Recent evidence of economic evaluation of artificial intelligence in ophthalmology.

PURPOSE OF REVIEW: 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. RECENT FINDINGS: 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. SUMMARY: Like other medical fields, there is limited evidence in assessing the value of artificial intelligence in ophthalmology and more appropriate HEE models are needed.

Data sharing implementation in top 10 ophthalmology journals in 2021.

BACKGROUND/AIMS: Deidentified individual participant data (IPD) sharing has been implemented in the International Committee of Medical Journal Editors journals since 2017. However, there were some published clinical trials that did not follow the new implemented policy. This study examines the number of clinical trials that endorsed IPD sharing policy among top ophthalmology journals. METHOD: All published original articles in 2021 in 10 highest-ranking ophthalmology journals according to the 2020 journal impact factor were included. Clinical trials were determined by the WHO definition of clinical trials. Each article was then thoroughly searched for the IPD sharing statement either in the manuscript or in the clinical trial registry. We collected the number of published clinical trials that implemented IPD sharing policy as our primary outcome. RESULTS: 1852 published articles in top 10 ophthalmology journals were identified, and 9.45% were clinical trials. Of these clinical trials, 44% had clinical trial registrations and 49.14% declared IPD sharing statements. Only 42 (48.83%) clinical trials were willing to share IPD, and 5 (10.21%) of these share IPD via an online repository platform. In terms of sharing period, 37 clinical trials were willing to share right after the publication and only 2 showed the ending of sharing period. CONCLUSION: This report shows that the number of clinical trials in top ophthalmology journals that endorsed the IPD sharing policy and the number of registrations is lower than half even though the policy has been implemented for several years. Future updates are necessary as policy evolves.

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

INTRODUCTION: Deep learning (DL) for screening diabetic retinopathy (DR) has the potential to address limited healthcare resources by enabling expanded access to healthcare. However, there is still limited health economic evaluation, particularly in low- and middle-income countries, on this subject to aid decision-making for DL adoption. METHODS: In the context of a middle-income country (MIC), using Thailand as a model, we constructed a decision tree-Markov hybrid model to estimate lifetime costs and outcomes of Thailand's national DR screening program via DL and trained human graders (HG). We calculated the incremental cost-effectiveness ratio (ICER) between the two strategies. Sensitivity analyses were performed to probe the influence of modeling parameters. RESULTS: From a societal perspective, screening with DL was associated with a reduction in costs of ~ US$ 2.70, similar quality-adjusted life-years (QALY) of + 0.0043, and an incremental net monetary benefit of ~ US$ 24.10 in the base case. In sensitivity analysis, DL remained cost-effective even with a price increase from US$ 1.00 to US$ 4.00 per patient at a Thai willingness-to-pay threshold of ~ US$ 4.997 per QALY gained. When further incorporating recent findings suggesting improved compliance to treatment referral with DL, our analysis models effectiveness benefits of ~ US$ 20 to US$ 50 depending on compliance. CONCLUSION: DR screening using DL in an MIC using Thailand as a model may result in societal cost-savings and similar health outcomes compared with HG. This study may provide an economic rationale to expand DL-based DR screening in MICs as an alternative solution for limited availability of skilled human resources for primary screening, particularly in MICs with similar prevalence of diabetes and low compliance to referrals for treatment.

Pharmacological Treatment in Presbyopia.

Pharmacological treatment of presbyopia may be an alternative for those who want a spectacle-free scenario and an easy-to-use method with lower risk of irreversible ocular adverse events. There are two main agents, miotics and lens softeners, investigated as agents for the pharmacological treatment. Miotic agents treat presbyopia by creating a pinhole effect which may increase the depth of focus at all working distances. The miotic agents have been studied for application to only one eye for monovision or both eyes. Their effect is temporary with common adverse events, such as headache and dim vision at nighttime, with no known long-term safety and efficacy. There have been studies on the miotic agents in combination with other agents for additive treatment effects or lessening adverse events, however, these combination effects are not clear. Lens softeners increase the elasticity of the lens, which is targeted at one of the etiologic mechanisms of presbyopia. There is only one lens softener being investigated in only a few trials. The results were inconclusive. The recent approval of 1.25% pilocarpine for treatment of presbyopia by the US FDA may be an important milestone for investigation of real-world data of pharmacological treatment of presbyopia.

