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

Authors

Satvir Saggi, Department of Neurological Surgery, University of California, San Francisco.
Ethan A. Winkler, Department of Neurological Surgery, University of California, San Francisco.
Simon G. Ammanuel, Department of Neurological Surgery, University of California, San Francisco.
Ramin A. Morshed, Department of Neurological Surgery, University of California, San Francisco.
Joseph H. Garcia, Department of Neurological Surgery, University of California, San Francisco.
Jacob S. Young, Department of Neurological Surgery, University of California, San Francisco.
Alexa Semonche, Department of Neurological Surgery, University of California, San Francisco.
Heather J. Fullerton, Pediatric Stroke and Cerebrovascular Disease Center, Department of Neurology, University of California, San Francisco.
Helen Kim, Center for Cerebrovascular Research, Department of Anesthesia and Perioperative Care, University of California, San Francisco.
Daniel L. Cooke, Department of Radiology and Biomedical Imaging, University of California, San Francisco, California.
Steven W. Hetts, Department of Radiology and Biomedical Imaging, University of California, San Francisco, California.
Adib Abla, Department of Neurological Surgery, University of California, San Francisco.
Michael T. Lawton, Department of Neurological Surgery, Barrow Neurological Institute, Phoenix, Arizona; and.Follow
Nalin Gupta, Department of Neurological Surgery, University of California, San Francisco.

Document Type

Article

Abstract

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.

Medical Subject Headings

Brain; Child; Hemorrhage; Humans; Intracranial Arteriovenous Malformations (complications, diagnostic imaging); Intracranial Hemorrhages (complications, etiology); Machine Learning; Retrospective Studies

Publication Date

8-1-2022

Publication Title

Journal of neurosurgery. Pediatrics

E-ISSN

1933-0715

Volume

30

Issue

2

First Page

203

Last Page

209

PubMed ID

35916099

Digital Object Identifier (DOI)

10.3171/2022.4.PEDS21470

Recommended Citation

Saggi, Satvir; Winkler, Ethan A.; Ammanuel, Simon G.; Morshed, Ramin A.; Garcia, Joseph H.; Young, Jacob S.; Semonche, Alexa; Fullerton, Heather J.; Kim, Helen; Cooke, Daniel L.; Hetts, Steven W.; Abla, Adib; Lawton, Michael T.; and Gupta, Nalin, "Machine learning for predicting hemorrhage in pediatric patients with brain arteriovenous malformation" (2022). Neurosurgery. 1810.
https://scholar.barrowneuro.org/neurosurgery/1810