Introduction Conventional methods for analysing MSK characteristics of healthy individuals and pathological patients are limited by their inaccuracies and confounding factors that preclude proper assessment and treatment strategies. However,  the recent research progress in the field of Artificial intelligence (AI) has re-iterated possibilities in healthcare applications (Rajpurkar et al., 2022; Volpp & Mohta, 2016), particularly in the domain of musculoskeletal (MSK) rehabilitation. Based on the current state of literature, this study proposes an AI-based approach for analysing MSK characteristics to provide accurate and robust assessment outcomes that will inform adequate and real-time therapeutic intervention for common MSK conditions. Aim This initiative is aimed at addressing the critical need for evidence-based practices and improved treatment outcomes, which are currently lacking in Sports Therapy and Rehabilitation (STR). Ethical Considerations While acknowledging ethical considerations raised by Kiani et al. (2020), the project will adhere to standardised protocols established by SPIRIT and CONSORT for rigorous evaluation of medical AI applications. The project would employ a collaborative effort between the University of Derby's AI research team and the STR clinics toward leveraging AI to enhance MSK assessment and treatment strategies. Objectives Additional expected contributions of the project include (a) the provision of an AI-powered platform that enables STR students to analyse various MSK conditions and make informed decisions, (b) the provisioning of real-world clinical datasets that can aid the advancement of research and development in the field of MSK analysis for researchers at the University and beyond.  Methods The research team will initially create a database with anonymised pictures and no-personal information collected from the STR clinic; these will then be processed by AI, which will identify the MSK condition and provide the best treatments. The AI will be coded using objective-oriented program language. All code and user information are stored in server-secured databases, not in clouds (e.g., Github), to prevent data leaks. Additionally, to compare and test the validity of AI, the STR practitioner will complete a full parallel screening, and the results between AI and STR experts will be compared to report the level of agreement and accuracy of the results. Conclusion This proposed project has the potential to make significant contributions to the burgeoning field of AI-powered MSK rehabilitation. By developing a robust AI framework within the STR clinics, we can enhance the students' learning experience, promote evidence-based practices, and improve patient outcomes. This initiative aligns with our research commitment to cutting-edge projects and dedication to providing students with the skills and knowledge necessary to excel in a rapidly evolving healthcare landscape. The project (titled MSC-AI) has recently applied for funding, and the methodological approach will be discussed at the conference.