Collaborative Patient Portals: Computer-based Agents and Patients??? Understandin

描述(由申请人提供)：我们的目标是提高不同计算能力和识字能力的老年人对通过电子健康记录(EHR)系统门户网站提供的信息的理解和使用。门户网站旨在支持以患者为中心的护理，但老年人没有充分利用门户网站，因为它们更多地是作为信息库，而不是患者教育的协作工具。自我管理健康通常取决于对数字信息的理解，这对数字能力较低的患者构成了挑战。老年人是健康信息最频繁的消费者，他们的算术能力也较低。根据健康传播理论，患者必须根据他们的目标和知识来解释数字信息，以便创建围绕评估/情感类别组织的要点表示法，以捕捉他们的健康底线。临床医生传统上是通过使用语言和非语言策略来帮助患者创建主旨陈述的关键，这些策略将信息联系起来。随着患者接触时间的减少，临床医生 挑战提供这种支持。HIT有可能通过提供对信息的访问来支持患者的理解，而不是短暂的临床会面的限制。然而，门户网站可能并不有效，因为它们消除了支持主旨理解的临床背景。我们将通过在门户环境中模拟面对面交流的最佳实践来帮助老年人使用数字信息。我们利用为人机系统开发基于计算机的代理(CA)方面的进展。我们的团队开发了一种带有非语言线索(如语音语调、面部表情)的认知语篇，以传达情感和认知意义。我们将改进CA，使其成为一个专业的临床中介，对测试结果提供简洁的评论，并通过非语言提示来帮助患者创建支持理解和产生信任的主旨陈述。我们致力于实现以下目标。1.确定门户消息以提高对临床测试结果的理解。我们将标准文本/数字消息与日益增强的格式进行比较。1)口头：提供标准信息，并用标签注解，以指示风险程度。2)图形：信息以图形、数字和口头的形式呈现。3)CA：相同的信息由CA说出，带有非语言提示，指示信息关联和引导情感解释。逐字和要点的理解，对更多信息的需求，以及对风险信息的态度进行了衡量。增强的消息应该更好地理解(特别是在要点级别)，并满足患者的信息需求。他们(尤其是CA)可能会通过减少对计算的需求和鼓励情感反应而特别受益于计算能力较低的参与者。2.确定使测试结果更具可操作性的信息。与检测结果一致的自我护理建议(例如，关于饮食)将被添加到消息中。在CA条件下，这些建议和测试结果都是通过强调关键信息和支持情感解释的非语言线索来提供的。将增加执行自我护理的意向措施。CA应该通过促进富有感情的有组织的主旨陈述来促进行动，从而增加这些意图。虽然门户网站有朝一日可能会通过增加对信息的访问来革命性地以患者为中心的护理，但许多老年人并不使用它们。我们将通过使信息更容易理解和可操作来帮助使门户网站更容易获得认知。

DESCRIPTION (provided by applicant): Our goal is to improve understanding and use of information provided through portals to Electronic Health Record (EHR) systems by older adults with diverse numeracy and literacy abilities. Portals are intended to support patient-centered care, but are underutilized by older adults because they serve more as information repositories than as collaborative tools for patient education. Self-managing health often hinges on comprehension of numeric information, which challenges lower numeracy patients. Older adults, the most frequent consumers of health information, also have lower numeracy. According to health communication theories, patients must interpret numeric information in terms of their goals and knowledge in order to create gist representations organized around evaluative/affective categories that capture the 'bottom-line' for their health. Clinicians are traditionally a key to helping patients create gist representations by using verbal and nonverbal strategies that contextualize the information. With decreasing patient contact time, clinicians are challenged to provide this support. HIT has the potential to support patient comprehension by providing access to information outside the constraints of brief clinical encounters. However, portals may not be effective because they eliminate the clinical context that supports gist comprehension. We will help older adults use numeric information by emulating in portal environments best practices from face-to-face communication. We leverage progress in developing computer-based agents (CA) for human- computer systems. Our team has developed a CA with nonverbal cues (e.g. voice intonation, facial expressions) to convey affective as well as cognitive meaning. We will refine the CA to serve as an expert clinical intermediary that provides succinct commentary on test results reinforced by nonverbal cues to help patients create gist representations that support understanding and engender trust. We address the following aims. 1. Identify portal messages that improve comprehension of clinical test results. We compare standard text/numeric messages to increasingly enhanced formats. 1) Verbal: Standard information is presented and annotated with labels to indicate degree of risk. 2) Graphic: The information is presented graphically as well as numerically and verbally. 3) CA: The same information is spoken by the CA, with nonverbal cues signaling information relevance and guiding affective interpretation. Verbatim and gist comprehension, need for more information, and attitude toward risk information is measured. Enhanced messages should be better understood (especially at the gist level) and meet patient information needs. They (particularly the CA) may especially benefit less numerate participants by reducing need for numeracy and encouraging affective response. 2. Identify messages that make test results more actionable. Self-care recommendations (e.g., about diet) consistent with the test results will be added to the messages. In the CA condition, these recommendations as well as the test results are delivered with nonverbal cues emphasizing key information and supporting affective interpretation. Measures of intention to perform self-care will be added. The CA should increase these intentions by promoting affectively organized gist representations that motivate action. While portals may one day revolutionize patient-centered care by increasing access to information, many older do not use them. We will help make portals more cognitively accessible by making information more easily understood and actionable.