Research Article

Predicting Trunk Muscle Activity in Chronic Low Back Pain: Development of a Supervised Machine Learning Model

Abstract

Background: Recently the adoption of machine learning has significantly increased across various applications, including prediction of diseases based on person’s clinical profile. This study aimed to develop and evaluate a supervised machine learning to predict trunk muscle’s activity in people with chronic low back pain.
Methods: This was a secondary analysis of data from a subgroup of people with nonspecific chronic low back pain. The correlation between labeled data and the output data of muscle activity level was measured through surface electromyography. The result showed a good correlation, suggesting the potential utility of this approach in distinguishing individuals with low back pain from pain-free controls.
Results: to validate the performance of the developed machine learning, the results were compared with SPSS. The model’s predictive performance was further assessed using various evaluation methods including area under the receiver operating characteristics curve. The study's findings indicate that the model achieved Area Under the Curve (AUC) values ranging from 0.5 to 0.9 across all muscles and different tasks for people with back pain. In contrast, the pain-free group exhibited AUC values between 0.4 and 0.8.
Conclusion: The findings suggest that the supervised machine learning approach using logistic regression may offer clinically meaningful predictions in defining the differences in trunk muscle activity between individuals with non-specific chronic low back pain and pain-free controls. While the obtained results demonstrate promise, further studies need to enhance the model's performance and achieve a more accurate estimation of muscle activity levels.

