Diabetic retinopathy (DR) is a leading cause of vision loss worldwide, making early detection critical to prevent blindness. IDX-DR, an FDA-approved autonomous artificial intelligence (AI) system, has emerged as an innovative solution to improve access to DR screening. This systematic review and meta-analysis aimed to evaluate the diagnostic accuracy of IDX-DR in detecting diabetic retinopathy.

Systematic review and meta-analysis.

A comprehensive literature search was conducted across PubMed, Embase, Scopus and Web of Science, identifying studies published through October 5, 2024. Studies involving adult patients with Type 1 or Type 2 diabetes and reporting diagnostic metrics such as sensitivity and specificity were included. The primary outcomes were pooled sensitivity and specificity of IDX-DR. A bivariate random-effects model was used for meta-analysis, and summary receiver operating characteristic (SROC) curves were generated to assess diagnostic performance. Statistical analyses were performed using MetaDisc software version 2.0.

Thirteen studies involving 13,233 participants met the inclusion criteria. IDX-DR's pooled sensitivity was 0.95 (95% CI: 0.82-0.99), and its pooled specificity was 0.91 (95% CI: 0.84-0.95). The SROC curve confirmed IDX-DR's high diagnostic accuracy in detecting diabetic retinopathy across various clinical environments. The AUC value of 0.95 demonstrated high sensitivity and specificity, indicating a robust diagnostic performance for IDX-DR in detecting diabetic retinopathy.

IDX-DR is a highly effective diagnostic tool for diabetic retinopathy screening, with robust sensitivity and good specificity. Its integration into clinical practice, especially in resource-limited settings, can potentially improve early detection and reduce vision loss. However, careful implementation is needed to address challenges such as over-diagnosis and ensure the tool complements clinical judgment. Future studies should explore the long-term impacts of AI-based screening and address ethical considerations surrounding its use.

This article discusses the implementation and impact of autonomous artificial intelligence (AI) systems for diabetic eye disease testing at the Johns Hopkins Medicine health system, highlighting improvements in screening rates, access to care, and health equity for underserved populations. The AI technology has been effective in both adult and pediatric populations and has reduced disparities and increased follow-up with eye care professionals. While considering the challenges and successes of this approach, this article also highlights the potential long-term impact of AI systems in improving visual health outcomes for people with diabetes in diverse health care settings.

Autonomous artificial intelligence (AI) for pediatric diabetic retinal disease (DRD) screening has demonstrated safety, effectiveness, and the potential to enhance health equity and clinician productivity. We examined the cost-effectiveness of an autonomous AI strategy versus a traditional eye care provider (ECP) strategy during the initial year of implementation from a health system perspective. The incremental cost-effectiveness ratio (ICER) was the main outcome measure. Compared to the ECP strategy, the base-case analysis shows that the AI strategy results in an additional cost of $242 per patient screened to a cost saving of $140 per patient screened, depending on health system size and patient volume. Notably, the AI screening strategy breaks even and demonstrates cost savings when a pediatric endocrine site screens 241 or more patients annually. Autonomous AI-based screening consistently results in more patients screened with greater cost savings in most health system scenarios.

With application of artificial intelligence (AI) in the disease screening, process reengineering occurred simultaneously. Whether process reengineering deserves special emphasis in AI implementation in the community-based blinding fundus diseases screening is not clear.

Cost-effectiveness and cost-utility analyses were performed employing decision-analytic Markov models. A hypothetical cohort of community residents was followed in the model over a period of 30 1-year Markov cycles, starting from the age of 60. The simulated cohort was based on work data of the Shanghai Digital Eye Disease Screening program (SDEDS). Three scenarios were compared: centralized screening with manual grading-based telemedicine systems (Scenario 1), centralized screening with an AI-assisted screening system (Scenario 2), and process reengineered screening with an AI-assisted screening system (Scenario 3). The main outcomes were incremental cost-effectiveness ratio (ICER) and incremental cost-utility ratio (ICUR).

