Hybrid Deep Learning Healthcare AI Framework for Real-Time Human Pose Estimation and Remote Patient Monitoring to Support TKR Physiotherapy
Conference paper
AbouGrad, H., Yegamati, M. and Mather, M. 2025. Hybrid Deep Learning Healthcare AI Framework for Real-Time Human Pose Estimation and Remote Patient Monitoring to Support TKR Physiotherapy. 14th International Conference on Human Interaction & Emerging Technologies: Future Systems and Artificial Intelligence Applications. University of East London, London, United Kingdom 10 - 12 Jun 2025 AHFE Open Access.
Authors | AbouGrad, H., Yegamati, M. and Mather, M. |
---|---|
Type | Conference paper |
Abstract | Total Knee Replacement (TKR) rehabilitation critically depends on precise physiotherapy exercise execution, and the rise of patient volumes and constrained clinical resources limit continuous supervision. This study presents an Artificial Intelligence (AI) framework for real-time assessment and feedback of TKR exercises using deep learning–based human pose estimation to empower remote rehabilitation. We investigate three architectures: a Dense Convolutional Neural Network (DCNN) incorporating frame decoupling for robust joint tracking; a pruned Generative Adversarial Network (Sparse GAN) optimised for computational efficiency; and a novel hybrid model that embeds the DCNN as a discriminator within the GAN model. A diverse dataset of over 10,000 annotated video clips, sourced from clinical environments and public repositories, was processed with OpenCV, and joint annotations were generated using OpenPose. Models were trained and evaluated on standard metrics (i.e. Precision, Recall, F1-score) alongside runtime and memory usage benchmarks. The hybrid architecture achieved the highest classification performance with 86.01% F1-score, which demonstrates the synergetic benefits of combining rich feature extraction with generative refinement, though it incurred elevated computational costs. The Sparse GAN provided faster inference suitable for mobile deployment, with only a marginal decrease in F1-score. The standalone DCNN provided a balance between accuracy and speed, but it did not match the hybrid’s precision. These results highlight a fundamental trade-off between model complexity and real-time usability in AI-driven therapeutic monitoring. The hybrid model is optimal for clinical settings where accuracy is paramount, while the Sparse GAN provides a practical solution for resource-constrained and edge-based applications. Future work will explore model compression, hardware acceleration, and edge-computing strategies to further optimise performance. By demonstrating the viability of advanced pose estimation techniques in a physiotherapy context, this research contributes to the broader discourse on the use of AI in healthcare for scalable, autonomous rehabilitation tools across several medical and wellbeing domains. |
Keywords | Healthcare AI Framework; Remote Rehabilitation; Physiotherapy Patient Monitoring; MedTech; Total Knee Replacement; Dense Convolutional Neural Network; Hybrid DCNN+GAN model |
Year | 2025 |
Conference | 14th International Conference on Human Interaction & Emerging Technologies: Future Systems and Artificial Intelligence Applications |
Publisher | AHFE Open Access |
Accepted author manuscript | License File Access Level Anyone |
Publication process dates | |
Accepted | 04 May 2025 |
Completed | 12 Jun 2025 |
Deposited | 13 May 2025 |
Journal citation | p. In press |
Web address (URL) | https://www.ihiet-fs.org/program.html |
Copyright holder | © 2025 The Authors |
https://repository.uel.ac.uk/item/8z7x6
Restricted files
Accepted author manuscript
36
total views1
total downloads9
views this month0
downloads this month