Caregiver Expectations of Interfacing With Voice Assistants to Support Complex Home Care: Mixed Methods Study
Bibliographic record
Abstract
BACKGROUND: Providing care in home environments is complex, and often the pressure is on caregivers to document information and ensure care continuity. Digital information management and communication technologies may support care coordination among caregivers. However, they have yet to be adopted in this context, partly because of issues with supporting long-term disease progression and caregiver anxiety. Voice assistant (VA) technology is a promising method for interfacing with digital health information that may aid in multiple aspects of being a caregiver, thereby influencing adoption. Understanding the expectations for VAs to support caregivers is fundamental to inform the practical development of this technology. OBJECTIVE: This study explored caregivers' perspectives on using VA technology to support caregiving and inform the design of future digital technologies in complex home care. METHODS: This study was part of a larger study of caregivers across North America on the design of digital health technologies to support health communication and information management in complex home care. Caregivers included parents, guardians, and hired caregivers such as personal support workers and home care nurses. Video interviews were conducted with caregivers to capture their mental models on the potential application of VAs in complex home care and were theoretically analyzed using the technology acceptance model. Interviews were followed up with Likert-scale questions exploring perspectives on other VA applications beyond participants' initial perceptions. RESULTS: Data were collected from 22 caregivers, and 3 themes were identified: caregivers' perceived usefulness of VAs in supporting documentation, care coordination, and person-centered care; caregivers' perceived ease of use in navigating information efficiently (they also had usability concerns with this interaction method); and caregivers' concerns, excitement, expected costs, and previous experience with VAs that influenced their attitudes toward use. From the Likert-scale questions, most participants (21/22, 95%) agreed that VAs should support prompted information recording and retrieval, and all participants (22/22, 100%) agreed that they should provide reminders. They also agreed that VAs should support them in an emergency (18/22, 82%)-but only for calling emergency services-and guide caregivers through tasks (21/22, 95%). However, participants were less agreeable on VAs expressing a personality (14/22, 64%)-concerned they would manipulate caregivers' perceptions-and listening ambiently to remind caregivers about their documentation (16/22, 73%). They were much less agreeable about VAs providing unprompted assistance on caregiving tasks (9/22, 41%). CONCLUSIONS: The interviews and Likert-scale results point toward the potential for VAs to support family caregivers and hired caregivers by easing their information management and health communication at home. However, beyond information interaction, the potential impact of VA personality traits on caregivers' perceptions of the care situation and the passive collection of audio data to improve user experience through context-specific interactions are critical design considerations that should be further examined.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.014 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".