Low-Back Pain Physical Rehabilitation by Movement Analysis in Clinical Trial

TL;DR

This paper introduces the Keraal dataset, a clinical collection of low-back pain rehabilitation exercises designed to enable intelligent tutoring systems and benchmark human movement analysis algorithms in a real-world medical setting.

Contribution

It provides a novel, clinically collected dataset for low-back pain rehabilitation exercises to advance intelligent tutoring systems and movement analysis methods.

Findings

Benchmark results of state-of-the-art algorithms on the Keraal dataset

Identification of key challenges in exercise monitoring

Potential improvements in rehabilitation assessment accuracy

Abstract

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