A Hybrid Rule-and Large Language Model–Based Embodied Voice Assistant (GRACE) for Cognitive Stimulation in Older Adults - Usability Study Assessing Technical Feasibility, Technology Acceptance, and Working Alliance

Q: What is GRACE and what components does it use?

GRACE is an embodied voice assistant designed to deliver cognitive stimulation. It combines rule-based methods with large language model capabilities to support interaction with older adults.

Q: How was the usability study conducted?

A pilot study involved 21 healthy German-speaking adults aged 60 and older. Participants interacted with GRACE in a laboratory setting for 10–15 minutes using structured cognitive stimulation, and data were gathered via pre/post questionnaires and semistructured interviews.

Sep 28, 2026

Uploaded by Valentina

Dementia imposes a substantial health and economic burden, yet no cure exists, making prevention and quality-of-life improvement interventions critical. This pilot study evaluates GRACE, an embodied voice assistant combining rule-based and large language model components, for technical feasibility, usability, user acceptance, and perceived working alliance with healthy older adults. Twenty-one German-speaking participants interacted in a lab for 10–15 minutes; data came from pre/post questionnaires and semistructured interviews. Results indicate positive ratings above neutral and thematic feedback highlighting ease, support, and areas for improvement such as personalization, delays, and voice quality.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

Background

Objective

Methods

Results

Conclusions

Introduction

Background

Voice assistants and digital assistive technologies

JMIR AGING Vinay et al Original Paper A Hybrid Rule-and Large Language Model–Based Embodied Voice Assistant (GRACE) for Cognitive Stimulation in Older Adults: Usability Study Assessing Technical Feasibility, Technology Acceptance, and Working Alliance | Rasita Vinay 1,2, PhD; Ekaterina Uetova3, MA; Nora Camilla Tommila2, MSc; Nikola Biller-Andorno 1, Prof Dr; Tobias Kowatsch2,4,5, Prof Dr | | --- | | 1Institute of Biomedical Ethics and History of Medicine, Faculty of Medicine, University of Zurich, Zurich, Switzerland 2Department of Management, Technology, and Economics, ETH Zurich, Zurich, Switzerland
3School of Computer Science, Technological University Dublin, Dublin, Ireland
4Institute for Implementation Science in Health Care, Faculty of Medicine, University of Zurich, Zurich, Switzerland 5School of Medicine, University of St. Gallen, St Gallen, Switzerland
Corresponding Author:
Rasita Vinay, PhD
Department of Management, Technology, and Economics ETH Zurich
Weinbergstrasse 56/58 Zurich, 8092 Switzerland
Phone: 41 44 632 69 52
Email: [rvinay@ethz.ch](rvinay@ethz.ch)
Abstract | | Background: The health and economic burden of dementia has led the World Health Organization to recognize it as a public health priority. Although there currently does not exist a cure for dementia, there are multiple interventions aimed at preventing the risk of dementia and improving the quality of life of people with dementia. Voice assistants (VAs), particularly those using large language models (LLMs), have emerged as promising tools to deliver these interventions to older adults due to their accessible and natural interface.
Objective: This pilot study aimed to evaluate the technical feasibility (ie, functional performance and usability) and user acceptance of the embodied rule-based and LLM VA GRACE, as well as the perceived strength of the collaborative relationship or working alliance, between GRACE and healthy older adults during the delivery of cognitive stimulation interventions. Methods: A pilot study was conducted with 21 healthy German-speaking adults aged 60 years and older. Participants interacted with GRACE in a laboratory setting for 10-15 minutes. The interaction involved a structured cognitive stimulation session using rule-based and LLM components. Data were collected using pre-and postinteraction questionnaires and semistructured interviews. Quantitative analysis included descriptive statistics and Wilcoxon signed rank tests. Qualitative data were analyzed thematically. Results: Participants rated GRACE positively, with statistically significant scores above neutral (P<.001 for perceived ease of use, usefulness, enjoyment, and working alliance; P=.009 for perceived control; and P=.009 for intention to continue interacting) . Thematic analysis revealed that GRACE was perceived as easy to understand and unambiguous, friendly, and supportive, with intervention components viewed as enjoyable and appropriately challenging. Areas for improvement included personalization, response delays, and voice quality.
Conclusions: The results suggest that embodied rule-based and LLM VAs like GRACE are feasible and well-received tools for delivering cognitive interventions to older adults. Future iterations will incorporate feedback and extend testing to individuals at risk for dementia.
(JMIR Aging 2025;8:e76489) doi: 10.2196/76489 | [https://aging.jmir.org/2025/1/e76489](https://aging.jmir.org/2025/1/e76489) XSL• FO RenderX JMIR Aging 2025 | vol. 8 | e76489 | p. 1 (page number not for citation purposes) JMIR AGING Vinay et al KEYWORDS voice assistant; dementia; older adults; human-computer interaction; embodied conversational agent; cognitive intervention; digital health interventions; large language model Introduction Background Dementia is a collection of symptoms severely affecting memory, thinking, and other cognitive skills in an individual’s daily life [1] . The most common

FAQs

What is GRACE and what components does it use?

GRACE is an embodied voice assistant designed to deliver cognitive stimulation. It combines rule-based methods with large language model capabilities to support interaction with older adults.

How was the usability study conducted?

A pilot study involved 21 healthy German-speaking adults aged 60 and older. Participants interacted with GRACE in a laboratory setting for 10–15 minutes using structured cognitive stimulation, and data were gathered via pre/post questionnaires and semistructured interviews.

What did participants think about GRACE?

Participants rated GRACE positively, with statistically significant scores above neutral for perceived ease of use, usefulness, enjoyment, and working alliance. Thematic findings described GRACE as easy to understand and supportive, while improvement areas included personalization, response delays, and voice quality.

Sep 28, 2026

Uploaded by Valentina