Usability of an Intelligent Virtual Assistant for Promoting Behavior Change and Self-Care in Older People with Type 2 Diabetes.

In the context of the VASelfCare project, we developed an application prototype of an intelligent anthropomorphic virtual assistant. Designed as a relational agent, the virtual assistant has the role of supporting older people with Type 2 Diabetes Mellitus (T2D) in medication adherence and lifestyle...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Medical Systems Vol. 44; no. 7; pp. 1 - 13
Autores principales: Balsa, João, Félix, Isa, Cláudio, Ana Paula, Carmo, Maria Beatriz, Silva, Isabel Costa e, Guerreiro, Ana, Guedes, Maria, Henriques, Adriana, Guerreiro, Mara Pereira
Formato: algorithm clinical trial pictorial research tables/charts Journal Article
Publicado: Springer Nature Jul2020
Acceso en línea:Ver este registro en EBSCOhost
Descripción
Sumario:In the context of the VASelfCare project, we developed an application prototype of an intelligent anthropomorphic virtual assistant. Designed as a relational agent, the virtual assistant has the role of supporting older people with Type 2 Diabetes Mellitus (T2D) in medication adherence and lifestyle changes. Our paper has two goals: describing the essentials of this prototype, and reporting on usability evaluation. We describe the general architecture of the prototype, including the graphical component, and focus on its main feature: the incorporation, in the way the dialogue flows, of Behavior Change Techniques, identified through a theoretical framework, the Behaviour Change Wheel. Usability was experimentally evaluated in field tests in a purposive sample of 20 participants (11 older adults with T2D and 9 experts). The Portuguese version of the System Usability Scale was employed, supplemented with qualitative data from open questions, diaries, digital notes and telephone follow-ups. The aggregated mean SUS score was 73,75 (SD 13,31), which corresponds to a borderline rating of excellent. Textual data were content analyzed and will be prioritized to further improve usability.