CoChat

A Virtual Agent to Support Individuals Living With Physical and Mental Comorbidities: Co-Design and Acceptability Testing

Open access

Published version of a preprint

The DOI matches its Crossref record; 27 of the 29 references it cites were found in a registry or an index; 4 of the 27 sources its claims cite were checked for support.

Abstract

BACKGROUND: Individuals living with long-term physical health conditions frequently experience co-occurring mental health problems. This comorbidity has a significant impact on an individual's levels of emotional distress, health outcomes, and associated health care utilization. As health care services struggle to meet demand and care increasingly moves to the community, digital tools are being promoted to support patients to self-manage their health. One such technology is the autonomous virtual agent (chatbot, conversational agent), which uses artificial intelligence (AI) to process the user's written or spoken natural language and then to select or construct the corresponding appropriate responses. OBJECTIVE: This study aimed to co-design the content, functionality, and interface modalities of an autonomous virtual agent to support self-management for patients with an exemplar long-term condition (LTC; chronic pulmonary obstructive disease [COPD]) and then to assess the acceptability and system content. METHODS: We conducted 2 co-design workshops and a proof-of-concept implementation of an autonomous virtual agent with natural language processing capabilities. This implementation formed the basis for video-based scenario testing of acceptability with adults with a diagnosis of COPD and health professionals involved in their care. RESULTS: Adults (n=6) with a diagnosis of COPD and health professionals (n=5) specified 4 priority self-management scenarios for which they would like to receive support: at the time of diagnosis (information provision), during acute exacerbations (crisis support), during periods of low mood (emotional support), and for general self-management (motivation). From the scenario testing, 12 additional adults with COPD felt the system to be both acceptable and engaging, particularly with regard to internet-of-things capabilities. They felt the system would be particularly useful for individuals living alone. CONCLUSIONS: Patients did not explicitly separate mental and physical health needs, although the content they developed for the virtual agent had a clear psychological approach. Supported self-management delivered via an autonomous virtual agent was acceptable to the participants. A co-design process has allowed the research team to identify key design principles, content, and functionality to underpin an autonomous agent for delivering self-management support to older adults living with COPD and potentially other LTCs.

Overview

CoChat Summary

TL;DR

This study co-designed and tested the acceptability of Avachat, an autonomous virtual agent intended to support self-management for people with COPD and comorbid mental health needs. Participants identified four priority support scenarios and generally found the prototype acceptable and engaging, especially its multimodal and internet-of-things possibilities.

Key findings

  • Co-design participants prioritized four self-management scenarios: at diagnosis (information provision), during acute exacerbations (crisis support), during periods of low mood (emotional support), and for general self-management (motivation).
  • In video-based scenario testing, 8 patients/carers viewed the film; the System Usability Scale median was 73.75, with 5/8 scores above 68 (72.5, 75, 75, 80, 85) and 3/8 below (52.2, 62.5, 65).
  • 4/8 participants strongly agreed they would like to use the system frequently, 7/8 strongly agreed it was easy to use, and all but 1 strongly agreed they would feel confident using it.
  • Participants did not explicitly separate mental and physical health needs, but the content they developed had a clear psychological approach; they valued multimodal access, internet-of-things capabilities, and thought the system would be particularly useful for individuals living alone.

Methods

  • Two co-design workshops were held with adults with COPD/carers and health professionals, using day-in-the-life mapping, missing-sentence prompts, mood boards, vignettes, role play, and script development; data were analyzed with content analysis and thematic analysis.
  • A semiautonomous Avachat prototype was developed with spoken and written interaction, then filmed in a Wizard of Oz setup as a short video (<8 min) showing two scenarios: crisis support and motivational support.
  • Acceptability testing screened the video with 8 patients/carers, followed by discussion around design, functionality, and content, plus self-completed System Usability Scale questionnaires.

