Acceptability of In-Home Ambient Sensors for Activity Recognition and Assessment Post-Stroke

Abstract

<h3>Research Objectives</h3> To explore the acceptability of an in-home ambient sensor for activity recognition and assessment post-stroke. <h3>Design</h3> Single arm pilot study. The DNS-6 depth sensor (Foresite Healthcare) was installed in the kitchen of enrolled participants for 3 months. Data collected from the depth sensor was used to develop, train, and test an algorithm for activity recognition and assessment. <h3>Setting</h3> Community homes. <h3>Participants</h3> Twenty individuals with chronic stroke were recruited via a stroke registry at the University of Missouri. Individuals were eligible if they had experienced a stroke at least 6 months prior, were able to ambulate with or without an assistive device, and reported some difficulty using their arm in everyday activities. <h3>Interventions</h3> Not applicable. <h3>Main Outcome Measures</h3> Semi-structured interviews were conducted with each study participant at the end of the 3-month period. Questions were focused on the study participant's attitudes and reactions to having the depth sensor in their home. <h3>Results</h3> Most study participants "forgot" that the sensor was installed in their home and went about their daily activities like normal. None of the study participants expressed concerns about the overall aesthetic of the depth sensor in their home. Some study participants expressed concerns about data privacy; however, none felt that their privacy or confidentiality was broken during their time in the study. All study participants agreed that the benefits of the depth sensor and data provided for clinicians outweighed any risks or privacy concerns. Some study participants wanted to see greater integration with other technologies such as video games and wearable devices to track activity in the home and community. <h3>Conclusions</h3> Despite the privacy concerns, all participants were able to understand the anticipated benefits and clinical implications of this sensor. This is consistent with past literature as most participants in Demiris et. al saw value and purpose of monitoring (2009). Future research will integrate the depth sensor and developed algorithm into a larger home-based sensor system for individuals post-stroke and other conditions. <h3>Author(s) Disclosures</h3> None