Advertisement

Efficacy of a machine learning-based approach in predicting neurological prognosis of cervical spinal cord injury patients following urgent surgery within 24 h after injury

Published:November 11, 2022DOI:https://doi.org/10.1016/j.jocn.2022.11.003

      Highlights

      • The ML models successfully predicted neurological outcomes of spinal cord injury.
      • AIS grade at admission was identified as the most important feature for the model.
      • Preoperative MRI findings were also identified as important features for the model.

      Abstract

      We aimed to develop a machine learning (ML) model for predicting the neurological outcomes of cervical spinal cord injury (CSCI). We retrospectively analyzed 135 patients with CSCI who underwent surgery within 24 h after injury. Patients were assessed with the American Spinal Injury Association Impairment Scale (AIS; grades A to E) 6 months after injury. A total of 34 features extracted from demographic variables, surgical factors, laboratory variables, neurological status, and radiological findings were analyzed. The ML model was created using Light GBM, XGBoost, and CatBoost. We evaluated Shapley Additive Explanations (SHAP) values to determine the variables that contributed most to the prediction models. We constructed multiclass prediction models for the five AIS grades and binary classification models to predict more than one-grade improvement in AIS 6 months after injury. Of the ML models used, CatBoost showed the highest accuracy (0.800) for the prediction of AIS grade and the highest AUC (0.90) for predicting improvement in AIS. AIS grade at admission, intramedullary hemorrhage, longitudinal extent of intramedullary T2 hyperintensity, and HbA1c were identified as important features for these prediction models. The ML models successfully predicted neurological outcomes 6 months after injury following urgent surgery in patients with CSCI.

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Journal of Clinical Neuroscience
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Shtar G.
        • Rokach L.
        • Shapira B.
        • Nissan R.
        • Hershkovitz A.
        Using Machine Learning to Predict Rehabilitation Outcomes in Postacute Hip Fracture Patients.
        Arch Phys Med Rehabil. 2021; 102: 386-394https://doi.org/10.1016/j.apmr.2020.08.011
        • Park D.
        • Kim B.H.
        • Lee S.E.
        • Kim D.Y.
        • Kim M.
        • Kwon H.D.
        • et al.
        Machine learning-based approach for disease severity classification of carpal tunnel syndrome.
        Sci Rep. 2021; 11: 17464https://doi.org/10.1038/s41598-021-97043-7
      1. Maki S, Furuya T, Yoshii T, Egawa S, Sakai K, Kusano K, et al. Machine Learning Approach in Predicting Clinically Significant Improvements After Surgery in Patients with Cervical Ossification of the Posterior Longitudinal Ligament. Spine (Phila Pa 1976). 2021;46:1683-9.10.1097/BRS.0000000000004125.

        • Merali Z.G.
        • Witiw C.D.
        • Badhiwala J.H.
        • Wilson J.R.
        • Fehlings M.G.
        Using a machine learning approach to predict outcome after surgery for degenerative cervical myelopathy.
        PLoS ONE. 2019; 14: e0215133
      2. Fan G, Yang S, Liu H, Xu N, Chen Y, He J, et al. Machine Learning-based Prediction of Prolonged ICU- Stay for Critical Patients With Spinal Cord Injury. Spine (Phila Pa 1976). 2021.10.1097/BRS.0000000000004267.

        • Fallah N.
        • Noonan V.K.
        • Waheed Z.
        • Rivers C.S.
        • Plashkes T.
        • Bedi M.
        • et al.
        Development of a machine learning algorithm for predicting in-hospital and 1-year mortality after traumatic spinal cord injury.
        Spine J. 2022; 22: 329-336https://doi.org/10.1016/j.spinee.2021.08.003
        • Inoue T.
        • Ichikawa D.
        • Ueno T.
        • Cheong M.
        • Inoue T.
        • Whetstone W.D.
        • et al.
        XGBoost, a Machine Learning Method, Predicts Neurological Recovery in Patients with Cervical Spinal Cord Injury.
        Neurotrauma Rep. 2020; 1: 8-16https://doi.org/10.1089/neur.2020.0009
      3. Fehlings MG, Vaccaro A, Wilson JR, Singh A, D WC, Harrop JS, et al. Early versus delayed decompression for traumatic cervical spinal cord injury: results of the Surgical Timing in Acute Spinal Cord Injury Study (STASCIS). PLoS One. 2012;7:e32037.10.1371/journal.pone.0032037.

