Machine learning accuracy for assessment of functional movement in Low back pain based on clinically applicable performance Metrics: A systematic review
Bibliographic record
Abstract
• This is the first systematic review to evaluate machine learning (ML) models for assessing functional movement in people with Low back pain (LBP) using psychometric properties. • Kinematic inputs such as IMU sensors and marker-based motion capture systems are commonly used in ML models for movement assessment. • Most studies emphasised binary classification (LBP and healthy) rather than variation within LBP populations. • Criterion validity was the most reported psychometric property, while reliability and measurement error were rarely assessed. • SVMs were the most frequently applied algorithm, but limited exploration of advanced ML models was observed. • Markerless motion capture remains underexplored despite its potential for clinical feasibility. • A dual risk-of-bias approach (NOS and COSMIN) provided insights into study design quality and psychometric rigour. • Validity was the strongest psychometric property whereas reliability and measurement error were consistently weak across studies. To assess whether machine learning (ML) can accurately evaluate functional kinematics in people with low back pain (LBP) when judged by psychometric properties, including validity, reliability, and measurement error. A systematic search of PubMed, Scopus, Web of Science, and IEEE Xplore identified studies applying ML with kinematic inputs for LBP assessment. Risk of bias was assessed using the Newcastle–Ottawa Scale and selected COSMIN domains. Twenty studies met inclusion. Most reported criterion validity via accuracy, while few examined reliability or measurement error. Inertial sensors and support vector machines were the most common methods. ML shows strong validity for LBP movement assessment, but limited psychometric reporting constrains clinical use.
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 | 0.017 | 0.022 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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".