Conversational Agents to Improve Quality of Life in Palliative Care

点击翻译按钮获取中文摘要

Background: Although many interventions have now been developed to address palliative care for specific chronic diseases, little has been done to address the overall quality of life for older adults with serious illness, spanning not only the functional aspects of symptom and medication management, but the affective aspects of suffering in a scalable and cost effective manner. Over the past decade we have developed and tested embodied conversational agents (ECA) — computer characters that simulate face- to-face conversation using voice, hand gesture, gaze cues and other nonverbal conversational behavior to provide a natural and intuitive computer interface that is capable of expressing empathy and other emotions. We have successfully developed and evaluated this interface in several clinical trials involving older patients of all levels of health and computer literacy. We now propose to adapt this innovative cutting edge technology to create and test a mobile ECA for palliative care (ECA-PAL) for patients with advanced illnesses, spanning: symptom and medication tracking and management; assessment and counseling to reduce social isolation, depression and unmet spiritual needs; and, promotion of and communication about advance care planning. Design: Randomized Controlled Trial Hypotheses: In comparison to participants receiving usual care, ECA-PAL participants will: (1) have greater quality of life; (2) a higher rate of receiving of palliative care services; (3) a lower rate of hospital service utilization; and (4) lower cost per patient-month. Population Studied: Adult patients at Boston Medical Center or affiliated Health Centers with life-limiting illness, who’s clinician endorses that it would not be a surprise if the patient died within 12 months. Methods: The ECA-PAL will be assessed with a randomized controlled trial of patients getting usual care (n=182) or usual care plus ECA-PAL (n=182). Each participant will be enrolled along with a caregiver surrogate subject. Outcome Measures: The primary outcome is quality of life. Secondary outcomes will be measured in the domains of receipt of palliative care services, hospital service utilization, cost, social isolation, depression, anxiety, physical symptoms, spiritual needs, advance care planning. Caregivers will also be interviewed to measure their quality of life. Expected Results: In this project we will evaluate a scalable patient-centered intervention to improve the quality of life for people with advanced illnesses.