.

METHODS

Retrospective review of patients who were assessed with autonomous AI at Johns Hopkins Medicine (8/2020 to 5/2021). We constructed a multivariable logistic regression model for nondiagnostic results to compare characteristics of patients with and without diagnostic results, using adjusted odds ratio (aOR). P < .05 was considered statistically significant.

RESULTS

Of 241 patients (59% female; median age = 59), 123 (51%) had nondiagnostic results. In multivariable analysis, type 1 diabetes (T1D, aOR = 5.82, 95% confidence interval [CI]: 1.45-23.40, P = .01), smoking (aOR = 2.86, 95% CI: 1.36-5.99, P = .005), and age (every 10-year increase, aOR = 2.12, 95% CI: 1.62-2.77, P < .001) were associated with nondiagnostic results. Following feature elimination, a predictive model was created using T1D, smoking, age, race, sex, and hypertension as inputs. The model showed an area under the receiver-operator characteristics curve of 0.76 in five-fold cross-validation.

CONCLUSIONS

We used factors associated with nondiagnostic results to design a novel, predictive dilation workflow, where patients most likely to benefit from pharmacologic dilation are dilated a priori. This new workflow has the potential to be more efficient than reflexive dilation, thus maximizing the number of at-risk patients receiving their diabetic retinal examinations.

Autonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the ACCESS randomized control trial

Diabetic retinopathy can be prevented with screening and early detection. We hypothesized that autonomous artificial intelligence (AI) diabetic eye exams at the point-of-care would increase diabetic eye exam completion rates in a racially and ethnically diverse youth population. AI for Children's diabetiC Eye ExamS (NCT05131451) is a parallel randomized controlled trial that randomized youth (ages 8-21 years) with type 1 and type 2 diabetes to intervention (autonomous artificial intelligence diabetic eye exam at the point of care), or control (scripted eye care provider referral and education) in an academic pediatric diabetes center. The primary outcome was diabetic eye exam completion rate within 6 months. The secondary outcome was the proportion of participants who completed follow-through with an eye care provider if deemed appropriate. Diabetic eye exam completion rate was significantly higher (100%, 95%CI: 95.5%, 100%) in the intervention group (n = 81) than the control group (n = 83) (22%, 95%CI: 14.2%, 32.4%)(p < 0.001). In the intervention arm, 25/81 participants had an abnormal result, of whom 64% (16/25) completed follow-through with an eye care provider, compared to 22% in the control arm (p < 0.001). Autonomous AI increases diabetic eye exam completion rates in youth with diabetes.

Artificial intelligence enhanced ophthalmological screening in children: insights from a cohort study in Lubelskie Voivodeship

This study aims to investigate the prevalence of visual impairments, such as myopia, hyperopia, and astigmatism, among school-age children (7-9 years) in Lubelskie Voivodeship (Republic of Poland) and apply artificial intelligence (AI) in the detection of severe ocular diseases. A total of 1049 participants (1.7% of the total child population in the region) were examined through a combination of standardized visual acuity tests, autorefraction, and assessment of fundus images by a convolutional neural network (CNN) model. The results from this artificial intelligence (AI) model were juxtaposed with assessments conducted by two experienced ophthalmologists to gauge the model's accuracy. The results demonstrated myopia, hyperopia, and astigmatism prevalences of 3.7%, 16.9%, and 7.8%, respectively, with myopia showing a significant age-related increase and hyperopia decreasing with age. The AI model performance was evaluated using the Dice coefficient, reaching 93.3%, indicating that the CNN model was highly accurate. The study underscores the utility of AI in the early detection and diagnosis of severe ocular diseases, providing a foundation for future research to improve paediatric ophthalmic screening and treatment outcomes.

AI-Human Hybrid Workflow Enhances Teleophthalmology for the Detection of Diabetic Retinopathy

Objective

Detection of diabetic retinopathy (DR) outside of specialized eye care settings is an important means of access to vision-preserving health maintenance. Remote interpretation of fundus photographs acquired in a primary care or other nonophthalmic setting in a store-and-forward manner is a predominant paradigm of teleophthalmology screening programs. Artificial intelligence (AI)-based image interpretation offers an alternative means of DR detection. IDx-DR (Digital Diagnostics Inc) is a Food and Drug Administration-authorized autonomous testing device for DR. We evaluated the diagnostic performance of IDx-DR compared with human-based teleophthalmology over 2 and a half years. Additionally, we evaluated an AI-human hybrid workflow that combines AI-system evaluation with human expert-based assessment for referable cases.

Design

Prospective cohort study and retrospective analysis.

Participants

Diabetic patients ≥ 18 years old without a prior DR diagnosis or DR examination in the past year presenting for routine DR screening in a primary care clinic.

Methods

Macula-centered and optic nerve-centered fundus photographs were evaluated by an AI algorithm followed by consensus-based overreading by retina specialists at the Stanford Ophthalmic Reading Center. Detection of more-than-mild diabetic retinopathy (MTMDR) was compared with in-person examination by a retina specialist.

Main Outcome Measures

Sensitivity, specificity, accuracy, positive predictive value, and gradability achieved by the AI algorithm and retina specialists.

Results

The AI algorithm had higher sensitivity (95.5% sensitivity; 95% confidence interval [CI], 86.7%-100%) but lower specificity (60.3% specificity; 95% CI, 47.7%-72.9%) for detection of MTMDR compared with remote image interpretation by retina specialists (69.5% sensitivity; 95% CI, 50.7%-88.3%; 96.9% specificity; 95% CI, 93.5%-100%). Gradability of encounters was also lower for the AI algorithm (62.5%) compared with retina specialists (93.1%). A 2-step AI-human hybrid workflow in which the AI algorithm initially rendered an assessment followed by overread by a retina specialist of MTMDR-positive encounters resulted in a sensitivity of 95.5% (95% CI, 86.7%-100%) and a specificity of 98.2% (95% CI, 94.6%-100%). Similarly, a 2-step overread by retina specialists of AI-ungradable encounters improved gradability from 63.5% to 95.6% of encounters.

Conclusions

Implementation of an AI-human hybrid teleophthalmology workflow may both decrease reliance on human specialist effort and improve diagnostic accuracy.

Financial Disclosures

Proprietary or commercial disclosure may be found after the references.

Artificial Intelligence (AI) in pediatric endocrinology

Artificial Intelligence (AI) is integrating itself throughout the medical community. AI's ability to analyze complex patterns and interpret large amounts of data will have considerable impact on all areas of medicine, including pediatric endocrinology. In this paper, we review and update the current studies of AI in pediatric endocrinology. Specific topics that are addressed include: diabetes management, bone growth, metabolism, obesity, and puberty. Becoming knowledgeable and comfortable with AI will assist pediatric endocrinologists, the goal of the paper.

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.

Considerations for addressing bias in artificial intelligence for health equity

Health equity is a primary goal of healthcare stakeholders: patients and their advocacy groups, clinicians, other providers and their professional societies, bioethicists, payors and value based care organizations, regulatory agencies, legislators, and creators of artificial intelligence/machine learning (AI/ML)-enabled medical devices. Lack of equitable access to diagnosis and treatment may be improved through new digital health technologies, especially AI/ML, but these may also exacerbate disparities, depending on how bias is addressed. We propose an expanded Total Product Lifecycle (TPLC) framework for healthcare AI/ML, describing the sources and impacts of undesirable bias in AI/ML systems in each phase, how these can be analyzed using appropriate metrics, and how they can be potentially mitigated. The goal of these "Considerations" is to educate stakeholders on how potential AI/ML bias may impact healthcare outcomes and how to identify and mitigate inequities; to initiate a discussion between stakeholders on these issues, in order to ensure health equity along the expanded AI/ML TPLC framework, and ultimately, better health outcomes for all.

Pediatric Type 1 Diabetes: Mechanisms and Impact of Technologies on Comorbidities and Life Expectancy

Type 1 diabetes (T1D) is one of the most common chronic diseases in childhood, with a progressively increasing incidence. T1D management requires lifelong insulin treatment and ongoing health care support. The main goal of treatment is to maintain blood glucose levels as close to the physiological range as possible, particularly to avoid blood glucose fluctuations, which have been linked to morbidity and mortality in patients with T1D. Indeed, the guidelines of the International Society for Pediatric and Adolescent Diabetes (ISPAD) recommend a glycated hemoglobin (HbA1c) level < 53 mmol/mol (<7.0%) for young people with T1D to avoid comorbidities. Moreover, diabetic disease strongly influences the quality of life of young patients who must undergo continuous monitoring of glycemic values and the administration of subcutaneous insulin. In recent decades, the development of automated insulin delivery (AID) systems improved the metabolic control and the quality of life of T1D patients. Continuous subcutaneous insulin infusion (CSII) combined with continuous glucose monitoring (CGM) devices connected to smartphones represent a good therapeutic option, especially in young children. In this literature review, we revised the mechanisms of the currently available technologies for T1D in pediatric age and explored their effect on short- and long-term diabetes-related comorbidities, quality of life, and life expectation.

Global trends and performances in diabetic retinopathy studies: A bibliometric analysis

Objective

The objective of this study is to conduct a comprehensive bibliometric analysis to identify and evaluate global trends in diabetic retinopathy (DR) research and visualize the focus and frontiers of this field.

Methods

Diabetic retinopathy-related publications from the establishment of the Web of Science (WOS) through 1 November 2022 were retrieved for qualitative and quantitative analyses. This study analyzed annual publication counts, prolific countries, institutions, journals, and the top 10 most cited literature. The findings were presented through descriptive statistics. VOSviewer 1.6.17 was used to exhibit keywords with high frequency and national cooperation networks, while CiteSpace 5.5.R2 displayed the timeline and burst keywords for each term.

Results

A total of 10,709 references were analyzed, and the number of publications continuously increased over the investigated period. America had the highest h-index and citation frequency, contributing to the most influence. China was the most prolific country, producing 3,168 articles. The University of London had the highest productivity. The top three productive journals were from America, and Investigative Ophthalmology Visual Science had the highest number of publications. The article from Gulshan et al. (2016; co-citation counts, 2,897) served as the representative and symbolic reference. The main research topics in this area were incidence, pathogenesis, treatment, and artificial intelligence (AI). Deep learning, models, biomarkers, and optical coherence tomography angiography (OCTA) of DR were frontier hotspots.

Conclusion

Bibliometric analysis in this study provided valuable insights into global trends in DR research frontiers. Four key study directions and three research frontiers were extracted from the extensive DR-related literature. As the incidence of DR continues to increase, DR prevention and treatment have become a pressing public health concern and a significant area of research interest. In addition, the development of AI technologies and telemedicine has emerged as promising research frontiers for balancing the number of doctors and patients.

Effectiveness of artificial intelligence screening in preventing vision loss from diabetes: a policy model

The effectiveness of using artificial intelligence (AI) systems to perform diabetic retinal exams ('screening') on preventing vision loss is not known. We designed the Care Process for Preventing Vision Loss from Diabetes (CAREVL), as a Markov model to compare the effectiveness of point-of-care autonomous AI-based screening with in-office clinical exam by an eye care provider (ECP), on preventing vision loss among patients with diabetes. The estimated incidence of vision loss at 5 years was 1535 per 100,000 in the AI-screened group compared to 1625 per 100,000 in the ECP group, leading to a modelled risk difference of 90 per 100,000. The base-case CAREVL model estimated that an autonomous AI-based screening strategy would result in 27,000 fewer Americans with vision loss at 5 years compared with ECP. Vision loss at 5 years remained lower in the AI-screened group compared to the ECP group, in a wide range of parameters including optimistic estimates biased toward ECP. Real-world modifiable factors associated with processes of care could further increase its effectiveness. Of these factors, increased adherence with treatment was estimated to have the greatest impact.

Equity within AI systems: What can health leaders expect?

Artificial Intelligence (AI) for health has a great potential; it has already proven to be successful in enhancing patient outcomes, facilitating professional work and benefiting administration. However, AI presents challenges related to health equity defined as an opportunity for people to reach their fullest health potential. This article discusses the opportunities and challenges that AI presents in health and examines ways in which inequities related to AI can be mitigated.

Global Prevalence of Diabetic Retinopathy in Pediatric Type 2 Diabetes: A Systematic Review and Meta-analysis

IMPORTANCE

Type 2 diabetes (T2D) is increasing globally. Diabetic retinopathy (DR) is a leading cause of blindness in adults with T2D; however, the global burden of DR in pediatric T2D is unknown. This knowledge can inform retinopathy screening and treatments to preserve vision in this population.

OBJECTIVE

To estimate the global prevalence of DR in pediatric T2D.

DATA SOURCES

MEDLINE, Embase, the Cumulative Index to Nursing and Allied Health Literature (CINAHL), the Cochrane Library, the Web of Science, and the gray literature (ie, literature containing information that is not available through traditional publishing and distribution channels) were searched for relevant records from the date of database inception to April 4, 2021, with updated searches conducted on May 17, 2022. Searches were limited to human studies. No language restrictions were applied. Search terms included diabetic retinopathy; diabetes mellitus, type 2; prevalence studies; and child, adolescent, teenage, youth, and pediatric.

STUDY SELECTION

Three teams, each with 2 reviewers, independently screened for observational studies with 10 or more participants that reported the prevalence of DR. Among 1989 screened articles, 27 studies met the inclusion criteria for the pooled analysis.

DATA EXTRACTION AND SYNTHESIS

This systematic review and meta-analysis followed the Meta-analysis of Observational Studies in Epidemiology (MOOSE) and the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guidelines for systematic reviews and meta-analyses. Two independent reviewers performed the risk of bias and level of evidence analyses. The results were pooled using a random-effects model, and heterogeneity was reported using χ2 and I2 statistics.

MAIN OUTCOMES AND MEASURES

The main outcome was the estimated pooled global prevalence of DR in pediatric T2D. Other outcomes included DR severity and current DR assessment methods. The association of diabetes duration, sex, race, age, and obesity with DR prevalence was also assessed.

RESULTS

Among the 27 studies included in the pooled analysis (5924 unique patients; age range at T2D diagnosis, 6.5-21.0 years), the global prevalence of DR in pediatric T2D was 6.99% (95% CI, 3.75%-11.00%; I2 = 95%; 615 patients). Fundoscopy was less sensitive than 7-field stereoscopic fundus photography in detecting retinopathy (0.47% [95% CI, 0%-3.30%; I2 = 0%] vs 13.55% [95% CI, 5.43%-24.29%; I2 = 92%]). The prevalence of DR increased over time and was 1.11% (95% CI, 0.04%-3.06%; I2 = 5%) at less than 2.5 years after T2D diagnosis, 9.04% (95% CI, 2.24%-19.55%; I2 = 88%) at 2.5 to 5.0 years after T2D diagnosis, and 28.14% (95% CI, 12.84%-46.45%; I2 = 96%) at more than 5 years after T2D diagnosis. The prevalence of DR increased with age, and no differences were noted based on sex, race, or obesity. Heterogeneity was high among studies.

CONCLUSIONS AND RELEVANCE

In this study, DR prevalence in pediatric T2D increased significantly at more than 5 years after diagnosis. These findings suggest that retinal microvasculature is an early target of T2D in children and adolescents, and annual screening with fundus photography beginning at diagnosis offers the best assessment method for early detection of DR in pediatric patients.

Digital innovations for retinal care in diabetic retinopathy

AIM

The purpose of this review is to examine the applications of novel digital technology domains for the screening and management of patients with diabetic retinopathy (DR).

METHODS

A PubMed engine search was performed, using the terms "Telemedicine", "Digital health", "Telehealth", "Telescreening", "Artificial intelligence", "Deep learning", "Smartphone", "Triage", "Screening", "Home-based", "Monitoring", "Ophthalmology", "Diabetes", "Diabetic Retinopathy", "Retinal imaging". Full-text English language studies from January 1, 2010, to February 1, 2022, and reference lists were considered for the conceptual framework of this review.

RESULTS

Diabetes mellitus and its eye complications, including DR, are particularly well suited to digital technologies, providing an ideal model for telehealth initiatives and real-world applications. The current development in the adoption of telemedicine, artificial intelligence and remote monitoring as an alternative to or in addition to traditional forms of care will be discussed.

CONCLUSIONS

Advances in digital health have created an ecosystem ripe for telemedicine in the field of DR to thrive. Stakeholders and policymakers should adopt a participatory approach to ensure sustained implementation of these technologies after the COVID-19 pandemic. This article belongs to the Topical Collection "Diabetic Eye Disease", managed by Giuseppe Querques.

Differences in retinopathy prevalence and associated risk factors across 11 countries in three continents: A cross-sectional study of 156,090 children and adolescents with type 1 diabetes

OBJECTIVE

To examine the prevalence, time trends, and risk factors of diabetic retinopathy (DR) among youth with type 1 diabetes (T1D) from 11 countries (Australia, Austria, Denmark, England, Germany, Italy, Luxemburg, Netherlands, Slovenia, United States, and Wales).

