Improving PRO Interpretation at the Individual Level for Patients with Cancer using Conversational Agents and Data Visualization

使用对话代理和数据可视化改善癌症患者个体水平的 PRO 解释

• 批准号: 10807160
• 负责人: TIMOTHY W. BICKMORE
• 金额: $ 73.06万
• 依托单位: TUFTS MEDICAL CENTER
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-03-01 至 2027-02-28
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10807160
• 关键词: Adherence; Adjuvant; Adverse event; Aftercare; Antineoplastic Agents; Anxiety; Aromatase Inhibitors; Behavior; Behavior Therapy; Behavioral Medicine; Breast Cancer therapy; Cellular Phone; Chemotherapy and/or radiation; Clinical; Clinical assessments; Common Terminology Criteria for Adverse Events; Communication; Communication Methods; Computers; Cues; Data; Data Collection; Discipline; Disease; Electronic Health Record; Empathy; Evolution; Fatigue; Foundations; Gestures; Hand; Head and Neck Cancer; Impaired cognition; Individual; Information Systems; Instruction; Interactive Communication; Internet; Malignant Neoplasms; Measurement; Measures; Medicine; Mental Depression; Monitor; Moods; Oral; Pain; Pain interference; Paper; Participant; Patient Agents; Patient Outcomes Assessments; Patients; Performance; Pharmaceutical Preparations; Physical Function; Population Intervention; Process; Psychometrics; Quality of life; Radiation therapy; Randomized; Research; Schedule; Scheme; Surveys; Symptoms; System; Tamoxifen; Testing; Time; Validity and Reliability; Visual; Visualization; Visualization software; Voice; Work; Writing; cancer therapy; chemotherapy; clinical decision-making; clinically relevant; computer science; cost; data visualization; design; field study; gastrointestinal; gaze; health assessment; health literacy; health related quality of life; hormone therapy; improved; individual patient; low health literacy; malignant breast neoplasm; medication compliance; non-verbal; novel; older patient; patient engagement; receptor; satisfaction; screening; substance use; time use; tool; user-friendly

There is increasing recognition of the importance of patient-reported outcomes (PROs) for assessment of health- related quality of life in both research and clinical settings. PROs are especially important for inherently subjective but crucial clinical phenomena such as pain, mood, and fatigue. Despite much research in PROs, concerns about reliability and validity persist, especially when used at the individual level, particularly among patients who may struggle to understand PRO questions, such as those with low health literacy or undetected cognitive impairment. Over the past decade, we have developed and tested a tool with the potential to enhance PROs at the individual level – embodied conversational agents (ECA), which are computer characters that simulate face- to-face conversation using voice, hand gestures, gaze cues and other nonverbal behavior. We have successfully used them in behavioral interventions for populations with limited health literacy, elderly patients, and patients with cancer. Face-to-face encounters, in conjunction with written instructions supported by pictures, remains one of the best methods for communicating information in general, but is particularly effective for individuals with limited health literacy. We have also demonstrated that ECAs can be used as valid alternatives to standard paper-based surveys for substance use screening, and that the display of empathy for patients and other relational behavior by ECAs leads to increased engagement by patients over time. We will adapt our prior work on ECAs to produce ECA-PRO, a framework for administering PROs over time using an ECA on patients’ smartphones in English and Spanish. The ECA-PRO system will include novel user interfaces to optimally communicate the results to patients and clinicians using clear visualizations. To demonstrate the generalizability of ECA-PRO, we will focus on two clinical scenarios: 1) longitudinal monitoring of symptoms and quality of life in patients undergoing cancer treatment, and 2) monitoring of medication adherence in patients taking long-term oral anti-cancer drugs. We hypothesize that the ECA-PRO system, designed for individual-patient-level interactions and data collection, will improve the reliability, validity, and overall clinical relevance of PROs collected during cancer treatment. We will develop and evaluate a PRO system that engages patients with interactive communication and empathy, while delivering standard PROs in a way that minimizes missing data and enables user-friendly visual sharing of results. The ECA-PRO system will create a strong foundation for PRO-based clinical decision-making. If successful, these tools can be rapidly and broadly disseminated.

人们越来越认识到患者报告结果（PRO）对于评估健康状况的重要性。 研究和临床环境中的相关生活质量对于固有的主观性尤其重要。 但尽管对 PRO 进行了大量研究，但关键的临床现象（例如疼痛、情绪和疲劳）仍令人担忧。 关于信度和效度的观点仍然存在，特别是在个人层面上使用时，尤其是在以下患者中： 可能难以理解 PRO 问题，例如健康素养较低或认知能力未被发现的问题 在过去的十年中，我们开发并测试了一种有潜力增强 PRO 的工具。 个人层面——具体会话代理（ECA），它们是模拟面部的计算机角色 我们已经成功地使用声音、手势、目光暗示和其他非语言行为进行面对面对话。 将它们用于健康素养有限的人群、老年患者和患者的行为干预 与癌症面对面的接触，结合图片支持的书面说明，仍然是一种方法。 一般而言，这是传达信息的最佳方法，但对于患有以下疾病的个人特别有效 我们还证明了 ECA 可以作为标准的有效替代方案。 物质使用筛查的纸质调查，以及对患者和其他人表现出的同理心 随着时间的推移，ECA 的关系行为会增加患者的参与度，我们将调整我们之前的工作。 ECA 生成 ECA-PRO，这是一个使用 ECA 对患者进行长期管理 PRO 的框架 ECA-PRO 系统将包括新颖的用户界面，以实现最佳的英语和西班牙语版本。 使用清晰的可视化向患者和爱好者传达结果以证明其普遍性。 ECA-PRO 中，我们将重点关注两个临床场景：1）纵向监测患者的症状和生活质量 接受癌症治疗的患者，以及 2) 监测长期服用药物的患者的药物依从性 我们搜查了针对个体患者水平设计的 ECA-PRO 系统。 相互作用和数据收集，将提高 PRO 的可靠性、有效性和整体临床相关性 我们将开发和评估一个 PRO 系统，让患者参与其中。 交互式沟通和同理心，同时以尽量减少丢失数据的方式提供标准 PRO 并实现用户友好的结果可视化共享。ECA-PRO 系统将为以下方面奠定坚实的基础。 基于 PRO 的临床决策如果成功，这些工具可以快速、广泛地传播。