Search Results

You are looking at 1 - 5 of 5 items for :

  • Author or Editor: Satvir Saggi x
  • Journal of Neurosurgery: Pediatrics x
  • Refine by Access: all x
Clear All Modify Search
Free access

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

Satvir Saggi, Ethan A. Winkler, Simon G. Ammanuel, Ramin A. Morshed, Joseph H. Garcia, Jacob S. Young, Alexa Semonche, Heather J. Fullerton, Helen Kim, Daniel L. Cooke, Steven W. Hetts, Adib Abla, Michael T. Lawton, and Nalin Gupta

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.

Free access

Factors associated with seizures at initial presentation in pediatric patients with cerebral arteriovenous malformations

Joseph H. Garcia, Ethan A. Winkler, Ramin A. Morshed, Alex Lu, Simon G. Ammanuel, Satvir Saggi, Elaina J. Wang, Steve Braunstein, Christine K. Fox, Heather J. Fullerton, Helen Kim, Daniel L. Cooke, Steven W. Hetts, Michael T. Lawton, Adib A. Abla, and Nalin Gupta

OBJECTIVE

Children with cerebral arteriovenous malformations (AVMs) can present with seizures, potentially increasing morbidity and impacting clinical management. However, the factors that lead to seizures as a presenting sign are not well defined. While AVM-related seizures have been described in case series, most studies have focused on adults and have included patients who developed seizures after an AVM rupture. To address this, the authors sought to analyze demographic and morphological characteristics of AVMs in a large cohort of children.

METHODS

The demographic, clinical, and AVM morphological characteristics of 189 pediatric patients from a single-center database were studied. Univariate and multivariate logistic regression models were used to test the effect of these characteristics on seizures as an initial presenting symptom in patients with unruptured brain AVMs.

RESULTS

Overall, 28 of 189 patients initially presented with seizures (14.8%). By univariate comparison, frontal lobe location (p = 0.02), larger AVM size (p = 0.003), older patient age (p = 0.04), and the Supplemented Spetzler-Martin (Supp-SM) grade (0.0006) were associated with seizure presentation. Multivariate analysis confirmed an independent effect of frontal lobe AVM location and higher Supp-SM grade. All patients presenting with seizures had AVMs in the cortex or subcortical white matter.

CONCLUSIONS

While children and adults share some risk factors for seizure presentation, their risk factor profiles do not entirely overlap. Pediatric patients with cortical AVMs in the frontal lobe were more likely to present with seizures. Additionally, the Supp-SM grade was highly associated with seizure presentation. Future clinical research should focus on the effect of therapeutic interventions targeting AVMs on seizure control in these patients.

Free access

Validation of the Ruptured Arteriovenous Malformation Grading Scale in a pediatric cohort

Joseph H. Garcia, Caleb Rutledge, Ethan A. Winkler, Luis Carrete, Ramin A. Morshed, Alex Y. Lu, Satvir Saggi, Christine K. Fox, Heather J. Fullerton, Helen Kim, Daniel L. Cooke, Steven W. Hetts, Michael T. Lawton, Nalin Gupta, and Adib A. Abla

OBJECTIVE

Pediatric brain arteriovenous malformations (AVMs) are the leading cause of spontaneous intracranial hemorrhage (SICH) in children. Although the incidence of SICH is low in pediatric populations, such events cause substantial morbidity. The recently created Ruptured Arteriovenous Malformation Grading Scale (RAGS) is proposed as a reliable and novel grading system to specifically serve as a predictor of clinical outcomes in patients following AVM rupture, similar to the Hunt and Hess (HH) grade for ruptured aneurysms. While these data are promising, pediatric patients were notably absent from the original study validating the RAGS. Therefore, correlation of the RAGS score with clinical outcomes following AVM rupture in individuals younger than 18 years of age using the RAGS score is needed. The objective of this study was to validate the RAGS in a cohort of pediatric patients with AVMs who presented with hemorrhage, thereby demonstrating the score’s generalizability, and expanding its external validity.

METHODS

A cohort of children with ruptured AVMs were retrospectively reviewed. Using disability, measured by the modified Rankin Scale (mRS), as the response variable, the area under the receiver operating characteristic curve (AUROC) was calculated for patients based on their RAGS scores for three time periods. The AUROC values were then compared with those generated by two commonly used clinical grading systems, the HH classification and Glasgow Coma Scale.

RESULTS

A total of 81 children who presented with ruptured AVMs were included in the study, with a mean follow-up duration of 4 years. The RAGS score outperformed other clinical grading scales in predicting mRS scores, with AUROC values of 0.81, 0.82, and 0.81 at three distinct follow-up periods.

CONCLUSIONS

The RAGS score correlated well with the clinical outcome after AVM rupture in pediatric patients. Additional validation studies across multiple treatment centers are needed to further demonstrate the generalizability of the scoring system.

Free access

Letter to the Editor. Seizures in pediatric patients with cerebral AVMs

Lei Zhao, Liwei Peng, Peng Wang, and Weixin Li

Free access

Letter to the Editor. Seizures in pediatric patients with cerebral AVMs

Lei Zhao, Liwei Peng, Peng Wang, and Weixin Li