Jump to content

Artificial Intelligence in Physiotherapy Education

This article is currently under review and may not be up to date. Please come back soon to see the finished work! (20/11/2026)

Artificial Intelligence in Physiotherapy Education

The Current Educational Landscape

The rapid integration of artificial intelligence (AI) into clinical rehabilitation has created an urgent imperative for physiotherapy curricula to evolve alongside clinical practice.[1] Historically, physiotherapy education has lagged behind medicine and dentistry in adopting and researching AI-supported pedagogy; an early 2024 literature search identified only one peer-reviewed article specifically examining AI in physiotherapy education, compared with over 6,000 in medical education and 241 in dental education.[2] Since then, however, scholarship in physiotherapy pedagogy has expanded rapidly, shifting from general awareness toward structured classroom integration, simulated patient encounters, and biomechanical analysis.[3][4][5] Preparing entry-level students for an AI-enabled healthcare environment requires moving beyond passive awareness toward active, supervised competence in both theoretical assimilation and clinical reasoning.[6]

Facilitating Movement Science and Biomechanical Understanding

Mastering movement science, functional anatomy, and kinesiology demands that students translate abstract biomechanical principles—such as joint reaction forces, muscle moment arms, and kinematic chains—into observable human movement. AI-supported educational tools bridge this gap between theoretical mechanics and visual clinical observation:

  • Computer-Vision and Markerless Motion Analysis: AI-driven pose-estimation algorithms allow students in teaching laboratories to capture real-time joint angles, spatiotemporal gait parameters, and postural deviations using standard cameras or mobile devices, democratising access to quantitative movement analysis previously restricted to high-cost optoelectronic laboratories.[7]
  • Teaching Normal and Pathological Gait: Generative AI and intelligent visual simulations enable educators to construct dynamic, frame-by-frame breakdowns of normal human gait cycles alongside simulated neurological or musculoskeletal gait deviations, helping novice learners connect neuromuscular activation patterns to observable kinematics.[5]
  • Adaptive Biofeedback and Motor Learning: Integrating AI-powered wearable sensors and virtual reality (VR) environments into practical classes gives students immediate, personalised feedback on their own handling techniques, therapeutic exercise execution, and motor control principles.[7][8]

Scaffolding Complex Theories and Clinical Reasoning

Physiotherapy students frequently struggle to synthesise dense foundational sciences—such as neurophysiology, pain neuroscience, and tissue healing mechanics—with multi-variable patient presentations. Generative AI (GAI) and large language models (LLMs) act as cognitive scaffolds when embedded within structured pedagogical frameworks:

  • Deconstructing Dense Theoretical Frameworks: Qualitative research demonstrates that physiotherapy students use GAI to simplify, translate, and summarise complex theoretical literature, allowing them to verify comprehension and build mental models of challenging physiological and biomechanical concepts before applying them in tutorials.[3]
  • AI-Enhanced Problem-Based Learning (AI-PBL): A randomised controlled trial evaluating an AI-based physiotherapy educational approach demonstrated that combining structured GAI interaction with problem-based learning significantly improved two-week knowledge retention ($d = 3.14$) and AI self-efficacy compared with traditional PBL alone, without increasing problematic internet use.[4]
  • Socratic Clinical Reasoning and Virtual Patient Simulations: Co-designed AI chatbots and virtual simulated patients allow learners to practise history-taking, differential diagnosis, and clinical hypothesis testing at scale.[1][9] Rather than replacing educator mentorship, well-prompted AI systems provide immediate, individualised Socratic feedback, prompting students to justify their clinical reasoning across musculoskeletal, neurological, and cardiorespiratory scenarios.[1][9]

Student and Educator Readiness

Both learners and faculty recognise the inevitability of AI in rehabilitation, yet readiness remains uneven across academic institutions:

  • Student Perspectives: Surveys and focus groups indicate that while healthcare and physiotherapy students express healthy scepticism regarding accuracy and over-reliance, the vast majority view AI positively and support its formal inclusion in the curriculum.[3][10] Students value GAI for generating practice cases and clarifying concepts, though they highlight the need for clear institutional guidelines on permitted usage.[3]
  • Faculty Preparedness: Effective integration depends on educators developing AI literacy and pedagogical strategies that align technology with learning outcomes.[1][6] Bridging the digital divide requires targeted faculty development, interdisciplinary collaboration with data and computer scientists, and moving away from didactic lecturing toward active, technology-enhanced learning.[2][6]