The Roles of Vitamins in Diabetic Retinopathy: A Narrative Review.

There have been attempts to evaluate the roles of vitamins for the prevention or treatment of eye conditions, such as glaucoma, age-related macular degeneration, and diabetic retinopathy (DR). Regarding DR, two main groups of studies can be identified. The first group focuses on the association between serum levels of an individual vitamin and DR. Many studies have found that lower serum levels of vitamins, particularly vitamin D, are significantly associated with the development, or severity, of DR, while some studies have not supported this trend. The second group evaluates dietary vitamin intakes and DR. A small, randomized placebo-controlled trial did not show any benefit of vitamin E intake on improving the area of retinal hemorrhage or diabetic macular edema at 12 months. A pilot study of patients with mild-to-moderate non-proliferative DR received tablets of combined vitamins B6, B9, and B12 for 6 months and significant improvement in retinal sensitivity and retinal thickness resulted. Two large prospective cohorts showed that high dietary intake of vitamin B6, and fruit rich in vitamin C and E, could significantly lower the risk of DR by 50% after an eight-year follow-up. Properly designed, randomized controlled trials are needed to support the results.

Economic Evaluations of Artificial Intelligence in Ophthalmology.

ABSTRACT: Artificial intelligence (AI) is expected to cause significant medical quality enhancements and cost-saving improvements in ophthalmology. Although there has been a rapid growth of studies on AI in the recent years, real-world adoption of AI is still rare. One reason may be because the data derived from economic evaluations of AI in health care, which policy makers used for adopting new technology, have been fragmented and scarce. Most data on economics of AI in ophthalmology are from diabetic retinopathy (DR) screening. Few studies classified costs of AI software, which has been considered as a medical device, into direct medical costs. These costs of AI are composed of initial and maintenance costs. The initial costs may include investment in research and development, and costs for validation of different datasets. Meanwhile, the maintenance costs include costs for algorithms upgrade and hardware maintenance in the long run. The cost of AI should be balanced between manufacturing price and reimbursements since it may pose significant challenges and barriers to providers. Evidence from cost-effectiveness analyses showed that AI, either standalone or used with humans, was more cost-effective than manual DR screening. Notably, economic evaluation of AI for DR screening can be used as a model for AI to other ophthalmic diseases.

Longitudinal Screening for Diabetic Retinopathy in a Nationwide Screening Program: Comparing Deep Learning and Human Graders.

OBJECTIVE: To evaluate diabetic retinopathy (DR) screening via deep learning (DL) and trained human graders (HG) in a longitudinal cohort, as case spectrum shifts based on treatment referral and new-onset DR. METHODS: We randomly selected patients with diabetes screened twice, two years apart within a nationwide screening program. The reference standard was established via adjudication by retina specialists. Each patient's color fundus photographs were graded, and a patient was considered as having sight-threatening DR (STDR) if the worse eye had severe nonproliferative DR, proliferative DR, or diabetic macular edema. We compared DR screening via two modalities: DL and HG. For each modality, we simulated treatment referral by excluding patients with detected STDR from the second screening using that modality. RESULTS: There were 5,738 patients (12.3% STDR) in the first screening. DL and HG captured different numbers of STDR cases, and after simulated referral and excluding ungradable cases, 4,148 and 4,263 patients remained in the second screening, respectively. The STDR prevalence at the second screening was 5.1% and 6.8% for DL- and HG-based screening, respectively. Along with the prevalence decrease, the sensitivity for both modalities decreased from the first to the second screening (DL: from 95% to 90%, p = 0.008; HG: from 74% to 57%, p < 0.001). At both the first and second screenings, the rate of false negatives for the DL was a fifth that of HG (0.5-0.6% vs. 2.9-3.2%). CONCLUSION: On 2-year longitudinal follow-up of a DR screening cohort, STDR prevalence decreased for both DL- and HG-based screening. Follow-up screenings in longitudinal DR screening can be more difficult and induce lower sensitivity for both DL and HG, though the false negative rate was substantially lower for DL. Our data may be useful for health-economics analyses of longitudinal screening settings.