BackTracker: Machine learning to identify kinematic phenotypes for personalised exercise management in non-specific low back pain

Liu, Zebang, Hicks, Yulia and Sheeran, Liba ORCID: https://orcid.org/0000-0002-1502-764X 2026. BackTracker: Machine learning to identify kinematic phenotypes for personalised exercise management in non-specific low back pain. International Journal of Medical Informatics 211 , 106335. 10.1016/j.ijmedinf.2026.106335

PDF - Published Version Available under License Creative Commons Attribution. Download (2MB)

Abstract

Background Low back pain (LBP) is a leading cause of global disability. Most cases are non-specific (NSLBP) and lack identifiable causes. Early active management is endorsed by clinical guidelines; however, exercises are rarely customised despite substantial variability in impairments. Existing classification systems can support targeted rehabilitation but require extensive clinical training and lengthy assessment procedures, limiting timely personalised care. Objective This study used AI methods to identify the two most common motor control impairments (MCIs)—flexion and extension patterns (FP/EP)—in NSLBP. The approach used spinal silhouettes extracted from movement videos to enable self-phenotyping and guide personalised exercise selection. Methods Data were collected from a research fellowship involving ninety NSLBP participants classified by an expert physiotherapist (LS) into FP or EP MCIs. Participants performed standard forward- and backward-bend tasks recorded in the sagittal plane. Pose estimation and instance segmentation techniques were applied to extract motion features and spine silhouettes. From each participant, a curated set of 80 black-and-white back images captured at specific bending angles was produced. These features were used to train a feedforward neural network. Model performance was assessed using five-fold cross-validation with accuracy, sensitivity, specificity, F1 score and AUC. Results The model achieved a diagnostic accuracy of 91.91% (95% CI 84.8–99.1) for backward-bend videos, exceeding reported inter-examiner agreement rates for trained physiotherapists. Robustness was supported by a mean AUC of 0.9422. Accuracy was lower for forward-bend images (86.69%), combined tasks (86.29%), or PROMs alone (63.82%). Adding PROMs to forward- or backward-bend tasks provided only modest improvements (66.32% and 71.62%, respectively). Conclusion The model reliably distinguished between FP and EP NSLBP subgroups, demonstrating the potential of AI to support timely personalised rehabilitation. The integration of PROMs with motion features reduced classification accuracy, suggesting that self-reported outcomes may provide limited benefit when tailoring exercises to specific physical impairments.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Schools > Healthcare Sciences
Additional Information:	License information from Publisher: LICENSE 1: Title: This article is under embargo with an end date yet to be finalised.
Publisher:	Elsevier
ISSN:	1386-5056
Date of First Compliant Deposit:	16 February 2026
Date of Acceptance:	2 February 2026
Last Modified:	16 Feb 2026 15:00
URI:	https://orca.cardiff.ac.uk/id/eprint/184886

Actions (repository staff only)

Edit Item