Progressive inner retinal neurodegeneration in non-proliferative macular telangiectasia type 2.

PURPOSE: Patients with non-proliferative macular telangiectasia type 2 (MacTel) have ganglion cell layer (GCL) and nerve fibre layer (NFL) loss, but it is unclear whether the thinning is progressive. We quantified the change in retinal layer thickness over time in MacTel with and without diabetes. METHODS: In this retrospective, multicentre, comparative case series, subjects with MacTel with at least two optical coherence tomographic (OCT) scans separated by >9 months OCTs were segmented using the Iowa Reference Algorithms. Mean NFL and GCL thickness was computed across the total area of the early treatment diabetic retinopathy study grid and for the inner temporal region to determine the rate of thinning over time. Mixed effects models were fit to each layer and region to determine retinal thinning for each sublayer over time. RESULTS: 115 patients with MacTel were included; 57 patients (50%) had diabetes and 21 (18%) had a history of carbonic anhydrase inhibitor (CAI) treatment. MacTel patients with and without diabetes had similar rates of thinning. In patients without diabetes and untreated with CAIs, the temporal parafoveal NFL thinned at a rate of -0.25±0.09 µm/year (95% CI [-0.42 to -0.09]; p=0.003). The GCL in subfield 4 thinned faster in the eyes treated with CAI (-1.23±0.21 µm/year; 95% CI [-1.64 to -0.82]) than in untreated eyes (-0.19±0.16; 95% CI [-0.50, 0.11]; p<0.001), an effect also seen for the inner nuclear layer. Progressive outer retinal thinning was observed. CONCLUSIONS: Patients with MacTel sustain progressive inner retinal neurodegeneration similar to those with diabetes without diabetic retinopathy. Further research is needed to understand the consequences of retinal thinning in MacTel.

Ethical Considerations in the Design and Conduct of Clinical Trials of Artificial Intelligence.

Importance: Safe integration of artificial intelligence (AI) into clinical settings often requires randomized clinical trials (RCT) to compare AI efficacy with conventional care. Diabetic retinopathy (DR) screening is at the forefront of clinical AI applications, marked by the first US Food and Drug Administration (FDA) De Novo authorization for an autonomous AI for such use. Objective: To determine the generalizability of the 7 ethical research principles for clinical trials endorsed by the National Institute of Health (NIH), and identify ethical concerns unique to clinical trials of AI. Design, Setting, and Participants: This qualitative study included semistructured interviews conducted with 11 investigators engaged in the design and implementation of clinical trials of AI for DR screening from November 11, 2022, to February 20, 2023. The study was a collaboration with the ACCESS (AI for Children's Diabetic Eye Exams) trial, the first clinical trial of autonomous AI in pediatrics. Participant recruitment initially utilized purposeful sampling, and later expanded with snowball sampling. Study methodology for analysis combined a deductive approach to explore investigators' perspectives of the 7 ethical principles for clinical research endorsed by the NIH and an inductive approach to uncover the broader ethical considerations implementing clinical trials of AI within care delivery. Results: A total of 11 participants (mean [SD] age, 47.5 [12.0] years; 7 male [64%], 4 female [36%]; 3 Asian [27%], 8 White [73%]) were included, with diverse expertise in ethics, ophthalmology, translational medicine, biostatistics, and AI development. Key themes revealed several ethical challenges unique to clinical trials of AI. These themes included difficulties in measuring social value, establishing scientific validity, ensuring fair participant selection, evaluating risk-benefit ratios across various patient subgroups, and addressing the complexities inherent in the data use terms of informed consent. Conclusions and Relevance: This qualitative study identified practical ethical challenges that investigators need to consider and negotiate when conducting AI clinical trials, exemplified by the DR screening use-case. These considerations call for further guidance on where to focus empirical and normative ethical efforts to best support conduct clinical trials of AI and minimize unintended harm to trial participants.

Autonomous artificial intelligence for diabetic eye disease increases access and health equity in underserved populations.

