skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

134 Recurrent Neural Networks Improve Classification of Episodic Memory Encoding

Neurosurgery, 2018-09, Vol.65 (CN_suppl_1), p.92-92 [Peer Reviewed Journal]

Copyright © 2018 by the Congress of Neurological Surgeons 2018 ;Copyright © by the Congress of Neurological Surgeons ;Copyright © 2018 by the Congress of Neurological Surgeons ;ISSN: 0148-396X ;EISSN: 1524-4040 ;DOI: 10.1093/neuros/nyy303.134

Full text available

Citations Cited by
  • Title:
    134 Recurrent Neural Networks Improve Classification of Episodic Memory Encoding
  • Author: Arora, Akshay ; Segar, Sarah ; Umbach, Gray ; Lega, Bradley
  • Subjects: Accuracy ; Brain ; Classification ; Epilepsy ; Machine learning ; Neural networks ; Neurosurgery ; Support vector machines
  • Is Part Of: Neurosurgery, 2018-09, Vol.65 (CN_suppl_1), p.92-92
  • Description: Abstract INTRODUCTION Closed-loop brain stimulation devices have demonstrated promise in improving episodic memory. However, such devices rely on accurate classification of real-time electrophysiological correlates of memory-related brain activity as either conducive or nonconducive to successful episodic encoding. We compared the classification accuracy of a recurrent neural networks (RNNs) paradigm to that of our group's previously reported highest performing machine learning classifier support vector machines (SVM) with t-distributed stochastic neighbor embedding (tSNE). Also, by withholding information recorded from various brain regions from the SVM/tSNE classifier, we predicted the impact of tissue resection during epilepsy surgery on episodic memory performance following the operation. METHODS Fifteen patients with medically refractory epilepsy were implanted with intracranial electrodes. All had contacts in the dominant hemisphere of 5 common brain regions—the hippocampus, precuneus, posterior cingular gyrus, lateral temporal cortex, and posterior lateral temporal cortex. While implanted, patients participated in an episodic memory task (free recall). EEG signals from memory encoding periods were organized by region (the 5 aforementioned), frequency band (6 logarithmically spaced bands ranging from 2.5 to 100 Hz), and time windows (6 sequential windows within the 1800 ms encoding events) and fed to both classifier types. RESULTS RNNs significantly outperformed the SVM/tSNE model as demonstrated by their respective area under the receiver operating characteristic curve values (RNNs = 0.72, SVM/tSNE = 0.68, P = .0026). When oscillatory information from each of the 5 regions was withheld from the SVM/tSNE classifier in turn, hippocampal information loss resulted in the greatest decline in classification accuracy (P = .0039). CONCLUSION Improving the classification accuracy of closed-loop stimulation devices through use of RNNs has the potential to boost the memory improvements seen with their use. Also, harnessing machine learning to quantify the relative importance of each region to classifier performance provides a novel way of predicting memory loss after tissue resection in epilepsy surgery.
  • Publisher: Oxford: Oxford University Press
  • Language: English
  • Identifier: ISSN: 0148-396X
    EISSN: 1524-4040
    DOI: 10.1093/neuros/nyy303.134
  • Source: ProQuest Central
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait