IFAST: Implicit function as squashing time for eeg analysis - application

Paolo Maria Rossini, Massimo Buscema, Enzo Grossi

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

It has been shown that a new procedure (Implicit Function as Squashing Time, IFAST) based on Artificial Neural Networks (ANNs) is able to compress eyes-closed resting electroencephalographic (EEG) data into spatial invariants of the instant voltage distributions for an automatic classification of mild cognitive impairment (MCI) and Alzheimer's disease (AD) subjects with classification accuracy of individual subjects higher than 92%. In this chapter the method has been applied to distinguish individual normal elderly (Nold) vs. Mild Cognitive Impairment (MCI) subjects, an important issue for the screening of large populations at high risk of AD. Eyes-closed resting EEG data (10-20 electrode montage) were recorded in 171 Nold and in 115 amnesic MCI subjects. The data inputs for the classification by IFAST were the weights of the connections within a non linear auto-associative ANN trained to generate the instant voltage distributions of 60-s artifact free EEG data. The most relevant features were selected and coincidently the dataset was split into two halves for the final binary classification (training and testing) performed by a supervised ANN. The classification of the individual Nold and MCI subjects reached 95.87% of sensitivity and 91.06% of specificity (93.46% of accuracy). These results indicate that IFAST can reliably distinguish eyes-closed resting EEG in individual Nold and MCI subjects, and may be used for large-scale periodic screening of large populations at risk of AD and personalized care.

Original languageEnglish
Title of host publicationArtificial Adaptive Systems in Medicine: New Theories and Models for New Applications in the Real World
PublisherBentham Science Publishers Ltd.
Pages104-113
Number of pages10
ISBN (Print)9781608053926
DOIs
Publication statusPublished - 2009

Fingerprint

Alzheimer Disease
Artifacts
Electrodes
Cognitive Dysfunction
Weights and Measures
Sensitivity and Specificity
Datasets

Keywords

  • Alzheimer's disease (AD)
  • Artificial neural networks (ANNs)
  • Electroencephalography (EEG)
  • Mild cognitive impairment (MCI)

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Rossini, P. M., Buscema, M., & Grossi, E. (2009). IFAST: Implicit function as squashing time for eeg analysis - application. In Artificial Adaptive Systems in Medicine: New Theories and Models for New Applications in the Real World (pp. 104-113). Bentham Science Publishers Ltd.. https://doi.org/10.2174/978160805042010901010104

IFAST : Implicit function as squashing time for eeg analysis - application. / Rossini, Paolo Maria; Buscema, Massimo; Grossi, Enzo.

Artificial Adaptive Systems in Medicine: New Theories and Models for New Applications in the Real World. Bentham Science Publishers Ltd., 2009. p. 104-113.

Research output: Chapter in Book/Report/Conference proceedingChapter

Rossini, PM, Buscema, M & Grossi, E 2009, IFAST: Implicit function as squashing time for eeg analysis - application. in Artificial Adaptive Systems in Medicine: New Theories and Models for New Applications in the Real World. Bentham Science Publishers Ltd., pp. 104-113. https://doi.org/10.2174/978160805042010901010104
Rossini PM, Buscema M, Grossi E. IFAST: Implicit function as squashing time for eeg analysis - application. In Artificial Adaptive Systems in Medicine: New Theories and Models for New Applications in the Real World. Bentham Science Publishers Ltd. 2009. p. 104-113 https://doi.org/10.2174/978160805042010901010104
Rossini, Paolo Maria ; Buscema, Massimo ; Grossi, Enzo. / IFAST : Implicit function as squashing time for eeg analysis - application. Artificial Adaptive Systems in Medicine: New Theories and Models for New Applications in the Real World. Bentham Science Publishers Ltd., 2009. pp. 104-113
@inbook{f1fc2cd8dd3d45deb929d93ab4b60c7a,
title = "IFAST: Implicit function as squashing time for eeg analysis - application",
abstract = "It has been shown that a new procedure (Implicit Function as Squashing Time, IFAST) based on Artificial Neural Networks (ANNs) is able to compress eyes-closed resting electroencephalographic (EEG) data into spatial invariants of the instant voltage distributions for an automatic classification of mild cognitive impairment (MCI) and Alzheimer's disease (AD) subjects with classification accuracy of individual subjects higher than 92{\%}. In this chapter the method has been applied to distinguish individual normal elderly (Nold) vs. Mild Cognitive Impairment (MCI) subjects, an important issue for the screening of large populations at high risk of AD. Eyes-closed resting EEG data (10-20 electrode montage) were recorded in 171 Nold and in 115 amnesic MCI subjects. The data inputs for the classification by IFAST were the weights of the connections within a non linear auto-associative ANN trained to generate the instant voltage distributions of 60-s artifact free EEG data. The most relevant features were selected and coincidently the dataset was split into two halves for the final binary classification (training and testing) performed by a supervised ANN. The classification of the individual Nold and MCI subjects reached 95.87{\%} of sensitivity and 91.06{\%} of specificity (93.46{\%} of accuracy). These results indicate that IFAST can reliably distinguish eyes-closed resting EEG in individual Nold and MCI subjects, and may be used for large-scale periodic screening of large populations at risk of AD and personalized care.",
keywords = "Alzheimer's disease (AD), Artificial neural networks (ANNs), Electroencephalography (EEG), Mild cognitive impairment (MCI)",
author = "Rossini, {Paolo Maria} and Massimo Buscema and Enzo Grossi",
year = "2009",
doi = "10.2174/978160805042010901010104",
language = "English",
isbn = "9781608053926",
pages = "104--113",
booktitle = "Artificial Adaptive Systems in Medicine: New Theories and Models for New Applications in the Real World",
publisher = "Bentham Science Publishers Ltd.",