Diabetic eye disease (DED) is a leading cause of blindness in the world. Annual DED testing is recommended for adults with diabetes, but adherence to this guideline has historically been low. In 2020, Johns Hopkins Medicine (JHM) began deploying autonomous AI for DED testing. In this study, we aimed to determine whether autonomous AI implementation was associated with increased adherence to annual DED testing, and how this differed across patient populations. JHM primary care sites were categorized as "non-AI" (no autonomous AI deployment) or "AI-switched" (autonomous AI deployment by 2021). We conducted a propensity score weighting analysis to compare change in adherence rates from 2019 to 2021 between non-AI and AI-switched sites. Our study included all adult patients with diabetes (>17,000) managed within JHM and has three major findings. First, AI-switched sites experienced a 7.6 percentage point greater increase in DED testing than non-AI sites from 2019 to 2021 (p < 0.001). Second, the adherence rate for Black/African Americans increased by 12.2 percentage points within AI-switched sites but decreased by 0.6% points within non-AI sites (p < 0.001), suggesting that autonomous AI deployment improved access to retinal evaluation for historically disadvantaged populations. Third, autonomous AI is associated with improved health equity, e.g. the adherence rate gap between Asian Americans and Black/African Americans shrank from 15.6% in 2019 to 3.5% in 2021. In summary, our results from real-world deployment in a large integrated healthcare system suggest that autonomous AI is associated with improvement in overall DED testing adherence, patient access, and health equity.

Autonomous Artificial Intelligence Increases Access and Health Equity in Underserved Populations with Diabetes.

Diabetic eye disease (DED) is a leading cause of blindness in the world. Early detection and treatment of DED have been shown to be both sight-saving and cost-effective. As such, annual testing for DED is recommended for adults with diabetes and is a Healthcare Effectiveness Data and Information Set (HEDIS) measure. However, adherence to this guideline has historically been low, and access to this sight-saving intervention has particularly been limited for specific populations, such as Black or African American patients. In 2018, the US Food and Drug Agency (FDA) De Novo cleared autonomous artificial intelligence (AI) for diagnosing DED in a primary care setting. In 2020, Johns Hopkins Medicine (JHM), an integrated healthcare system with over 30 primary care sites, began deploying autonomous AI for DED testing in some of its primary care clinics. In this retrospective study, we aimed to determine whether autonomous AI implementation was associated with increased adherence to annual DED testing, and whether this was different for specific populations. JHM primary care sites were categorized as "non-AI" sites (sites with no autonomous AI deployment over the study period and where patients are referred to eyecare for DED testing) or "AI-switched" sites (sites that did not have autonomous AI testing in 2019 but did by 2021). We conducted a difference-in-difference analysis using a logistic regression model to compare change in adherence rates from 2019 to 2021 between non-AI and AI-switched sites. Our study included all adult patients with diabetes managed within our health system (17,674 patients for the 2019 cohort and 17,590 patients for the 2021 cohort) and has three major findings. First, after controlling for a wide range of potential confounders, our regression analysis demonstrated that the odds ratio of adherence at AI-switched sites was 36% higher than that of non-AI sites, suggesting that there was a higher increase in DED testing between 2019 and 2021 at AI-switched sites than at non-AI sites. Second, our data suggested autonomous AI improved access for historically disadvantaged populations. The adherence rate for Black/African Americans increased by 11.9% within AI-switched sites whereas it decreased by 1.2% within non-AI sites over the same time frame. Third, the data suggest that autonomous AI improved health equity by closing care gaps. For example, in 2019, a large adherence rate gap existed between Asian Americans and Black/African Americans (61.1% vs. 45.5%). This 15.6% gap shrank to 3.5% by 2021. In summary, our real-world deployment results in a large integrated healthcare system suggest that autonomous AI improves adherence to a HEDIS measure, patient access, and health equity for patients with diabetes - particularly in historically disadvantaged patient groups. While our findings are encouraging, they will need to be replicated and validated in a prospective manner across more diverse settings.

A New Approach to Staging Diabetic Eye Disease: Staging of Diabetic Retinal Neurodegeneration and Diabetic Macular Edema.

Topic: The goal of this review was to summarize the current level of evidence on biomarkers to quantify diabetic retinal neurodegeneration (DRN) and diabetic macular edema (DME). Clinical relevance: With advances in retinal diagnostics, we have more data on patients with diabetes than ever before. However, the staging system for diabetic retinal disease is still based only on color fundus photographs and we do not have clear guidelines on how to incorporate data from the relatively newer modalities into clinical practice. Methods: In this review, we use a Delphi process with experts to identify the most promising modalities to identify DRN and DME. These included microperimetry, full-field flash electroretinogram, spectral-domain OCT, adaptive optics, and OCT angiography. We then used a previously published method of determining the evidence level to complete detailed evidence grids for each modality. Results: Our results showed that among the modalities evaluated, the level of evidence to quantify DRN and DME was highest for OCT (level 1) and lowest for adaptive optics (level 4). Conclusion: For most of the modalities evaluated, prospective studies are needed to elucidate their role in the management and outcomes of diabetic retinal diseases. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

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.

