Considerations for Artificial Intelligence Real-World Implementation in Ophthalmology: Providers' and Patients' Perspectives

Tseng, Rachel Marjorie Wei Wen; Gunasekeran, Dinesh Visva; Tan, Sarah Shwu Huey; Rim, Tyler Hyungtaek; Lum, Elaine; Tan, Gavin Siew Wei; Wong, Tien Yin; Tham, Yih‐Chung

doi:10.1097/apo.0000000000000400

Cited by 15 publications

(11 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, although many algorithms have been developed, barriers hamper real-world applications. The variable performance [even in FDA-approved algorithms (42)], economic inequality in developing countries, technophobia in the application of AI systems in daily practice, and ethical concerns remain challenges for the implementation of AI (28). Multidisciplinary groups including medical doctors, computer engineers, data scientists, and informatics technologists are necessary for implementing AI from benchmark algorithms to ethical autonomous healthcare tools (35) (43)(44)(45).…”

Section: Discussionmentioning

confidence: 99%

Ophthalmology and Artificial Intelligence: Present or Future? A Diabetic Retinopathy Screening Perspective of the Pursuit for Fairness

Nakayama¹,

Ribeiro²,

Malerbi³

et al. 2022

Front. Ophthalmol.

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Ophthalmology and Artificial Intelligence: Present or Future? A Diabetic Retinopathy Screening Perspective of the Pursuit for Fairness

Nakayama¹,

Ribeiro²,

Malerbi³

et al. 2022

Front. Ophthalmol.

View full text Add to dashboard Cite

“…This is strikingly so in ophthalmology given the field's increasing reliance on innovative enhanced imaging technologies for age-related macular degeneration [12][13][14][15][16], diabetic retinopathy [17][18][19][20][21], and glaucoma [22][23][24][25][26] in clinical practice. It is also an emerging technology for large-scale screening for vision impairment [27,28] and an aid for diseases in pediatric populations when there can be significant subjectivity and variation in diagnostic agreement [29,30].…”

Section: Ophthalmology Imaging-a Case In Pointmentioning

confidence: 99%

Artificial Intelligence, Heuristic Biases, and the Optimization of Health Outcomes: Cautionary Optimism

Feehan

Owen

McKinnon

et al. 2021

JCM

View full text Add to dashboard Cite

The use of artificial intelligence (AI) and machine learning (ML) in clinical care offers great promise to improve patient health outcomes and reduce health inequity across patient populations. However, inherent biases in these applications, and the subsequent potential risk of harm can limit current use. Multi-modal workflows designed to minimize these limitations in the development, implementation, and evaluation of ML systems in real-world settings are needed to improve efficacy while reducing bias and the risk of potential harms. Comprehensive consideration of rapidly evolving AI technologies and the inherent risks of bias, the expanding volume and nature of data sources, and the evolving regulatory landscapes, can contribute meaningfully to the development of AI-enhanced clinical decision making and the reduction in health inequity.

show abstract

“…devices for the screening of common eye conditions, it is evident that change is already coming. 7,8 The use of new technologies will help transform ophthalmology from a backline reactive referral specialty into a high-reliability field. The benefits of digital innovations are quite apparent: they will help address the challenges facing medicine and ophthalmology by decreasing the cost of services, optimizing efficiency, decreasing health disparities, increasing access to care, and improving outcomes on a population level.…”

mentioning

confidence: 99%

“…Although future studies are needed to understand the benefits of using AI, telemedicine, and home monitoring devices for the screening of common eye conditions, it is evident that change is already coming 7,8. The use of new technologies will help transform ophthalmology from a backline reactive referral specialty into a high-reliability field.…”

mentioning

confidence: 99%

Transformation of Eye Care Through Innovations

Al-Aswad

Rakitina

2023

Asia-Pacific Journal of Ophthalmology

View full text Add to dashboard Cite

I s change good? Regardless of where on the spectrum 1 might fall in answering this question, 1 thing is for sure, change is inevitable. But when it comes to health care, change is usually perceived as threatening and any effort to alter the status quo is being scrutinized relentlessly.What are the dominant factors driving change in health care now? First, health care expenditure, which is projected to increase to 5.7% from 4.8% in 2019 and reach nearly $6.0 trillion by 2027. While the nominal US Gross Domestic Product (GDP) growth is expected to average 4.6% during this period, health care spend as a percent of GDP is expected to increase to 19.4% by 2027, up from 17.8% in 2019. 1 Second, physician shortage is expected to reach 5400 by 2026. Moreover, the US population is estimated to expand to 438 million by 2050 which will influence the overall burden of eye disease, currently projected to increase amongst all sectors of the population over the next 20 or more years with cataract accounting for 45.6 million, diabetic retinopathy (DR) 13.1 million, glaucoma 5.5 million, and age-related macular degeneration 4.4 million. 2 Within the existing model of eye care, which can be best described as reactive, eye care providers position themselves on the sidelines, waiting for the patients to be referred to the ophthalmologist's office (Fig. 1A). Eye care providers get their patients through referrals from primary care colleagues, emergency departments, acute care hospitals, and long-term care facilities. However, patients residing in chronic care facilities are rarely referred to specialty ophthalmology services. Most of the referrals are made for already symptomatic patients. For instance, 2.7 million people in the United States have glaucoma but only 50% of them know about it. This means that over a million people with glaucoma will not get to the eye care specialist in time.A more efficient future model of care will be proactive in nature and will help reduce the burden of eye disease by integrating eye care providers through primary care practices, emergency departments, acute care hospitals, and long-term care facilities, with diagnostics, therapeutics, and preventative services available on site (Fig. 1B). This will lead to improved access to care and early capture of asymptomatic patients, thus leading to early detection of the disease on the population level and decreasing the burden of eye disease broadly.It may be inferred from this model that higher number of patients would be identified with a percentage of false-positive results. Consequently, the need for more eye care specialists would be required to match the demand for their services. To address this care gap, we need to utilize technologies, such as telemedicine, centralized reading centers with large databases that utilize a combination of eye care providers and artificial intelligence (AI). This would allow underserved populations and people living in chronic care facilities to be captured through telehealth visits. This would reduce disparities betw...

show abstract

Considerations for Artificial Intelligence Real-World Implementation in Ophthalmology: Providers' and Patients' Perspectives

Cited by 15 publications

References 64 publications

Ophthalmology and Artificial Intelligence: Present or Future? A Diabetic Retinopathy Screening Perspective of the Pursuit for Fairness

Ophthalmology and Artificial Intelligence: Present or Future? A Diabetic Retinopathy Screening Perspective of the Pursuit for Fairness

Artificial Intelligence, Heuristic Biases, and the Optimization of Health Outcomes: Cautionary Optimism

Transformation of Eye Care Through Innovations

Contact Info

Product

Resources

About