Automated and Computer-Assisted Detection, Classification, and Diagnosis of Diabetic Retinopathy.

Background: The introduction of artificial intelligence (AI) in medicine has raised significant ethical, economic, and scientific controversies. Introduction: Because an explicit goal of AI is to perform processes previously reserved for human clinicians and other health care personnel, there is justified concern about the impact on patient safety, efficacy, equity, and liability. Discussion: Systems for computer-assisted and fully automated detection, triage, and diagnosis of diabetic retinopathy (DR) from retinal images show great variation in design, level of autonomy, and intended use. Moreover, the degree to which these systems have been evaluated and validated is heterogeneous. We use the term DR AI system as a general term for any system that interprets retinal images with at least some degree of autonomy from a human grader. We put forth these standardized descriptors to form a means to categorize systems for computer-assisted and fully automated detection, triage, and diagnosis of DR. The components of the categorization system include level of device autonomy, intended use, level of evidence for diagnostic accuracy, and system design. Conclusion: There is currently minimal empirical basis to assert that certain combinations of autonomy, accuracy, or intended use are better or more appropriate than any other. Therefore, at the current stage of development of this document, we have been descriptive rather than prescriptive, and we treat the different categorizations as independent and organized along multiple axes.

Practice Guidelines for Ocular Telehealth-Diabetic Retinopathy, Third Edition.

Contributors The following document and appendices represent the third edition of the Practice Guidelines for Ocular Telehealth-Diabetic Retinopathy. These guidelines were developed by the Diabetic Retinopathy Telehealth Practice Guidelines Working Group. This working group consisted of a large number of subject matter experts in clinical applications for telehealth in ophthalmology. The editorial committee consisted of Mark B. Horton, OD, MD, who served as working group chair and Christopher J. Brady, MD, MHS, and Jerry Cavallerano, OD, PhD, who served as cochairs. The writing committees were separated into seven different categories. They are as follows: 1.Clinical/operational: Jerry Cavallerano, OD, PhD (Chair), Gail Barker, PhD, MBA, Christopher J. Brady, MD, MHS, Yao Liu, MD, MS, Siddarth Rathi, MD, MBA, Veeral Sheth, MD, MBA, Paolo Silva, MD, and Ingrid Zimmer-Galler, MD. 2.Equipment: Veeral Sheth, MD (Chair), Mark B. Horton, OD, MD, Siddarth Rathi, MD, MBA, Paolo Silva, MD, and Kristen Stebbins, MSPH. 3.Quality assurance: Mark B. Horton, OD, MD (Chair), Seema Garg, MD, PhD, Yao Liu, MD, MS, and Ingrid Zimmer-Galler, MD. 4.Glaucoma: Yao Liu, MD, MS (Chair) and Siddarth Rathi, MD, MBA. 5.Retinopathy of prematurity: Christopher J. Brady, MD, MHS (Chair) and Ingrid Zimmer-Galler, MD. 6.Age-related macular degeneration: Christopher J. Brady, MD, MHS (Chair) and Ingrid Zimmer-Galler, MD. 7.Autonomous and computer assisted detection, classification and diagnosis of diabetic retinopathy: Michael Abramoff, MD, PhD (Chair), Michael F. Chiang, MD, and Paolo Silva, MD.

The Indian Health Service Primary Care-Based Teleophthalmology Program for Diabetic Eye Disease Surveillance and Management.

Background: Historically, fewer than half of American Indians and Alaska Natives (AI/AN) with diabetes received the annual diabetic retinopathy (DR) examination that is considered the minimum standard of care; this rate is similar to that of the general United States (U.S.) population with diabetes. Solution: The Indian Health Service-Joslin Vision Network (IHS-JVN) Teleophthalmology Program in 2000 to increase compliance with DR standards of care among AI/AN through validated, primary care-based telemedicine. The IHS-JVN provides remote diagnosis of DR severity, with a report including management recommendations that is returned to the patient's primary care provider. The program conforms with the American Telemedicine Association (ATA) Practice Guidelines for Ocular Telehealth-Diabetic Retinopathy. Outcomes: The IHS-JVN has been expanding incrementally since the first patients were recruited in 2000; this expansion coincides with large improvements in the annual DR examination rates reported as part of local, regional, and national regulatory compliance under the Government Performance and Results Act (GPRA). Currently, with 99 clinical implementations in 23 states, IHS-JVN is the largest primary care-based ATA validation category three telemedicine program in the U.S. Summary: This article describes the program's workflow, imaging and reading technologies, diagnostic protocols, reports to providers, training, quality assurance processes, and geographical distribution. In addition to its clinical use, the program has been utilized in research on utilization of diabetic eye care, cost-effectiveness, technology development, and DR epidemiology of the AI/AN population. Potential next steps for this program are discussed.