SUBJECTS AND METHODS

Data on individuals aged 10-21 years with T1D for >1 year during the period 2000-2020 were analyzed. We used a cross-sectional design using the most recent year of visit to investigate the time trend. For datasets with longitudinal data, we aggregated the variables per participant and observational year, using data of the most recent year to take the longest observation period into account. DR screening was performed through quality assured national screening programs. Multiple logistic regression models adjusted for the year of the eye examination, age, gender, minority status, and duration of T1D were used to evaluate clinical characteristics and the risk of DR.

RESULTS

Data from 156,090 individuals (47.1% female, median age 15.7 years, median duration of diabetes 5.2 years) were included. Overall, the unadjusted prevalence of any DR was 5.8%, varying from 0.0% (0/276) to 16.2% between countries. The probability of DR increased with longer disease duration (aORper-1-year-increase  = 1.04, 95% CI: 1.03-1.04, p < 0.0001), and decreased over time (aORper-1-year-increase  = 0.99, 95% CI: 0.98-1.00, p = 0.0093). Evaluating possible modifiable risk factors in the exploratory analysis, the probability of DR increased with higher HbA1c (aORper-1-mmol/mol-increase-in-HbA1c  = 1.03, 95% CI: 1.03-1.03, p < 0.0001) and was higher among individuals with hypertension (aOR = 1.24, 95% CI: 1.11-1.38, p < 0.0001) and smokers (aOR = 1.30, 95% CI: 1.17-1.44, p < 0.0001).

CONCLUSIONS

The prevalence of DR in this large cohort of youth with T1D varied among countries, increased with diabetes duration, decreased over time, and was associated with higher HbA1c, hypertension, and smoking.

Social Determinants of Health and Impact on Screening, Prevalence, and Management of Diabetic Retinopathy in Adults: A Narrative Review

Diabetic retinal disease (DRD) is the leading cause of blindness among working-aged individuals with diabetes. In the United States, underserved and minority populations are disproportionately affected by diabetic retinopathy and other diabetes-related health outcomes. In this narrative review, we describe racial disparities in the prevalence and screening of diabetic retinopathy, as well as the wide-range of disparities associated with social determinants of health (SDOH), which include socioeconomic status, geography, health-care access, and education.

American Association of Clinical Endocrinology Clinical Practice Guideline: Developing a Diabetes Mellitus Comprehensive Care Plan-2022 Update

OBJECTIVE

The objective of this clinical practice guideline is to provide updated and new evidence-based recommendations for the comprehensive care of persons with diabetes mellitus to clinicians, diabetes-care teams, other health care professionals and stakeholders, and individuals with diabetes and their caregivers.

METHODS

The American Association of Clinical Endocrinology selected a task force of medical experts and staff who updated and assessed clinical questions and recommendations from the prior 2015 version of this guideline and conducted literature searches for relevant scientific papers published from January 1, 2015, through May 15, 2022. Selected studies from results of literature searches composed the evidence base to update 2015 recommendations as well as to develop new recommendations based on review of clinical evidence, current practice, expertise, and consensus, according to established American Association of Clinical Endocrinology protocol for guideline development.

RESULTS

This guideline includes 170 updated and new evidence-based clinical practice recommendations for the comprehensive care of persons with diabetes. Recommendations are divided into four sections: (1) screening, diagnosis, glycemic targets, and glycemic monitoring; (2) comorbidities and complications, including obesity and management with lifestyle, nutrition, and bariatric surgery, hypertension, dyslipidemia, retinopathy, neuropathy, diabetic kidney disease, and cardiovascular disease; (3) management of prediabetes, type 2 diabetes with antihyperglycemic pharmacotherapy and glycemic targets, type 1 diabetes with insulin therapy, hypoglycemia, hospitalized persons, and women with diabetes in pregnancy; (4) education and new topics regarding diabetes and infertility, nutritional supplements, secondary diabetes, social determinants of health, and virtual care, as well as updated recommendations on cancer risk, nonpharmacologic components of pediatric care plans, depression, education and team approach, occupational risk, role of sleep medicine, and vaccinations in persons with diabetes.

CONCLUSIONS

This updated clinical practice guideline provides evidence-based recommendations to assist with person-centered, team-based clinical decision-making to improve the care of persons with diabetes mellitus.

Artificial Intelligence Algorithms in Diabetic Retinopathy Screening

PURPOSE OF REVIEW

In this review, we focus on artificial intelligence (AI) algorithms for diabetic retinopathy (DR) screening and risk stratification and factors to consider when implementing AI algorithms in the clinic.

