You are here

  1. Home
  2. A Personalized Voice-Based Diet Assistant for Caregivers of Alzheimer Disease and Related Dementias: System Development and Validation

A Personalized Voice-Based Diet Assistant for Caregivers of Alzheimer Disease and Related Dementias: System Development and Validation

Background: The world's aging population is increasing, with an expected increase in the prevalence of Alzheimer disease and related dementias (ADRD). Proper nutrition and good eating behavior show promise for preventing and slowing the progression of ADRD and consequently improving patients with ADRD's health status and quality of life. Most ADRD care is provided by informal caregivers, so assisting caregivers to manage patients with ADRD's diet is important. Objective: This study aims to design, develop, and test an artificial intelligence-powered voice assistant to help informal caregivers manage the daily diet of patients with ADRD and learn food and nutrition-related knowledge. Methods: The voice assistant is being implemented in several steps: construction of a comprehensive knowledge base with ontologies that define ADRD diet care and user profiles, and is extended with external knowledge graphs; management of conversation between users and the voice assistant; personalized ADRD diet services provided through a semantics-based knowledge graph search and reasoning engine; and system evaluation in use cases with additional qualitative evaluations. Results: A prototype voice assistant was evaluated in the lab using various use cases. Preliminary qualitative test results demonstrate reasonable rates of dialogue success and recommendation correctness. Conclusions: The voice assistant provides a natural, interactive interface for users, and it does not require the user to have a technical background, which may facilitate senior caregivers' use in their daily care tasks. This study suggests the feasibility of using the intelligent voice assistant to help caregivers manage patients with ADRD's diet.

Access source material through DOI

Key Information

Type of Reference
Jour
Type of Work
Journal article
Publisher
JMIR Publications
ISBN/ISSN
1438-8871
Publication Year
2020
Issue Number
9
Journal Titles
Journal of Medical Internet Research
Volume Number
22
Start Page
e19897