Compared with Scenario 1, Scenario 2 results in incremental 187.03 years of blindness avoided and incremental 106.78 QALYs at an additional cost of $ 490010.62 per 10,000 people screened, with an ICER of $2619.98 per year of blindness avoided and an ICUR of $4589.13 per QALY. Compared with Scenario 1, Scenario 3 results in incremental 187.03 years of blindness avoided and incremental 106.78 QALYs at an additional cost of $242313.23 per 10,000 people screened, with an ICER of $1295.60 per year of blindness avoided and an ICUR of $2269.35 per QALY. Although Scenario 2 and 3 could be considered cost-effective, the screening cost of Scenario 3 was 27.6 % and the total cost was 1.1 % lower, with the same expected effectiveness and utility. The probabilistic sensitivity analyses show that Scenario 3 dominated 69.1 % and 70.3 % of simulations under one and three times the local GDP per capita thresholds.

AI can improve the cost-effectiveness and cost-utility of screenings, especially when process reengineering is performed. Therefore, process reengineering is strongly recommended when AI is implemented.

Systemic diseases, such as cardiovascular and cerebrovascular conditions, pose significant global health challenges due to their high mortality rates. Early identification and intervention in systemic diseases can substantially enhance their prognosis. However, diagnosing systemic diseases often necessitates complex, expensive, and invasive tests, posing challenges in their timely detection. Therefore, simple, cost-effective, and non-invasive methods for the management (such as screening, diagnosis, and monitoring) of systemic diseases are needed to reduce associated comorbidities and mortality rates.

This systematic review examines the application of artificial intelligence (AI) algorithms in managing systemic diseases by analyzing ophthalmic features (oculomics) obtained from convenient, affordable, and non-invasive ophthalmic imaging.

Our analysis demonstrates the promising accuracy of AI in predicting systemic diseases. Subgroup analysis reveals promising capabilities of oculomics-based AI for disease staging, while caution is warranted due to the possible overestimation of AI capabilities in low-quality studies. These systems are cost-effective and safe, with high rates of acceptance among patients and clinicians. This review underscores the potential of oculomics-based AI approaches in revolutionizing the management of systemic diseases.

The utilization of non-mydriatic fundus photography-assisted telemedicine to screen patients with diabetes mellitus for diabetic retinopathy provides an accurate, efficient, and cost-effective method to improve early detection of disease. It has also been shown to correlate with increased participation of patients in other aspects of diabetes care. In particular, patients who undergo teleretinal imaging are more likely to meet Comprehensive Diabetes Care Healthcare Effectiveness Data and Information Set metrics, which are linked to preservation of quality-adjusted life years and additional downstream healthcare savings.

Artificial Intelligence (AI) has become a focus of research in the rapidly evolving field of ophthalmology. Nevertheless, there is a lack of systematic studies on the health economics of AI in this field. We examine studies from the PubMed, Google Scholar, and Web of Science databases that employed quantitative analysis, retrieved up to July 2023. Most of the studies indicate that AI leads to cost savings and improved efficiency in ophthalmology. On the other hand, some studies suggest that using AI in healthcare may raise costs for patients, especially when taking into account factors such as labor costs, infrastructure, and patient adherence. Future research should cover a wider range of ophthalmic diseases beyond common eye conditions. Moreover, conducting extensive health economic research, designed to collect data relevant to its own context, is imperative.

