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

点击翻译按钮获取中文摘要

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.