RII Track-1: AI-enabled Devices for the Advancement of Personalized and Transformative Healthcare in South Carolina

“促进南卡罗来纳州个性化和变革性医疗保健的人工智能设备”（ADAPT）项目的愿景是通过基础研究、教育、劳动力发展和行业合作伙伴关系，在人工智能（AI）、生命和社会科学以及生物工程的纽带上建立研究能力。建立这种能力将大大加快人工智能解决方案的开发和部署，以创建下一代生物医学设备，从而改善医疗保健结果，满足南卡罗来纳州人（特别是服务不足地区的人）的医疗保健需求。ADAPT将通过在全州范围内促进交叉STEM研究并将研究成果转化为新技术，为南卡罗来纳州的人工智能生物医学设备产业做出贡献。通过招募和支持来自传统上代表性不足的群体的受训者，通过STEM训练营、教师参与以及STEM管道中的保留/持续计划，将扩大对人工智能开发和相关生物医学设备研究的参与。ADAPT将由克莱姆森大学牵头，与本尼迪克特学院、城堡学院、克拉夫林大学、查尔斯顿学院、弗朗西斯马里昂大学、南卡罗来纳医科大学、南卡罗来纳研究机构、南卡罗来纳州立大学、三县技术学院、南卡罗来纳大学和温斯罗普大学合作。ADAPT研究将重点关注新兴的生物医学人工智能及其与目标生物医学设备的整合，用于医疗干预的三个阶段：诊断、治疗和康复。人工智能核心将承担生物医学人工智能的基础研究，解决数据采集、多模态数据融合、数据表示学习、元学习、基于物理的机器学习、安全性和可信赖的人工智能等问题，为每个研究重点开发的生物医学设备提供集成解决方案。ADAPT人工智能支持核心的人工智能伦理团队的任务是制定人工智能伦理标准，设计创新的教育和培训计划，以确保人工智能生物医学设备在实践中得到医疗保健提供者和接受者的信任。研究将解决生物医学人工智能中的关键问题，包括将伦理纳入设计决策；通过可解释的人工智能消除“黑盒子”；基于深度学习模型的多模态数据集成以及通过数字孪生实现人工智能设备集成。ADAPT将为开发生物医学设备、教育和培训生物医学人工智能劳动力以及与利益相关者互动提供一个新的国家模式。ADAPT将通过以下方式使南卡罗来纳州受益：(1)在医疗保健人工智能方面的领导地位和全国突出地位；(2)开展人工智能扫盲运动，促进利用人工智能解决医疗保健差距问题；(3)社会对AI在精准医疗中的重要性的认识；(4)通过医疗保健专业人员（例如护士、医生和医疗保健管理人员）的继续教育学分，提高人工智能的专业能力。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The vision of the "Artificial Intelligence-enabled Devices for the Advancement of Personalized and Transformative Healthcare in South Carolina" (ADAPT) project is to build research capacity at the nexus of artificial intelligence (AI), life and social sciences, and bioengineering through fundamental research, education, workforce development, and industry partnerships. Building this capacity will significantly accelerate the development and deployment of AI solutions to create next-generation biomedical devices that will improve healthcare outcomes and address the healthcare needs of South Carolinians, especially those in underserved regions. ADAPT will contribute to South Carolina’s AI-enabled biomedical device industry by fostering cross-cutting STEM research throughout the state and translating research outcomes into new technologies. Participation in AI development and associated biomedical device research will be expanded by recruiting and supporting trainees from groups traditionally underrepresented through STEM camps, teacher engagement, and retention/persistence initiatives along the STEM pipeline. ADAPT will be led by Clemson University in partnership with Benedict College, The Citadel, Claflin University, College of Charleston, Francis Marion University, Medical University of South Carolina, South Carolina Research Authority, South Carolina State University, Tri-County Technical College, University of South Carolina, and Winthrop University. ADAPT research will focus on emerging biomedical AI and its integration with targeted biomedical devices for use in three phases of medical interventions: diagnosis, treatment, and rehabilitation. The AI-enabling Core will take on fundamental research in biomedical AI, tackling issues such as data acquisition, multimodal data fusion, data representation learning, meta-learning, physics-informed machine learning, security, and trustworthy AI to provide integrated solutions for the biomedical devices developed in each research thrust. The AI ethics team in ADAPT’s AI-enabling Core is tasked to set AI ethics standards and design innovative education and training programs to ensure that the AI-enabled biomedical devices are trusted by both healthcare providers and receivers in practice. Research will address critical issues in biomedical AI, including incorporation of ethics into design decisions; elimination of the “black box” via explainable AI; integration of multimodal data via deep learning models; and AI-device integration via digital twins. ADAPT will deliver a new national model for developing biomedical devices, educating and training a biomedical AI workforce, and interacting with stakeholders. ADAPT will benefit the State of South Carolina through: (1) leadership and national prominence in healthcare AI; (2) an AI-literacy campaign to promote the use of AI in addressing healthcare disparities; (3) social awareness of the importance of AI in precision medicine; and (4) professional competency in AI through continuing education credits for healthcare professionals (e.g., nurses, physicians, and healthcare administrators).This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.