Low-Back Pain Physical Rehabilitation by Movement Analysis in Clinical Trial
This work provides a domain-specific dataset for physical rehabilitation, enabling incremental improvements in intelligent tutoring systems for low-back pain patients.
The authors tackled the problem of developing intelligent tutoring systems for low-back pain rehabilitation by introducing the Keraal dataset, a clinically collected dataset of patient rehabilitation exercises, and benchmarked it on state-of-the-art human movement analysis algorithms to address challenges in motion assessment, error recognition, and localization.
To allow the development and assessment of physical rehabilitation by an intelligent tutoring system, we propose a medical dataset of clinical patients carrying out low back-pain rehabilitation exercises and benchmark on state of the art human movement analysis algorithms. This dataset is valuable because it includes rehabilitation motions in a clinical setting with patients in their rehabilitation program. This paper introduces the Keraal dataset, a clinically collected dataset to enable intelligent tutoring systems (ITS) for rehabilitation. It addresses four challenges in exercise monitoring: motion assessment, error recognition, spatial localization, temporal localization