Diabetic retinopathy (DR), a vision-threatening microvascular complication of diabetes mellitus (DM), is a leading cause of blindness worldwide that requires early detection and intervention. However, diagnosing DR early remains challenging due to the subtle nature of initial pathological changes. This review explores developments in multimodal imaging and functional tests for early DR detection. Where conventional color fundus photography is limited in the field of view and resolution, advanced quantitative analysis of retinal vessel traits such as retinal microvascular caliber, tortuosity, and fractal dimension (FD) can provide additional prognostic value. Optical coherence tomography (OCT) has also emerged as a reliable structural imaging tool for assessing retinal and choroidal neurodegenerative changes, which show potential as early DR biomarkers. Optical coherence tomography angiography (OCTA) enables the evaluation of vascular perfusion and the contours of the foveal avascular zone (FAZ), providing valuable insights into early retinal and choroidal vascular changes. Functional tests, including multifocal electroretinography (mfERG), visual evoked potential (VEP), multifocal pupillographic objective perimetry (mfPOP), microperimetry, and contrast sensitivity (CS), offer complementary data on early functional deficits in DR. More importantly, combining structural and functional imaging data may facilitate earlier detection of DR and targeted management strategies based on disease progression. Artificial intelligence (AI) techniques show promise for automated lesion detection, risk stratification, and biomarker discovery from various imaging data. Additionally, hematological parameters, such as neutrophil-lymphocyte ratio (NLR) and neutrophil extracellular traps (NETs), may be useful in predicting DR risk and progression. Although current methods can detect early DR, there is still a need for further research and development of reliable, cost-effective methods for large-scale screening and monitoring of individuals with DM.

Artificial intelligence (AI) has emerged as a transformative force in medical research and is garnering increased attention in the public consciousness. This represents a critical time period in which medical researchers, healthcare providers, insurers, regulatory agencies, and patients are all developing and shaping their beliefs and policies regarding the use of AI in the healthcare sector. The successful deployment of AI will require support from all these groups. This commentary proposes that widespread support for medical AI must be driven by clear and transparent scientific reporting, beginning at the earliest stages of scientific research.

A review of relevant guidelines and literature describing how scientific reporting plays a central role at key stages in the life cycle of an AI software product was conducted. To contextualize this principle within a specific medical domain, we discuss the current state of predictive tissue outcome modeling in acute ischemic stroke and the unique challenges presented therein.

Translating AI methods from the research to the clinical domain is complicated by challenges related to model design and validation studies, medical product regulations, and healthcare providers' reservations regarding AI's efficacy and affordability. However, each of these limitations is also an opportunity for high-impact research that will help to accelerate the clinical adoption of state-of-the-art medical AI. In all cases, establishing and adhering to appropriate reporting standards is an important responsibility that is shared by all of the parties involved in the life cycle of a prospective AI software product.

Diabetic retinopathy (DR) is a major complication of diabetes mellitus and is a leading cause of vision loss globally. A prompt and accurate diagnosis is crucial for ensuring favorable visual outcomes, highlighting the need for increased access to medical care. The recent remarkable advancements in artificial intelligence (AI) have raised high expectations for its role in disease diagnosis and prognosis prediction across various medical fields. In addition to achieving high precision comparable to that of ophthalmologists, AI-based diagnosis of DR has the potential to improve medical accessibility, especially through telemedicine. In this review paper, we aim to examine the current role of AI in the diagnosis of DR and explore future directions.

Diabetic retinopathy (DR) is the leading cause of adult blindness in the working age population worldwide, which can be prevented by early detection. Regular eye examinations are recommended and crucial for detecting sight-threatening DR. Use of artificial intelligence (AI) to lessen the burden on the healthcare system is needed.

To perform a pilot cost-analysis study for detecting DR in a cohort of minority women with DM in Oslo, Norway, that have the highest prevalence of diabetes mellitus (DM) in the country, using both manual (ophthalmologist) and autonomous (AI) grading. This is the first study in Norway, as far as we know, that uses AI in DR- grading of retinal images.

On Minority Women's Day, November 1, 2017, in Oslo, Norway, 33 patients (66 eyes) over 18 years of age diagnosed with DM (T1D and T2D) were screened. The Eidon - True Color Confocal Scanner (CenterVue, United States) was used for retinal imaging and graded for DR after screening had been completed, by an ophthalmologist and automatically, using EyeArt Automated DR Detection System, version 2.1.0 (EyeArt, EyeNuk, CA, USA). The gradings were based on the International Clinical Diabetic Retinopathy (ICDR) severity scale [1] detecting the presence or absence of referable DR. Cost-minimization analyses were performed for both grading methods.

