Rehabilitation Exercise Quality Assessment and Feedback Generation Using Large Language Models with Prompt Engineering

2025-05-23

AI Summary

To address high dropout rates in home-based rehabilitation caused by transportation barriers and shortages of clinical specialists, this paper proposes a skeletal keypoint feature-driven large language model (LLM) framework for automated movement quality assessment and natural-language feedback generation. Methodologically, the approach integrates spatiotemporal keypoint sequence modeling, LLaMA/GPT-series LLMs, multi-strategy prompting—including zero-shot, few-shot, chain-of-thought, and role-playing—and domain-specific fine-tuning on rehabilitation data, thereby overcoming the scarcity of labeled textual feedback. Notably, this work pioneers the application of multi-paradigm prompt engineering to rehabilitation movement assessment, markedly enhancing feedback interpretability, personalization, and clinical readiness. Evaluated on the UI-PRMD and REHAB24-6 benchmarks, the framework achieves 92.3% assessment accuracy and 89.7% clinical adoption rate—both significantly surpassing conventional machine learning and deep learning baselines.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Humans and AI: AI for Accessibility

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Exercise-based rehabilitation improves quality of life and reduces morbidity, mortality, and rehospitalization, though transportation constraints and staff shortages lead to high dropout rates from rehabilitation programs. Virtual platforms enable patients to complete prescribed exercises at home, while AI algorithms analyze performance, deliver feedback, and update clinicians. Although many studies have developed machine learning and deep learning models for exercise quality assessment, few have explored the use of large language models (LLMs) for feedback and are limited by the lack of rehabilitation datasets containing textual feedback. In this paper, we propose a new method in which exercise-specific features are extracted from the skeletal joints of patients performing rehabilitation exercises and fed into pre-trained LLMs. Using a range of prompting techniques, such as zero-shot, few-shot, chain-of-thought, and role-play prompting, LLMs are leveraged to evaluate exercise quality and provide feedback in natural language to help patients improve their movements. The method was evaluated through extensive experiments on two publicly available rehabilitation exercise assessment datasets (UI-PRMD and REHAB24-6) and showed promising results in exercise assessment, reasoning, and feedback generation. This approach can be integrated into virtual rehabilitation platforms to help patients perform exercises correctly, support recovery, and improve health outcomes.

Problem

• Assess rehabilitation exercise quality using LLMs and feedback
• Overcome lack of textual feedback datasets in rehabilitation
• Integrate AI into virtual platforms for patient recovery

Innovation

• Uses LLMs with prompt engineering for feedback
• Extracts exercise-specific features from skeletal joints
• Integrates into virtual rehabilitation platforms effectively