Currently submitted to: Journal of Participatory Medicine
Date Submitted: Jul 27, 2026
Open Peer Review Period: Aug 4, 2026 - Sep 29, 2026
(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Warning: This is an author submission that is not peer-reviewed or edited.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.
Co-creation of an AI-Powered Virtual Motivational Interviewing Training Tool for Physical Therapists (VMI-PT)
ABSTRACT
Background:
Physical therapists frequently struggle to operationalize biopsychosocial care in daily practice. Although Motivational Interviewing (MI) can strengthen patient engagement and support behavior change, existing MI training models are resource-intensive, inconsistently implemented, and provide limited opportunities for deliberate practice and feedback.
Objective:
To describe the collaborator-engaged co-creation of an AI-powered mobile application (VMI-PT) designed to train physical therapists in MI through interactive patient simulations and real-time, theory-driven feedback.
Methods:
Using a design-thinking framework, we engaged 7 licensed physical therapists, 2 psychologists, 2 licensed clinical social workers, and a software development team in iterative co-creation over 8 months. The development process included three phases: inspiration (collaborator needs assessment), ideation (prototype co-creation), and implementation planning. The final application employs generative artificial intelligence to simulate patient interactions, provides real-time feedback using a novel three-tier classification system, and supports deliberate practice principles through scaffolded skill progression.
Results:
Collaborator identified critical communication challenges in physical therapy and refined four clinically authentic patient personas representing diverse biopsychosocial scenarios. Co-creation produced a mobile application featuring adaptive AI-driven patient interactions, immediate MI-specific feedback categorized as “Healing Partner,” “Friendly Provider,” or “Technician,” and skill-progression pathways. Multidisciplinary input informed natural language processing algorithms for real-time MI technique classification and responsive patient dialogue.
Conclusions:
Collaborator-engaged co-creation yielded a clinically relevant, pedagogically grounded, AI-powered MI training tool tailored to the needs of physical therapists. This methodology highlights a feasible pathway for integrating AI into healthcare education while preserving clinical authenticity and maximizing end-user acceptance. Clinical Trial: N/A
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© 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.