Is there a correlation between dominant extremity and cervical disc herniation using machine learning methods?

Abstract

We aimed to investigate the possibility of determining the relationship between the dominant extremity and cervical disc herniation using a machine learning approach. A total of 561 patients diagnosed with cervical disc herniation were examined for dominant extremity, level and side of cervical disc herniation, and the nature of the herniation (calcified/soft). These patients formed the basis for a two-step machine learning system creation. The first step (included the data of 80% of the patients) focused on determining the type of cervical disc herniation by selecting the top five performing classification models out of 15 different models and tuning the hyperparameters. In the second step, the machine learning system was validated using data from a randomly selected subset of patients (20% of the patients). The study results showed that while most models performed well, the gradient boosting classifier was the most accurate (89.38%) for determining the herniated disc nature. However, for classifying the disc herniation direction, the models did not exhibit strong performance. Thus, machine learning can accurately identify the relationship between cervical disc herniation and dominant extremity with a high degree of accuracy.

Keywords

• machine learning
• artificial intelligence
• disc degeneration
• spinal disease

References

1. 1. McDermott MBA, Wang S, Marinsek N, Ranganath R, Foschini L, Ghassemi M. Reproducibility in machine learning for health research: Still a ways to go. Sci Transl Med. 2021; 13(586): eabb1655. doi: 10.1126/scitranslmed.abb1655.
2. 2. Yin Z, Sulieman LM, Malin BA. A systematic literature review of machine learning in online personal health data. J Am Med Inform Assoc. 2019; 26(6): 561-576. doi: 10.1093/jamia/ocz009.
3. 3. Karabacak M, Margetis K. Machine learning-based prediction of short-term adverse postoperative outcomes in cervical disc arthroplasty patients. World Neurosurg. 2023; 1878-8750(23): 00796-00799. doi: 10.1016/j.wneu.2023.06.025.
4. 4. Vujović, Ž. Classification model evaluation metrics. Int J Adv Comp Sci Appl. 2021; 12(6): 599-606.
5. 5. Scarcia L, Pileggi M, Camilli A, Romi A, Bartolo A, Giubbolini F, et al. Degenerative disc disease of the spine: from anatomy to pathophysiology and radiological appearance, with morphological and functional considerations. J Pers Med. 2022; 12(11): 1810. doi: 10.3390/jpm12111810.
6. 6. Takahashi Y, Yasuhara T, Kumamoto S, Yoneda K, Tanoue T, Nakahara M, et al. Laterality of cervical disc herniation. Eur Spine J. 2013; 22(1): 178-182. doi: 10.1007/s00586-012-2565-8.
7. 7. Kang KC, Lee HS, Lee JH. Cervical radiculopathy focus on characteristics and differential diagnosis. Asian Spine J. 2020; 14(6): 921-930. doi: 10.31616/asj.2020.0647.
8. 8. Fine N, Lively S, Séguin CA, Perruccio AV, Kapoor M, Rampersaud R. Intervertebral disc degeneration and osteoarthritis: a common molecular disease spectrum. Nat Rev Rheumatol. 2023; 19(3): 136-152. doi: 10.1038/s41584-022-00888-z.