Machine Learning Models for Analyzing Nerve Conduction Velocity

Document Type : Original Paper

Authors

1 Department of Physics, Faculty of Sciences, Arak University, Arak 38156-8-8349, Iran

2 Department of Radiotherapy and Medical Physics, Arak University of Medical Sciences and Khonsari Hospital, Arak, Iran

3 Industrial and Systems Engineering, Tarbiat Modares University, Tehran 4117-13114, Iran

10.22038/ijmp.2025.85526.2502

Abstract

Introduction: The objective of this study was to utilize Machine Learning (ML) techniques to assess the conduction of nerves located in the upper extremities, specifically the median, ulnar, and radial nerves. The study aimed to establish normal values for nerve conduction (NC) and evaluate the influence of variables such as gender, age, weight, and height on NC.
Material and Methods: Electrodiagnostic tests were employed to assess the conduction of both motor and sensory nerves. ML techniques were applied to analyze the data and predict NC values. The study considered historical background and thorough medical assessments to ensure the absence of any NC agents or underlying medical conditions.
Results: The investigation successfully established normal values for NC. The ML models demonstrated favorable performance in predicting NC values, considering the influence of variables such as gender, age, weight, and height.
Conclusion: The study successfully established normal values for nerve conduction in the upper extremities and demonstrated the effectiveness of ML models in predicting NC values. These findings highlight the potential of ML techniques in enhancing the assessment and understanding of nerve conduction, considering various influencing factors. However, this study has limitations, including its single-center design and a relatively small female cohort, which may affect the generalizability of the results.

