Search Results

You are looking at 1 - 2 of 2 items for

  • Author or Editor: Alexa Semonche x
  • Refine by Access: all x
Clear All Modify Search
Restricted access

Daniel G. Eichberg, Ashish H. Shah, Long Di, Alexa M. Semonche, George Jimsheleishvili, Evan M. Luther, Christopher A. Sarkiss, Allan D. Levi, Sakir H. Gultekin, Ricardo J. Komotar, and Michael E. Ivan

OBJECTIVE

In some centers where brain tumor surgery is performed, the opportunity for expert intraoperative neuropathology consultation is lacking. Consequently, surgeons may not have access to the highest quality diagnostic histological data to inform surgical decision-making. Stimulated Raman histology (SRH) is a novel technology that allows for rapid acquisition of diagnostic histological images at the bedside.

METHODS

The authors performed a prospective blinded cohort study of 82 consecutive patients undergoing resection of CNS tumors to compare diagnostic time and accuracy of SRH simulation to the gold standard, i.e., frozen and permanent section diagnosis. Diagnostic accuracy was determined by concordance of SRH-simulated intraoperative pathology consultation with a blinded board-certified neuropathologist, with official frozen section and permanent section results.

RESULTS

Overall, the mean time to diagnosis was 30.5 ± 13.2 minutes faster (p < 0.0001) for SRH simulation than for frozen section, with similar diagnostic correlation: 91.5% (κ = 0.834, p < 0.0001) between SRH simulation and permanent section, and 91.5% between frozen and permanent section (κ = 0.894, p < 0.0001).

CONCLUSIONS

SRH-simulated intraoperative pathology consultation was significantly faster and equally accurate as frozen section.

Restricted access

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.