Prototype Development of a Responsive Emotive Sensing System (DRESS) to aid older persons with dementia to dress independently.

Background: Prior research has critiqued the lack of attention to the stressors associated with dementia related dressing issues, stigmatizing patient clothing, and wearable technology challenges. This paper describes the conceptual development and feasibility testing of an innovative 'smart dresser' context aware affective system (DRESS) to enable dressing by people with moderate memory loss through individualized audio and visual task prompting in real time.
Methods: Mixed method feasibility study involving qualitative focus groups with 25 Alzheimer's family caregivers experiencing dressing difficulties to iteratively inform system design and a quantitative usability trial with 10 healthy subjects in a controlled laboratory setting to assess validity of technical operations.
Results: Caregivers voiced the need for tangible dressing assistance to reduce their frustration from time spent in repetitive cueing and power struggles over dressing. They contributed 6 changes that influenced the prototype development, most notably adding a dresser top iPad to mimic a familiar 'TV screen' for the audio and visual cueing. DRESS demonstrated promising overall functionality, however the validity of identification of dressing status ranged from 0% for the correct pants dressing to 100% for all shirts dressing scenarios. Adjustments were made to the detection components of the system raising the accuracy of detection of all acted dressing scenarios for pants from 50% to 82%.
Conclusions: Findings demonstrate family caregiver acceptability of the proposed system, the successful interoperability of the built system's components, and the system's ability to interpret correct and incorrect dressing actions in controlled laboratory simulations. Future research will advance the system to the alpha stage and subsequent testing with end users in real world settings.