        • Chikuda H.
        • Koyama Y.
        • Matsubayashi Y.
        • Ogata T.
        • Ohtsu H.
        • Sugita S.
        • et al.
        Effect of Early vs Delayed Surgical Treatment on Motor Recovery in Incomplete Cervical Spinal Cord Injury With Preexisting Cervical Stenosis: A Randomized Clinical Trial.
        JAMA Netw Open. 2021; 4: e2133604
        • Kirshblum S.C.
        • Burns S.P.
        • Biering-Sorensen F.
        • Donovan W.
        • Graves D.E.
        • Jha A.
        • et al.
        International standards for neurological classification of spinal cord injury (revised 2011).
        J Spinal Cord Med. 2011; 34: 535-546https://doi.org/10.1179/204577211x13207446293695
        • Resnick D.
        • Niwayama G.
        Radiographic and pathologic features of spinal involvement in diffuse idiopathic skeletal hyperostosis (DISH).
        Radiology. 1976; 119: 559-568https://doi.org/10.1148/119.3.559
      4. Doi T, Sakamoto R, Horii C, Okamoto N, Nakajima K, Hirai S, et al. Risk factors for progression of ossification of the posterior longitudinal ligament in asymptomatic subjects. J Neurosurg Spine. 2020:1-7.10.3171/2020.3.Spine2082.

        • Rutges J.
        • Kwon B.K.
        • Heran M.
        • Ailon T.
        • Street J.T.
        • Dvorak M.F.
        A prospective serial MRI study following acute traumatic cervical spinal cord injury.
        Eur Spine J. 2017; 26: 2324-2332https://doi.org/10.1007/s00586-017-5097-4
        • Ozaki M.
        • Suda K.
        • Konomi T.
        • Harmon S.M.
        • Komatsu M.
        • Minami A.
        • et al.
        Serum C-reactive protein is an early, simple and inexpensive prognostic marker for the progression of intramedullary lesion on magnetic resonance imaging from acute to subacute stage in patients with spinal cord injury.
        Spinal Cord. 2021; 59: 1155-1161https://doi.org/10.1038/s41393-021-00640-6
        • Haefeli J.
        • Mabray M.C.
        • Whetstone W.D.
        • Dhall S.S.
        • Pan J.Z.
        • Upadhyayula P.
        • et al.
        Multivariate Analysis of MRI Biomarkers for Predicting Neurologic Impairment in Cervical Spinal Cord Injury.
        AJNR Am J Neuroradiol. 2017; 38: 648-655https://doi.org/10.3174/ajnr.A5021
      5. Fehlings MG, Rao SC, Tator CH, Skaf G, Arnold P, Benzel E, et al. The optimal radiologic method for assessing spinal canal compromise and cord compression in patients with cervical spinal cord injury. Part II: Results of a multicenter study. Spine (Phila Pa 1976). 1999;24:605-13.10.1097/00007632-199903150-00023.

        • Konomi T.
        • Suda K.
        • Ozaki M.
        • Harmon S.M.
        • Komatsu M.
        • Iimoto S.
        • et al.
        Predictive factors for irreversible motor paralysis following cervical spinal cord injury.
        Spinal Cord. 2021; 59: 554-562https://doi.org/10.1038/s41393-020-0513-8
      6. Chen T, Guestrin C. XGBoost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining2016. p. 785-94.

