Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Currently submitted to: JMIR mHealth and uHealth

Date Submitted: Nov 16, 2026
Open Peer Review Period: Nov 17, 2026 - Jan 12, 2027
(currently open for review)

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

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

  • Penelope Rekkas; 
  • Stijn Keyaerts; 
  • Veerle Ross; 
  • Liesbeth Daenen; 
  • Janne Goossens; 
  • Shahenaz Najjar; 
  • Katrien Verbert; 
  • Vero Vanden Abeele

ABSTRACT

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.


 Citation

Please cite as:

Rekkas P, Keyaerts S, Ross V, Daenen L, Goossens J, Najjar S, Verbert K, Vanden Abeele V

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

JMIR Preprints. 16/11/2026:116872

DOI: 10.2196/preprints.116872

URL: https://preprints.jmir.org/preprint/116872

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.