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.

Generative Artificial Intelligence Through ChatGPT and Other Large Language Models in Ophthalmology: Clinical Applications and Challenges.

The rapid progress of large language models (LLMs) driving generative artificial intelligence applications heralds the potential of opportunities in health care. We conducted a review up to April 2023 on Google Scholar, Embase, MEDLINE, and Scopus using the following terms: "large language models," "generative artificial intelligence," "ophthalmology," "ChatGPT," and "eye," based on relevance to this review. From a clinical viewpoint specific to ophthalmologists, we explore from the different stakeholders' perspectives-including patients, physicians, and policymakers-the potential LLM applications in education, research, and clinical domains specific to ophthalmology. We also highlight the foreseeable challenges of LLM implementation into clinical practice, including the concerns of accuracy, interpretability, perpetuating bias, and data security. As LLMs continue to mature, it is essential for stakeholders to jointly establish standards for best practices to safeguard patient safety. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Autonomous artificial intelligence increases real-world specialist clinic productivity in a cluster-randomized trial.

Autonomous artificial intelligence (AI) promises to increase healthcare productivity, but real-world evidence is lacking. We developed a clinic productivity model to generate testable hypotheses and study design for a preregistered cluster-randomized clinical trial, in which we tested the hypothesis that a previously validated US FDA-authorized AI for diabetic eye exams increases clinic productivity (number of completed care encounters per hour per specialist physician) among patients with diabetes. Here we report that 105 clinic days are cluster randomized to either intervention (using AI diagnosis; 51 days; 494 patients) or control (not using AI diagnosis; 54 days; 499 patients). The prespecified primary endpoint is met: AI leads to 40% higher productivity (1.59 encounters/hour, 95% confidence interval [CI]: 1.37-1.80) than control (1.14 encounters/hour, 95% CI: 1.02-1.25), p < 0.00; the secondary endpoint (productivity in all patients) is also met. Autonomous AI increases healthcare system productivity, which could potentially increase access and reduce health disparities. ClinicalTrials.gov NCT05182580.

Autonomous AI systems in the face of liability, regulations and costs.

Autonomous AI systems in medicine promise improved outcomes but raise concerns about liability, regulation, and costs. With the advent of large-language models, which can understand and generate medical text, the urgency for addressing these concerns increases as they create opportunities for more sophisticated autonomous AI systems. This perspective explores the liability implications for physicians, hospitals, and creators of AI technology, as well as the evolving regulatory landscape and payment models. Physicians may be favored in malpractice cases if they follow rigorously validated AI recommendations. However, AI developers may face liability for failing to adhere to industry-standard best practices during development and implementation. The evolving regulatory landscape, led by the FDA, seeks to ensure transparency, evaluation, and real-world monitoring of AI systems, while payment models such as MPFS, NTAP, and commercial payers adapt to accommodate them. The widespread adoption of autonomous AI systems can potentially streamline workflows and allow doctors to concentrate on the human aspects of healthcare.

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.

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.

Evaluation of retinal nerve fibre layer thickness as a possible measure of diabetic retinal neurodegeneration in the EPIC-Norfolk Eye Study.

BACKGROUND/AIMS: Markers to clinically evaluate structural changes from diabetic retinal neurodegeneration (DRN) have not yet been established. To study the potential role of peripapillary retinal nerve fibre layer (pRNFL) thickness as a marker for DRN, we evaluated the relationship between diabetes, as well as glycaemic control irrespective of diabetes status and pRNFL thickness. METHODS: Leveraging data from a population-based cohort, we used general linear mixed models (GLMMs) with a random intercept for patient and eye to assess the association between pRNFL thickness (measured using GDx) and demographic, systemic and ocular parameters after adjusting for typical scan score. GLMMs were also used to determine: (1) the relationship between: (A) glycated haemoglobin (HbA1c) irrespective of diabetes diagnosis and pRNFL thickness, (B) diabetes and pRNFL thickness and (2) which quadrants of pRNFL may be affected in participants with diabetes and in relation to HbA1c. RESULTS: 7076 participants were included. After controlling for covariates, inferior pRNFL thickness was 0.94 µm lower (95% CI -1.28 µm to -0.60 µm), superior pRNFL thickness was 0.83 µm lower (95% CI -1.17 µm to -0.49 µm) and temporal pRNFL thickness was 1.33 µm higher (95% CI 0.99 µm to 1.67 µm) per unit increase in HbA1c. Nasal pRNFL thickness was not significantly associated with HbA1c (p=0.23). Similar trends were noted when diabetes was used as the predictor. CONCLUSION: Superior and inferior pRNFL was significantly thinner among those with higher HbA1c levels and/or diabetes, representing areas of the pRNFL that may be most affected by diabetes.

