Using a Motion Sensor to Categorize Low Back Pain Patients: A Machine Learning Approach
Open accessPreprint — published as 10.3390/s20123600 · Paper page
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
Low back pain (LBP) remains a critical health issue impacting literally millions of people worldwide. Currently, clinical practitioners rely on subjective measures such as the STarT Back Screening Tool to categorize LBP patients, which then informs specific treatment regimens. This study sought to develop a machine learning model to classify LBP patients into different groups according to kinematic data. Specifically, an inertial measurement unit (IMU) was attached to each patient’s chest while he performed trunk flexion/extension motions at a self-selected pace. Machine learning algorithms such as support vector machine (SVM) and multi-layer perceptron (MLP) were implemented to evaluate the efficiency of the models. The results showed that the kinematic data we obtained could be used to categorize the patients into two groups: high vs. low-medium risk. We achieved accuracy levels of ~75% and 60% for SVM and MLP, respectively. Additionally, among a range of variables detailed herein, we determined that time-scaled IMU signal resulted in the highest accuracy. Our findings support the use of body-motion measures in developing prognosis tools for healthcare applications. Our results could help overcome the need for objective clinic-based diagnosis approaches, which in turn would lead to assigning better treatment approaches and rehabilitation services for LBP sufferers.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures



Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761
Research works printed but not linked: 50
- 2003, Burden of major musculoskeletal conditions, Bulletin of the World Health Organization, 81, 646
- 2012, Years lived with disability (YLDs) for 1160 sequelae of 289 diseases and injuries 1990–2010: a systematic analysis for the Global Burden of Disease Study 2010, The lancet, 380, 2163, 10.1016/S0140-6736(12)61729-2 · DOI · Paper page
- 2010, Back pain and work, Best Practice & Research Clinical Rheumatology, 24, 227, 10.1016/j.berh.2009.11.007 · DOI
- S. G. Wheeler , J. E. Wipf , T. O. Staiger , R. A. Deyo , and J. G. Jarvik , “Evaluation of low back pain in adults,” UpToDate. April, vol. 27, 2016.
- W. S. G. o. t. B. o. M. C. a. t. S. o. t. N. Millennium, “The burden of musculoskeletal conditions at the start of the new millennium,” World Health Organization technical report series, vol. 919, 2003.
- 2018, What are the most common conditions in primary care?: Systematic review, Canadian Family Physician, 64, 832
- 10.1016/j.math.2010.05.013 · DOI
- 10.1097/BRS.0b013e31815e39f9 · DOI · Paper page
- 10.1007/s00586-010-1502-y · DOI · Paper page
- 10.1136/bmj.38495.686736.E0 · DOI · Paper page
- 2008, A primary care back pain screening tool: identifying patient subgroups for initial treatment, Arthritis Care & Research: Official Journal of the American College of Rheumatology, 59, 632, 10.1002/art.23563 · DOI · Paper page
- 10.1097/01.brs.0000173900.46863.02 · DOI · Paper page
- P. O’SULLIVAN , “Clinical instability’of the lumbar spine: its pathological basis, diagnosis and conservative management,” Grieve’s modern manual therapy: the vertebral column, pp. 311–331, 2004.
- 10.1016/j.math.2005.02.001 · DOI · Paper page
- 2008, A randomised clinical trial of subgrouping and targeted treatment for low back pain compared with best current care. The STarT Back Trial Study Protocol, BMC musculoskeletal disorders, 9, 58, 10.1186/1471-2474-9-58 · DOI · Paper page
- 10.2522/ptj.20120207 · DOI · Paper page
- 2011, Comparison of stratified primary care management for low back pain with current best practice (STarT Back): a randomised controlled trial, The Lancet, 378, 1560, 10.1016/S0140-6736(11)60937-9 · DOI · Paper page
- 10.1016/j.physio.2011.03.003 · DOI
- 10.1136/bmj.b606 · DOI · Paper page
- 2017, A novel approach to spinal 3-D kinematic assessment using inertial sensors: Towards effective quantitative evaluation of low back pain in clinical settings, Comput Biol Med, 89, 144, 10.1016/j.compbiomed.2017.08.002 · DOI
- E. Papi , A. M. Bull , and A. H. McGregor , “Is there evidence to use kinematic/kinetic measures clinically in low back pain patients? A systematic review,” Clinical Biomechanics, 2018. · DOI
- 2006, Effects of pelvic asymmetry and low back pain on trunk kinematics during sitting: a comparison with standing, Spine, 31, E135, 10.1097/01.brs.0000201325.89493.5f · DOI · Paper page
- 2016, Multi-segment analysis of spinal kinematics during sit-to-stand in patients with chronic low back pain, Journal of biomechanics, 49, 2060, 10.1016/j.jbiomech.2016.05.015 · DOI
- 2014, Comparing lumbo-pelvic kinematics in people with and without back pain: a systematic review and meta-analysis, BMC musculoskeletal disorders, 15, 229, 10.1186/1471-2474-15-229 · DOI · Paper page
