FW-HTF-P: Teaming Transplant Professionals and Artificial Intelligence Tools to Reduce Kidney Discard

由于工作流程效率低下以及对使用低质量或高风险器官的负面看法，每年有数千个获得的肾脏被丢弃。虽然其中一些在医学上是必要的，但有些则意味着失去了让患者摆脱透析和延长寿命的机会。这项人类技术前沿计划资助项目的未来工作旨在改变器官移植匹配过程。未来的技术是一种人工智能（AI）系统，具有可用的可靠接口，可以完全集成到需求方（移植中心）和供应方（器官采购组织）之间的移植医疗工作环境中。未来的工作者是器官采购协调员和移植协调员、内科医生和外科医生。在一个移植中心接受它之前，一个肾脏可能会有数千个捐献者。目前手工放置低质量器官的过程加剧了失去的机会。人工智能系统将识别出最有可能接受较低质量器官的移植团队和候选人，以便快速识别匹配，减少器官被丢弃的可能性。这项规划拨款将建立将人工智能纳入移植医疗保健的能力，并让工作人员以及移植前和移植后患者参与设计马拉松活动。这项研究是由圣路易斯大学医院的移植专家和密苏里科技大学的人工智能和人为因素专家共同推动的。一旦得到验证，这项研究也可以应用于其他数据密集型高风险场景（例如军事行动、关键基础设施）。人工智能系统经常受到技术、人力和集成方面的挑战。在计划拨款的过程中，我们将(1)记录移植工作系统架构并确定重新设计该工作流程的挑战，(2)开发概念验证人工智能系统，以预测哪些候选人最有可能接受有丢弃风险的低质量肾脏，以及(3)进行人体受试者实验，以确定界面设计的范围并预测技术采用因素。人工设计神经结构耗时且成本高，因此本项目提出了一种使用进化算法为特定数据集找到最佳结构的方法。随着时间的推移，这将促进数据输入的实时适应。此外，人工智能系统的可解释性和透明度至关重要，特别是在高风险环境中。该项目将对非专业人群进行人体实验，以评估不确定性可视化和度量如何影响性能、信心、信任、技术接受度以及选择风险更高的选项的意愿。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。

Thousands of procured kidneys are discarded each year due to inefficient workflow processes and negative perceptions for using lower quality or higher risk organs. While some of this discard is medically necessary, some represents lost opportunities to get patients off of dialysis and increase lifespans. This Future of Work at the Human Technology Frontier planning grant project aims to transform the organ transplant matching process. The future technology is an artificial intelligence (AI) system with usable trustworthy interfaces that are fully integrated into the transplant healthcare work context between the demand-side (transplant center) and supply-side (organ procurement organization). The future workers are organ procurement coordinators and transplant coordinators, physicians and surgeons. A single kidney can have thousands of offers before one, if any, transplant center accepts it. The current process of manually placing lower quality organs exacerbates lost opportunities. The AI system will identify transplant teams and candidates that are most likely to accept a lower quality organ so that the match can be identified quickly and the organ is less likely to be discarded. This planning grant will build capacity for integrating AI into transplant healthcare and engage workers as well as pre- and post-transplant patients in a design-a-thon event. This research is driven by transplant experts at Saint Louis University Hospital and experts in AI and human factors from Missouri University of Science & Technology. Once validated, this research can also be applied to other data-intensive high-stakes scenarios (e.g. military operations, critical infrastructure).AI systems often suffer from technical, human, and integration challenges. Over the course of the planning grant, we will (1) document a transplant work system architecture and identify challenges for re-designing this work process, (2) develop a proof-of-concept AI system to predict which candidates are most likely to accept a lower quality kidney that is at risk of discard, and (3) perform human subjects experiments to scope the interface design and predict technology adoption factors. It is time-consuming and costly to manually design neural architectures, so this project proposes an approach that uses evolutionary algorithms to find the optimal architecture for a particular data set. This will facilitate real-time adaptation as the data inputs evolve over time. In addition, it is critical for AI systems to be explainable and transparent, particularly in high stakes contexts. The project will perform human subject experiments with lay populations to evaluate how uncertainty visualizations and metrics influence performance, confidence, trust, technology acceptance, and willingness to choose riskier options.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.