Developing current procedural terminology codes that describe the work performed by machines.

The "Taxonomy of Artificial Intelligence for Medical Services and Procedures" became part of the Current Procedural Terminology (CPT®) code set effective January 1, 2022. It provides a framework for discrete and differentiable CPT codes which; are consistent with the features of the devices' output, characterize interaction between the device and the physician or other qualified health care professional, and foster appropriate payment. Descriptors include "Assistive", "Augmentative", and "Autonomous". As software increasingly augments the provision of medical services the taxonomy will foster consistent language in coding enabling patient, provider, and payer access to the benefits of innovation.

Total retinal thickness: a neglected factor in the evaluation of inner retinal thickness.

AIM: To determine whether macular retinal nerve fibre layer (mRNFL) and ganglion cell-inner plexiform layer (GC-IPL) thicknesses vary by ethnicity after accounting for total retinal thickness. METHODS: We included healthy participants from the UK Biobank cohort who underwent macula-centred spectral domain-optical coherence tomography scans. mRNFL and GC-IPL thicknesses were determined for groups from different self-reported ethnic backgrounds. Multivariable regression models adjusting for covariables including age, gender, ethnicity and refractive error were built, with and without adjusting for total retinal thickness. RESULTS: 20237 participants were analysed. Prior to accounting for total retinal thickness, mRNFL thickness was on average 0.9 µm (-1.2, -0.6; p<0.001) lower among Asians and 1.5 µm (-2.3, -0.6; p<0.001) lower among black participants compared with white participants. Prior to accounting for total retinal thickness, the average GC-IPL thickness was 1.9 µm (-2.5, -1.4; p<0.001) lower among Asians compared with white participants, and 2.4 µm (-3.9, -1.0; p=0.001) lower among black participants compared with white participants. After accounting for total retinal thickness, the layer thicknesses were not significantly different among ethnic groups. When considered as a proportion of total retinal thickness, mRNFL thickness was ~0.1 and GC-IPL thickness was ~0.2 across age, gender and ethnic groups. CONCLUSIONS: The previously reported ethnic differences in layer thickness among groups are likely driven by differences in total retinal thickness. Our results suggest using layer thickness ratio (retinal layer thicknesses/total retinal thickness) rather than absolute thickness values when comparing retinal layer thicknesses across groups.

Biological Correlations and Confounders for Quantification of Retinal Ganglion Cells by Optical Coherence Tomography Based on Studies of Outbred Mice.

Purpose: Despite popularity of optical coherence tomography (OCT) in glaucoma studies, it's unclear how well OCT-derived metrics compare to traditional measures of retinal ganglion cell (RGC) abundance. Here, Diversity Outbred (J:DO) mice are used to directly compare ganglion cell complex (GCC) thickness measured by OCT to metrics of retinal anatomy measured ex vivo with retinal wholemounts and optic nerve histology. Methods: J:DO mice (n = 48) underwent fundoscopic and OCT examinations, with automated segmentation of GCC thickness. RGC axons were quantified from para-phenylenediamine-stained optic nerve cross-sections and somas from BRN3A-immunolabeled retinal wholemounts, with total inner retinal cellularity assessed by TO-PRO and subsequent hematoxylin staining. Results: J:DO tissues lacked overt disease. GCC thickness, RGC abundance, and total cell abundance varied broadly across individuals. GCC thickness correlated significantly to RGC somal density (r = 0.58) and axon number (r = 0.44), but not total cell density. Retinal area and nerve cross-sectional area varied widely. No metrics were significantly influenced by sex. In bilateral comparisons, GCC thickness (r = 0.95), axon (r = 0.72), and total cell density (r = 0.47) correlated significantly within individuals. Conclusions: Amongst outbred mice, OCT-derived measurements of GCC thickness correlate significantly to RGC somal and axon abundance. Factors limiting correlation are likely both biological and methodological, including differences in retinal area that distort sampling-based estimates of RGC abundance. Translational Relevance: There are significant-but imperfect-correlations between GCC thickness and RGC abundance across genetic contexts in mice, highlighting valid uses and ongoing challenges for meaningful use of OCT-derived metrics.