SCH: INT: VOLI: Voice Assistant for Quality of Life and Healthcare Improvement in Aging Populations

点击翻译按钮获取中文摘要

According to the latest US Census Bureau predictions, by 2035 older people are projected to outnumber children for the first time in US history. This brings significant societal challenges based on their unique living and health-related conditions stemming from reduced sensory, motor, and cognitive capabilities, as wen as multiple chronic conditions. We propose a personalized and context-aware voice-based digital assistant to improve the quality of life and the healthcare of older adults. VOLI will leverage the growing capabilities of existing technologies, such as mobile devices and smart speakers, and go well beyond the basics of weather reports, news services, and simple games, to provide more complex voice-based services and to focus on the healthcare domain with its many challenges and constraints. We will pursue three parallel research aims: 1) Our technical aim will investigate how digital assistants, natural language processing, and machine learning can produce meaningful health-related conversations by leveraging population- and patient-level data from Electronic Health Records (EHRs); 2) Our social, behavioral, and cognitive aim will focus on designing services for older adults based on their needs to support independence and investigate the acceptability of digital assistants for the aging population; and 3) Our clinical aim will investigate how digital assistants can detect new symptoms and correlate them with medication side effects and interactions, worsening of existing conditions, or onset of new illnesses. Using our VOLI voice-assistant, older adults will be able to get medication reminders and instructions based on prescriptions and clinical notes from EHRs, notify their family/caregiver about their well-being status, interact with their healthcare provider, request an Uber/Lyft car or other third-party services, engage in cognitive games, report symptoms as they occur throughout the day and over the counter medications they are taking, ask questions about symptoms and medications, and so on. VOLi integrates information from EHRs, clinical ontologies, and patient-level terminology. This work will be supported by innovations in natural language understanding, deep learning, and human-computer interfaces. Our work is guided by both clinicians and researchers in human-centered computing. Our team has a history of successful interdisciplinary work in healthcare, expert systems in clinical care, EHR integration, patient monitoring and self-report, ubiquitous computing, data analytics, and field studies.