BACK-to-MOVE: Machine learning and computer vision model automating clinical classification of non-specific low back pain for personalised management

Hartley, Thomas, Hicks, Yulia ORCID: https://orcid.org/0000-0002-7179-4587, Davies, Jennifer L. ORCID: https://orcid.org/0000-0001-7635-4815, Cazzola, Dario and Sheeran, Liba ORCID: https://orcid.org/0000-0002-1502-764X 2024. BACK-to-MOVE: Machine learning and computer vision model automating clinical classification of non-specific low back pain for personalised management. PLoS ONE 19 (5) , e0302899. 10.1371/journal.pone.0302899

PDF - Published Version Available under License Creative Commons Attribution. Download (1MB)

Abstract

Background: Low back pain (LBP) is a major global disability contributor with profound health and socio-economic implications. The predominant form is non-specific LBP (NSLBP), lacking treatable pathology. Active physical interventions tailored to individual needs and capabilities are crucial for its management. However, the intricate nature of NSLBP and complexity of clinical classification systems necessitating extensive clinical training, hinder customised treatment access. Recent advancements in machine learning and computer vision demonstrate promise in characterising NSLBP altered movement patters through wearable sensors and optical motion capture. This study aimed to develop and evaluate a machine learning model (i.e., ’BACK-to-MOVE’) for NSLBP classification trained with expert clinical classification, spinal motion data from a standard video alongside patient-reported outcome measures (PROMs). Methods: Synchronised video and three-dimensional (3D) motion data was collected during forward spinal flexion from 83 NSLBP patients. Two physiotherapists independently classified them as motor control impairment (MCI) or movement impairment (MI), with conflicts resolved by a third expert. The Convolutional Neural Networks (CNNs) architecture, HigherHRNet, was chosen for effective pose estimation from video data. The model was validated against 3D motion data (subset of 62) and trained on the freely available MS-COCO dataset for feature extraction. The Back-to-Move classifier underwent fine-tuning through feed-forward neural networks using labelled examples from the training dataset. Evaluation utilised 5-fold cross-validation to assess accuracy, specificity, sensitivity, and F1 measure. Results: Pose estimation’s Mean Square Error of 0.35 degrees against 3D motion data demonstrated strong criterion validity. Back-to-Move proficiently differentiated MI and MCI classes, yielding 93.98% accuracy, 96.49% sensitivity (MI detection), 88.46% specificity (MCI detection), and an F1 measure of .957. Incorporating PROMs curtailed classifier performance (accuracy: 68.67%, sensitivity: 91.23%, specificity: 18.52%, F1: .800). Conclusion: This study is the first to demonstrate automated clinical classification of NSLBP using computer vision and machine learning with standard video data, achieving accuracy comparable to expert consensus. Automated classification of NSLBP based on altered movement patters video-recorded during routine clinical examination could expedite personalised NSLBP rehabilitation management, circumventing existing healthcare constraints. This advancement holds significant promise for patients and healthcare services alike.

Item Type:	Article
Date Type:	Published Online
Status:	Published
Schools:	Advanced Research Computing @ Cardiff (ARCCA) Computer Science & Informatics Engineering Healthcare Sciences
Additional Information:	License information from Publisher: LICENSE 1: URL: http://creativecommons.org/licenses/by/4.0/
Publisher:	Public Library of Science
Funders:	Wellcome Trust
Date of First Compliant Deposit:	13 May 2024
Date of Acceptance:	15 April 2024
Last Modified:	17 Jun 2024 12:28
URI:	https://orca.cardiff.ac.uk/id/eprint/168866

Actions (repository staff only)

Edit Item