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

Thomas Hartley, Yulia Hicks, Jennifer L Davies, Dario Cazzola, Liba Sheeran

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish
Article numbere0302899
Number of pages21
JournalPLoS ONE
Issue number5
Early online date10 May 2024
Publication statusPublished - 15 May 2024

Data Availability Statement

Due to ethical considerations regarding privacy, the video data utilized in this study cannot be shared publicly as they may contain potentially identifying and sensitive information, such as tattoos, birthmarks, sex, ethnicity, and unique movement characteristics. Complete de-identification, noise addition, or blocking of portions of the dataset while preserving its usefulness to replicate study results is not feasible. However, external requests for access to the data can be directed to Professor Valerie Sparkes at


  • Humans
  • Low Back Pain/therapy
  • Machine Learning
  • Male
  • Female
  • Adult
  • Middle Aged
  • Neural Networks, Computer
  • Movement
  • Precision Medicine/methods
  • Patient Reported Outcome Measures

Cite this