RECENT FINDINGS

AI algorithms have been adopted, and have received regulatory approval, for automated detection of referable DR with clinically acceptable diagnostic performance. While these metrics are an important first step, performance metrics that go beyond measures of technical accuracy are needed to fully evaluate the impact of AI algorithm on patient outcomes. Recent advances in AI present an exciting opportunity to improve patient care. Using DR as an example, we have reviewed factors to consider in the implementation of AI algorithms in real-world clinical practice. These include real-world evaluation of safety, efficacy, and equity (bias); impact on patient outcomes; ethical, logistical, and regulatory factors.

Pediatric Diabetic Retinopathy: Updates in Prevalence, Risk Factors, Screening, and Management

PURPOSE OF REVIEW

Diabetic retinopathy (DR) is a microvascular complication of diabetes mellitus and a major cause of vision loss worldwide. The purpose of this review is to provide an update on the prevalence of diabetic retinopathy in youth, discuss risk factors, and review recent advances in diabetic retinopathy screening.

RECENT FINDINGS

While DR has long been considered a microvascular complication, recent data suggests that retinal neurodegeneration may precede the vascular changes associated with DR. The prevalence of DR has decreased in type 1 diabetes (T1D) patients following the results of the Diabetes Control and Complications Trial and implementation of intensive insulin therapy, with prevalence ranging from 14-20% before the year 2000 to 3.7-6% after 2000. In contrast, the prevalence of diabetic retinopathy in pediatric type 2 diabetes (T2D) is higher, ranging from 9.1-50%. Risk factors for diabetic retinopathy are well established and include glycemic control, diabetes duration, hypertension, and hyperlipidemia, whereas diabetes technology use including insulin pumps and continuous glucose monitors has been shown to have protective effects. Screening for DR is recommended for youth with T1D once they are aged ≥ 11 years or puberty has started and diabetes duration of 3-5 years. Pediatric T2D patients are advised to undergo screening at or soon after diagnosis, and annually thereafter, due to the insidious nature of T2D. Recent advances in DR screening methods including point of care and artificial intelligence technology have increased access to DR screening, while being cost-saving to patients and cost-effective to healthcare systems. While the prevalence of diabetic retinopathy in youth with T1D has been declining over the last few decades, there has been a significant increase in the prevalence of DR in youth with T2D. Improving access to diabetic retinopathy screening using novel screening methods may help improve detection and early treatment of diabetic retinopathy.

Clinical and Demographic Factors Associated With Diabetic Retinopathy Among Young Patients With Diabetes

IMPORTANCE

Diabetic retinopathy (DR) is a leading cause of vision loss worldwide. As the incidence of both type 1 and type 2 diabetes among youths continues to increase around the world, understanding the factors associated with the development of DR in this age group is important.

OBJECTIVE

To identify factors associated with DR among children, adolescents, and young adults with type 1 or type 2 diabetes in the US.

DESIGN, SETTING, AND PARTICIPANTS

This cross-sectional study pooled data from 2 large academic pediatric centers in the US (Baylor College of Medicine/Texas Children's Hospital [BCM/TCH] Diabetes and Endocrine Care Center and Johns Hopkins University [JHU] Pediatric Diabetes Center) to form a diverse population for analysis. Data were collected prospectively at the JHU center (via point-of-care screening using fundus photography) from December 3, 2018, to November 1, 2019, and retrospectively at the BCM/TCH center (via electronic health records of patients who received point-of-care screening using retinal cameras between June 1, 2016, and May 31, 2019). A total of 1640 individuals aged 5 to 21 years with type 1 or type 2 diabetes (308 participants from the JHU center and 1332 participants from the BCM/TCH center) completed DR screening and had gradable images.

MAIN OUTCOME AND MEASURES

Prevalence of DR, as identified on fundus photography, and factors associated with DR.

