Voice Assistive Technology for Activities of Daily Living: Developing an Alexa Telehealth Training for Adults with Cognitive-Communication Disorders

Intelligent Voice Assistants (Alexa, Siri, etc.)Special Education TechnologySpeech-Language Pathologists & AudiologistsFamily CaregiversDisability Service Providers

Title of the Literature

Voice Assistive Technology for Activities of Daily Living: Developing an Alexa Telehealth Training for Adults with Cognitive-Communication Disorders

Literature Information

  • Subject Area: Application and training models of voice assistive technology in activities of daily living for adults with cognitive-communication disorders
  • Keywords: Cognitive-communication disorders, voice assistive technology, activities of daily living, telehealth, Amazon Alexa

Research Background and Issues

  • Identified Problems or Challenges:

    • Cognitive-communication disorders (CCD) significantly impact memory, attention, language, planning, and organizational abilities, greatly reducing the ability of affected individuals to independently complete activities of daily living (ADLs).
    • Existing voice assistive technology (VAT) has limited functionality and is not specifically optimized or tailored for CCD patients.
    • Research on the use and effectiveness of VAT in home environments remains scarce, particularly in testing its practical application in natural settings.
  • Significance:

    • CCD affects the quality of life of millions globally, especially among older adults, where the ability to complete ADLs directly correlates with independence and self-esteem.
    • The use of VAT represents a frontier in technological intervention, assisting CCD patients in enhancing independence and alleviating caregiver burden.
  • Research Motivation and Related Work:

    • Previous studies have shown that VAT can improve the execution of ADL tasks, facilitate social interaction, and boost behavioral confidence.
    • However, challenges remain, such as insufficient voice recognition, complex command operations, and difficulties in device setup.
    • This study, based on an understanding of the characteristics of CCD patients, designed and implemented a specialized remote VAT training program to optimize their ability to independently complete ADLs.

Solution

  • Proposed Solution:

    • Designed and implemented a specialized telehealth training program using Amazon Alexa as a voice assistive technology tool to train adults with CCD in optimizing their abilities in various ADL domains.
    • The program covered five key topics: scheduling and reminders, entertainment, personal care and medical needs, news and information exchange, and meal preparation.
  • Innovations:

    • This is the first study to use Alexa commands to support CCD patients in completing complex ADL tasks.
    • The training program integrates clinical language and cognitive assessment standards, providing personalized content to simulate home usage environments.
    • It incorporates multimodal learning methods, using visual and verbal prompts to support patients in learning to interact with the device.
  • Implementation Steps and Techniques:

    • Participant Selection: Recruited adult patients with CCD of varying ages and disorder types.
    • Training Method: Conducted weekly online sessions via Zoom, utilizing Amazon Echo Show devices for task training and command operation practice.
    • Data Collection and Analysis: Used standard assessment tools (e.g., CLQT+, WAB) for pre- and post-training evaluations, collected data on task success rates, types of prompts needed, and technical limitations; extracted feedback through thematic analysis of interviews.
    • Personalized Strategies: Adjusted training content and prompt modes based on participant needs, such as reducing visual prompts and providing more verbal guidance for patients with low literacy levels.

Research Outcomes

  • Specific Results:

    • CCD patients significantly improved their familiarity with Alexa devices and enhanced their ability to independently complete ADL tasks through the training.
    • Challenges included technical response delays, voice recognition errors, and low technological literacy, which were addressed through feedback-driven adjustments to the training program.
    • Caregivers' understanding of VAT also improved, enabling them to better assist with operations and daily management.
  • Advantages over Existing Solutions:

    • The VAT training program provided highly personalized and convenient home service support, significantly enhancing independence and reducing reliance on caregivers.
    • Compared to traditional clinical interventions, this training model offered high flexibility and improved the practical application abilities of CCD patients.
  • Experimental or Evaluation Results:

    • Task completion accuracy among participants in two training cohorts ranged from 18% to 97%, with most participants demonstrating consistent progress across multiple ADL domains.
    • The inter-rater reliability of video analysis reached approximately 88.6%, indicating the stability of the training content and methods.
    • Overwhelming feedback suggested that VAT training provided innovative solutions for daily tasks, particularly improving reliance on scheduling, meal preparation, and news information retrieval.
  • Limitations and Future Directions:

    • A small sample size and partial data gaps limited feasible statistical analysis.
    • Issues with technological accessibility (device malfunctions, voice recognition problems) remained evident.
    • Future work should expand the sample size, design long-term follow-up evaluations, further explore the integration of VAT with CCD rehabilitation, and optimize user interaction experiences with the devices (e.g., introducing delay parameter settings).

This literature clearly elucidates the potential of voice assistive technology in enhancing the independence of CCD patients in completing ADLs, paving the way for future technological support in rehabilitation and providing a practical case for telehealth services.

Quick Actions

Share

Share this page

ios_share

https://hci.top/en/papers/chi/147679/2024

AdRecommended

Learn AI Coding at CodeNow

open_in_newOpen DOI Link
DOI: https://doi.org/10.1145/3613904.3642788
At a Glance

Paper Snapshot

fact_check
dataset
Source
CHI
calendar_month
Year
2024
emoji_events
Award
No award tagged
group
Authors
6 authors
sell
Subtopics
Intelligent Voice Assistants (Alexa, Siri, etc.), Special Education Technology
work
Professions
Speech-Language Pathologists & Audiologists, Family Caregivers, Disability Service Providers
article
Content Status
Full text indexed
hub
Related Papers
0 related papers