Integrating multidimensional data analytics for precision diagnosis of chronic low back pain

Sam Vickery; Frederick Junker; Rebekka Döding; Daniel L. Belavy; Maia Angelova; Chandan Karmakar; Luis Becker; Nima Taheri; Matthias Pumberger; Sandra Reitmaier; Hendrik Schmidt

doi:10.1038/s41598-025-93106-1

Integrating multidimensional data analytics for precision diagnosis of chronic low back pain

Sam Vickery, Frederick Junker, Rebekka Döding, Daniel L. Belavy, Maia Angelova, Chandan Karmakar, Luis Becker, Nima Taheri, Matthias Pumberger, Sandra Reitmaier, Hendrik Schmidt^*

^*Corresponding author for this work

Aston Digital Futures Institute

Research output: Contribution to journal › Article › peer-review

1 Citation (SciVal)

21 Downloads (Pure)

Abstract

Low back pain (LBP) is a leading cause of disability worldwide, with up to 25% of cases become chronic (cLBP). Whilst multi-factorial, the relative importance of contributors to cLBP remains unclear. We leveraged a comprehensive multi-dimensional data-set and machine learning-based variable importance selection to identify the most effective modalities for differentiating whether a person has cLBP. The dataset included questionnaire data, clinical and functional assessments, and spino-pelvic magnetic resonance imaging (MRI), encompassing a total of 144 parameters from 1,161 adults with (n = 512) and without cLBP (n = 649). Boruta and random forest were utilised for variable importance selection and cLBP classification respectively. A multimodal model including questionnaire, clinical, and MRI data was the most effective in differentiating people with and without cLBP. From this, the most robust variables (n = 9) were psychosocial factors, neck and hip mobility, as well as lower lumbar disc herniation and degeneration. This finding persisted in an unseen holdout dataset. Beyond demonstrating the importance of a multi-dimensional approach to cLBP, our findings will guide the development of targeted diagnostics and personalized treatment strategies for cLBP patients.

Original language	English
Article number	9675
Number of pages	14
Journal	Scientific Reports
Volume	15
Issue number	1
Early online date	20 Mar 2025
DOIs	https://doi.org/10.1038/s41598-025-93106-1
Publication status	Published - Dec 2025

Bibliographical note

Copyright © The Author(s) 2025. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/

Data Access Statement

All results in this study are provided in the (Supplementary) tables. The Berlin Back study is currently ongoing (end date 31/12/2025) and therefore the raw data used in this manuscript cannot be provided. The raw data will be openly released from the Berlin Back Study as per agreement with the funding agency following the completion of the data acquisition. A link to the raw data will be provided on the Github repository where the analysis code is located (https://github.com/viko18/BerlinBack_FeatImp/) when it is made available.

Keywords

Data-driven
Classification
Multi-modality
Psychosocial
MRI
Feature selection
Chronic low back pain

Access to Document

10.1038/s41598-025-93106-1Licence: CC BY 4.0

Supplementary tables_41598_2025_93106_MOESM1_ESM.pdf
Copyright © The Author(s) 2025. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/
Accepted author manuscript, 13.1 MBLicence: CC BY 4.0
S Vickery et al_Integrating multidimensional data analytics for precision diagnosis of chronic low back pain
Copyright © The Author(s) 2025. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/
Final published version, 1.8 MBLicence: CC BY 4.0

Cite this

@article{c236e1ea67744efbbf14f56b49318d74,

title = "Integrating multidimensional data analytics for precision diagnosis of chronic low back pain",

abstract = "Low back pain (LBP) is a leading cause of disability worldwide, with up to 25% of cases become chronic (cLBP). Whilst multi-factorial, the relative importance of contributors to cLBP remains unclear. We leveraged a comprehensive multi-dimensional data-set and machine learning-based variable importance selection to identify the most effective modalities for differentiating whether a person has cLBP. The dataset included questionnaire data, clinical and functional assessments, and spino-pelvic magnetic resonance imaging (MRI), encompassing a total of 144 parameters from 1,161 adults with (n = 512) and without cLBP (n = 649). Boruta and random forest were utilised for variable importance selection and cLBP classification respectively. A multimodal model including questionnaire, clinical, and MRI data was the most effective in differentiating people with and without cLBP. From this, the most robust variables (n = 9) were psychosocial factors, neck and hip mobility, as well as lower lumbar disc herniation and degeneration. This finding persisted in an unseen holdout dataset. Beyond demonstrating the importance of a multi-dimensional approach to cLBP, our findings will guide the development of targeted diagnostics and personalized treatment strategies for cLBP patients.",

