Collaborative Research: FW-HTF-R: Embedding Preferences in Adaptable Artificial Intelligence Decision Support for Transplant Healthcare to Reduce Kidney Discard

合作研究：FW-HTF-R：在移植医疗保健的适应性人工智能决策支持中嵌入偏好，以减少肾脏废弃

• 批准号: 2222801
• 负责人: Casey Canfield
• 金额: $ 180万
• 依托单位: Missouri University of Science and Technology
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-10-01 至 2026-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2222801&HistoricalAwards=false
• 关键词: Collaborative; Research; FW; HTF; Embedding

Transplantation provides patients suffering from end-stage kidney disease a better quality of life and long-term survival compared to chronic dialysis. However, approximately 20% of deceased donor kidneys are discarded and never transplanted. While some discards may be medically appropriate, others reflect missed opportunities. Even kidneys deemed less desirable may provide survival benefits to some patients. Organ Procurement Organizations (OPOs) have great difficulty finding transplant centers to accept less medically desirable (higher risk) kidneys. At their discretion, OPOs can use accelerated placement to bypass the priority list for “hard-to-place” kidneys. However, due to a lack of data-driven guidance, this mechanism is not systematically applied and likely underutilized. To enable transformative change, we will integrate Artificial Intelligence (AI) decision support into the kidney offer process for both demand at the transplant center and supply at the OPO. Key workers include OPO staff (organ procurement coordinators, operations directors, medical directors), transplant center staff (coordinators, physicians, surgeons), and transplant patients. This research is driven by a partnership between transplant and ethics experts at Saint Louis University Hospital, behavioral scientists at the United Network for Organ Sharing (UNOS), and experts in AI and human factors from Missouri University of Science & Technology.Building on a FW-HTF planning grant, this project is developing an AI decision support system for (a) transplant centers to accept/deny high-risk kidney offers and (b) OPOs to identify hard-to-place kidneys sooner. This research will (1) measure worker preferences to customize the support system’s operation and interface, (2) aggregate fairness preferences as defined by diverse stakeholders to improve fairness in the model output, (3) evaluate the effect of embedding uncertainty and explainability into the interface, (4) develop deep learning ensemble models that can adapt over time while being explainable, and (5) conduct randomized control trials using UNOS Lab’s SimUNet, a realistic kidney offer simulation platform for behavioral experiments, to estimate the impact on kidney discard. Within the deep learning model, this project will impose trade-offs to increase fairness without significantly reducing accuracy, enhance explainability by converting feature relevance into linguistic expressions, and integrate new data (such as customizing for worker preferences) through transfer learning as conditions change in kidney transplant practices. Ultimately, this research aims to reduce kidney discard for “hard-to-place” organs by at least 10%. In addition, this work will support critical advancements in ethics and training, issues that will be critical in overcoming system-level barriers to integrate AI into healthcare.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.

与慢性透析相比，移植为终末期肾病患者提供了更好的生活质量和长期生存。然而，大约20%的已故供体肾脏被丢弃，永远不会被移植。虽然一些丢弃可能在医学上是合适的，但另一些则反映了错失的机会。即使是被认为不太可取的肾脏，也可能为一些患者提供生存益处。器官采购组织(OPO)很难找到移植中心接受医学上不太可取(风险更高)的肾脏。OPO可以根据自己的决定，使用加速放置来绕过“难以放置”肾脏的优先列表。然而，由于缺乏数据驱动的指导，这一机制没有得到系统的应用，很可能没有得到充分利用。为了实现变革性的变化，我们将把人工智能(AI)决策支持集成到肾脏提供流程中，以满足移植中心的需求和OPO的供应。主要工作人员包括OPO工作人员(器官采购协调员、手术主任、医疗主任)、移植中心工作人员(协调员、医生、外科医生)和移植患者。这项研究是由圣路易斯大学医院的移植和伦理专家、联合器官共享网络(UNOS)的行为科学家以及密苏里科技大学的人工智能和人类因素专家共同推动的。该项目在FW-HTF计划拨款的基础上，正在开发一个人工智能决策支持系统，用于(A)移植中心接受/拒绝高风险的肾脏捐赠，以及(B)OPO，以更快地识别难以放置的肾脏。这项研究将(1)测量员工偏好以定制支持系统的操作和界面，(2)聚合不同利益相关者定义的公平偏好以提高模型输出的公平性，(3)评估在界面中嵌入不确定性和可解释性的效果，(4)开发可随时间适应且可解释的深度学习集成模型，以及(5)使用UNOS Lab的SimUNet(一个现实的肾脏提供行为实验模拟平台)进行随机对照试验，以估计对肾脏丢弃的影响。在深度学习模型中，该项目将在不显著降低准确性的情况下进行权衡，以提高公平性，通过将特征相关性转换为语言表达来增强可解释性，并随着肾脏移植实践中的条件变化通过迁移学习整合新数据(如为工人的偏好定制)。最终，这项研究的目标是将因“难以放置”的器官而丢弃的肾脏减少至少10%。此外，这项工作将支持道德和培训方面的关键进步，这些问题将是克服系统级障碍将人工智能融入医疗保健的关键问题。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Complex System Methodology for Meta Architecture Optimization of the Kidney Transplant System of Systems

肾移植系统元架构优化的复杂系统方法

• 发表时间: 2022
• 期刊: IEEE International Conference on System of Systems Engineering
• 作者: Threlkeld, R.;Ashiku, L.;Dagli, C.
• 通讯作者: Dagli, C.

A Use Case for Developing Meta Architectures with Artificial Intelligence and Agent Based Simulation in the Kidney Transplant Complex System of Systems

在肾移植复杂系统中使用人工智能和基于代理的模拟开发元架构的用例

• 发表时间: 2023
• 期刊: IEEE International Conference on System of Systems Engineering
• 作者: Threlkeld, R.;Ashiku, L.;Dagli, C.
• 通讯作者: Dagli, C.

Identify Hard-to-Place Kidneys for Early Engagement in Accelerated Placement With a Deep Learning Optimization Approach

通过深度学习优化方法识别难以放置的肾脏，以便尽早参与加速放置

• DOI: 10.1016/j.transproceed.2022.12.005
• 发表时间: 2023
• 期刊: Transplantation Proceedings
• 影响因子: 0.9
• 作者: Ashiku, Lirim;Dagli, Cihan
• 通讯作者: Dagli, Cihan

AI-Enabled Digital Support to Increase Placement of Hard-to-Place Deceased Donor Kidneys

支持人工智能的数字支持可增加难以放置的已故捐献肾脏的放置

• 发表时间: 2023
• 期刊: American journal of transplantation
• 影响因子: 8.8
• 作者: Threlkeld, R.;Ashiku, L.;Dagli, C.;Dzieran, R.;Canfield, C.;Lentine, K.;Schnitzler, M.;Marklin, G.;Rothweiler, R.;Speir, L.
• 通讯作者: Speir, L.