Usability and Acceptance of the Embodied Conversational Agent Anne by People with Dementia and their Caregivers: an exploratory study in home environment settings (Preprint)

Abstract

Background Information and communication technologies are tools that are able to support cognitive functions, monitor health and movements, provide reminders to maintain residual memory abilities, and promote social support, especially among patients with dementia. Among these technologies, embodied conversational agents (ECAs) are seen as screen-based entities designed to stimulate human face-to-face conversation skills, allowing for natural human-machine interaction. Unfortunately, the evidence that such agents deliver care benefits in supporting people affected by dementia and their caregivers has not yet been well studied. Therefore, research in this area is essential for the entire scientific community. Objective This study aims to evaluate the usability and acceptability of the virtual agent Anne by people living with dementia. The study is also designed to assess the ability of target users to use the system independently and receive valuable information from it. Methods We conducted a 4-week trial that involved 20 older adults living with dementia and 14 family caregivers in home environment settings in Italy. This study used a mixed methods approach, balancing quantitative and qualitative instruments to gather data from users. Telemetry data were also collected. Results Older users were particularly engaged in providing significant responses and participating in system improvements. Some of them clearly discussed how technical problems related to speech recognition had a negative impact on the intention to use, adaptiveness, usefulness, and trust. Moreover, the usability of the system achieved an encouraging score, and half of the sample recognized a role of the agent Anne. This study confirms that the quality of automatic speech recognition and synthesis is still a technical issue and has room for improvement, whereas the touch screen modality is almost stable and positively used by patients with dementia. Conclusions This study demonstrated the ability of target users to use the system independently in their home environment; overall, the involved participants shared good engagement with the system, approaching the virtual agents as a companion able to support memory and enjoyment needs. Therefore, this research provides data that sustain the use of ECAs as future eHealth systems that are able to address the basic and higher-level needs of people living with dementia. This specific field of research is novel and poorly discussed in the scientific community. This could be because of its novelty, yet there is an urgent need to strengthen data, research, and innovation to accelerate the implementation of ECAs as a future method to offer nonpharmacological support to community-dwelling people with dementia.

Toward the Integration of Technology-Based Interventions in the Care Pathway for People with Dementia: A Cross-National Study

“…Design for dementia is a complex area, and this poses several challenges when conducting research [ 45 ]. To our best knowledge, apart from Stara et al [ 19 ], no other study within a similar setting such as the Living Well four-week use of an embodied conversation agent in a home setting among 55 individuals living with dementia and the usage of telemetry data, could be found in the current research literature.…”

“…Indeed, the risk of loneliness and social isolation has been recognized as evident during the COVID-19 pandemic [ 43 ] with separation, loss, confusion, despair, and abandonment; stress and exhaustion exacerbation were detected as the main themes among people with dementia [ 44 , 45 , 46 ]. With regards to the late stage of dementia, for safety reasons, formal/professional caregivers may have to use the embodied conversational agent within a supervised environment (i.e., in nursing homes or daycare centers) because dramatic swings in mood and behavior can be frequent, and it is not predictable how individuals react in front of an unknown virtual assistant [ 19 ]. From a technical point of view, in the future, personalization may be completely individually tailored for each user or even more to their current status at the moment of interaction [ 47 ].…”

“…Although there are opportunities to advance the state of the art on dementia-focused embodied conversational agents in general, it is important that such virtual agents should be evidence based and designed by multidisciplinary teams, following patient-centered care as well as user-centered design (UCD) approaches [ 19 ].…”

“…The ECA was adapted for people living with forgetfulness, as is typical at the beginning of dementia. All the functionalities and features of the system shown in Figure 1 , were developed following a user-driven approach, with the engagement of a multidisciplinary team and the involvement of users in the requirements definition process [ 19 ]. The virtual assistant works on a Surface Pro tablet under the Microsoft Windows 10 operating system and supports Dutch, English, German, Italian, and French.…”

“…Similar to Stara et al [ 19 ], a mixed-method study design was used to gather data from users. Data collected was then used to uncover individuals’ cluster characteristics and designed personas accordingly.…”