Co-Designing a Clinician-Centered Video Gait Assessment System for Cerebral Palsy Based on the Framework for...

Clinical gait assessment is essential for monitoring functional progress in children with cerebral palsy (CP); however, traditional visual observation remains inherently subjective and labor-intensive. Although AI-supported video gait assessment may provide more objective and automated outputs, many tools remain difficult to integrate into routine clinical workflows.

This study aimed to iteratively develop and evaluate a clinician-centered, automated gait analysis system for children with CP by using a structured co-design process, ensuring the tool effectively supports clinical decision-making and integrates into routine practice.

This study adopted the Framework for Co-design of Clinical Practice Tools (FRESCO) to guide a 5-step iterative development process. A multidisciplinary advisory group, comprising rehabilitation physicians, therapists, biomechanics experts, and human factors engineers, collaborated throughout the study. The process involved the following: (1) identifying baseline clinical needs and initial system requirements through advisory group input and review of existing gait-analysis systems; (2) developing an initial system prototype based on these requirements; (3) conducting think-aloud evaluations and System Usability Scale (SUS) assessments with 19 rehabilitation professionals to identify usability barriers, additional user requirements, and prototype refinement needs; (4) testing workflow integration and safety in clinical simulations with 12 rehabilitation professionals; and (5) finalizing prototype specifications, workflow procedures, and implementation guidelines through a consensus workshop.

By targeting workflow alignment, interpretability, and the delivery of useful system outputs, the iterative co-design process supported progressive prototype refinement. The baseline needs-identification phase generated initial system requirements across system content, workflow integration, and clinical usability support, which informed the first prototype. The think-aloud phase demonstrated good perceived usability (SUS score: mean 75.8, SD 7.5) and identified additional refinement needs related to functional expansion, report interpretability, and workflow compatibility. In the clinical simulation phase, the prototype was perceived as stable and safe for use in routine clinical settings, with no safety incidents observed, while also revealing implementation needs related to video capture and output interpretation. This work culminated in 2 key outputs: a refined prototype ready for large-scale clinical testing and a comprehensive implementation guideline. Conceptually, the study articulated two data-informed design principles: (1) supporting workflow-compatible implementation by minimizing technical and operational barriers, and (2) prioritizing clinical autonomy and actionability.

FRESCO provided a structured approach for narrowing the gap between technical feasibility and clinical utility in the development of a clinician-centered video gait assessment system. By iteratively involving a multidisciplinary team, we transformed a video-based analysis tool into a stable, interpretable, and workflow-compatible decision-support prototype. Broadly, the identified design principles may provide practical reference points for developing clinician-centered digital health tools intended to support clinical decision-making in routine practice.