33 women (64 eyes) were eligible for the analysis. A very good inter-rater agreement was found: 0.98 (P < 0.01), between the human and AI-based EyeArt grading system for detecting DR. The prevalence of DR was 18.6% (95% CI: 11.4-25.8%), and the sensitivity and specificity were 100% (95% CI: 100-100% and 95% CI: 100-100%), respectively. The cost difference for AI screening compared to human screening was $143 lower per patient (cost-saving) in favour of AI.

Our results indicate that The EyeArt AI system is both a reliable, cost-saving, and useful tool for DR grading in clinical practice.

In China, the prevalence of diabetic retinopathy (DR) is increasing, so it is necessary to provide convenient and effective community outreach screening programs for DR, especially in rural and remote areas. The purpose of this study was to use the results of ophthalmologists as the gold standard to evaluate the accuracy of community general practitioners' judgement and grading of DR to find a feasible and convenient DR screening method to reduce the risk of visual impairment and blindness in known diabetes patients. Retinal images of 1646 diabetic patients who underwent DR screening through teleophthalmology at Nanchang First Hospital were collected for 30 months (January 2020 to June 2022). Retinal images were collected without medication for mydriasis, stored by community general practitioner, and diagnosed by both community general practitioner and ophthalmologist of our hospital through teleophthalmology. The grading of ophthalmologist was used as a reference or gold standard for comparison with that of community general practitioner. A total of 1646 patients and 3185 eyes were examined, including 2310 eyes with DR. The evaluation by the community general practitioner had a Kappa value of 0.578, sensitivity of 80.58%, specificity of 89.94%, and accuracy of 83.38%% in 2020; a Kappa value of 0.685, sensitivity of 95.43%, specificity of 78.55%, and accuracy of 90.77% in 2021; and a Kappa value of 0.744, sensitivity of 93.99%, specificity of 88.97%, and accuracy of 92.86% in 2022. Teleophthalmology helped with large-scale screening of DR and made it possible for community general practitioner to grade images with high accuracy after appropriate training. It is possible to solve the current shortage of eye care personnel, promote the early recognition of disease and reduce the impact of diabetes-associated blindness.

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.

Health economic evaluation (HEE) is essential for assessing value of health interventions, including artificial intelligence. Recent approaches, current challenges, and future directions of HEE of artificial intelligence in ophthalmology are reviewed.

Majority of recent HEEs of artificial intelligence in ophthalmology were for diabetic retinopathy screening. Two models, one conducted in the rural USA (5-year period) and another in China (35-year period), found artificial intelligence to be more cost-effective than without screening for diabetic retinopathy. Two additional models, which compared artificial intelligence with human screeners in Brazil and Thailand for the lifetime of patients, found artificial intelligence to be more expensive from a healthcare system perspective. In the Thailand analysis, however, artificial intelligence was less expensive when opportunity loss from blindness was included. An artificial intelligence model for screening retinopathy of prematurity was cost-effective in the USA. A model for screening age-related macular degeneration in Japan and another for primary angle close in China did not find artificial intelligence to be cost-effective, compared with no screening. The costs of artificial intelligence varied widely in these models.

Like other medical fields, there is limited evidence in assessing the value of artificial intelligence in ophthalmology and more appropriate HEE models are needed.

Diabetes is a rapidly growing global health crisis disproportionately affecting low- and middle-income countries (LMICs). The emergence of diabetes as a global pandemic is one of the major challenges to human health, as long-term microvascular complications such as diabetic retinopathy (DR) can lead to irreversible blindness. Leveraging artificial intelligence (AI) technology may improve the diagnostic accuracy, efficiency, and accessibility of DR screenings across LMICs. However, there is a gap between the potential of AI technology and its implementation in clinical practice. The main objective of this systematic review is to summarize the currently available literature on the health economic assessments of AI implementation for DR screening in LMICs. The review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines. We conducted an extensive systematic search of PubMed/MEDLINE, Scopus, and the Web of Science on July 15, 2023. Our review included full-text English-language articles from any publication year. The Joanna Briggs Institute's (JBI) critical appraisal checklist for economic evaluations was used to rate the quality and rigor of the selected articles. The initial search generated 1,423 records and was narrowed to five full-text articles through comprehensive inclusion and exclusion criteria. Of the five articles included in our systematic review, two used a cost-effectiveness analysis, two used a cost-utility analysis, and one used both a cost-effectiveness analysis and a cost-utility analysis. Across the five articles, LMICs such as China, Thailand, and Brazil were represented in the economic evaluations and models. Overall, three out of the five articles concluded that AI-based DR screening was more cost-effective in comparison to standard-of-care screening methods. Our systematic review highlights the need for more primary health economic analyses that carefully evaluate the economic implications of adopting AI technology for DR screening in LMICs. We hope this systematic review will offer valuable guidance to healthcare providers, scientists, and legislators to support appropriate decision-making regarding the implementation of AI algorithms for DR screening in healthcare workflows.

