JMIR Publications

ABSTRACT

Background:

Musculoskeletal disorders are common among musicians, requiring precise diagnostic and therapeutic approaches. Physiotherapists face unique challenges due to the complex relationship between musculoskeletal health and the demands of musical performance. Traditional methods often lack the necessary precision for this specialized field. Integrating Clinical Decision Support (CDS) tools with Clinical Movement Analysis (CMA) could improve diagnostic accuracy and therapeutic outcomes by offering detailed biomechanical insights and facilitating data-driven decision-making.

Objective:

This study aimed to identify design requirements for a specialized CDS tool incorporating CMA to support physiotherapists in diagnosing and treating musculoskeletal disorders in musicians, thereby improving diagnostic accuracy, therapy effectiveness, and patient outcomes.

Methods:

A qualitative user research study was conducted, utilizing Human Factors Engineering methods from problemdriven research, user-centered design, and decision-centered design. Data collection included a domain-specific literature review, workflow observations, and focus group discussions with domain experts, including three musicians' physiotherapists and a movement scientist. This qualitative data was triangulated to characterize the domain, identify the CMA workflow, user needs, key cognitive tasks, and decision requirements. These insights were translated into concrete design requirements for a CDS tool.

Results:

A workflow for integrating musician-specific CMA into physiotherapy was established. Twenty-one user requirements, seven key cognitive tasks, and five key decision requirements were defined, along with forty-nine design seeds, which informed the design requirements for the CDS tool. Key features identified include: (1) efficient integration of musician-specific biomechanical findings into therapy; (2) combining heterogeneous data types for holistic assessment; (3) providing an adaptive overview of patient-related information; (4) utilizing adequate visual representations and interaction techniques; (5) facilitating efficient visual-interactive analysis of findings and treatment results; (6) enabling preparation and export of therapy findings and analysis results. Additionally, eleven technical prerequisites and fourteen decision support recommendations were identified. These requirements will guide the design and development of a CDS tool featuring advanced visualization tools, interactive data exploration capabilities, and contextual integration of clinical and biomechanical data.

Conclusions:

A specialized CDS tool incorporating CMA data holds significant potential to enhance decision-making in musicians' physiotherapy. By addressing cognitive demands and integrating advanced visualization techniques, the tool can support physiotherapists in making more accurate assessments, potentially improving patient outcomes, reducing injury recurrence, and supporting musicians' career longevity. Ongoing research is essential to refine the tool and validate its clinical effectiveness. Future studies should incorporate advanced analytics and explore broader therapeutic applications to enhance its impact.