Machine learning for predicting hemorrhage in pediatric patients with brain arteriovenous malformation

View More View Less
  • 1 Department of Neurological Surgery, University of California, San Francisco;
  • | 2 Pediatric Stroke and Cerebrovascular Disease Center, Department of Neurology, University of California, San Francisco;
  • | 3 Center for Cerebrovascular Research, Department of Anesthesia and Perioperative Care, University of California, San Francisco;
  • | 4 Department of Radiology and Biomedical Imaging, University of California, San Francisco, California;
  • | 5 Department of Neurological Surgery, Barrow Neurological Institute, Phoenix, Arizona; and
  • | 6 Department of Pediatrics, University of California, San Francisco, California
Restricted access

Purchase Now

USD  $45.00

JNS + Pediatrics - 1 year subscription bundle (Individuals Only)

USD  $515.00

JNS + Pediatrics + Spine - 1 year subscription bundle (Individuals Only)

USD  $612.00
USD  $45.00
USD  $515.00
USD  $612.00
Print or Print + Online Sign in

OBJECTIVE

Ruptured brain arteriovenous malformations (bAVMs) in a child are associated with substantial morbidity and mortality. Prior studies investigating predictors of hemorrhagic presentation of a bAVM during childhood are limited. Machine learning (ML), which has high predictive accuracy when applied to large data sets, can be a useful adjunct for predicting hemorrhagic presentation. The goal of this study was to use ML in conjunction with a traditional regression approach to identify predictors of hemorrhagic presentation in pediatric patients based on a retrospective cohort study design.

METHODS

Using data obtained from 186 pediatric patients over a 19-year study period, the authors implemented three ML algorithms (random forest models, gradient boosted decision trees, and AdaBoost) to identify features that were most important for predicting hemorrhagic presentation. Additionally, logistic regression analysis was used to ascertain significant predictors of hemorrhagic presentation as a comparison.

RESULTS

All three ML models were consistent in identifying bAVM size and patient age at presentation as the two most important factors for predicting hemorrhagic presentation. Age at presentation was not identified as a significant predictor of hemorrhagic presentation in multivariable logistic regression. Gradient boosted decision trees/AdaBoost and random forest models identified bAVM location and a concurrent arterial aneurysm as the third most important factors, respectively. Finally, logistic regression identified a left-sided bAVM, small bAVM size, and the presence of a concurrent arterial aneurysm as significant risk factors for hemorrhagic presentation.

CONCLUSIONS

By using an ML approach, the authors found predictors of hemorrhagic presentation that were not identified using a conventional regression approach.

ABBREVIATIONS

bAVM = brain arteriovenous malformation; GBDT = gradient boosted decision trees; ICH = intracranial hemorrhage; ML = machine learning.

Supplementary Materials

    • Supplementary Figures 1 and 2 (PDF 405 KB)

JNS + Pediatrics - 1 year subscription bundle (Individuals Only)

USD  $515.00

JNS + Pediatrics + Spine - 1 year subscription bundle (Individuals Only)

USD  $612.00
USD  $515.00
USD  $612.00
  • 1

    Bristol RE, Albuquerque FC, Spetzler RF, Rekate HL, McDougall CG, Zabramski JM. Surgical management of arteriovenous malformations in children. J Neurosurg. 2006;105(2)(suppl):8893.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 2

    Kondziolka D, Humphreys RP, Hoffman HJ, Hendrick EB, Drake JM. Arteriovenous malformations of the brain in children: a forty year experience. Can J Neurol Sci. 1992;19(1):4045.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 3

    Hetts SW, Cooke DL, Nelson J, et al. Influence of patient age on angioarchitecture of brain arteriovenous malformations. AJNR Am J Neuroradiol. 2014;35(7):13761380.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 4

    Al-Shahi R, Bhattacharya JJ, Currie DG, et al. Scottish Intracranial Vascular Malformation Study (SIVMS): evaluation of methods, ICD-10 coding, and potential sources of bias in a prospective, population-based cohort. Stroke. 2003;34(5):11561162.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 5

    Mohr JP, Parides MK, Stapf C, et al. Medical management with or without interventional therapy for unruptured brain arteriovenous malformations (ARUBA): a multicentre, non-blinded, randomised trial. Lancet. 2014;383(9917):614621.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 6

    Ai X, Ye Z, Xu J, You C, Jiang Y. The factors associated with hemorrhagic presentation in children with untreated brain arteriovenous malformation: a meta-analysis. J Neurosurg Pediatr. 2018;23(3):343354.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 7

    Sanchez-Mejia RO, Chennupati SK, Gupta N, Fullerton H, Young WL, Lawton MT. Superior outcomes in children compared with adults after microsurgical resection of brain arteriovenous malformations. J Neurosurg. 2006;105(2)(suppl):8287.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 8

    Darsaut TE, Guzman R, Marcellus ML, et al. Management of pediatric intracranial arteriovenous malformations: experience with multimodality therapy. Neurosurgery. 2011;69(3):540556.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 9

    Ellis MJ, Armstrong D, Vachhrajani S, et al. Angioarchitectural features associated with hemorrhagic presentation in pediatric cerebral arteriovenous malformations. J Neurointerv Surg. 2013;5(3):191195.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 10

    Sidey-Gibbons JAM, Sidey-Gibbons CJ. Machine learning in medicine: a practical introduction. BMC Med Res Methodol. 2019;19(1):64.

