دورية أكاديمية
أعرض في EDS

Development of Machine Learning-Based Models to Predict Treatment Response to Spinal Cord Stimulation.

التفاصيل البيبلوغرافية
العنوان: Development of Machine Learning-Based Models to Predict Treatment Response to Spinal Cord Stimulation.
المؤلفون: Hadanny A; Department of Neurosurgery, Albany Medical College, Albany, New York, USA., Harland T; Department of Neurosurgery, Albany Medical College, Albany, New York, USA., Khazen O; Department of Neuroscience and Experimental Therapeutics, Albany Medical College, Albany, New York, USA., DiMarzio M; Department of Neuroscience and Experimental Therapeutics, Albany Medical College, Albany, New York, USA., Marchese A; Department of Neuroscience and Experimental Therapeutics, Albany Medical College, Albany, New York, USA., Telkes I; Department of Neuroscience and Experimental Therapeutics, Albany Medical College, Albany, New York, USA., Sukul V; Department of Neurosurgery, Albany Medical College, Albany, New York, USA., Pilitsis JG; Department of Neurosurgery, Albany Medical College, Albany, New York, USA.; Department of Neuroscience and Experimental Therapeutics, Albany Medical College, Albany, New York, USA.
المصدر: Neurosurgery [Neurosurgery] 2022 May 01; Vol. 90 (5), pp. 523-532.
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Lippincott Williams & Wilkins, Inc Country of Publication: United States NLM ID: 7802914 Publication Model: Print Cited Medium: Internet ISSN: 1524-4040 (Electronic) Linking ISSN: 0148396X NLM ISO Abbreviation: Neurosurgery Subsets: MEDLINE
أسماء مطبوعة: Publication: 2022- : [Philadelphia] : Lippincott Williams & Wilkins, Inc.
Original Publication: Baltimore, Williams & Wilkins.
مواضيع طبية MeSH: Chronic Pain*/therapy , Spinal Cord Stimulation*, Cohort Studies ; Humans ; Logistic Models ; Machine Learning ; Treatment Outcome
مستخلص: Background: Despite spinal cord stimulation's (SCS) proven efficacy, failure rates are high with no clear understanding of which patients benefit long term. Currently, patient selection for SCS is based on the subjective experience of the implanting physician.
Objective: To develop machine learning (ML)-based predictive models of long-term SCS response.
Methods: A combined unsupervised (clustering) and supervised (classification) ML technique was applied on a prospectively collected cohort of 151 patients, which included 31 features. Clusters identified using unsupervised K-means clustering were fitted with individualized predictive models of logistic regression, random forest, and XGBoost.
Results: Two distinct clusters were found, and patients in the cohorts significantly differed in age, duration of chronic pain, preoperative numeric rating scale, and preoperative pain catastrophizing scale scores. Using the 10 most influential features, logistic regression predictive models with a nested cross-validation demonstrated the highest overall performance with the area under the curve of 0.757 and 0.708 for each respective cluster.
Conclusion: This combined unsupervised-supervised learning approach yielded high predictive performance, suggesting that advanced ML-derived approaches have potential to be used as a functional clinical tool to improve long-term SCS outcomes. Further studies are needed for optimization and external validation of these models.
(Copyright © Congress of Neurological Surgeons 2022. All rights reserved.)
التعليقات: Comment in: Neurosurgery. 2022 Jul 1;91(1):e30. (PMID: 35467563)
Comment in: Neurosurgery. 2022 Aug 1;91(2):e68-e70. (PMID: 35603938)
References: Leung N, Tsourmas NF, Yuspeh L, et al. Increased spinal cord stimulator use and continued opioid treatment among injured workers: a regional pilot study. J Occup Environ Med. 2020;62(8):e436.
Brinzeu A, Cuny E, Fontaine D, et al. Spinal cord stimulation for chronic refractory pain: long-term effectiveness and safety data from a multicentre registry. Eur J Pain. 2019;23(5):1031-1044.
Nissen M, Ikäheimo TM, Huttunen J, Leinonen V, von Und Zu Fraunberg M. Long-term outcome of spinal cord stimulation in failed back surgery syndrome: 20 years of experience with 224 consecutive patients. Neurosurgery. 2019;84(5):1011-1018.
Bagherzadeh-Khiabani F, Ramezankhani A, Azizi F, Hadaegh F, Steyerberg EW, Khalili D. A tutorial on variable selection for clinical prediction models: feature selection methods in data mining could improve the results. J Clin Epidemiol. 2016;71:76-85.
Prabhala T, Sabourin S, DiMarzio M, Gillogly M, Prusik J, Pilitsis JG. Duloxetine improves spinal cord stimulation outcomes for chronic pain. Neuromodulation. 2019;22(2):215-218.
Slyer J, Scott S, Sheldon B, Hancu M, Bridger C, Pilitsis JG. Less pain relief, more depression, and female sex correlate with spinal cord stimulation explants. Neuromodulation. 2020;23(5):673-679.
Sheldon BL, Khazen O, Feustel PJ, et al. Correlations between family history of psychiatric illnesses and outcomes of spinal cord stimulation. Neuromodulation. 2020;23(5):667-672.
Khan H, Pilitsis JG, Prusik J, Smith H, McCallum SE. Pain remission at one-year follow-up with spinal cord stimulation. Neuromodulation. 2018;21(1):101-105.
Williamson A, Hoggart B. Pain: a review of three commonly used pain rating scales. J Clin Nurs. 2005;14(7):798-804.
