Automated Smart Home Assessment to Support Pain Management: Multiple Methods Analysis.

BACKGROUND: Poorly managed pain can lead to substance use disorders, depression, suicide, worsening health, and increased use of health services. Most pain assessments occur in clinical settings away from patients' natural environments. Advances in smart home technology may allow observation of pain in the home setting. Smart homes recognizing human behaviors may be useful for quantifying functional pain interference, thereby creating new ways of assessing pain and supporting people living with pain. OBJECTIVE: This study aimed to determine if a smart home can detect pain-related behaviors to perform automated assessment and support intervention for persons with chronic pain. METHODS: A multiple methods, secondary data analysis was conducted using historic ambient sensor data and weekly nursing assessment data from 11 independent older adults reporting pain across 1-2 years of smart home monitoring. A qualitative approach was used to interpret sensor-based data of 27 unique pain events to support clinician-guided training of a machine learning model. A periodogram was used to calculate circadian rhythm strength, and a random forest containing 100 trees was employed to train a machine learning model to recognize pain-related behaviors. The model extracted 550 behavioral markers for each sensor-based data segment. These were treated as both a binary classification problem (event, control) and a regression problem. RESULTS: We found 13 clinically relevant behaviors, revealing 6 pain-related behavioral qualitative themes. Quantitative results were classified using a clinician-guided random forest technique that yielded a classification accuracy of 0.70, sensitivity of 0.72, specificity of 0.69, area under the receiver operating characteristic curve of 0.756, and area under the precision-recall curve of 0.777 in comparison to using standard anomaly detection techniques without clinician guidance (0.16 accuracy achieved; P<.001). The regression formulation achieved moderate correlation, with r=0.42. CONCLUSIONS: Findings of this secondary data analysis reveal that a pain-assessing smart home may recognize pain-related behaviors. Utilizing clinicians' real-world knowledge when developing pain-assessing machine learning models improves the model's performance. A larger study focusing on pain-related behaviors is warranted to improve and test model performance.

A nurse-driven method for developing artificial intelligence in "smart" homes for aging-in-place.

OBJECTIVES: To offer practical guidance to nurse investigators interested in multidisciplinary research that includes assisting in the development of artificial intelligence (AI) algorithms for "smart" health management and aging-in-place. METHODS: Ten health-assistive Smart Homes were deployed to chronically ill older adults from 2015 to 2018. Data were collected using five sensor types (infrared motion, contact, light, temperature, and humidity). Nurses used telehealth and home visitation to collect health data and provide ground truth annotation for training intelligent algorithms using raw sensor data containing health events. FINDINGS: Nurses assisting with the development of health-assistive AI may encounter unique challenges and opportunities. We recommend: (a) using a practical and consistent method for collecting field data, (b) using nurse-driven measures for data analytics, (c) multidisciplinary communication occur on an engineering-preferred platform. CONCLUSIONS: Practical frameworks to guide nurse investigators integrating clinical data with sensor data for training machine learning algorithms may build capacity for nurses to make significant contributions to developing AI for health-assistive Smart Homes.

Data Collection via In-Depth Email Interviewing: Lessons From the Field.

This methods article is a reflection on the use of in-depth email interviewing in a qualitative descriptive study. The use of emailing to conduct interviews is thought to be an effective way to collect qualitative data. Building on current methodological literature in qualitative research regarding in-depth email interviewing, we move the conversation toward elicitation of quality data and management of multiple concurrent email interviews. Excerpts are shared from a field journal that was kept throughout one study, with commentary on developing insights. Valuable lessons learned include the importance of (a) logistics and timing related to the management of multiple concurrent email interviews, (b) language and eliciting the data, (c) constructing the email, and (d) processing text-based data and preparing transcripts. Qualitative researchers seeking deeply reflective answers and geographically diverse samples may wish to consider using in-depth email interviews.

Interpreting Health Events in Big Data Using Qualitative Traditions.

