Literature DB >> 30211695

Comparison of logistic regression, support vector machines, and deep learning classifiers for predicting memory encoding success using human intracranial EEG recordings.

Akshay Arora1, Jui-Jui Lin, Alec Gasperian, Joseph Maldjian, Joel Stein, Michael Kahana, Bradley Lega.   

Abstract

OBJECTIVE: We sought to test the performance of three strategies for binary classification (logistic regression, support vector machines, and deep learning) for the problem of predicting successful episodic memory encoding using direct brain recordings obtained from human stereo EEG subjects. We also sought to test the impact of applying t-distributed stochastic neighbor embedding (tSNE) for unsupervised dimensionality reduction, as well as testing the effect of reducing input features to a core set of memory relevant brain areas. This work builds upon published efforts to develop a closed-loop stimulation device to improve memory performance. APPROACH: We used a unique data set consisting of 30 stereo EEG patients with electrodes implanted into a core set of five common brain regions (along with other areas) who performed the free recall episodic memory task as brain activity was recorded. Using three different machine learning strategies, we trained classifiers to predict successful versus unsuccessful memory encoding and compared the difference in classifier performance (as measured by the AUC) at the subject level and in aggregate across modalities. We report the impact of feature reduction on the classifiers, including reducing the number of input brain regions, frequency bands, and the impact of tSNE.
RESULTS: Deep learning classifiers outperformed both support vector machines (SVM) and logistic regression (LR). A priori selection of core brain regions also improved classifier performance for LR and SVM models, especially when combined with tSNE. SIGNIFICANCE: We report for the first time a direct comparison among traditional and deep learning methods of binary classification to the problem of predicting successful memory encoding using human brain electrophysiological data. Our findings will inform the design of brain machine interface devices to affect memory processing.

Entities:  

Mesh:

Year:  2018        PMID: 30211695      PMCID: PMC9020643          DOI: 10.1088/1741-2552/aae131

Source DB:  PubMed          Journal:  J Neural Eng        ISSN: 1741-2552            Impact factor:   5.043


  26 in total

1.  Measuring phase synchrony in brain signals.

Authors:  J P Lachaux; E Rodriguez; J Martinerie; F J Varela
Journal:  Hum Brain Mapp       Date:  1999       Impact factor: 5.038

2.  The stereotactic approach for mapping epileptic networks: a prospective study of 200 patients.

Authors:  Demitre Serletis; Juan Bulacio; William Bingaman; Imad Najm; Jorge González-Martínez
Journal:  J Neurosurg       Date:  2014-08-22       Impact factor: 5.115

3.  Theta and high-frequency activity mark spontaneous recall of episodic memories.

Authors:  John F Burke; Ashwini D Sharan; Michael R Sperling; Ashwin G Ramayya; James J Evans; M Karl Healey; Erin N Beck; Kathryn A Davis; Timothy H Lucas; Michael J Kahana
Journal:  J Neurosci       Date:  2014-08-20       Impact factor: 6.167

4.  Human intracranial high-frequency activity maps episodic memory formation in space and time.

Authors:  John F Burke; Nicole M Long; Kareem A Zaghloul; Ashwini D Sharan; Michael R Sperling; Michael J Kahana
Journal:  Neuroimage       Date:  2013-07-01       Impact factor: 6.556

5.  Theta band power increases in the posterior hippocampus predict successful episodic memory encoding in humans.

Authors:  Jui-Jui Lin; Michael D Rugg; Sandhitsu Das; Joel Stein; Daniel S Rizzuto; Michael J Kahana; Bradley C Lega
Journal:  Hippocampus       Date:  2017-06-30       Impact factor: 3.899

6.  Chronux: a platform for analyzing neural signals.

Authors:  Hemant Bokil; Peter Andrews; Jayant E Kulkarni; Samar Mehta; Partha P Mitra
Journal:  J Neurosci Methods       Date:  2010-07-15       Impact factor: 2.390

7.  Direct Brain Stimulation Modulates Encoding States and Memory Performance in Humans.

Authors:  Youssef Ezzyat; James E Kragel; John F Burke; Deborah F Levy; Anastasia Lyalenko; Paul Wanda; Logan O'Sullivan; Katherine B Hurley; Stanislav Busygin; Isaac Pedisich; Michael R Sperling; Gregory A Worrell; Michal T Kucewicz; Kathryn A Davis; Timothy H Lucas; Cory S Inman; Bradley C Lega; Barbara C Jobst; Sameer A Sheth; Kareem Zaghloul; Michael J Jutras; Joel M Stein; Sandhitsu R Das; Richard Gorniak; Daniel S Rizzuto; Michael J Kahana
Journal:  Curr Biol       Date:  2017-04-20       Impact factor: 10.834

8.  Neural activity reveals interactions between episodic and semantic memory systems during retrieval.

Authors:  Christoph T Weidemann; James E Kragel; Bradley C Lega; Gregory A Worrell; Michael R Sperling; Ashwini D Sharan; Barbara C Jobst; Fatemeh Khadjevand; Kathryn A Davis; Paul A Wanda; Allison Kadel; Daniel S Rizzuto; Michael J Kahana
Journal:  J Exp Psychol Gen       Date:  2019-01

9.  Frequency-specific network connectivity increases underlie accurate spatiotemporal memory retrieval.

Authors:  Andrew J Watrous; Nitin Tandon; Chris R Conner; Thomas Pieters; Arne D Ekstrom
Journal:  Nat Neurosci       Date:  2013-01-27       Impact factor: 24.884

10.  Classification of EEG signals using a multiple kernel learning support vector machine.

Authors:  Xiaoou Li; Xun Chen; Yuning Yan; Wenshi Wei; Z Jane Wang
Journal:  Sensors (Basel)       Date:  2014-07-17       Impact factor: 3.576

View more
  4 in total

1.  Decoding Intracranial EEG With Machine Learning: A Systematic Review.

Authors:  Nykan Mirchi; Nebras M Warsi; Frederick Zhang; Simeon M Wong; Hrishikesh Suresh; Karim Mithani; Lauren Erdman; George M Ibrahim
Journal:  Front Hum Neurosci       Date:  2022-06-27       Impact factor: 3.473

2.  A Control-Theoretical System for Modulating Hippocampal Gamma Oscillations Using Stimulation of the Posterior Cingulate Cortex.

Authors:  Carlos E Davila; David X Wang; Maxwell Ritzer; Rosalyn Moran; Bradley C Lega
Journal:  IEEE Trans Neural Syst Rehabil Eng       Date:  2022-08-17       Impact factor: 4.528

3.  Gene-expression correlates of the oscillatory signatures supporting human episodic memory encoding.

Authors:  Stefano Berto; Miles R Fontenot; Sarah Seger; Fatma Ayhan; Emre Caglayan; Ashwinikumar Kulkarni; Connor Douglas; Carol A Tamminga; Bradley C Lega; Genevieve Konopka
Journal:  Nat Neurosci       Date:  2021-03-08       Impact factor: 28.771

4.  Evaluation of classification approaches for distinguishing brain states predictive of episodic memory performance from electroencephalography: Abbreviated Title: Evaluating methods of classifying memory states from EEG.

Authors:  Soroush Mirjalili; Patrick Powell; Jonathan Strunk; Taylor James; Audrey Duarte
Journal:  Neuroimage       Date:  2021-12-22       Impact factor: 6.556

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.