Background & Aims

Chronic low back pain (CLBP) is a widespread health problem worldwide and a major cause of disability. Accurate and timely detection of the causes and severity of low back pain is crucial for effective treatment and management. Traditional diagnosis methods for low back pain often rely on subjective assessments and are prone to inter-observer variability. The lack of quantifiable metrics to base clinical decisions leads to imprecise treatments, unnecessary surgery, and reduced patient outcomes. In recent years, image processing techniques have emerged as valuable tools for analyzing medical images and providing objective diagnostic information. Brain neuroimaging holds promise for discovering biomarkers that will improve the treatment of chronic LBP. A very high proportion of individuals with LBP (low back pain) usually show no or minimal significant abnormalities in modern spinal imaging.

Methods

Diagnostic Brain Biomarkers
A diagnostic biomarker is defined as one that is “used to detect or confirm the presence of a disease or condition of interest or to identify individuals with a subtype of the disease”. As published in recent study, a review of EEG (Electroencephalogram) patterns in patients with chronic pain especially CLBP reported increased theta and alpha power compared to controls, but results are very diverse. More recent EEG and MEG (Magnetoencephalography) studies used machine learning approaches to discriminate between chronic pain patients and healthy controls. An observation common in a lot of studies showed the identification of highly distributive predictive brain patterns involving all four lobes of brain and cerebellum. In keeping with thalamocortical dysrhythmia theory of chronic pain, CLBP patients have a potency to dwell or stay longer in a state of increased connectivity between the sub-cortical (including the thalamus) and the somatosensory networks.

Results

Potential brain biomarkers for Low back pain (LBP): Cortical thickness (CT) appears to reflect the functional organization of the human cortex and act as a potential marker for the development of LBP. Regional changes in grey matter of the brain have also been reported in several pain studies (Bagarinao et al., 2014; Bernab´eu-Sanz et al., 2020, Lamichhane et al. 2021). Many studies have found morphological changes in cerebral cortical thickness (CT) and resting-state functional connectivity (rsFC) (signal between functionally related brain regions in the absence of any stimulus) measures as some of the potential biomarkers in this space. Studies have found variations between LBP and healthy controls in terms of CT, and structural MRI when correlated with self-reported clinical summary scores, the Physical Component Summary and Mental Component Summary scores. LBP patients often show differences on a structural and functional level within the brain.

Conclusions

Implication on Healthcare Systems: Healthcare costs for LBP in the United States have ballooned to nearly 1 trillion dollars (Dieleman et al., 2016), with a spend of 100-200 billion dollars annually on the treatment, making it one of the costliest diseases in the United States. The diagnosis and treatment of chronic LBP have been complicated by heterogeneous etiologies and neuroimaging modalities that fail to measure central mechanisms of pain (Dieleman et al., 2016). Innovative technologies like Machine learning have shown excellent performance in improving the predictive value of statistics in medical imaging, postoperative clinical outcomes and as the technology which holds a great value for the diagnosis of chronic low back pain.

References

1. Lamichhane B, Jayasekera D, Jakes R, Glasser MF, Zhang J, Yang C, Grimes D, Frank TL, Ray WZ, Leuthardt EC, Hawasli AH. Multi-modal biomarkers of low back pain: A machine learning approach. Neuroimage Clin. 2021;29:102530.
2. Zhang Z, Gewandter JS, Geha P. Brain Imaging Biomarkers for Chronic Pain. Front Neurol. 2022 Jan 3;12:734821.
3. Shahid, M., Vetrimani, Sharma, G., & Tripathi, R. C. (2023). Detection of Low Back Pain Based on Image Processing with Neural Network. International Journal of Intelligent Systems and Applications in Engineering, 11(8s), 455–460.
4. Gaonkar, B., Cook, K., Yoo, B., Salehi, B., Macyszyn, L. (2022). Imaging Biomarker Development for Lower Back Pain Using Machine Learning: How Image Analysis Can Help Back Pain. In: Ossandon, M.R., Baker, H., Rasooly, A. (eds) Biomedical Engineering Technologies. Methods in Molecular Biology, vol 2393.
5. Shim JG, Ryu KH, Cho EA, Ahn JH, Kim HK, Lee YJ, Lee SH. Machine Learning Approaches to Predict Chronic Lower Back Pain in People Aged over 50 Years. Medicina (Kaunas). 2021 Nov 11;57(11):1230.
6. Rockholt MM, Kenefati G, Doan LV, Chen ZS and Wang J (2023) In search of a composite biomarker for chronic pain by way of EEG and machine learning: where do we currently stand? Front. Neurosci. 17:1186418.
7. Bagarinao, E., Johnson, K.A., Martucci, K.T., Ichesco, E., Farmer, M.A., Labus, J., Ness, T. J., Harris, R., Deutsch, G., Apkarian, A.V., Mayer, E.A., Clauw, D.J., Mackey, S., 2014. Preliminary structural MRI based brain classification of chronic pelvic pain: a MAPP network study. Pain 155, 2502–2509
8. Bernab´eu-Sanz, ´A., Moll´a-Torr´o, J.V., L´opez-Celada, S., Moreno L´opez, P., Fern´andez- Jover, E., 2020. MRI evidence of brain atrophy, white matter damage, and functional adaptive changes in patients with cervical spondylosis and prolonged spinal cord compression. Eur. Radiol. 30, 357–369.

Presenting Author

Sebnem Er

Poster Authors

Ashish Bajaj

M.D.

Viatris

Lead Author

Chris Walker

Viatris

Lead Author

Sebnem Er

Viatris

Lead Author

Topics

  • Specific Pain Conditions/Pain in Specific Populations: Low Back Pain