Autonomous AI to mitigate disparities for diabetic retinopathy screening in youth during and after COVID-19

自主人工智能可减少 COVID-19 期间和之后青年糖尿病视网膜病变筛查的差异

• 批准号: 10689400
• 负责人: Risa Michelle Wolf
• 金额: $ 20.13万
• 依托单位: JOHNS HOPKINS UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10689400
• 关键词: Address; Administrative Supplement; Adult; Affect; Age; Artificial Intelligence; Award; Blindness; COVID-19; COVID-19 impact; Caring; Child; Childhood; Childhood diabetes; Clinic; Clinical; Clinical Data; Clinical Trials; Communities; Complications of Diabetes Mellitus; Computer software; Consensus; Cost Savings; Data; Data Set; Decision Modeling; Detection; Diabetes Mellitus; Diabetic Retinopathy; Early Diagnosis; Effectiveness; Evaluation; Expert Systems; Eye; FDA approved; Foundations; Funding; Fundus photography; Future; Health; Health Services Accessibility; Health Technology; Healthcare Systems; Household; Improve Access; Income; Infrastructure; Institution; Insulin-Dependent Diabetes Mellitus; Insurance; Internet; Intervention; Low income; Medicaid; Methods; Minority; Multicenter Studies; Non-Insulin-Dependent Diabetes Mellitus; Ophthalmic examination and evaluation; Ophthalmologist; Parents; Participant; Patient-Focused Outcomes; Patients; Pediatrics; Persons; Pilot Projects; Population; Prevalence; Randomized Controlled Trials; Research Personnel; Risk; Safety; Screening Result; Site; System; Technology; Telemedicine; Time; United States National Institutes of Health; Youth; adherence rate; arm; behavioral economics; care outcomes; cost; cost effective; cost effectiveness; diabetic; digital healthcare; disparity elimination; experience; follow-up; health care delivery; high risk; improved; innovation; minority children; multidisciplinary; pandemic disease; point of care; prevent; prospective; racial bias; response; retinal imaging; routine care; routine screening; screening; screening guidelines; social; socioeconomics; standard of care; success; underserved community; underserved minority

Project Summary Diabetic retinopathy affects 4-15% of youth with type 1 and type 2 diabetes and is a leading cause of blindness in adults as early as age 20. Yearly screening for DR is recommended, but only 35-72% of youth undergo screening, with minority youth and children from lower socioeconomic backgrounds less likely to undergo screening. Early detection of DR through screening prevents progression to vision loss. The current standard of care for pediatric DR screening is referral to an ECP for a dilated eye exam. In 2018, the FDA approved the first autonomous artificial intelligence (AI) software that interprets retinal images taken with a non-mydriatic fundus camera, providing an immediate result for DR screening at the point of care (POC) for adults with diabetes. In a pilot study at our institution, we were the first to implement this technology in pediatrics, demonstrating safety, effectiveness and equity, and cost-savings to the patient. We also found that minority youth, those with lower household income and Medicaid insurance were less likely to undergo recommended screening, yet were more likely to have DR. We hypothesize that implementing POC autonomous AI in the diabetes care setting will increase DR screening rates in youth with diabetes, mitigate disparities in access to screening, and be cost-effective to the health care system. In the parent award, Aim1 is a randomized control trial at two clinic sites to determine if autonomous AI increases screening compared to ECP, and if those who screen positive by AI are more likely to go for follow-up at the ECP. Aim2 is a prospective observational trial of AI screening to determine if AI mitigates disparities in screening, and improves the proportion of at-risk, minority and low income, youth who go for follow-up if their AI screen is positive. In Aim 3, we will use a decision model to determine if AI is cost-effective and cost-savings to the health care system. If AI is shown to increase screening rates while mitigating disparities in access to care, it has the potential to reshape screening methods now and in the future, and will have a major impact on improving care for underserved minority and low-income youth. In this administrative supplement to the parent award, we are requesting additional support to conduct the aims of the parent award and disseminate the results, as well as funds to create a high-quality prospectively collected dataset of pediatric retinal images with corresponding clinical data that can be utilized by other investigators.

项目摘要 糖尿病视网膜病变影响4 - 15%的1型和2型糖尿病青年，是糖尿病的主要原因。 成年人在20岁时失明。建议每年进行DR筛查，但只有35 - 72%的年轻人 接受筛查，少数民族青年和来自较低社会经济背景的儿童不太可能接受筛查， 进行筛选。通过筛查早期发现DR可防止进展为视力丧失。当前 儿科DR筛查的标准护理是转诊至ECP进行散瞳眼检查。2018年，FDA 批准了第一个自主人工智能（AI）软件，该软件可以解释用 非散瞳眼底照相机，在护理点（POC）为DR筛查提供即时结果， 成人糖尿病患者在我们机构的一项试点研究中，我们是第一个在 儿科，证明安全性，有效性和公平性，并为患者节省成本。我们还发现 少数民族青年，那些家庭收入较低和医疗补助保险的人不太可能接受 推荐的筛查，但更有可能有DR。 我们假设在糖尿病护理环境中实施POC自主AI将 提高糖尿病青年患者的DR筛查率，减少筛查机会的差异， 对医疗保健系统具有成本效益。在父母奖中，Aim1是一项随机对照试验， 临床研究中心，以确定与ECP相比，自主AI是否增加了筛查， AI阳性的患者更有可能在ECP接受随访。Aim2是一项关于AI的前瞻性观察性试验 筛查，以确定人工智能是否减轻了筛查中的差异，并提高了处于风险中的少数群体的比例。 和低收入的年轻人，如果他们的AI屏幕是积极的，他们会去跟进。在目标3中，我们将使用决策模型 以确定人工智能是否具有成本效益，并为医疗保健系统节省成本。 如果人工智能被证明可以提高筛查率，同时减轻获得医疗服务的差距， 有潜力重塑现在和未来的筛查方法，并将对改善护理产生重大影响。 为服务不足的少数民族和低收入青年。 在此行政补充家长奖，我们要求额外的支持，以进行 家长奖的目的和传播的结果，以及资金，以创造一个高质量的 前瞻性收集的儿科视网膜图像数据集，以及可利用的相应临床数据 其他调查员。