Enhancing Rehabilitation Assessment with Artificial Intelligence: A Comprehensive Investigation of Posture Quality Prediction Using Machine Learning
This paper comprehensively reviews the application of Artificial Intelligence (AI) in rehabilitation exercise assessment, with a particular focus on posture quality prediction. AI techniques, including Support Vector Machines (SVM), decision trees, random forests, Convolutional Neural Networks (CNN)...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | ITM Web of Conferences |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_02025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This paper comprehensively reviews the application of Artificial Intelligence (AI) in rehabilitation exercise assessment, with a particular focus on posture quality prediction. AI techniques, including Support Vector Machines (SVM), decision trees, random forests, Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN), show great potential in improving the accuracy and personalization of rehabilitation assessment. Various supervised and unsupervised learning methods are analyzed and their effectiveness in classifying rehabilitation movements and providing real-time feedback to improve rehabilitation outcomes is demonstrated. Despite some progress in the application of AI techniques in rehabilitation exercises, some challenges remain, especially in terms of model interpretability, generalizability to different patient populations, and handling differences in data distribution between clinical and home settings. Techniques such as Explainable Artificial Intelligence (XAI), transfer learning, and privacy-preserving machine learning can be a way to unlock the limitations of adopting AI techniques in a wider range of rehabilitation settings. This paper concludes by highlighting the need for more adaptable and interpretable AI systems that can be seamlessly integrated into different rehabilitation scenarios while maintaining patient data privacy and ethical standards. |
|---|---|
| ISSN: | 2271-2097 |