RESULTS

Among 1640 participants (mean [SD] age, 15.7 [3.6] years; 867 female individuals [52.9%]), 1216 (74.1%) had type 1 diabetes, and 416 (25.4%) had type 2 diabetes. A total of 506 participants (30.9%) were Hispanic, 384 (23.4%) were non-Hispanic Black or African American, 647 (39.5%) were non-Hispanic White, and 103 (6.3%) were of other races or ethnicities (1 was American Indian or Alaska Native, 50 were Asian, 1 was Native Hawaiian or Pacific Islander, and 51 did not specify race or ethnicity, specified other race or ethnicity, or had unavailable data on race or ethnicity). Overall, 558 of 1216 patients (45.9%) with type 1 diabetes used an insulin pump, and 5 of 416 patients (1.2%) with type 2 diabetes used an insulin pump. Diabetic retinopathy was found in 57 of 1640 patients (3.5%). Patients with DR vs without DR had a greater duration of diabetes (mean [SD], 9.4 [4.4] years vs 6.6 [4.4] years; P < .001) and higher hemoglobin A1c (HbA1c) levels (mean [SD], 10.3% [2.4%] vs 9.2% [2.1%]; P < .001). Among those with type 1 diabetes, insulin pump use was associated with a lower likelihood of DR after adjusting for race and ethnicity, insurance status, diabetes duration, and HbA1c level (odds ratio [OR], 0.43; 95% CI, 0.20-0.93; P = .03). The likelihood of having DR was 2.1 times higher among Black or African American participants compared with White participants (OR, 2.12; 95% CI, 1.12-4.01; P = .02); this difference was no longer significant after adjusting for duration of diabetes, insurance status, insulin pump use (among patients with type 1 diabetes only), and mean HbA1c level (type 1 diabetes: OR, 1.79; 95% CI, 0.83-3.89; P = .14; type 2 diabetes: OR, 1.08; 95% CI, 0.30-3.85; P = .91).

CONCLUSIONS AND RELEVANCE

This study found that although the duration of diabetes and suboptimal glycemic control have long been associated with DR, insulin pump use (among those with type 1 diabetes) was independently associated with a lower likelihood of DR, which is likely owing to decreased glycemic variability and increased time in range (ie, the percentage of time blood glucose levels remain within the 70-180 mg/dL range). Black or African American race was found to be associated with DR in the univariable analysis but not in the multivariable analysis, which may represent disparities in access to diabetes technologies and care.

Racial/Ethnic Disparities and Barriers to Diabetic Retinopathy Screening in Youths

Importance

Diabetic retinopathy is a major complication of diabetes for which regular screening improves visual health outcomes, yet adherence to screening is suboptimal.

Objective

To assess disparities in diabetic eye examination completion rates and evaluate barriers in those not previously screened.

Design, Setting, and Participants

In this cohort study at a single academic center (Johns Hopkins Hospital pediatric diabetes center in Baltimore, Maryland) from December 2018 to November 2019, youths with type 1 or type 2 diabetes who met criteria for diabetic retinopathy screening and were enrolled in a prospective observational trial implementing point-of-care diabetic retinopathy screening were asked about prior diabetic retinopathy screening.

Main Outcomes and Measures

Demographic and clinical characteristics were compared between those who did and did not have a previous diabetic eye examination and stratified according to race/ethnicity, using t tests and χ2 tests. Multivariate logistic regression was used to analyze the association between race/ethnicity, screening, and other social determinants of health. A questionnaire assessing barriers to screening adherence was administered.

Results

Of 149 participants (76 male patients [51.0%]; mean [SD] age, 14.5 [2.3] years), 51 (34.2%) had not had a prior diabetic eye examination. These individuals were more likely than those who had prior diabetic eye examinations to be non-White youths (38 [75%] vs 31 [32%]; P < .001) and have type 2 diabetes (38 [75%] vs 10 [10%]; P < .001), Medicaid or public insurance (43 [84%] vs 31 [32%]; P < .001), lower household income (annual income ≤$25 000, 21 [41%] vs 9 [9%]; P < .001), and parents with education levels of high school or less (29 [67%] vs 22 [35%]; P < .001). The main barriers reported included not recalling being recommended to obtain a diabetic eye examination (19 [56%]), difficulty finding time for an additional appointment (10 [29%]), and transportation issues (7 [20%]). Minority youths were less likely to have a previous diabetic eye examination (non-White, 34 [46%] vs White, 64 [85%]; P < .001) and more likely to have diabetic retinopathy (11 [15%] v 2 [3%]; P = .008). Minority youths were less likely to get diabetic eye examinations even after adjusting for insurance, household income, and parental education level (odds ratio, 0.29 [95% CI, 0.10-0.79]; P = .02).

Conclusions and Relevance

In this cohort study, non-White youths were less likely to undergo diabetic eye examinations yet more likely to have diabetic retinopathy compared with White youths. Addressing barriers to diabetic retinopathy screening may improve access to diabetic eye examination and facilitate early detection.