Machine learning in the diagnosis, management, and care of patients with low back pain: a scoping review of the literature and future directions.
Date
2024-09
Journal Title
Journal ISSN
Volume Title
Citation Stats
Attention Stats
Abstract
Background context
Low back pain (LBP) remains the leading cause of disability globally. In recent years, machine learning (ML) has emerged as a potentially useful tool to aid the diagnosis, management, and prognostication of LBP.Purpose
In this review, we assess the scope of ML applications in the LBP literature and outline gaps and opportunities.Study design/setting
A scoping review was performed in accordance with the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) guidelines.Methods
Articles were extracted from the Web of Science, Scopus, PubMed, and IEEE Xplore databases. Title/abstract and full-text screening was performed by two reviewers. Data on model type, model inputs, predicted outcomes, and ML methods were collected.Results
In total, 223 unique studies published between 1988 and 2023 were identified, with just over 50% focused on low-back-pain detection. Neural networks were used in 106 of these articles. Common inputs included patient history, demographics, and lab values (67% total). Articles published after 2010 were also likely to incorporate imaging data into their models (41.7% of articles). Of the 212 supervised learning articles identified, 168 (79.4%) mentioned use of a training or testing dataset, 116 (54.7%) utilized cross-validation, and 46 (21.7%) implemented hyperparameter optimization. Of all articles, only 8 included external validation and 9 had publicly available code.Conclusions
Despite the rapid application of ML in LBP research, a majority of articles do not follow standard ML best practices. Furthermore, over 95% of articles cannot be reproduced or authenticated due to lack of code availability. Increased collaboration and code sharing are needed to support future growth and implementation of ML in the care of patients with LBP.Type
Department
Description
Provenance
Subjects
Citation
Permalink
Published Version (Please cite this version)
Publication Info
Seas, Andreas, Tanner J Zachem, Bruno Valan, Christine Goertz, Shiva Nischal, Sully F Chen, David Sykes, Troy Q Tabarestani, et al. (2024). Machine learning in the diagnosis, management, and care of patients with low back pain: a scoping review of the literature and future directions. The spine journal : official journal of the North American Spine Society. p. S1529-9430(24)01029-5. 10.1016/j.spinee.2024.09.010 Retrieved from https://hdl.handle.net/10161/31599.
This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.
Collections
Scholars@Duke
Andreas Seas
Tanner Zachem
Christine Goertz
Christine Goertz, D.C., Ph.D., is a Professor in Musculoskeletal Research and Vice Chair for Implementation of Spine Health Innovations in the Department of Orthopaedic Surgery at Duke University School of Medicine. She spearheaded the development and implementation of the Duke Spine Health Program and leads interdisciplinary teams to design and implement clinical research studies that increase understanding of the effectiveness of patient-centered, non-drug treatments for spine-related disorders. Dr. Goertz has co-authored more than 150 scientific papers, and her work has been cited more than 7000 thousand times. She has received nearly $45M in federal funding as a principal investigator and was ranked in the top 10 for NIH funding among investigators in the Medical School Department of Orthopedics by the Blue Ridge Institute for Medical Research in 2022, 2023, and 2024. Dr. Goertz has previously served as a Member of the Interagency Pain Research Coordinating Committee, the Centers for Disease Control and Prevention’s Opioid Working Group, and as Chairperson of the Board of Governors for the Patient Centered Outcomes Research Institute. She is also the author of the book Take Your Back Back: Whole Health Healing for Low Back Pain, which Simon and Schuster will release on October 6, 2026. Dr. Goertz received her Doctor of Chiropractic degree from Northwestern Health Sciences University in 1991 and her Ph.D. in Health Services Research, Policy, and Administration from the School of Public Health at the University of Minnesota in 1999.
Beth Blackwood
Beth Blackwood (she, her) is a Research & Education Librarian at the Medical Center Library & Archives, where she serves as the Lead for Research Impact and the Liaison to the Department of Global Health. Her primary duties focus on assisting researchers and administrators with bibliometric questions and program evaluations, as well as specialized teaching and searching. Prior to Duke, she served as the Digital Archivist & Data Librarian at California State University Channel Islands, where she on-boarded a variety of new library infrastructure, developed and taught for-credit courses in data and algorithmic literacy, and implemented data management best practices across campus.
Oren N Gottfried
I specialize in the surgical management of all complex cervical, thoracic, lumbar, or sacral spinal diseases by using minimally invasive as well as standard approaches for arthritis or degenerative disease, deformity, tumors, and trauma. I have a special interest in the treatment of thoracolumbar deformities, occipital-cervical problems, and in helping patients with complex spinal issues from previously unsuccessful surgery or recurrent disease.I listen to my patients to understand their symptoms and experiences so I can provide them with the information and education they need to manage their disease. I make sure my patients understand their treatment options, and what will work best for their individual condition. I treat all my patients with care and concern – just as I would treat my family. I am available to address my patients' concerns before and after surgery. I aim to improve surgical outcomes for my patients and care of all spine patients with active research evaluating clinical and radiological results after spine surgery with multiple prospective databases. I am particularly interested in prevention of spinal deformity, infections, complications, and recurrent spinal disease. Also, I study whether patient specific variables including pelvic/sacral anatomy and sagittal spinal balance predict complications from spine surgery.
Christopher Ignatius Shaffrey
I have more than 25 years of experience treating patients of all ages with spinal disorders. I have had an interest in the management of spinal disorders since starting my medical education. I performed residencies in both orthopaedic surgery and neurosurgery to gain a comprehensive understanding of the entire range of spinal disorders. My goal has been to find innovative ways to manage the range of spinal conditions, straightforward to complex. I have a focus on managing patients with complex spinal disorders. My patient evaluation and management philosophy is to provide engaged, compassionate care that focuses on providing the simplest and least aggressive treatment option for a particular condition. In many cases, non-operative treatment options exist to improve a patient’s symptoms. I have been actively engaged in clinical research to find the best ways to manage spinal disorders in order to achieve better results with fewer complications.
Muhammad Abd-El-Barr
As a Neurosurgeon with fellowship training in Spine Surgery, I have dedicated my professional life to treating patients with spine disorders. These include spinal stenosis, spondylolisthesis, scoliosis, herniated discs and spine tumors. I incorporate minimally-invasive spine (MIS) techniques whenever appropriate to minimize pain and length of stay, yet not compromise on achieving the goals of surgery, which is ultimately to get you back to the quality of life you once enjoyed. I was drawn to medicine and neurosurgery for the unique ability to incorporate the latest in technology and neuroscience to making patients better. I will treat you and your loved ones with the same kind of care I would want my loved ones to be treated with. In addition to my clinical practice, I will be working with Duke Bioengineers and Neurobiologists on important basic and translational questions surrounding spinal cord injuries (SCI), which we hope to bring to clinical relevance.
Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.