1. Andersson GB. Epidemiological features of chronic low-back pain. The lancet. 1999;354(9178):581-5.
2. Cho KH, Beom JW, Lee TS, Lim JH, Lee TH, Yuk JH. Trunk muscles strength as a risk factor for nonspecific low back pain: a pilot study. Ann Rehabil Med. 2014;38(2):234.
3. Shim J-G, Ryu K-H, Cho E-A, Ahn JH, Kim HK, Lee Y-J, et al. Machine learning approaches to predict chronic lower back pain in people aged over 50 years. Medicina. 2021;57(11):1230.
4. O'Sullivan P. It's time for change with the management of non-specific chronic low back pain. BMJ sport Med; 2012. p. 224-7.
5. Gordon R, Bloxham S, editors. A systematic review of the effects of exercise and physical activity on non-specific chronic low back pain. Healthcare; 2016: MDPI.
6. van Dieën JH, Selen LP, Cholewicki J. Trunk muscle activation in low-back pain patients, an analysis of the literature. J EMG Kinesiol. 2003;13(4):333-51.
7. Salamat S, Talebian S, Maroufi N, Kalbassi G, Salamat D, O’Sullivan K. People With Low Back Pain Exhibit Higher Trunk Muscle Activity and Impaired Postural Control During Static and Dynamic Functional Tasks: A Cross-Sectional Study. J App Biomech. 2023;40(1):1-8.
8. Tagliaferri SD, Owen PJ, Miller CT, Angelova M, Fitzgibbon BM, Wilkin T, et al. Towards data-driven biopsychosocial classification of non-specific chronic low back pain: a pilot study. Scie Reports. 2023;13(1):13112.
9. Hartley T, Hicks Y, Davies JL, Cazzola D, Sheeran L. BACK-to-MOVE: Machine learning and computer vision model automating clinical classification of non-specific low back pain for personalised management. Plos one. 2024;19(5):e0302899.
10. Kadhim MA. FNDSB: A fuzzy-neuro decision support system for back pain diagnosis. Cogn Syst Res. 2018;52:691-700.
11. Amorim P, Paulo JR, Silva PA, Peixoto P, Castelo-Branco M, Martins H. Machine learning applied to low back pain rehabilitation–a systematic review. Int J Digit Health. 2021;1(1):10.
12. Sidey-Gibbons JA, Sidey-Gibbons CJ. Machine learning in medicine: a practical introduction. BMC medical research methodology. 2019;19:1-18.
13. Caldo D, Bologna S, Conte L, Amin MS, Anselma L, Basile V, et al. Machine learning algorithms distinguish discrete digital emotional fingerprints for web pages related to back pain. Sci Rep. 2023;13(1):4654.
14. Mizuguchi Y, Nakao M, Nagai T, Takahashi Y, Abe T, Kakinoki S, et al. Machine learning–based gait analysis to predict clinical frailty scale in elderly patients with heart failure. Europ Heart J Digit Health. 2024;5(2):152-62.
15. Yoon M, Park JJ, Hur T, Hua C-H, Hussain M, Lee S, et al. Application and Potential of Artificial Intelligence in Heart Failure: Past, Present, and Future. IntJ Heart Fail. 2024;6(1):11.
16. Hartman DJ. Applications of Artificial Intelligence in Lung Pathology. Surg Pathol Clin. 2023.
17. Salamat S, Talebian S, Bagheri H, Maroufi N, Shaterzadeh MJ, Kalbasi G, et al. Effect of movement control and stabilization exercises in people with extension related non-specific low back pain-a pilot study. J Bodyw Mov Ther. 2017;21(4):860-5.
18. Dankaerts W, O'Sullivan P, Burnett A, Straker L. Altered patterns of superficial trunk muscle activation during sitting in nonspecific chronic low back pain patients: importance of subclassification. Spine. 2006;31(17):2017-23.
19. Chen B. From Logistic Regression to Deep Learning: Machine Learning Advances for Credit Card Churn. IJERMCA. 2024;13(2).
20. Rescio G, Leone A, Siciliano P. Supervised machine learning scheme for electromyography-based pre-fall detection system. Expert Syst Appl. 2018;100:95-105.
21. Kutrani H, Eltalhi S, Ashleik N, editors. Predicting factors influencing survival of breast cancer patients using logistic regression of machine learning. The 7th International Conference on Engineering & MIS 2021; 2021.
22. Jinjri WM, Keikhosrokiani P, Abdullah NL, editors. Machine learning algorithms for the classification of cardiovascular disease-A comparative study. 2021 International Conference on Information Technology (ICIT); 2021: IEEE.
23. Barbosa VP, Said dos Reis JLM, von Zuben de Valega Negrão C, Barboza VR, Simoes Marcondes KCB, Rezende EP, et al. Machine Learning Model to Predict Allocation of Patients with Chronic Back Pain for Integrated Practice Units in a System of Value-based Health Care. medRxiv. 2023:2023.11. 05.23298111.
24. Rahman MM, Hossain MB, Sayed A, Thakur S. ASSESSMENT OF LIQUEFACTION POTENTIAL BASED ON THE LOGISTIC REGRESSION MACHINE LEARNING ALGORITHM.
25. Mohsen S, Sadeghijam M, Talebian S, Pourbakht A. Use of Some Relevant Parameters for Primary Prediction of Brain Activity in Idiopathic Tinnitus Based on a Machine Learning Application. Audiol Neurotol. 2023;28(6):446-57.
26. Joensuu L, Rautiainen I, Hautala A, Siekkinen K, Pirnes K, Tammelin TH. Prediction of multisite pain incidence in adolescence using a machine learning approach. medRxiv. 2023:2023.07. 04.23292222.
27. Nasr A, Inkol KA, Bell S, McPhee J. InverseMuscleNET: alternative machine learning solution to static optimization and inverse muscle modeling. Front Comput Neuroscie. 2021;15:759489.
28. Kizyte A, Lei Y, Wang R. Influence of Input Features and EMG Type on Ankle Joint Torque Prediction With Support Vector Regression. IEEE Trans Neural Syst Rehabil Eng. 2023.
29. Wu D, Yang J, Sawan M. Transfer learning on electromyography (EMG) tasks: approaches and beyond. IEEE Trans Neural Syst Rehabil Eng. 2023.
30. Michelsen C, Jørgensen CC, Heltberg M, Jensen MH, Lucchetti A, Petersen PB, et al. Machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty—a comparative study. BMC anesthesiol. 2023;23(1):391.
IssueArticles in Press QRcode
SectionResearch Article(s)
Keywords
Chronic low back pain; artificial intelligence; machine learning; trunk muscle activity
Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
1.
Salamat S, Montazeri V, Talebian S. Predicting Trunk Muscle Activity in Chronic Low Back Pain: Development of a Supervised Machine Learning Model. jmr. 2025;(-).