Use of graded Semmes Weinstein monofilament testing for ascertaining peripheral neuropathy in people with and without diabetes.

AIMS: To assess peripheral neuropathy (PN) using graded Semmes Weinstein monofilaments (SWMs) and determine factors associated with PN among adult volunteers with and without diabetes. METHODS: Adult volunteers were assessed for distal sensory PN using three graded SWMs. Four PN levels were defined: 0 (no PN; felt all three filaments), 1 (subclinical PN; insensate to 1-g filament), 2 (insensate to 10-g), or 3 (insensate to 75-g). Levels 2-3 were considered clinical PN. Associations with PN were determined using ordinal logistic regression. RESULTS: In 1564 subjects (median age 41.9 years, 50.1% women), PN was subclinical or worse in 68.9% and clinical in 11.2%. Age-sex-race-adjusted prevalence of clinical PN was greater in people with diabetes (15.3%) than without (6.1%; P < 0.001). Associated factors included older age, male sex, greater BMI, greater heart rate, lower mean arterial pressure, and family history of diabetes or cardiovascular diseases. Higher PN levels associated with worse albuminuria and retinopathy. Only older age and male sex associated with PN both in people with and without diabetes. CONCLUSIONS: PN is common in our sample, notably in those without diabetes, although diabetes greatly increases its risk. Using graded SWMs may have a prognostic value as it permits the identification of subclinical PN.

Prevalence of diabetic retinopathy and diabetic macular edema in a primary care-based teleophthalmology program for American Indians and Alaskan Natives.

BACKGROUND: Diabetes and its complications are more common in American Indians and Alaska Natives (AI/AN) than other US racial/ethnic populations. Prior reports of diabetic retinopathy (DR) prevalence in AI/AN are dated, and research on diabetic macular edema (DME) is limited. This study characterizes the recent prevalence of DR and DME in AI/AN using primary care-based teleophthalmology surveillance. METHODS: This is a multi-site, clinic-based, cross-sectional study of DR and DME. The sample is composed of AI /AN patients with diabetes (n = 53,998), served by the nationally distributed Indian Health Service-Joslin Vision Network Teleophthalmology Program (IHS-JVN) in primary care clinics of US Indian Health Service (IHS), Tribal, and Urban Indian health care facilities (I/T/U) from 1 November 2011 to 31 October 2016. Patients were recruited opportunistically for a retinal examination using the IHS-JVN during their regular diabetes care. The IHS-JVN used clinically validated, non-mydriatic, retinal imaging and retinopathy assessment protocols to identify the severity levels of non-proliferative diabetic retinopathy (NPDR), proliferative diabetic retinopathy (PDR), DME, and sight threatening retinopathy (STR; a composite measure). Key social-demographic (age, gender, IHS area), diabetes-related health (diabetes therapy, duration of diabetes, A1c), and imaging technology variables were examined. The analysis calculated frequencies and percentages of severity levels of disease. RESULTS: Prevalence of any NPDR, PDR, DME, and STR among AI/AN patients undergoing DR teleophthalmology surveillance by IHS-JVN was 17.7%, 2.3%, 2.3%, and 4.2%, respectively. Prevalence was lowest in Alaska and highest among patients with A1c >/ = 8%, duration of diabetes > 10 years, or using insulin. CONCLUSIONS: Prevalence of DR in this cohort was approximately half that in previous reports for AI/AN, and prevalence of DME was less than that reported in non-AI/AN populations. A similar reduction in diabetes related end-stage renal disease in the same population and time period has been reported by other researchers. Since these two diabetic complications share a common microvasculopathic mechanism, this coincident change in prevalence may also share a common basis, possibly related to improved diabetes management.

Access to Digital Communication Technology and Perceptions of Telemedicine for Patient Education among American Indian Patients with Diabetes.