        • Yan J.
        • Xu Y.
        • Cheng Q.
        • Jiang S.
        • Wang Q.
        • Xiao Y.
        • et al.
        LightGBM: accelerated genomically designed crop breeding through ensemble learning.
        Genome Biol. 2021; 22: 271https://doi.org/10.1186/s13059-021-02492-y
        • Hancock J.T.
        • Khoshgoftaar T.M.
        CatBoost for big data: an interdisciplinary review.
        J Big Data. 2020; 7: 94https://doi.org/10.1186/s40537-020-00369-8
        • Waters R.L.
        • Adkins R.H.
        • Yakura J.S.
        • Sie I.
        Motor and sensory recovery following incomplete tetraplegia.
        Arch Phys Med Rehabil. 1994; 75: 306-311https://doi.org/10.1016/0003-9993(94)90034-5
        • Koo B.S.
        • Eun S.
        • Shin K.
        • Yoon H.
        • Hong C.
        • Kim D.H.
        • et al.
        Machine learning model for identifying important clinical features for predicting remission in patients with rheumatoid arthritis treated with biologics.
        Arthritis Res Ther. 2021; 23: 178https://doi.org/10.1186/s13075-021-02567-y
        • Lama L.
        • Wilhelmsson O.
        • Norlander E.
        • Gustafsson L.
        • Lager A.
        • Tynelius P.
        • et al.
        Machine learning for prediction of diabetes risk in middle-aged Swedish people.
        Heliyon. 2021; 7: e07419
        • Ter Wengel P.V.
        • Post M.W.M.
        • Martin E.
        • Stolwijk-Swuste J.
        • Hosman A.J.F.
        • Sadiqi S.
        • et al.
        Neurological recovery after traumatic spinal cord injury: what is meaningful? A patients' and physicians' perspective.
        Spinal Cord. 2020; 58: 865-872https://doi.org/10.1038/s41393-020-0436-4
        • Aarabi B.
        • Sansur C.A.
        • Ibrahimi D.M.
        • Simard J.M.
        • Hersh D.S.
        • Le E.
        • et al.
        Intramedullary Lesion Length on Postoperative Magnetic Resonance Imaging is a Strong Predictor of ASIA Impairment Scale Grade Conversion Following Decompressive Surgery in Cervical Spinal Cord Injury.
        Neurosurgery. 2017; 80: 610-620https://doi.org/10.1093/neuros/nyw053
      7. Kobayakawa K, Kumamaru H, Saiwai H, Kubota K, Ohkawa Y, Kishimoto J, et al. Acute hyperglycemia impairs functional improvement after spinal cord injury in mice and humans. Sci Transl Med. 2014;6:256ra137.10.1126/scitranslmed.3009430.

        • Park K.S.
        • Kim J.B.
        • Keung M.
        • Seo Y.J.
        • Seo S.Y.
        • Mun S.A.
        • et al.
        Chronic Hyperglycemia before Spinal Cord Injury Increases Inflammatory Reaction and Astrogliosis after Injury: Human and Rat Studies.
        J Neurotrauma. 2020; 37: 1165-1181https://doi.org/10.1089/neu.2019.6724
        • Nagata K.
        • Inokuchi K.
        • Chikuda H.
        • Ishii K.
        • Kobayashi A.
        • Kanai H.
        • et al.
        Early versus delayed reduction of cervical spine dislocation with complete motor paralysis: a multicenter study.
        Eur Spine J. 2017; 26: 1272-1276https://doi.org/10.1007/s00586-017-5004-z
      8. Tsuji O, Suda K, Takahata M, Matsumoto-Harmon S, Komatsu M, Menjo Y, et al. Early surgical intervention may facilitate recovery of cervical spinal cord injury in DISH. J Orthop Surg (Hong Kong). 2019;27:2309499019834783.10.1177/2309499019834783.

        • Kirshblum S.
        • Snider B.
        • Eren F.
        • Guest J.
        Characterizing Natural Recovery after Traumatic Spinal Cord Injury.
        J Neurotrauma. 2021; 38: 1267-1284https://doi.org/10.1089/neu.2020.7473