Co-Designing a Conversational Agent with Frail and Impaired Older People to Enhance Ageing in Place through Self-management and Empowerment
Bibliographic record
Abstract
Background: SMILE is a collaborative project between Norway, Denmark, The Netherlands, Canada, and Greece. The aim is to enable older people to live an independent and active life, irrespective of frailty, physical and/or cognitive impairments using eHealth solutions developed in co-creation with service users. The aim of the eHealth solution is to enable ageing in place, by combining prevention, prediction, communication, timely care, and assistance to help older people be engaged in their own condition and remain connected with their community. A user requirement specification and co-creation workshops was conducted in 2021 prior to the development of a Digital Care Facilitator (DCF) and a Conversational Agent (CA). Methods: The co-creation process entails initial interviews and observations conducted in Denmark, Norway, and the Netherlands, and 4 phases of co-creation workshops with service users. The initial interviews and observations provided an overview of the service users current practices e.g., daily activities and self-management of own health condition, their use of technology, and insight into requirements and needs for a future eHealth solution. Specifically, nine areas of interest were identified: 1) clinical condition, 2) physical activities, 3) sleep quality, 4) nutrition and hydration, 5) hygiene, 6) mental health, 7) social health, 8) air quality and 9) entertainment. The nine features were presented and discussed among 16 participants with COPD at phase 1 workshops in Denmark and Norway in May 2022. The features were presented to the participants in paper format, where partici-pants could ask questions and share thoughts. Then the participants were given four post-it’s on which they individually could write down the four features they found most valuable and that met their daily needs the most. Results: The phase 1 workshops helped narrow down nine areas of interest, to four specific features to include in the design of a conversational agent (CA), based on direct input from service users. The four features from the phase 1 workshops include: 1) health condition, 2) daily activity 3) social life, and 4) circadian rhythm. Input from the participants suggest that the valuable features of interest can enable an independent lifestyle and wellbeing without being disease or diagnose specific. Conclusion: The four features identified through input from the services user’s, formed the basis for development of a mock-up of the CA. The CA was presented at a phase 2 workshop, where input from user’s will be used to further develop and design the interface and the content of the CA and the DCF. The initial interviews and observations suggest that designing an interface for older frail people to ease information access and communication with care givers should not be specific to one condition but address how to support physiological, psychological, and social parameters that are meaningful for the age group. The results indicate that a focus on the four areas; health condition, daily activity, social life, and circadian rhythm, are relevant to ad-dress in future development of service design for older adults (65+), as they may contribute to increased empowerment, well-being and ageing in place.
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 | 0.005 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".