Limitations

  • Stated: the sample was small, white, British, medically stable, and regional; no participants reported a current mental health problem, though all referred to past low mood or worry; recruitment through support groups likely selected people already experienced in self-management.
  • Stated: health practitioners contributed relatively little compared with patients, so it is unclear whether they endorsed the final scenarios as clinical priorities or best practice; the project was not a software development project, limiting development effort.
  • Stated: possible negative consequences, incorrect advice, and wider ethical implications were not discussed; evident from the text: the abstract reports 12 additional adults with COPD in scenario testing, while the Results section reports 8 patients/carers screened, and the prototype was Wizard-of-Oz rather than fully autonomous, so acceptability of the actual autonomous system was not directly tested.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.2196/12996

Cites

27 of 27 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Figures

Figure 1 Persona worksheets. COPD: chronic obstructive pulmonary disease; GP: general practitioner.
Figure 1 Persona worksheets. COPD: chronic obstructive pulmonary disease; GP: general practitioner.CC BY · PubMed Central
Figure 2 Vignette feedback sheets. COPD: chronic obstructive pulmonary disease; GP: general practitioner; PR: pulmonary rehabilitation.
Figure 2 Vignette feedback sheets. COPD: chronic obstructive pulmonary disease; GP: general practitioner; PR: pulmonary rehabilitation.CC BY · PubMed Central
Figure 3 A day in the life of a chronic obstructive pulmonary disease patient. COPD: chronic obstructive pulmonary disease; OA: osteoarthritis.
Figure 3 A day in the life of a chronic obstructive pulmonary disease patient. COPD: chronic obstructive pulmonary disease; OA: osteoarthritis.CC BY · PubMed Central
Figure 4 User specifications for Avachat (avatar graphic shown courtesy of Bot Libre). COPD: chronic obstructive pulmonary disease; GP: general practitioner.
Figure 4 User specifications for Avachat (avatar graphic shown courtesy of Bot Libre). COPD: chronic obstructive pulmonary disease; GP: general practitioner.CC BY · PubMed Central
Figure 5 Persona crisis support. COPD: chronic obstructive pulmonary disease; 999 and 111 are the UK telephone numbers for life-threatening and non-life-threatening emergencies respectively.
Figure 5 Persona crisis support. COPD: chronic obstructive pulmonary disease; 999 and 111 are the UK telephone numbers for life-threatening and non-life-threatening emergencies respectively.CC BY · PubMed Central

Verification

Claims the paper makes

2 Valid · 1 Not valid · 9 Not checked · 83 Own results and interpretations

33 more claims

Create a free account to see all 95 claims and to verify the 23 references still open.

See all claims — free account
  • Probably not a substantial claim. 47
  • It may state two separate claims as one. 23

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

5 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

4 of 4

Citations

Cites

Show all 27 references

Research works printed but not linked: 6

  1. 2011, No Health Without Mental Health: A Cross-Government Mental Health Outcomes Strategy for People of All Ages
  2. de Silva, D, 2011, Evidence: Helping People Help Themselves
  3. Luxton, DD, 2015, Artificial Intelligence in Behavioural and Mental Healthcare
  4. Stickdorn, M, 2011, This Is Service Design Thinking
  5. Ortiz, A, 2007, Universal Access In Ambient Intelligence Environments: 9th Ercim Workshop On User Interfaces For All, Königswinter, Germany, September 27-28, 2006, Revised Papers (Lecture Notes In Computer Science)
  6. Carrasco, E, 2008, Computers Helping People With Special Needs. ICCHP 2008. Lecture Notes in Computer Science, vol 5105

Cited by

Metadata

Authors
Easton, K., Potter, S., Bec, R., Bennion, M., Christensen, H., Grindell, C., Mirheidari, B., Weich, S., de Witte, L., Wolstenholme, D., & Hawley, M. S.
Affiliations
  • University of Sheffield (GB)
  • Royal Hallamshire Hospital (GB)
Corresponding author
Easton, Katherine
Venue
Journal of Medical Internet Research
Published
2019-05-30
Volume
21
Issue
5
Pages
e12996
ISSN
1438-8871 (ISSN-L)
OpenAlex
W2953947009
Cited by
88
References
29
Citations by year
2026: 11 · 2025: 19 · 2024: 8 · 2023: 17 · 2022: 13 · 2021: 11 · 2020: 7 · 2019: 2
FWCI
9.32
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Journal of Medical Internet Research (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (acceptedVersion)
  • SHURA (Sheffield Hallam University Research Archive) (Sheffield Hallam University) (acceptedVersion)
Funders
Medical Research Council (MC_PC_14115)
Topics
  • Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
  • Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
  • Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
Keywords
virtual agents, chatbots, chronic obstructive pulmonary disease, self-management support, co-design, acceptability, natural language processing, Internet of Things, older adults, emotional support, crisis support, living alone, chronic disease
MeSH terms
Adult, Female, Humans, Male, Mental Health, Middle Aged, Social Support, Comorbidity, Pulmonary Disease, Chronic Obstructive, Virtual Reality Exposure Therapy

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-04, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-04 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.