Recommendations for the Design and Integration of Mental Health Chatbots into Blended Care: A Focus Group and Co-Design Study with Clients and Healthcare Professionals (Preprint)
BACKGROUND Mental health chatbots are increasingly explored to address gaps in access to mental healthcare. While they can provide accessible, personalized, and empathetic support, concerns remain regarding accuracy, privacy, and safety. Recent research stresses the need for human-centered design approaches and the integration of chatbots into healthcare through blended care models combining digital and human support. However, practical guidance for designing and integrating mental health chatbots into blended care remains limited. OBJECTIVE This study aimed to explore the perspectives of clients and healthcare professionals (HPs) through joint co-design activities and derive recommendations for designing and integrating mental health chatbots into blended care. METHODS We conducted a qualitative study involving 11 clients and 11 HPs recruited through two Belgian occupational and mental health service providers in July and September 2025. The study comprised focus groups and co-design workshops, drawing on the Turning Tables power-balancing method. Participants were organized into four groups, each comprising two teams: one of two to three clients and one of two to three HPs. During focus groups, teams used the ChatBlend card deck to evaluate and discuss chatbot features and implementation strategies. In co-design workshops, teams completed journey-mapping exercises to design blended care pathways for fictional personas. Session recordings were analyzed using inductive thematic analysis, with physical artifacts supporting interpretation. RESULTS Participants (N=22) had a mean age of 43.35 years (SD 16.07; n=17), with 18 (81.82%) identifying as female. Five themes emerged from the analysis. First, participants emphasized the need to balance emotional connection with clear human-AI boundaries, supporting empathic and relatable chatbots, while avoiding deception and ambiguity regarding their nonhuman nature. Second, participants viewed self-reflection and action-oriented support as key chatbot functions but cautioned against designs that could reinforce rumination or negative thinking. Third, participants expected chatbots to adapt dynamically to user feedback, context, and preferences while preserving privacy, autonomy, and user control over personal information. Fourth, participants envisioned blended care models in which chatbots complement rather than replace HPs, with professional oversight, shared decision-making, and reciprocal data exchange. Fifth, participants highlighted the importance of streamlining access to care through referral pathways, triage mechanisms, and affordable access while protecting HP workload and managing user expectations. Drawing on participants’ contributions, we proposed 57 recommendations aligned with the identified themes, covering chatbot functionality, application design, and integration into blended care. CONCLUSIONS Participants were generally receptive to mental health chatbots integrated into blended care, provided they align with values such as transparency and psychological safety, while supporting desired outcomes such as connection and self-reflection. The resulting recommendations offer preliminary guidance for their design and integration, although further validation and real-world evaluation, including across more diverse populations, are warranted.
Authors
- Stijn Keyaerts (ORCID: https://orcid.org/0000-0001-6431-092X)
- Veerle Ross (ORCID: https://orcid.org/0000-0002-7830-7892)
- Vero Vanden Abeele (ORCID: https://orcid.org/0000-0002-3031-9579)
- Janne Goossens (ORCID: https://orcid.org/0000-0002-9383-8886)
- Shahenaz Najjar (ORCID: https://orcid.org/0000-0002-4555-7713)
- Katrien Verbert (ORCID: https://orcid.org/0000-0001-6699-7710)
- Liesbeth Daenen (ORCID: https://orcid.org/0000-0002-7780-183X)
- Penelope Rekkas (ORCID: https://orcid.org/0009-0001-5328-7418)
Publication Details
- Published
- 2026-11-16
- DOI
- https://doi.org/10.2196/preprints.116872
- Primary Topic
- Digital Mental Health Interventions
- Type
- preprint