INTRODUCTION: Health care access for medically underserved patients managing chronic conditions is challenging. While telemedicine can support patient education and engagement, the "digital divide" may be particularly problematic among the medically underserved. This study evaluated physical access to digital devices, use of e-mail and social media tools, and perceptions of telemedicine among American Indian (AI) patients with diabetes mellitus (DM). METHODS: Survey data were collected from AI patients with DM during teleophthalmology exams. RESULTS: Eighty-eight percent of patients had access to digital device(s), 70% used e-mail, and 56% used social media. Younger age and greater education were positively associated with e-mail and social media use (p < .05). Most (60%) considered telemedicine an excellent medium for health-related patient education. DISCUSSION: American Indian patients with DM had access enabling patient education via telemedicine. Future work should examine patient technology preferences and effectiveness of technology-based education in improving outcomes among medically underserved populations.

Operational Components of Telemedicine Programs for Diabetic Retinopathy.

Diabetic retinopathy is a leading cause of new-onset vision loss worldwide. Treatments supported by large clinical trials are effective in preserving vision, but many persons do not receive timely diagnosis and treatment of diabetic retinopathy, which is typically asymptomatic when most treatable. Telemedicine evaluation to identify diabetic retinopathy has the potential to improve access to care and improve outcomes, but incomplete implementation of published standards creates a risk to program utility and sustainability. In a prior article, we reviewed the literature regarding the impact of imaging device, number and size of retinal images, pupil dilation, type of image grader, and diagnostic accuracy on telemedicine assessment for diabetic retinopathy. This article reviews the literature regarding the impact of automated image grading, cost effectiveness, program standards, and quality assurance (QA) on telemedicine assessment of diabetic retinopathy. Telemedicine assessment of diabetic retinopathy has the potential to preserve vision, but greater attention to development and implementation of standards is needed to better realize its potential.

Clinical Components of Telemedicine Programs for Diabetic Retinopathy.

Diabetic retinopathy is a leading cause of new-onset vision loss worldwide. Treatments supported by large clinical trials are effective in preserving vision, but many persons do not receive timely diagnosis and treatment of diabetic retinopathy, which is typically asymptomatic when most treatable. Telemedicine evaluation to identify diabetic retinopathy has the potential to improve access to care, but there are no universal standards regarding camera choice or protocol for ocular telemedicine. We review the literature regarding the impact of imaging device, number and size of retinal images, pupil dilation, type of image grader, and diagnostic accuracy on telemedicine assessment for diabetic retinopathy. Telemedicine assessment of diabetic retinopathy has the potential to preserve vision, but further development of telemedicine specific technology and standardization of operations are needed to better realize its potential.

Identification of Diabetic Retinopathy and Ungradable Image Rate with Ultrawide Field Imaging in a National Teleophthalmology Program.

PURPOSE: To compare diabetic retinopathy (DR) identification and ungradable image rates between nonmydriatic ultrawide field (UWF) imaging and nonmydriatic multifield fundus photography (NMFP) in a large multistate population-based DR teleophthalmology program. DESIGN: Multiple-site, nonrandomized, consecutive, cross-sectional, retrospective, uncontrolled imaging device evaluation. PARTICIPANTS: Thirty-five thousand fifty-two eyes (17 526 patients) imaged using NMFP and 16 218 eyes (8109 patients) imaged using UWF imaging. METHODS: All patients undergoing Joslin Vision Network (JVN) imaging with either NMFP or UWF imaging from May 1, 2014, through August 30, 2015, within the Indian Health Service-JVN program, which serves American Indian and Alaska Native communities at 97 sites across 25 states, were evaluated. All retinal images were graded using a standardized validated protocol in a centralized reading center. MAIN OUTCOME MEASURES: Ungradable rate for DR and diabetic macular edema (DME). RESULTS: The ungradable rate per patient for DR and DME was significantly lower with UWF imaging compared with NMFP (DR, 2.8% vs. 26.9% [P < 0.0001]; DME, 3.8% vs. 26.2% [P < 0.0001]). Identification of eyes with either DR or referable DR (moderate nonproliferative DR or DME or worse) was increased using UWF imaging from 11.7% to 24.2% (P < 0.0001) and from 6.2% to 13.6% (P < 0.0001), respectively. In eyes with DR imaged with UWF imaging (n = 3926 eyes of 2402 patients), the presence of predominantly peripheral lesions suggested a more severe level of DR in 7.2% of eyes (9.6% of patients). CONCLUSIONS: In a large, widely distributed DR ocular telehealth program, as compared with NMFP, nonmydriatic UWF imaging reduced the number of ungradable eyes by 81%, increased the identification of DR nearly 2-fold, and identified peripheral lesions suggesting more severe DR in almost 10% of patients, thus demonstrating significant benefits of this imaging method for large DR teleophthalmology programs.