}

TY - CHAP

T1 - IFAST

T2 - Implicit function as squashing time for eeg analysis - application

AU - Rossini, Paolo Maria

AU - Buscema, Massimo

AU - Grossi, Enzo

PY - 2009

Y1 - 2009

N2 - It has been shown that a new procedure (Implicit Function as Squashing Time, IFAST) based on Artificial Neural Networks (ANNs) is able to compress eyes-closed resting electroencephalographic (EEG) data into spatial invariants of the instant voltage distributions for an automatic classification of mild cognitive impairment (MCI) and Alzheimer's disease (AD) subjects with classification accuracy of individual subjects higher than 92%. In this chapter the method has been applied to distinguish individual normal elderly (Nold) vs. Mild Cognitive Impairment (MCI) subjects, an important issue for the screening of large populations at high risk of AD. Eyes-closed resting EEG data (10-20 electrode montage) were recorded in 171 Nold and in 115 amnesic MCI subjects. The data inputs for the classification by IFAST were the weights of the connections within a non linear auto-associative ANN trained to generate the instant voltage distributions of 60-s artifact free EEG data. The most relevant features were selected and coincidently the dataset was split into two halves for the final binary classification (training and testing) performed by a supervised ANN. The classification of the individual Nold and MCI subjects reached 95.87% of sensitivity and 91.06% of specificity (93.46% of accuracy). These results indicate that IFAST can reliably distinguish eyes-closed resting EEG in individual Nold and MCI subjects, and may be used for large-scale periodic screening of large populations at risk of AD and personalized care.

AB - It has been shown that a new procedure (Implicit Function as Squashing Time, IFAST) based on Artificial Neural Networks (ANNs) is able to compress eyes-closed resting electroencephalographic (EEG) data into spatial invariants of the instant voltage distributions for an automatic classification of mild cognitive impairment (MCI) and Alzheimer's disease (AD) subjects with classification accuracy of individual subjects higher than 92%. In this chapter the method has been applied to distinguish individual normal elderly (Nold) vs. Mild Cognitive Impairment (MCI) subjects, an important issue for the screening of large populations at high risk of AD. Eyes-closed resting EEG data (10-20 electrode montage) were recorded in 171 Nold and in 115 amnesic MCI subjects. The data inputs for the classification by IFAST were the weights of the connections within a non linear auto-associative ANN trained to generate the instant voltage distributions of 60-s artifact free EEG data. The most relevant features were selected and coincidently the dataset was split into two halves for the final binary classification (training and testing) performed by a supervised ANN. The classification of the individual Nold and MCI subjects reached 95.87% of sensitivity and 91.06% of specificity (93.46% of accuracy). These results indicate that IFAST can reliably distinguish eyes-closed resting EEG in individual Nold and MCI subjects, and may be used for large-scale periodic screening of large populations at risk of AD and personalized care.

KW - Alzheimer's disease (AD)

KW - Artificial neural networks (ANNs)

KW - Electroencephalography (EEG)

KW - Mild cognitive impairment (MCI)

UR - http://www.scopus.com/inward/record.url?scp=84882581013&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882581013&partnerID=8YFLogxK

U2 - 10.2174/978160805042010901010104

DO - 10.2174/978160805042010901010104

M3 - Chapter

AN - SCOPUS:84882581013

SN - 9781608053926

SP - 104

EP - 113

BT - Artificial Adaptive Systems in Medicine: New Theories and Models for New Applications in the Real World

PB - Bentham Science Publishers Ltd.

ER -