STTR Phase I: Artificial Intelligence Tool to Optimize Organ Transplantation Outcomes (Transplant-AI)

STTR 第一阶段：优化器官移植结果的人工智能工具（Transplant-AI）

• 批准号: 2014827
• 负责人: Jim Havelka
• 金额: $ 22.5万
• 依托单位: InformAI, Inc.
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-08-15 至 2021-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2014827&HistoricalAwards=false
• 关键词: STTR; Phase; Artificial; Intelligence; Tool

The broader impact of this Small Business Technology Transfer (STTR) Phase I project will be to improve solid organ transplantation outcomes. Few significant clinical or technological advancements have been made within the last two decades to improve organ matching success, and the accuracies of current models predicting survival outcomes are diminishing. There is a great need for clinicians to have better decision-making support tools. Every 12 minutes, a new person is added to the organ transplant waiting list, a number growing by about five percent each year. Within a single day, 21 people die waiting for a kidney, liver, or other organ match. Although 36,500 kidney and liver transplants are performed each year, the patient demand for donor organs far outweighs supply by four to one, so the need to improve donor-recipient matching is urgent. Optimizing the donor organ-patient match is a key determining factor for improving transplant success and patient survival. This project's artificial intelligence (AI) model will guide transplant surgeons, physicians, and other healthcare professionals will deliver precise, accurate, quantitative information for real-time predictions.This Small Business Technology Transfer (STTR) Phase I project proposes artificial intelligence to predict outcomes after solid organ transplantation procedures. Clinicians currently consider several factors when determining organ allocation and candidate patient ranking on the recipient waitlist, including extent of disease pathology, functional status of the recipient, and intrinsic donor and recipient compatibility factors. Measures, indices and functional status scores have been designed to predict specific outcomes but are not easily combined into one optimized decision to guide organ allocation decisions. To date, no organ-matching predictive outcome model has comprehensively synthesized all available patient- and donor-specific variables at the time of transplantation. This project will train an artificial intelligence (AI) algorithm to comprehensively integrate all information available at the time of transplantation procedures (hundreds of variables) into a predictive model. An AI model of this nature would be a substantial improvement from linear models able to synthesize only a modest number of parameters (approximately 15) to date. It is expected that the proposed technology will predict both pre- and post-transplant survival more accurately than currently accepted models.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.

该小企业技术转让 (STTR) 第一阶段项目的更广泛影响将是改善实体器官移植的结果。在过去的二十年里，在提高器官匹配成功率方面几乎没有取得重大的临床或技术进步，并且当前模型预测生存结果的准确性正在下降。临床医生非常需要拥有更好的决策支持工具。每 12 分钟就有一个新人被添加到器官移植等候名单中，这个数字每年增长约 5%。一天之内，就有 21 个人在等待肾脏、肝脏或其他器官匹配的过程中死去。尽管每年进行36,500例肾移植和肝移植，但患者对供体器官的需求远远超过供应，因此迫切需要改善供体与受体的匹配。优化供体器官与患者的匹配是提高移植成功率和患者生存率的关键决定因素。该项目的人工智能（AI）模型将指导移植外科医生、内科医生和其他医疗保健专业人员提供精确、准确、定量的信息以进行实时预测。该小型企业技术转让（STTR）第一阶段项目提出人工智能来预测结果实体器官移植手术后。目前，临床医生在确定器官分配和候选患者在接受者候补名单上的排名时会考虑几个因素，包括疾病病理的程度、接受者的功能状态以及内在的供者和接受者相容性因素。措施、指数和功能状态评分旨在预测特定结果，但不容易合并为一项优化决策来指导器官分配决策。迄今为止，还没有器官匹配预测结果模型全面综合了移植时所有可用的患者和供体特异性变量。该项目将训练人工智能（AI）算法，将移植过程中可用的所有信息（数百个变量）全面整合到预测模型中。这种性质的人工智能模型将是对迄今为止只能合成少量参数（大约 15 个）的线性模型的重大改进。预计所提出的技术将比目前接受的模型更准确地预测移植前和移植后的存活率。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力优点和更广泛的影响审查标准进行评估，被认为值得支持。