Regular eye examinations to screen for the initial signs of diabetic retinopathy (DR) are crucial for preventing vision loss. Teleretinal imaging (TRI) offered in a primary care setting provides a means to improve adherence to DR screening, particularly for patients who face challenges in visiting eye care providers regularly. The present study evaluates the utilization of TRI to screen for DR in an outpatient, hospital-based primary care clinic. Patients with diabetes mellitus (DM) but without DR were eligible for point-of-care screening facilitated by their primary care provider, utilizing a non-mydriatic, handheld fundus camera. Patient demographics and clinical characteristics were extracted from the electronic medical record. Patients who underwent TRI were more likely to be male, non-White, and have up-to-date monitoring and treatment measures, including hemoglobin A1c (HbA1c), microalbumin, and low-density lipoprotein (LDL) levels, in accordance with Healthcare Effectiveness Data and Information Set (HEDIS) guidelines. Our findings demonstrate that TRI can reduce screening costs compared to a strategy where all patients are referred for in-person eye examinations. A net present value (NPV) analysis indicates that a screening site reaches the break-even point of operation within one year if an average of two patients are screened per workday.

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.

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.

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.

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.

Because existing publication guidelines and checklists have limitations when used to assess the quality of cost-effectiveness analysis, we developed a novel quality assessment tool for cost-effectiveness analyses, differentiating methods and reporting quality and incorporating the relative importance of different quality attributes.

We defined 15 quality domains from a scoping review and identified 72 methods and reporting quality attributes (36 each). After designing a best-worst scaling survey, we fielded an online survey to researchers and practitioners to estimate the relative importance of the attributes in February 2021. We analyzed the survey data using a sequential conditional logit model. The final tool included 48 quality attributes deemed most important for assessing methods and reporting quality (24 each), accompanied by a free and web-based scoring system.

A total of 524 participants completed the methodology section, and 372 completed both methodology and reporting sections. Quality attributes pertaining to the "modeling" and "data inputs and evidence synthesis" domains were deemed most important for methods quality, including "structure of the model reflects the underlying condition and intervention's impact" and "model validation is conducted." Quality attributes pertaining to "modeling" and "Intervention/comparator(s)" domains were considered most important for reporting quality, including "model descriptions are detailed enough for replication." Despite its growing prominence, "equity considerations" were not deemed as important as other quality attributes.

The Criteria for Health Economic Quality Evaluation tool allows users to differentiate methods and reporting as well as quantifies the relative importance of quality attributes. Alongside other considerations, it could help assess and improve the quality of cost-effectiveness evidence to inform value-based decisions.

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.

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.

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.

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.

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.

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.

The health care industry is an inherently resource-intense sector. Emerging technologies such as artificial intelligence (AI) are at the forefront of advancements in health care. The health economic implications of this technology have not been clearly established and represent a substantial barrier to adoption both in Australia and globally. This review aims to determine the health economic impact of implementing AI to ophthalmology in Australia.

A systematic search of the databases PubMed/MEDLINE, EMBASE, and CENTRAL was conducted to March 2022, before data collection and risk of bias analysis in accordance with preferred reporting items for systematic ceviews and meta-analyses 2020 guidelines (PROSPERO number CRD42022325511). Included were full-text primary research articles analyzing a population of patients who have or are being evaluated for an ophthalmological diagnosis, using a health economic assessment system to assess the cost-effectiveness of AI.