Moving toward implementation: the potential for accountable care organizations and private-public partnerships to advance active neighborhood design.

The 2010 Affordable Care Act's (ACA) aims of lowering costs and improving quality of care will renew focus on preventive health strategies. This coincides with a trend in medicine to reconsider population health approaches as part of the standard curriculum. This intersection of new policy and educational climates presents a unique opportunity to reconsider traditional healthcare structures. This paper introduces and advances an alignment that few have considered. We propose that accountable care organizations (ACOs), which are expected to proliferate under the ACA, present the best opportunity to establish partnerships between healthcare, public health, and community-based organizations to achieve the legislation's goals. One example is encouraging daily physical activity via built environment interventions and programs, which is recommended by numerous groups. We highlight how nonprofit organizations in Sacramento, California have been able to leverage influence, capital, and policy to encourage design for active living, and how their work is coordinating with public health and healthcare initiatives. In conclusion, we critically examine potential barriers to the success of partnerships between ACOs and community organizations and encourage further exploration and evaluation.

Telehealth and Indian healthcare: moving to scale and sustainability.

Telehealth innovation has brought important improvements in access to quality healthcare for American Indian and Alaska Native communities. Despite these improvements, substantive work remains before telehealth capability can be more available and sustainable across Indian healthcare. Some of this work will rely on system change guided by new care model development. Such care model development depends on expansion of telehealth reimbursement. The U.S. Indian healthcare system is an ideal framework for implementing and evaluating large-scale change in U.S. telehealth reimbursement policy.

Special requirements for electronic health record systems in ophthalmology.

UNLABELLED: The field of ophthalmology has a number of unique features compared with other medical and surgical specialties regarding clinical workflow and data management. This has important implications for the design of electronic health record (EHR) systems that can be used intuitively and efficiently by ophthalmologists and that can promote improved quality of care. Ophthalmologists often lament the absence of these specialty-specific features in EHRs, particularly in systems that were developed originally for primary care physicians or other medical specialists. The purpose of this article is to summarize the special requirements of EHRs that are important for ophthalmology. The hope is that this will help ophthalmologists to identify important features when searching for EHR systems, to stimulate vendors to recognize and incorporate these functions into systems, and to assist federal agencies to develop future guidelines regarding meaningful use of EHRs. More broadly, the American Academy of Ophthalmology believes that these functions are elements of good system design that will improve access to relevant information at the point of care between the ophthalmologist and the patient, will enhance timely communications between primary care providers and ophthalmologists, will mitigate risk, and ultimately will improve the ability of physicians to deliver the highest-quality medical care. FINANCIAL DISCLOSURE(S): Proprietary or commercial interest disclosure may be found after the references.

A modeled economic analysis of a digital tele-ophthalmology system as used by three federal health care agencies for detecting proliferative diabetic retinopathy.

The objective of this study was to compare, using a 12-month time frame, the cost-effectiveness of a non-mydriatic digital tele-ophthalmology system (Joslin Vision Network) versus traditional clinic-based ophthalmoscopy examinations with pupil dilation to detect proliferative diabetic retinopathy and its consequences. Decision analysis techniques, including Monte Carlo simulation, were used to model the use of the Joslin Vision Network versus conventional clinic-based ophthalmoscopy among the entire diabetic populations served by the Indian Health Service, the Department of Veterans Affairs, and the active duty Department of Defense. The economic perspective analyzed was that of each federal agency. Data sources for costs and outcomes included the published literature, epidemiologic data, administrative data, market prices, and expert opinion. Outcome measures included the number of true positive cases of proliferative diabetic retinopathy detected, the number of patients treated with panretinal laser photocoagulation, and the number of cases of severe vision loss averted. In the base-case analyses, the Joslin Vision Network was the dominant strategy in all but two of the nine modeled scenarios, meaning that it was both less costly and more effective. In the active duty Department of Defense population, the Joslin Vision Network would be more effective but cost an extra 1,618 dollars per additional patient treated with panretinal laser photo-coagulation and an additional 13,748 dollars per severe vision loss event averted. Based on our economic model, the Joslin Vision Network has the potential to be more effective than clinic-based ophthalmoscopy for detecting proliferative diabetic retinopathy and averting cases of severe vision loss, and may do so at lower cost.