- 10.1016/0304-3959(85)90285-4 · DOI · Paper page
- 10.1016/j.gaitpost.2008.07.011 · DOI · Paper page
- 10.1016/0022-510X(90)90184-O · DOI · Paper page
- 10.1007/s00167-005-0005-6 · DOI · Paper page
- 10.1093/gerona/glu225 · DOI · Paper page
- R. Varatharajan , G. Manogaran , M. Priyan , and R. Sundarasekar , “Wearable sensor devices for early detection of Alzheimer disease using dynamic time warping algorithm,” Cluster Computing, pp. 1–10, 2017. · DOI · Paper page
- 1993, The role of dynamic three-dimensional trunk motion in occupationally-related low back disorders. The effects of workplace factors, trunk position, and trunk motion characteristics on risk of injury, Spine (Phila Pa 1976), 18, 617, 10.1097/00007632-199304000-00015 · DOI · Paper page
- 1995, The classification of anatomic-and symptom-based low back disorders using motion measure models, Spine (Phila Pa 1976), 20, 2531, 10.1097/00007632-199512000-00013 · DOI · Paper page
- 2005, Differences among outcome measures in occupational low back pain, J Occup Rehabil, 15, 329, 10.1007/s10926-005-5940-4 · DOI
- 2009, Quantification of a meaningful change in low back functional impairment, Spine (Phila Pa 1976), 34, 2060, 10.1097/BRS.0b013e3181b34764 · DOI
- 2000, Impairment magnification during dynamic trunk motions, Spine (Phila Pa 1976), 25, 587, 10.1097/00007632-200003010-00009 · DOI
- 2010, The effect of neck pain on cervical kinematics, as assessed in a virtual environment, Arch Phys Med Rehabil, 91, 1884, 10.1016/j.apmr.2010.09.007 · DOI
- 1982, An approach to backache, British journal of hospital medicine, 28, 187
- 10.1007/BF00541514 · DOI · Paper page
- 10.1016/0304-3959(95)00208-1 · DOI · Paper page
- 10.1111/j.1600-0447.1983.tb09716.x · DOI · Paper page
- S. Kori , “Kinisophobia: a new view of chronic pain behavior,” Pain Manage, pp. 35–43, 1990.
- 2015, Translation and validation of the Persian version of the STarT Back Screening Tool in patients with nonspecific low back pain, Manual therapy, 20, 850, 10.1016/j.math.2015.04.006 · DOI
- 10.1080/03610928308827180 · DOI · Paper page
- 2013, Falls classification using tri-axial accelerometers during the five-times-sit-to-stand test, Gait & posture, 38, 1021, 10.1016/j.gaitpost.2013.05.013 · DOI
- 2012, Quantitative falls risk estimation through multi-sensor assessment of standing balance, Physiological measurement, 33, 2049, 10.1088/0967-3334/33/12/2049 · DOI
- 2017, Fall Risk Assessment Through Automatic Combination of Clinical Fall Risk Factors and Body-Worn Sensor Data, IEEE J Biomed Health Inform, 21, 725, 10.1109/JBHI.2016.2539098 · DOI
- 2017, Feature selection for elderly faller classification based on wearable sensors, Journal of neuroengineering and rehabilitation, 14, 47, 10.1186/s12984-017-0255-9 · DOI · Paper page
- W. Jiang and Z. Yin , “Human activity recognition using wearable sensors by deep convolutional neural networks,” in Proceedings of the 23rd ACM international conference on Multimedia, 2015: Acm, pp. 1307–1310. · DOI · Paper page
- 1993, Two-group classification using neural networks, Decision Sciences, 24, 825, 10.1111/j.1540-5915.1993.tb00491.x · DOI · Paper page
- 2016, Smartphone ownership and internet usage continues to climb in emerging economies, Pew Research Center, 22, 1
Metadata
- Authors
- Abdollahi, M., Ashouri, S., Abedi, M., Azadeh-Fard, N., Parnianpour, M., & Rashedi, E.
- Affiliations
- Rochester Institute of Technology (US)
- RMIT University (AU)
- Shahid Beheshti University (IR)
- Sharif University of Technology (IR)
- Corresponding author
- Rashedi, Ehsan
- Venue
- Sensors
- Publisher
- openRxiv
- Published
- 2019-10-13
- Volume
- 20
- Issue
- 12
- Pages
- 3600-3600
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC7348921
- OpenAlex
- W3038007004
- Cited by
- 69
- References
- 1
- Citations by year
- 2026: 7 · 2025: 17 · 2024: 18 · 2023: 7 · 2022: 10 · 2021: 6 · 2020: 4
- FWCI
- 4.05
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- cc-by
- Locations
- Sensors (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RMIT Research Repository (RMIT University Library) (submittedVersion, other-oa)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Figshare (submittedVersion, cc-by)
- Topics
- Health Sciences › Health Professions › Physical Therapy, Sports Therapy and Rehabilitation › Musculoskeletal pain and rehabilitation
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- non-specific low back pain, risk stratification, inertial measurement unit, trunk kinematics, balance, STarT Back Screening Tool, wearable sensors, trunk flexion and extension, personalized rehabilitation, prognostic tools
- MeSH terms
- Machine Learning, Adult, Biomechanical Phenomena, Humans, Middle Aged, Low Back Pain, Torso
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.