Moore RA, Moore OA, Derry S, Peloso PM, Gammaitoni AR, Wang H. Responder analysis for pain relief and numbers needed to treat in a meta-analysis of etoricoxib osteoarthritis trials: bridging a gap between clinical trials an d clinical practice. Ann Rheum Dis. 2010;69(2):374-379.
Levitt J, Edhi MM, Thorpe RV, et al. Pain phenotypes classified by machine learning using electroencephalography features. NeuroImage. 2020;223:117256.
Jain AK. Data clustering: 50 years beyond K-means. Pattern Recognition Lett. 2010;31(8):651-666.
Vabalas A, Gowen E, Poliakoff E, Casson AJ. Machine learning algorithm validation with a limited sample size. PLoS One 2019;14(11):e0224365.
Higgins JP, Thomos J, Chandler J, et al, editors. Cochrane Handbook for Systematic Reviews of Interventions Version 6.1 (Updated September 2020). Cochrane; 2020. Available at www.training.cochrane.org/handbook .
Elbattah M, Molloy O. Clustering-aided approach for predicting patient outcomes with application to elderly healthcare in Ireland. In: Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, 2017.
De Jaeger M, Goudman L, Brouns R, et al. The long-term response to high-dose spinal cord stimulation in patients with failed back surgery syndrome after conversion from standard spinal cord stimulation: an effectiveness and prediction study. Neuromodulation. 2020;24(3):546-555.
Goudman L, Van Buyten JP, De Smedt A, et al. Predicting the response of high frequency spinal cord stimulation in patients with failed back surgery syndrome: a retrospective study with machine learning techniques. J Clin Med. 2020;9(12):4131.
Hajian-Tilaki K. Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation. Caspian J Intern Med. 2013;4(2):627-635.
Pilitsis JG, Fahey M, Custozzo A, Chakravarthy K, Capobianco R. Composite score is a better reflection of patient response to chronic pain therapy compared with pain intensity alone. Neuromodulation. 2020;24(1):68-75.
Marola O, Cherala R, Prusik J, et al. BMI as a predictor of spinal cord stimulation success in chronic pain patients. Neuromodulation. 2017;20(3):269-273.
Sparkes E, Duarte RV, Mann S, Lawrence TR, Raphael JH. Analysis of psychological characteristics impacting spinal cord stimulation treatment outcomes: a prospective assessment. Pain Phys. 2015;18(3):E369-E377.
Patel SK, Gozal YM, Saleh MS, Gibson JL, Karsy M, Mandybur GT. Spinal cord stimulation failure: evaluation of factors underlying hardware explantation. J Neurosurg Spine. Published online ahead of print October 4, 2019. doi: 10.3171/2019.6.SPINE181099. (PMID: 10.3171/2019.6.SPINE181099)
Sparkes E, Raphael JH, Duarte RV, LeMarchand K, Jackson C, Ashford RL. A systematic literature review of psychological characteristics as determinants of outcome for spinal cord stimulation therapy. Pain. 2010;150(2):284-289.
Campbell CM, Jamison RN, Edwards RR. Psychological screening/phenotyping as predictors for spinal cord stimulation. Curr Pain Headache Rep. 2013;17(1):307.
Mekhail N, Azer G, Saweris Y, Mehanny DS, Costandi S, Mao G. The impact of tobacco cigarette smoking on spinal cord stimulation effectiveness in chronic spine-related pain patients. Reg Anesth Pain Med. 2018;43(7):768-775.
Turner JA, Hollingworth W, Comstock BA, Deyo RA. Spinal cord stimulation for failed back surgery syndrome: outcomes in a workers' compensation setting. Pain. 2010;148(1):14-25.
Amirdelfan K, Yu C, Doust MW, et al. Long-term quality of life improvement for chronic intractable back and leg pain patients using spinal cord stimulation: 12-month results from the SENZA-RCT. Qual Life Res. 2018;27(8):2035-2044.
Levy R, Deer TR, Poree L, et al. Multicenter, randomized, double-blind study protocol using human spinal cord recording comparing safety, efficacy, and neurophysiological responses between patients being treated with evoked compound action potential-controlled closed-loop spinal cord stimulation or open-loop spinal cord stimulation (the evoke study). Neuromodulation. 2019;22(3):317-326.
Deer T, Slavin KV, Amirdelfan K, et al. Success using neuromodulation with BURST (SUNBURST) study: results from a prospective, randomized controlled trial using a novel burst waveform. Neuromodulation. 2018;21(1):56-66.
Fishman MA, Calodney A, Kim P, et al. Prospective, multicenter feasibility study to evaluate differential target multiplexed spinal cord stimulation programming in subjects with chronic intractable back pain with or without leg pain. Pain Pract. 2020;20(7):761-768.
Safikhani S, Gries KS, Trudeau JJ, et al. Response scale selection in adult pain measures: results from a literature review. J Patient Rep Outcomes. 2017;2:40.
معلومات مُعتمدة: K99 NS119672 United States NS NINDS NIH HHS
تواريخ الأحداث: Date Created: 20220218 Date Completed: 20220420 Latest Revision: 20230322
رمز التحديث: 20230323
مُعرف محوري في PubMed: PMC9514733
DOI: 10.1227/neu.0000000000001855
PMID: 35179133
قاعدة البيانات: MEDLINE
الوصف
تدمد:1524-4040
DOI:10.1227/neu.0000000000001855