Keywords

Main Subjects


  1. Bolton CF, Carter KM. Human sensory nerve compound action potential amplitude: Variation with sex and finger circumference. J Neurol Neurosurg Psychiatry. 1980;43: 925-8.
  2. Aminoff MJ, Daube JR. Electrodiagnosis in Clinical Neurology. 4th ed. New York: Churchill Livingstone. 1986: 253-290.
  3. Jayasinghe SS, Pathirana KD, Gunasinghe KK. Normative values of motor and sensory nerve conduction studies. Galle Med J. 2010;15:43–
  4. Bromberg MB, Jaros L. Symmetry of Normal Motor and Sensory Nerve Conduction Measurement. Muscle Nerve. 1998; 21(4): 498-503.
  5. Zhang Y, Li J, Wang T, Wang J. Amplitude of sensory nerve action potential in early stage diabetic peripheral neuropathy: An analysis of 500 cases. Neural Regen Res. 2014;9:1389–
  6. Naik BM, Pal P, Pal GK, Balakumar B, Dutta TK. Assessment of motor nerve conduction in healthy obese Indian population. Int J Clin Exp Physiol. 2014;1:277–
  7. Falco FJ, Hennessey WJ, Braddom RL, Goldberg G. Standardized nerve conduction studies in the upper limb of the healthy elderly. Am J Phys Med Rehabil. 1992;71:263-71.
  8. Hennessey WJ, Falco FJ, Goldberg G, Braddom RL. Gender and arm length: Influence on nerve conduction parameters in the upper limb. Arch Phys Med Rehabil. 1994;75:265-9.
  9. Garg R, Bansal N, Kaur H, Arora KS. Nerve conduction studies in the upper limb in the malwa region-normative data. J Clin Diagn Res. 2013;7:201–
  10. Ogura T, Akiyo N, Kubo T, Kira Y, Aramaki S, Nakanishi F. The relationship between nerve conduction study and clinical grading of carpal tunnel syndrome. J Orthop Surg (Hong Kong). 2003;11:190–
  11. Mora-Brambila AB, Trujillo-Hernandez B, Coll-Cardenas R, Huerta M, Trujillo X, Vasquez C, et al. Blink reflex, H-reflex and nerve-conduction alterations in leprosy patients. Lepr Rev. 2006;77:114–
  12. Saeed S, Akram M. Impact of anthropometric measures on sural nerve conduction in healthy subjects. J Ayub Med Coll Abbottabad. 2008;20:112–
  13. Thakur D, Paudel BH, Jha CB. Nerve conduction study in healthy individuals a preliminary age based study. Kathmandu Univ Med J. 2010;8:3.
  14. Marbut MM, Najim RS, Mohsen MA. Determination of normal values of nerve conduction of tibial and peroneal nerves among normal healthy subjects. Tikrit Med J. 2012;18:1-8.
  15. Khosrawi S, Dehghan F. Determination of the median nerve residual latency values in the diagnosis of carpal tunnel syndrome in comparison with other electrodiagnostic parameters. J Res Med Sci. 2013;18:934–
  16. Salerno DF. Median and Ulnar Nerve Conduction Studies Among Workers: Normal values. Muscle Nerve. 1998; 21(8): 999-1005.
  17. Eman AM, Mye A, Basheer S, Waly H, Elkholy N. Egyptian demographic effect on Median nerve conduction studies. Egypt J Neurol Psychiatry Neurosurg. 2013;50:277-84.
  18. Manjinder S, Sharat G, Kamal DS, and Avnish Kumar. Normative Data for Median Nerve Conduction in Healthy Young Adults from Punjab, India. J Neurosci Rural Pract. 2017; 8: S83–
  19. Taylor PK. Nonlinear Effects of Age on Nerve Conduction in Adults. J Neurol Sci. 1984: 66: 223-234.
  20. Robinson LR, Rubner DE, Wahl PW, Fujimoto WY, Stolov WC. Influences of height and gender on normal nerve conduction studies. Arch Phys Med Rehabil. 1993;74:1134-8.
  21. Rivner MH, Swift TR, Malik K. Influence of age and height on nerve conduction. Muscle Nerve. 2001;24:1134–
  22. Kommalage M, Gunawardena S. Influence of age, gender, and sidedness on ulnar nerve conduction. J Clin Neurophysiol. 2013;30:98–
  23. Senthilkumari KR, Umamaheswari K, Bhaskaran M. A study on median nerve conduction velocity in different age groups. Int J Res Med Sci. 2015;3:3313-7.
  24. Patel GJ, Vekariya NN. To assess the nerve conduction velocity declination rate according to age in the median nerve of healthy subjects. Int J Sci Res. 2016;5:1036–
  25. Kumari SK, Kannan U, Patil AB. Influence of age, height, gender on median, and ulnar nerve conduction study. Natl J Physiol Pharm Pharmacol. 2018;8:202-6.
  26. Palve SS, Palve SB. Impact of aging on nerve conduction velocities and late responses in healthy individuals. J Neurosci Rural Pract. 2018;9:112-6.
  27. Jena SK, Acharya M. Age variation of motor nerve conduction study in healthy adults: A physiological reference. APIK J Int Med. 2023;11:24-7.
  28. [28] Hamdan FB. Nerve conduction studies in healthy Iraqis: Normative data. Iraqi J Med Sci. 2009;7:75–
  29. Ahmed MI, Mahbub-Or-Rashid M, Islam F. Prediction of Death Counts Based on Short term Mortality Fluctuations Data Series using Multi-output Regression Models. Int J Adv Comput Sci Appl. 2023;14(5).
  30. Cantillo-Luna S, Moreno-Chuquen R, Chamorro HR, Riquelme-Dominguez JM, Gonzalez-Longatt F. Locational Marginal Price Forecasting Using SVR-Based Multi-Output Regression in Electricity Markets. Energies. 2022;15:293.
  31. Li H. House price prediction and analysis based on random forest and XGBoost models. Highlights in Business, Economics and Management. 2023 Dec;21:934-8.
  32. James G, Witten D, Hastie T, Tibshirani R, Taylor J. Linear regression: An introduction to statistical learning: With applications in python (pp. 69-134). Cham: Springer International Publishing.
  33. Rambabu M, Ramakrishna NSS, Polamarasetty PK. Prediction and Analysis of Household Energy Consumption by Machine Learning Algorithms in Energy Management. In E3SWeb of Conf 2022;350:02002.
  34. Masud M, Mubashar A, Iqbal S, Ejaz H, Raheem SA. Tree-Based Machine Learning Approach for Predicting the Impact Behavior of Carbon/Flax Bio-Hybrid Fiber-Reinforced Polymer Composite Laminates. Eng Proc. 2024;75(1):23.
  35. Ahmed MI, Mahbub-Or-Rashid M, Islam F. Enhancing EMG signal classification using convolution neural network optimized with fractional order bat algorithm. Int J Adv Eng Sci Appl Math. 2024;16(1).
  36. Soliz P, Wigdahl J, Soliz S, Saint-Lot S, Bhandarkar A, Bhatia S, et al. Computer-Based Diagnosis of Early Signs of Diabetic Peripheral Neuropathy in Thermal Videos of the Plantar Foot. In2024 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI). 2024: 25-28.