Accepted for/Published in: JMIR Formative Research
Date Submitted: Sep 30, 2025
Date Accepted: Jun 4, 2026
Warning: This is an author submission that is not peer-reviewed or edited.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.
Co-developing an evidence-based AI Virtual Assistant for young people living with ADHD: Recommendations from Experts by Lived Experience
ABSTRACT
Background:
UK healthcare is failing young people living with ADHD, due to long waiting lists for diagnostic assessment and limited access to services. One way to improve access, potentially increase engagement, reduce healthcare inequalities and enhance care is by co-developing digital responsive interventions. These have the potential to support long-term condition management and are a priority for the UK’s National Health Service (NHS). Virtual assistants that use large language models (LLMs) can provide information in response to questions and learn to tailor communication to suit an individual's user needs. This can be especially valuable for people with ADHD who often struggle to regulate attention and can experience communication challenges. Involving people with lived experience in the co-design process is crucial for development of effective digital interventions. Therefore, this article explores the views and preferences of people with ADHD who supported co-development of a prototype chatbot.
Objective:
We aimed to co-develop an evidence-based chatbot prototype, intended to help young people living with ADHD to thrive by helping them to access healthcare information, psychoeducation, and self-management strategies.
Methods:
An interdisciplinary team was established, including researchers, software developers, clinicians and lived experience collaborators. Research advisory and working groups were set up in ways that facilitated flexible involvement. Following the person-based-approach (PBA), guiding principles were established, and workshops held with young people living with ADHD and supporters of young people living with ADHD to co-develop a prototype chatbot. Feedback on the prototype was sought via think-aloud interviews with lived experience collaborators.
Results:
Following the person-based approach (PBA), consultation was carried out in five workshops: four with experts by lived experience, and one with healthcare professionals. Nine experts by lived experience and three healthcare professionals engaged. Feedback was combined with principles of human-computer interaction and the PBA to create a prototype of the SmartADHD chatbot. Think-Aloud interviews were carried out with six lived experience collaborators who provided feedback on the chatbot prototype, including the overall conversational flow and feel, the avatar, the text-to-speech, the chatbox feature and the content of the messages. Five recommendations are made for future development. Findings will inform the SmartADHD program of work.
Conclusions:
These findings provide rich data on the preferences of people with ADHD. Specific recommendations for a chatbot for young adults with ADHD have not been investigated before with young people, making this paper a novel contribution to the field. These findings provide an excellent foundation for chatbot development for this group and may be relevant for those developing digital tools for people with ADHD across the lifespan and other neurodevelopmental conditions.
Citation
