CRII: SCH: Visualization for Better Medical Decision-Making

该项目开发可视化方法，用于向患者传达复杂的健康风险数据。该项目确定了视觉辅助工具的使用如何影响决策，以及视觉辅助工具是否会导致、加强或减轻偏见。此外，该项目还确定了人们在做出医疗决定时使用的策略。这项工作的结果将产生广泛和不同的影响。从这个项目中获得的知识将使人们更好地理解人们如何用卫生统计进行推理和决策，以及我们如何改进或创建新的设计，以便在医疗领域之外交流这种复杂的数据。该项目的输出将是一个经过测试的可视化设计数据库，以支持知情的医疗决策。尽管医学统计数据是基于证据的决策的基本组成部分，但众所周知，它不直观，而且很难让人们理解。因此，为医疗决策提供患者支持已成为医学界面临的重大挑战。本研究通过呼吁关注医疗风险沟通和可视化理论之间的协同作用来解决这一问题。该项目将为视觉表现如何影响决策创建一个理论框架。结果将展示不同的设计如何创造、加强或减轻与风险感知相关的偏见，并将确定可能介导认知偏见的个体特征。此外，该项目将开发计算方法，用于人们如何在整个决策过程中使用可视化，并将确定人们倾向于使用或忽略哪些视觉元素。本研究将以医疗风险沟通为实验平台，探讨可视化社区的核心课题，同时为医学界做出贡献。该项目的核心产品将是基于web的多维健康风险可视化推荐系统。所有出版物、数据和源代码都将是公开的。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。

This project develops visualization methods for communicating complex health risk data to patients. The project determines how the use of visual aids can impact decision-making and whether visual aids can cause, reinforce or mitigate biases. Additionally, the project identifies strategies people use when making medical decisions. Results of this work will have broad and varying impacts. The knowledge gained from this project will provide a better understanding of how people reason and make decisions with health statistics, and how we can improve or create novel designs for communicating such complex data beyond the medical field. The output of the project will be a database of tested visualization designs for supporting informed medical decision-making. Despite being fundamental components of evidence-based decision-making, medical statistics are notoriously unintuitive and arduous for people to understand. As a result, providing patient support for health decision-making has become a significant challenge for the medical community. This research addresses this problem by calling attention to synergies between medical risk communication and visualization theory. The project will create a theoretical framework for how visual representations impact decisions. The results will demonstrate how different designs can create, reinforce, or mitigate biases related to risk perception, and will identify individual characteristics that may mediate cognitive biases. Furthermore, the project will develop computational approaches for how people use visualization throughout the decision-making process and will determine which visual elements people tend to use or ignore. Using medical risk communication as a test bed, this research will investigate core topics in the Visualization community and simultaneously make contributions to the medical community. A core product of this project will be a web-based multi-dimensional recommendation system for health risk visualization. All publications, data, and source code will be publicly available.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.