The training of artificial intelligence requires integrating real-world context and mathematical computations. To achieve efficacious smart health artificial intelligence, contextual clinical knowledge serving as ground truth is required. Qualitative methods are well-suited to lend consistent and valid ground truth. In this methods article, we illustrate the use of qualitative descriptive methods for providing ground truth when training an intelligent agent to detect Restless Leg Syndrome. We show how one interdisciplinary, inter-methodological research team used both sensor-based data and the participant's description of their experience with an episode of Restless Leg Syndrome for training the intelligent agent. We make the case for clinicians with qualitative research expertise to be included at the design table to ensure optimal efficacy of smart health artificial intelligence and a positive end-user experience.

Health-Assistive Smart Homes for Aging in Place: Leading the Way for Integration of the Asian Immigrant Minority Voice.

Caring for America's aging population is a complex humanitarian issue. The number of older adults is expected to increase to 98.5 million by 2060 with a 295% growth in foreign-born older adults, including Asian immigrants. Most older adults will have one or more chronic conditions and 95% of healthcare costs will be attributed to caring for these conditions. Among Asian Americans, common chronic conditions include respiratory disease, cancer, cardiovascular disease, and pain. The National Institutes of Health, Institute on Aging, and National Science Foundation call for innovative technologies to be developed by multidisciplinary teams to address these concerns. Asian community leaders at Asian Health & Service Center and community members in Oregon identified the use of health-assistive technologies as a priority for potentially reducing stress and improving quality of life for both older adults and their caregivers. The purpose of this article is to introduce nurses and healthcare workers, advocating for the interests of Asian/Pacific Island community members, to the innovative health-assistive smart home. The health-assistive smart home uses artificial intelligence to identify and predict health events. Inclusion of minority persons' data in the development of artificial intelligence has been generally overlooked. This may result in continued health inequities and is incompatible with the goals of global health. Integration of minority voices while exploring the efficacious use of the health-assistive smart home is of significant value to minority populations. Asian immigrant older adults engaging in smart home research and development will enhance the cultural and technical safety of future devices. Asian families may be particularly interested in smart homes for extending independence because they place an emphasis on collective culture and family-based care. Community engagement of stakeholders and steadfast leadership are needed so that future technologies used in healthcare delivery are both technically and culturally sound. A community-engaged research approach promotes community empowerment that is responsive to community identified priorities and is a good fit for studying adoption of smart home monitoring for health-assistance.

Interactive CO-learning for Research Engagement and Education (I-COREE) Curriculum to Build Capacity Between Community Partners and Academic Researchers.

The voice of diverse communities continues to be minimal in academic research. Few models exist for education and training of new research topics and terminology and building partnership capacity in community-engaged research. Little is known about integrative education and training when building participatory research partnerships for sustainability and developing trust and rapport. Community partners at an Asian community-based health and social services center in a large metropolitan area wanted to explore the cultural context of a health-assistive smart home that monitors and auto-alerts with changes in health. With historical and recent rising trends in culturally insensitive research in several diverse communities, the concept of technology-enabled monitoring in the privacy of one's home brings uncertainty. Academic nurse researchers and community partners co-created a culturally safe integrative education and training curriculum, the Interactive CO-learning for Research Engagement and Education (I-COREE). The purpose was to design, implement, and evaluate the curriculum to respond to the community partners' needs to create a culturally safe space through an integrative education and training to facilitate building partnership capacity for research engagement including developing trust and rapport and addressing uncertainties in health-assistive technologies. Popular education tenets informed the curriculum. Twelve academic and community partners participated, four were team teachers who co-led the session. Implementation of the experiential, multimodal co-learning activities were conducted within ahalf-day. The curriculum evaluation indicated that it helped bridge critical conversations about partners' fears of the unknown, approach culturally sensitive topics safely, and trust and rapport. Key elements may be translatable to other partnerships.