Machine Learning for Functional Movement Assessment in People with Low Back Pain: A Systematic Review
Bibliographic record
Abstract
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. 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. 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). This study aims to investigate whether artificial intelligence-based functional movements assessment is valid and reliable in people with low back pain.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".