Overview

Master AI & Machine Learning for 50% Off

Go under the hood of AI — neural networks, real-world applications & more. Designed by UNSW experts.

This advanced course teaches rehabilitation practitioners and students to verify AI-generated movement analyses, exercise recommendations, recovery forecasts, pain assessments, and remote-monitoring alerts. Learners apply MOVE, LOAD-R, RISK-R, and SCOPE-A frameworks across simulated multidisciplinary patient encounters while addressing patient safety, informed consent, documentation, and professional scope.

Syllabus

Evaluate AI-generated movement analysis outputs (e.g., markerless motion capture, pose estimation, gait analytics) using the MOVE verification framework.
Verify AI-generated exercise load and progression recommendations using the LOAD-R framework before clinical implementation.
Interpret AI recovery predictions and return-to-function forecasts, distinguishing probabilistic outputs from deterministic clinical conclusions.
Assess AI-generated biomechanical and gait analyses from wearables, smart insoles, and pressure mapping systems using anatomical and biomechanical knowledge.
Use AI tools to support biopsychosocial assessment in chronic pain without reducing complex patient experiences to algorithmic labels.
Evaluate AI-driven remote monitoring systems (e.g., telerehabilitation analysis, fall detection, adherence tracking) using the RISK-R safety protocol.
Identify when AI outputs approach or exceed professional scope of practice using the SCOPE-A framework.
Apply AI tools across movement analysis, load management, chronic pain monitoring, ethics, and specialist rehabilitation practice using structured clinical verification frameworks while maintaining patient safety and professional scope.
Evaluate AI-generated movement analysis outputs using the MOVE verification framework, distinguishing between AI-detected movement patterns and clinically meaningful dysfunction while recognising failure modes in markerless motion capture and gait analysis tools.
Apply the LOAD-R framework to verify AI-generated exercise dose and load recommendations, interpret recovery trajectory forecasts as probability-based predictions, and identify high-risk populations where AI load models carry the greatest risk of misapplication.
Analyse AI-generated biopsychosocial risk scores for chronic pain without communicating diagnostic labels to patients and apply the RISK-R safety protocol to evaluate remote monitoring AI alerts before clinical escalation.
Implement the SCOPE-A framework to protect professional registration boundaries when AI tools generate recommendations beyond scope, and apply allied health-specific informed consent and documentation requirements for AI-assisted practice.
Evaluate AI applications specific to physiotherapy, occupational therapy, chiropractic, podiatry, osteopathy, and exercise physiology, identifying discipline-specific failure modes, scope sensitivities, and clinical validation requirements.
Integrate the MOVE, LOAD-R, RISK-R, and SCOPE-A frameworks across six simulated patient encounters to demonstrate safe, defensible AI-assisted rehabilitation decision-making in a multidisciplinary clinical environment.
Design a personal AI learning plan for rehabilitation practice by applying foundational frameworks in supervised clinical contexts, articulating AI literacy competencies for job interviews, and understanding the student medico-legal position in AI-assisted environments.