keywords = "Data-driven, Classification, Multi-modality, Psychosocial, MRI, Feature selection, Chronic low back pain",

author = "Sam Vickery and Frederick Junker and Rebekka D{\"o}ding and Belavy, {Daniel L.} and Maia Angelova and Chandan Karmakar and Luis Becker and Nima Taheri and Matthias Pumberger and Sandra Reitmaier and Hendrik Schmidt",

note = "Copyright {\textcopyright} The Author(s) 2025. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/",

year = "2025",

month = dec,

doi = "10.1038/s41598-025-93106-1",

language = "English",

volume = "15",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "Nature Publishing Group",

number = "1",

}

TY - JOUR

T1 - Integrating multidimensional data analytics for precision diagnosis of chronic low back pain

AU - Vickery, Sam

AU - Junker, Frederick

AU - Döding, Rebekka

AU - Belavy, Daniel L.

AU - Angelova, Maia

AU - Karmakar, Chandan

AU - Becker, Luis

AU - Taheri, Nima

AU - Pumberger, Matthias

AU - Reitmaier, Sandra

AU - Schmidt, Hendrik

N1 - Copyright © The Author(s) 2025. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/

PY - 2025/12

Y1 - 2025/12

N2 - Low back pain (LBP) is a leading cause of disability worldwide, with up to 25% of cases become chronic (cLBP). Whilst multi-factorial, the relative importance of contributors to cLBP remains unclear. We leveraged a comprehensive multi-dimensional data-set and machine learning-based variable importance selection to identify the most effective modalities for differentiating whether a person has cLBP. The dataset included questionnaire data, clinical and functional assessments, and spino-pelvic magnetic resonance imaging (MRI), encompassing a total of 144 parameters from 1,161 adults with (n = 512) and without cLBP (n = 649). Boruta and random forest were utilised for variable importance selection and cLBP classification respectively. A multimodal model including questionnaire, clinical, and MRI data was the most effective in differentiating people with and without cLBP. From this, the most robust variables (n = 9) were psychosocial factors, neck and hip mobility, as well as lower lumbar disc herniation and degeneration. This finding persisted in an unseen holdout dataset. Beyond demonstrating the importance of a multi-dimensional approach to cLBP, our findings will guide the development of targeted diagnostics and personalized treatment strategies for cLBP patients.

AB - Low back pain (LBP) is a leading cause of disability worldwide, with up to 25% of cases become chronic (cLBP). Whilst multi-factorial, the relative importance of contributors to cLBP remains unclear. We leveraged a comprehensive multi-dimensional data-set and machine learning-based variable importance selection to identify the most effective modalities for differentiating whether a person has cLBP. The dataset included questionnaire data, clinical and functional assessments, and spino-pelvic magnetic resonance imaging (MRI), encompassing a total of 144 parameters from 1,161 adults with (n = 512) and without cLBP (n = 649). Boruta and random forest were utilised for variable importance selection and cLBP classification respectively. A multimodal model including questionnaire, clinical, and MRI data was the most effective in differentiating people with and without cLBP. From this, the most robust variables (n = 9) were psychosocial factors, neck and hip mobility, as well as lower lumbar disc herniation and degeneration. This finding persisted in an unseen holdout dataset. Beyond demonstrating the importance of a multi-dimensional approach to cLBP, our findings will guide the development of targeted diagnostics and personalized treatment strategies for cLBP patients.

KW - Data-driven

KW - Classification

KW - Multi-modality

KW - Psychosocial

KW - MRI

KW - Feature selection

KW - Chronic low back pain

UR - https://www.nature.com/articles/s41598-025-93106-1

UR - http://www.scopus.com/inward/record.url?scp=105000514543&partnerID=8YFLogxK

U2 - 10.1038/s41598-025-93106-1

DO - 10.1038/s41598-025-93106-1

M3 - Article

SN - 2045-2322

VL - 15

JO - Scientific Reports

JF - Scientific Reports

IS - 1

M1 - 9675

ER -

Integrating multidimensional data analytics for precision diagnosis of chronic low back pain

Abstract

Bibliographical note

Data Access Statement

Keywords

Access to Document

Other files and links

Fingerprint

Cite this