  • 11

    Oermann EK, Rubinsteyn A, Ding D, et al. Using a machine learning approach to predict outcomes after radiosurgery for cerebral arteriovenous malformations. Sci Rep. 2016;6(1):21161.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 12

    Formeister EJ, Baum R, Knott PD, et al. Machine learning for predicting complications in head and neck microvascular free tissue transfer. Laryngoscope. 2020;130(12):E843E849.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 13

    satvirsaggi. Satvirsaggi/Pediatric_Hemorrhage-: AVM Code Release 1. Zenodo. Posted online February 27, 2022.doi:10.5281/zenodo.6301711

    • Crossref
    • PubMed
    • Export Citation
  • 14

    Wang T, Lei Y, Tian S, et al. Learning-based automatic segmentation of arteriovenous malformations on contrast CT images in brain stereotactic radiosurgery. Med Phys. 2019;46(7):31333141.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 15

    Lee CC, Yang HC, Lin CJ, et al. Intervening nidal brain parenchyma and risk of radiation-induced changes after radiosurgery for brain arteriovenous malformation: a study using an unsupervised machine learning algorithm. World Neurosurg. 2019;125:e132e138.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 16

    Zhang Y, Yan P, Liang F, Ma C, Liang S, Jiang C. Predictors of epilepsy presentation in unruptured brain arteriovenous malformations: a quantitative evaluation of location and radiomics features on T2-weighted imaging. World Neurosurg. 2019;125:e1008e1015.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 17

    Asadi H, Kok HK, Looby S, Brennan P, O’Hare A, Thornton J. Outcomes and complications after endovascular treatment of brain arteriovenous malformations: a prognostication attempt using artificial intelligence. World Neurosurg. 2016;96:562569.e1.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 18

    Stapf C, Khaw AV, Sciacca RR, et al. Effect of age on clinical and morphological characteristics in patients with brain arteriovenous malformation. Stroke. 2003;34(11):26642669.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 19

    Mori K, Murata T, Hashimoto N, Handa H. Clinical analysis of arteriovenous malformations in children. Childs Brain. 1980;6(1):1325.

  • 20

    Spetzler RF, Hargraves RW, McCormick PW, Zabramski JM, Flom RA, Zimmerman RS. Relationship of perfusion pressure and size to risk of hemorrhage from arteriovenous malformations. J Neurosurg. 1992;76(6):918923.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 21

    Stefani MA, Porter PJ, terBrugge KG, Montanera W, Willinsky RA, Wallace MC. Large and deep brain arteriovenous malformations are associated with risk of future hemorrhage. Stroke. 2002;33(5):12201224.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 22

    Stapf C, Mast H, Sciacca RR, et al. Predictors of hemorrhage in patients with untreated brain arteriovenous malformation. Neurology. 2006;66(9):13501355.

  • 23

    Hernesniemi JA, Dashti R, Juvela S, Väärt K, Niemelä M, Laakso A. Natural history of brain arteriovenous malformations: a long-term follow-up study of risk of hemorrhage in 238 patients. Neurosurgery. 2008;63(5):823831.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 24

    Niazi TN, Klimo P Jr, Anderson RCE, Raffel C. Diagnosis and management of arteriovenous malformations in children. Neurosurg Clin N Am. 2010;21(3):443456.

  • 25

    Itoyama Y, Uemura S, Ushio Y, et al. Natural course of unoperated intracranial arteriovenous malformations: study of 50 cases. J Neurosurg. 1989;71(6):805809.

  • 26

    Ding D, Starke RM, Kano H, et al. International multicenter cohort study of pediatric brain arteriovenous malformations. Part 1: Predictors of hemorrhagic presentation. J Neurosurg Pediatr. 2017;19(2):127135.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 27

    Kiriş T, Sencer A, Sahinbaş M, Sencer S, Imer M, Izgi N. Surgical results in pediatric Spetzler-Martin grades I-III intracranial arteriovenous malformations. Childs Nerv Syst. 2005;21(1):6976.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 28

    Hoh BL, Ogilvy CS, Butler WE, Loeffler JS, Putman CM, Chapman PH. Multimodality treatment of nongalenic arteriovenous malformations in pediatric patients. Neurosurgery. 2000;47(2):346358.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 29

    Di Rocco C, Tamburrini G, Rollo M. Cerebral arteriovenous malformations in children. Acta Neurochir (Wien). 2000;142(2):145158.

  • 30

    Blauwblomme T, Bourgeois M, Meyer P, et al. Long-term outcome of 106 consecutive pediatric ruptured brain arteriovenous malformations after combined treatment. Stroke. 2014;45(6):16641671.

    • Search Google Scholar
    • Export Citation

Metrics

All Time Past Year Past 30 Days
Abstract Views 287 287 287
Full Text Views 21 21 21
PDF Downloads 22 22 22
EPUB Downloads 0 0 0