This study aims to investigate whether artificial intelligence-based functional movements assessment is valid and reliable in people with low back pain.
A systematic review was conducted across five databases (MEDLINE, Embase, Scopus, SportDiscus, and CINAHL) from inception to 2024. Inclusion criteria included experimental or observational studies conducted in adults aged 18 to 65 with low back pain. Included studies utilised machine learning algorithms in the assessment of functional movements and reported clinometric properties of their machine learning algorithms (e.g., reliability, validity, specificity, sensitivity). Independent screening was conducted by two reviewers. Two reviewers performed the data extraction and quality assessment. Quality assessment of the studies was performed using the Newcastle-Ottawa Scale and COSMIN tool. The systematic review was registered prospectively in PROSPERO (ID: CRD42024540218).
Ten articles were included in the review. Construct validity was reported in eight studies, whereas two studies reported criterion validity. Only five studies demonstrated a low risk of bias (scoring 7 or above on the Newcastle-Ottawa Scale), and no study demonstrated adequate or good reliability on the COSMIN scale. Seven studies reported high accuracy of artificial intelligence-based movement analysis (75-97%). Overall, artificial intelligence-based analysis demonstrated high sensitivity (80-100%), specificity (80-95%) and diagnostic accuracy (Area Under Receiver Operating Characteristic curve of 0.85-0.99).
Artificial intelligence could offer a promising solution to assess functional movements in people with low back pain in the clinical setting in the near future. However, more studies are required to investigate the reliability of artificial intelligence-based functional movement analysis in people with low back pain before applying it in the clinical setting.
Artificial Intelligence-based functional movement assessment provides precise, real-time kinematic data, enhancing diagnosis and personalised treatment for low back pain.
Adoption of Artificial Intelligence technology could streamline the assessment process and reduce variability in clinical evaluations.
Further validation and standardisation of this technology are necessary to ensure reliability and practical utility in clinical settings.
low back pain
movement analysis
