Enabling the Development and Application of Artificial Intelligence in the NHS

推动人工智能在 NHS 中的开发和应用

基本信息

批准号：
MR/T019050/1
负责人：
Pearse Keane
金额：
$ 137.73万
依托单位：
University College London
依托单位国家：
英国
项目类别：
Fellowship
财政年份：
2020
资助国家：
英国
起止时间：
2020 至无数据
项目状态：
未结题

来源：
https://gtr.ukri.org/projects?ref=MR%2FT019050%2F1
关键词：
Enabling Development Application Artificial Intelligence

项目摘要

THE PROMISE OF AI IN HEALTHCAREArtificial intelligence (AI) is a field of study which tries to get computers to behave in ways we would consider intelligent if those same behaviours were exhibited by humans - for example, the replication of human cognitive skills such as problem solving. But AI has huge potential beyond the mimicking of human behaviours - it is a fundamental technology that can allow meaningful processing of data beyond the comprehension of the human brain. The promise of AI for healthcare is thus clear - it could allow every diagnosis and treatment to be personalized on the basis of all known information about a patient, incorporating lessons from collective experience. By streamlining workflows, providing automated diagnosis of routine, non-serious conditions, and by allowing liberation from keyboards, AI could ultimately provide healthcare professionals the "gift of time" - the dedicated time really required to provide the best possible care for patients.OBJECTIVEMuch of the exceptional recent progress in the application of AI to healthcare has come in the diagnosis of eye disease. This includes work that I initiated and led - the collaboration between Moorfields Eye Hospital and Google DeepMind to apply AI to retinal diseases such as age-related macular degeneration (AMD). My fundamental objective in this fellowship will be to drive the development and application of AI on the NHS using ophthalmology as a model. By emphasizing a central role for patients, and a thoughtful approach to use of their data, this fellowship will provide experience that can be shared with other medical specialties, helping the NHS become a world leader in AI. TRAINING AND DEVELOPMENTThis fellowship will allow me to become a world leader in the application of AI to healthcare, developing the leadership and technical skills to lead a diverse and multi-disciplinary research group, establish collaborations, and drive innovation.CASE FOR SUPPORTThe infrastructure component will focus on development of an ophthalmic bioresource that can be used to build AI systems and to evaluate their clinical performance. Using this, I will lead novel approaches to educating patients about how their data is used to develop AI systems. The research component will begin by investigating the feasibility in healthcare of "AI that can build AI" - recently developed platforms that can allow healthcare professionals without any computer programming experience to explore AI. It will next focus on developing novel AI systems that can provide more individualized treatment of retinal diseases like AMD, can enhance and transform ophthalmic images to allow better diagnosis, and which can generate "imitation" ophthalmic images indistinguishable from real versions. Finally, the research component will focus on links between the eye and the rest of the body, using AI in an attempt to predict the future development of diseases such as Alzheimer's, stroke, and heart attack.Finally, in years 5-7 of the fellowship, I plan to focus more on the practical implementation of AI systems in patient care pathways in the NHS and around the world. POTENTIAL APPLICATIONS AND BENEFITSThis fellowship will benefit the academic community and industry by greatly facilitating the development of AI systems for ophthalmology. Through the creation of benchmark datasets, it will assist regulators to ensure the safety and effectiveness of AI systems before they are implemented in the real world. Most importantly, these systems will ultimately provide direct benefits for patients with better diagnosis and treatment of eye disease. The NHS will also benefit by allowing hospital eye services to become both more efficient and less expensive. Finally, this fellowship will benefit the public and policy makers by developing and disseminating best practice regarding the use of patient data in AI, as well as allowing them to visualize and contextualize its use.

人工智能在医疗保健领域的前景人工智能 (AI) 是一个研究领域，它试图让计算机以我们认为智能的方式行事，如果人类也表现出同样的行为，例如，复制人类认知技能，例如解决问题的能力。但人工智能除了模仿人类行为之外还具有巨大的潜力——它是一项基础技术，可以对超出人脑理解范围的数据进行有意义的处理。因此，人工智能在医疗保健方面的前景是明确的——它可以根据患者的所有已知信息，结合集体经验教训，实现每次诊断和治疗的个性化。通过简化工作流程，提供对常规、非严重疾病的自动诊断，并允许从键盘中解放出来，人工智能最终可以为医疗保健专业人员提供“时间的礼物”——为患者提供最佳护理所需的专门时间。目标人工智能在医疗保健领域的应用最近取得了巨大进展，其中之一就是眼科疾病的诊断。这包括我发起和领导的工作——莫菲尔德眼科医院和 Google DeepMind 之间的合作，将人工智能应用于年龄相关性黄斑变性 (AMD) 等视网膜疾病。我在这项奖学金中的基本目标是以眼科为模型，推动 NHS 中人工智能的开发和应用。通过强调患者的核心作用以及使用患者数据的深思熟虑的方法，该奖学金将提供可与其他医学专业分享的经验，帮助 NHS 成为人工智能领域的世界领导者。培训和发展这项奖学金将使我成为人工智能在医疗保健应用方面的世界领导者，培养领导力和技术技能，以领导多元化和多学科的研究小组，建立合作并推动创新。支持案例基础设施部分将专注于开发可用于构建人工智能系统并评估其临床表现的眼科生物资源。利用这一点，我将引导新的方法来教育患者如何使用他们的数据来开发人工智能系统。研究部分将首先调查“可以构建人工智能的人工智能”在医疗保健领域的可行性——最近开发的平台可以让没有任何计算机编程经验的医疗保健专业人员探索人工智能。接下来，该公司将专注于开发新型人工智能系统，该系统可以为 AMD 等视网膜疾病提供更个性化的治疗，可以增强和转换眼科图像以实现更好的诊断，并且可以生成与真实版本无法区分的“模仿”眼科图像。最后，研究部分将重点关注眼睛和身体其他部位之间的联系，利用人工智能试图预测阿尔茨海默氏症、中风和心脏病等疾病的未来发展。最后，在该计划的第 5-7 年作为奖学金，我计划更多地关注人工智能系统在 NHS 和世界各地患者护理路径中的实际实施。潜在的应用和好处该奖学金将极大地促进眼科人工智能系统的发展，从而使学术界和行业受益。通过创建基准数据集，它将协助监管机构确保人工智能系统在现实世界中实施之前的安全性和有效性。最重要的是，这些系统最终将为患者提供直接的好处，更好地诊断和治疗眼部疾病。 NHS 还将通过提高医院眼科服务的效率和成本而受益。最后，该奖学金将通过开发和传播有关在人工智能中使用患者数据的最佳实践，以及允许他们将其使用可视化和情境化，使公众和政策制定者受益。