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: 10598686
• 负责人: Risa Michelle Wolf
• 金额: $ 34.35万
• 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/10598686
• 关键词: Address; Adult; Area; Artificial Intelligence; Award; Biological; Black race; COVID-19; Caring; Clinic; Clinical; Clinical Research; Clinical Trials; Cognitive; Communities; Computer software; Conduct Clinical Trials; Conflict (Psychology); Consensus; Cost Savings; Decision Making; Development; Diabetes Mellitus; Diabetic Retinopathy; Diagnosis; Diagnostic; Effectiveness; Ensure; Equipoise; Ethical Analysis; Ethical Issues; Ethics; Ethnic Origin; Expert Systems; Exposure to; Eye; FDA approved; Fundus photography; Future; Gold; Health Services Accessibility; Healthcare; Healthcare Systems; Household; Image; Income; Individual; Informed Consent; Insurance; Intervention; Interview; Latinx; Low income; Measures; Medicaid; Medicine; Methodology; Methods; Minority; Modeling; Operative Surgical Procedures; Ophthalmology; Outcome; Parents; Participant; Patients; Pediatrics; Performance; Population; Process; Race; Randomized Controlled Trials; Recommendation; Research; Research Personnel; Resolution; Risk; Safety; Sensitivity and Specificity; Series; Site; Subgroup; Technology; Therapeutic Intervention; Thoracic Radiography; Time; Underserved Population; United States National Institutes of Health; Work; Youth; base; computer science; cost effective; design; drug efficacy; efficacy testing; experience; follow-up; improved; minority children; point of care; population health; predictive modeling; pressure; prospective; retinal imaging; risk benefit ratio; screening; screening guidelines; sex; therapy outcome

Project Summary In 2018 the FDA approved the first autonomous healthcare artificial intelligence (AI-HC) software that interprets retinal images taken with a non-mydriatic fundus camera, providing an immediate result for diabetic retinopathy (DR) screening at the point of care (POC) for adults with diabetes. The PIs of the parent award were the first to implement this technology in pediatrics, demonstrating safety, effectiveness and equity, and cost-savings to the patient. They 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. The parent award hypothesizes 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, Aim 1 is a randomized control trial at two clinic sites to determine if autonomous AI increases screening compared to an eye-care professional (ECP), and if those who screen positive by AI are more likely to go for follow-up at the ECP. Aim 2 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. If AI is shown to increase screening rates while mitigating disparities in access to care, it has the potential to reshape screening methods. Partnering with the parent award presents a unique opportunity to address two pressing ethical questions: What are the ethical challenges with conducting clinical trials for AI? How do you anticipate, identify, and address ethical problems with AI-HC before they cause harm? The supplement team has worked closely with the parent award investigators during their F.D.A. review, in the Collaborative Community on Ophthalmic Imaging for the F.D.A. and, from these experiences, in development of a methodology to identify and address ethical challenges with AI for healthcare. In this supplement we will pilot our ethical analysis methodology to: 1) identify the ethical issues emerging with clinical trials of AI-HC for DR in real time as such trials are being conducted through the parent award; 2) develop expert consensus on how to address these identified ethical challenges for the parent award; and 3) in doing 1 & 2, refine a generalizable approach for identifying and addressing ethical challenges with an AI-HC and a roadmap for how to address ethical concerns with future clinical trials of AI-HC.

项目摘要 2018年，FDA批准了第一个自主医疗人工智能（AI-HC）软件， 使用非散瞳眼底照相机拍摄的视网膜图像，提供糖尿病视网膜病变的即时结果 (DR)在护理点（POC）筛查成人糖尿病患者。家长奖的PI是第一个 在儿科实施这项技术，证明安全性，有效性和公平性，并节省成本， 病人他们还发现，少数民族青年，那些家庭收入较低和医疗补助保险 不太可能接受推荐的筛查，但更有可能患有DR。 假设在糖尿病护理环境中实施POC自主AI将增加DR筛查 降低糖尿病青年的发病率，减少筛查机会的不平等，并提高医疗保健的成本效益。 系统在父母奖，目标1是一个随机对照试验，在两个诊所，以确定是否自主 与眼科护理专业人员（ECP）相比，AI增加了筛查，如果那些通过AI筛查呈阳性的人 更有可能去ECP接受后续治疗目的2是一项AI筛查的前瞻性观察性试验， 确定人工智能是否减轻了筛查中的差异，并提高了高危、少数和低风险人群的比例。 收入，如果他们的人工智能屏幕是积极的，去随访的年轻人。如果AI被证明可以提高筛查率， 减少在获得护理方面的差距，它有可能重塑筛查方法。 与家长奖合作提供了一个独特的机会，以解决两个紧迫的道德问题： 进行人工智能临床试验的伦理挑战是什么？你如何预测，识别， 在AI-HC造成伤害之前解决它们的伦理问题？补充团队与 在美国食品药品管理局（FDA）的审查中， 为FDA成像，并根据这些经验，开发一种方法来识别和解决 AI在医疗保健领域的伦理挑战。在本附录中，我们将引导我们的道德分析方法：1） 确定真实的DR AI-HC临床试验中出现的伦理问题，因为这些试验正在进行 通过母公司奖进行; 2）就如何解决这些确定的道德问题达成专家共识 挑战的父母奖;和3）在做1和2，完善了一个普遍的方法，以确定和 通过AI-HC解决道德挑战，并制定未来如何解决道德问题的路线图 AI-HC的临床试验