Pedagogical Challenges and Ethical Considerations

Integrating AI into physiotherapy teaching introduces distinct educational and professional risks that must be actively managed:

  • Cognitive Offloading and Knowledge Gaps: Uncritical reliance on generative tools can bypass the productive struggle required to develop independent clinical reasoning, potentially leaving students with superficial knowledge or undetected misconceptions caused by AI hallucinations.[3][4]
  • Algorithmic Bias and Explainability: Students must be trained to interrogate the "black box" nature of clinical algorithms, recognising how biased training datasets can skew movement assessments or prognostic predictions across diverse patient populations.[7]
  • Data Privacy and Academic Integrity: Educators must establish transparent boundaries governing patient confidentiality in clinical placements alongside clear assessment standards that evaluate genuine student reasoning rather than AI-generated output.[2][3]

Moving Forward Responsibly

Embedding AI into physiotherapy education is not about automating instruction or diminishing the hands-on, empathetic core of the profession. Instead, AI serves as an analytical and pedagogical amplifier—helping students visualise complex movement science, deconstruct intricate physiological theories, and rehearse clinical reasoning in low-risk environments. By pairing structured, evidence-based AI workflows with critical appraisal skills and human mentorship, physiotherapy programmes can graduate clinicians who are both technologically fluent and deeply grounded in patient-centred care.

References


References

  1. Lowe SW. The role of artificial intelligence in Physical Therapy education. Bull Fac Phys Ther. 2024;29:13. doi:10.1186/s43161-024-00177-8
  2. Veras M, Dyer JO, Kairy D. Artificial Intelligence and Digital Divide in Physiotherapy Education. Cureus. 2024 Jan 20;16(1):e52617. doi:10.7759/cureus.52617. PMID: 38374829; PMCID: PMC10875905
  3. Lindbäck Y, Schröder K, Engström T, Valeskog K, Sonesson S. Generative artificial intelligence in physiotherapy education: great potential amidst challenges—a qualitative interview study. BMC Med Educ. 2025 Apr 24;25(1):603. doi:10.1186/s12909-025-07106-w
  4. Ergezen Sahin G, Aras Bayram G, Sanchez Sierra A, et al. Effects of artificial intelligence based physiotherapy educational approach in developing clinical reasoning skills: a randomized controlled trial. BMC Med Educ. 2025 Oct 9;25(1):1378. doi:10.1186/s12909-025-07926-w
  5. Lowe SW. The use of artificial intelligence in crafting a novel method for teaching normal human gait. Eur J Phys. 2025;27(4):259-263. doi:10.1080/21679169.2024.2393136
  6. Issa WB, Shorbagi A, Al-Sharman A, et al. Shaping the future: perspectives on the Integration of Artificial Intelligence in health profession education: a multi-country survey. BMC Med Educ. 2024;24:1166. doi:10.1186/s12909-024-06076-9
  7. Hanafi B, Hasan A, Ahmad A, Ali M. Advancing public health through artificial intelligence in physiotherapy: a bibliometric analysis. Informatics and Health. 2025 Sep 1;2(2):99-118.
  8. Attoh-Mensah E, Boujut A, Desmons M, Perrochon A. Artificial intelligence in personalized rehabilitation: current applications and a SWOT analysis. Front Digit Health. 2025 Jul 24;7:1606088. doi:10.3389/fdgth.2025.1606088
  9. Al Zoubi FMQ, Wang K, Fong CKJ. AI-driven platform for advancing clinical reasoning in musculoskeletal subjects. Presented at: The 2nd International Conference on Teaching and Learning Innovations in Rehabilitation Sciences; Dec 11-12, 2025; Hong Kong.
  10. Teng M, Singla R, Yau O, et al. Health Care Students' Perspectives on Artificial Intelligence: Countrywide Survey in Canada. JMIR Med Educ. 2022 Jan 31;8(1):e33390. doi:10.2196/33390