Seven articles were identified for inclusion. Economic viability was defined as direct cost to the patient that is equal to or less than costs incurred with human clinician assessment. Despite the lack of Australia-specific data, foreign analyses overwhelmingly showed that AI is just as economically viable, if not more so, than traditional human screening programs while maintaining comparable clinical effectiveness. This evidence was largely in the setting of diabetic retinopathy screening.

Primary Australian research is needed to accurately analyze the health economic implications of implementing AI on a large scale. Further research is also required to analyze the economic feasibility of adoption of AI technology in other areas of ophthalmology, such as glaucoma and cataract screening.

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.

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.

This study aimed to systematically review recent health economic evaluations (HEEs) of artificial intelligence (AI) applications in healthcare. The aim was to discuss pertinent methods, reporting quality and challenges for future implementation of AI in healthcare, and additionally advise future HEEs.

A systematic literature review was conducted in 2 databases (PubMed and Scopus) for articles published in the last 5 years. Two reviewers performed independent screening, full-text inclusion, data extraction, and appraisal. The Consolidated Health Economic Evaluation Reporting Standards and Philips checklist were used for the quality assessment of included studies.

A total of 884 unique studies were identified; 20 were included for full-text review, covering a wide range of medical specialties and care pathway phases. The most commonly evaluated type of AI was automated medical image analysis models (n = 9, 45%). The prevailing health economic analysis was cost minimization (n = 8, 40%) with the costs saved per case as preferred outcome measure. A total of 9 studies (45%) reported model-based HEEs, 4 of which applied a time horizon >1 year. The evidence supporting the chosen analytical methods, assessment of uncertainty, and model structures was underreported. The reporting quality of the articles was moderate as on average studies reported on 66% of Consolidated Health Economic Evaluation Reporting Standards items.

HEEs of AI in healthcare are limited and often focus on costs rather than health impact. Surprisingly, model-based long-term evaluations are just as uncommon as model-based short-term evaluations. Consequently, insight into the actual benefits offered by AI is lagging behind current technological developments.

Diabetic retinopathy (DR) has become a leading cause of global blindness as a microvascular complication of diabetes. Regular screening of diabetic retinopathy is strongly recommended for people with diabetes so that timely treatment can be provided to reduce the incidence of visual impairment. However, DR screening is not well carried out due to lack of eye care facilities, especially in the rural areas of China. Artificial intelligence (AI) based DR screening has emerged as a novel strategy and show promising diagnostic performance in sensitivity and specificity, relieving the pressure of the shortage of facilities and ophthalmologists because of its quick and accurate diagnosis. In this study, we estimated the cost-effectiveness of AI screening for DR in rural China based on Markov model, providing evidence for extending use of AI screening for DR.

We estimated the cost-effectiveness of AI screening and compared it with ophthalmologist screening in which fundus images are evaluated by ophthalmologists. We developed a Markov model-based hybrid decision tree to analyze the costs, effectiveness and incremental cost-effectiveness ratio (ICER) of AI screening strategies relative to no screening strategies and ophthalmologist screening strategies (dominated) over 35 years (mean life expectancy of diabetes patients in rural China). The analysis was conducted from the health system perspective (included direct medical costs) and societal perspective (included medical and nonmedical costs). Effectiveness was analyzed with quality-adjusted life years (QALYs). The robustness of results was estimated by performing one-way sensitivity analysis and probabilistic analysis.

From the health system perspective, AI screening and ophthalmologist screening had incremental costs of $180.19 and $215.05 but more quality-adjusted life years (QALYs) compared with no screening. AI screening had an ICER of $1,107.63. From the societal perspective which considers all direct and indirect costs, AI screening had an ICER of $10,347.12 compared with no screening, below the cost-effective threshold (1-3 times per capita GDP of Chinese in 2019).

Our analysis demonstrates that AI-based screening is more cost-effective compared with conventional ophthalmologist screening and holds great promise to be an alternative approach for DR screening in the rural area of China.

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.

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.