Computer Based Screening for Diabetic Retinopathy

描述（由申请人提供）：本II期竞争性更新项目的目的是实施临床研究，以收集数据来验证EyeStar（tm）软件系统 作为糖尿病视网膜病变（DR）所有阶段的全面筛查的基础。根据CDC的数据，美国约有8000万人患有某种形式的眼病，其中包括2000万糖尿病患者。据估计，只有不到一半的糖尿病患者定期接受DR筛查。缺乏医疗保险和医疗服务提供者给近1000万糖尿病患者带来了重大障碍。创建一个负担得起的和可访问的解决方案，为这些糖尿病患者提供筛查服务，这对医疗保健界提出了一个重大挑战。最初的第二阶段拨款的目的是展示一种“自上而下”的筛选算法，用于使用一种新技术，即调幅-调频（AM-FM），从可疑视网膜中筛选正常，即没有疾病，以分析多场数字视网膜图像。作为第二阶段赠款的结果，开发了用于糖尿病视网膜病变筛查的EyeStar（tm）软件。在本项目中，我们将进行临床验证，以使我们能够申请美国食品药品监督管理局（FDA）的510（k）许可。为了实现这一目标，我们将这一建议分为三个目标。在目标1中，我们将建立一个临床网络，并满足进行临床研究所需病例数量的要求，以获得FDA对我们的集成自动筛选系统的批准。在目标2中，我们将进行独立验证，以便向FDA提交510（k）许可申请。在目标#3中，我们将在接近“实时”的环境中操作所有EyeStar（tm）组件。 该项目的重要性主要有两个原因：提高生产率和安全测试。首先，通过自动化提高DR筛查中心的生产率，更多的高危人群将获得这项服务，从而通过早期检测和治疗提高生产率和生活质量。其次，通过向FDA提供一个高度有效和敏感的系统，我们将确保满足糖尿病视网膜病变半自动筛查的安全要求。 FDA批准的软件将被整合到我们在德克萨斯州和新墨西哥州现有的视网膜筛查网站网络中，作为商业化的第一步。 公共卫生相关性：根据CDC的数据，美国有超过2500万糖尿病患者，其中不到50%的人得到了推荐的年度眼科检查。这导致糖尿病视网膜病变的发病率增加，使其成为第二大致盲原因。我们提出的DR筛查系统EyeStar（tm）将允许增加数百万处于风险中的美国人的检查，而不会对我们的医疗保健系统产生重大影响。拟议项目将对该系统进行必要的临床确认，以获得FDA批准。

DESCRIPTION (provided by applicant): The objective of this Phase II competitive renewal project is to implement a clinical study to collect data to validate EyeStar(tm), a software system as the basis for comprehensive telescreening for all stages of diabetic retinopathy (DR). According to the CDC, approximately 80 million people in the U.S. have some form of eye disease, including 20 million diabetics at risk for retinopathy. It is estimated that less than hal of those individuals with diabetes are screened periodically for DR. Lack of medical coverage and access to healthcare providers imposes major obstacles for nearly 10 million diabetics. Creating an affordable and accessible solution to providing screening services to these diabetics presents a significant challenge to the healthcare community. The objective of the original Phase II grant was to demonstrate a "top-down" screening algorithm for triaging normal, i.e. no disease, from suspect retinas using a new technique, amplitude modulation-frequency modulation (AM-FM), to analyze multi-field digital retinal images. As a result of the Phase II grant, the EyeStar(tm) software for diabetic retinopathy screening was developed. In this project, we will perform a clinical validation that will allow us to apply for 510(k) clearance by the Food and Drug Administration (FDA). To meet this goal, we have divided this proposal in three aims. In Aim #1, we will establish a clinical network and meet the requirements for the number of cases needed to perform a clinical study in order to obtain FDA clearance for our integrated, automatic screening system. In Aim #2, we will perform an independent validation for purposes of submitting to the FDA a 510(k) clearance application. In Aim #3, we will operate all the EyeStar(tm) components in a near "real-time" environment. This project is significant for two main reasons: increase of productivity and safety testing. Firs, by increasing the productivity of DR screening centers through automation, a much larger population of at-risk individuals will have access to this service, leading to improved productivit and quality of life through early detection and treatment. Second, by providing to the FDA a system that is highly effective and sensitive, we will insure that the safety requirements of semi-automatic screening for diabetic retinopathy are met. The FDA-cleared software will be integrated into our existing network of retinal screening sites in Texas and New Mexico as the first step toward commercialization. PUBLIC HEALTH RELEVANCE: According to the CDC, there are over 25 million diabetics in the United States, of which less than 50% get their recommended yearly eye exams. This has resulted in an increase of the incidence of diabetic retinopathy, making it the second leading cause of blindness. Our proposed DR screening system, EyeStar(tm), would allow for an increase in examinations available to millions of Americans at risk, without major impact on our healthcare system. The proposed project will perform the necessary clinical validation of the system for FDA approval..