The IFAST model, a novel parallel nonlinear EEG analysis technique, distinguishes mild cognitive impairment and Alzheimer's disease patients with high degree of accuracy

Massimo Buscema, Paolo Rossini, Claudio Babiloni, Enzo Grossi

Research output: Contribution to journalArticle

Abstract

Objective: This paper presents the results obtained with the innovative use of special types of artificial neural networks (ANNs) assembled in a novel methodology named IFAST (implicit function as squashing time) capable of compressing the temporal sequence of electroencephalographic (EEG) data into spatial invariants. The aim of this study is to assess the potential of this parallel and nonlinear EEG analysis technique in distinguishing between subjects with mild cognitive impairment (MCI) and Alzheimer's disease (AD) patients with a high degree of accuracy in comparison with standard and advanced nonlinear techniques. The principal aim of the study was testing the hypothesis that automatic classification of MCI and AD subjects can be reasonably correct when the spatial content of the EEG voltage is properly extracted by ANNs. Methods and material: Resting eyes-closed EEG data were recorded in 180 AD patients and in 115 MCI subjects. The spatial content of the EEG voltage was extracted by IFAST step-wise procedure using ANNs. The data input for the classification operated by ANNs were not the EEG data, but the connections weights of a nonlinear auto-associative ANN trained to reproduce the recorded EEG tracks. These weights represented a good model of the peculiar spatial features of the EEG patterns at scalp surface. The classification based on these parameters was binary (MCI versus AD) and was performed by a supervised ANN. Half of the EEG database was used for the ANN training and the remaining half was utilised for the automatic classification phase (testing). Results: The best results distinguishing between AD and MCI reached to 92.33%. The comparative results obtained with the best method so far described in the literature, based on blind source separation and Wavelet pre-processing, were 80.43% (p <0.001). Conclusion: The results confirmed the working hypothesis that a correct automatic classification of MCI and AD subjects can be obtained extracting spatial information content of the resting EEG voltage by ANNs and represent the basis for research aimed at integrating spatial and temporal information content of the EEG.

Original languageEnglish
Pages (from-to)127-141
Number of pages15
JournalArtificial Intelligence in Medicine
Volume40
Issue number2
DOIs
Publication statusPublished - Jun 2007

Fingerprint

Nonlinear analysis
Alzheimer Disease
Neural networks
Weights and Measures
Electric potential
Scalp
Blind source separation
Cognitive Dysfunction
Testing
Databases
Research
Processing

Keywords

  • Alzheimer's disease
  • Artificial neural networks
  • Electroencephalography
  • Mild cognitive impairment

ASJC Scopus subject areas

  • Artificial Intelligence
  • Medicine(all)

Cite this

The IFAST model, a novel parallel nonlinear EEG analysis technique, distinguishes mild cognitive impairment and Alzheimer's disease patients with high degree of accuracy. / Buscema, Massimo; Rossini, Paolo; Babiloni, Claudio; Grossi, Enzo.

In: Artificial Intelligence in Medicine, Vol. 40, No. 2, 06.2007, p. 127-141.

Research output: Contribution to journalArticle

@article{54781e65a11a412cac1dc427b580a315,
title = "The IFAST model, a novel parallel nonlinear EEG analysis technique, distinguishes mild cognitive impairment and Alzheimer's disease patients with high degree of accuracy",
abstract = "Objective: This paper presents the results obtained with the innovative use of special types of artificial neural networks (ANNs) assembled in a novel methodology named IFAST (implicit function as squashing time) capable of compressing the temporal sequence of electroencephalographic (EEG) data into spatial invariants. The aim of this study is to assess the potential of this parallel and nonlinear EEG analysis technique in distinguishing between subjects with mild cognitive impairment (MCI) and Alzheimer's disease (AD) patients with a high degree of accuracy in comparison with standard and advanced nonlinear techniques. The principal aim of the study was testing the hypothesis that automatic classification of MCI and AD subjects can be reasonably correct when the spatial content of the EEG voltage is properly extracted by ANNs. Methods and material: Resting eyes-closed EEG data were recorded in 180 AD patients and in 115 MCI subjects. The spatial content of the EEG voltage was extracted by IFAST step-wise procedure using ANNs. The data input for the classification operated by ANNs were not the EEG data, but the connections weights of a nonlinear auto-associative ANN trained to reproduce the recorded EEG tracks. These weights represented a good model of the peculiar spatial features of the EEG patterns at scalp surface. The classification based on these parameters was binary (MCI versus AD) and was performed by a supervised ANN. Half of the EEG database was used for the ANN training and the remaining half was utilised for the automatic classification phase (testing). Results: The best results distinguishing between AD and MCI reached to 92.33{\%}. The comparative results obtained with the best method so far described in the literature, based on blind source separation and Wavelet pre-processing, were 80.43{\%} (p <0.001). Conclusion: The results confirmed the working hypothesis that a correct automatic classification of MCI and AD subjects can be obtained extracting spatial information content of the resting EEG voltage by ANNs and represent the basis for research aimed at integrating spatial and temporal information content of the EEG.",
keywords = "Alzheimer's disease, Artificial neural networks, Electroencephalography, Mild cognitive impairment",
author = "Massimo Buscema and Paolo Rossini and Claudio Babiloni and Enzo Grossi",
year = "2007",
month = "6",
doi = "10.1016/j.artmed.2007.02.006",
language = "English",
volume = "40",
pages = "127--141",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - The IFAST model, a novel parallel nonlinear EEG analysis technique, distinguishes mild cognitive impairment and Alzheimer's disease patients with high degree of accuracy

AU - Buscema, Massimo

AU - Rossini, Paolo

AU - Babiloni, Claudio

AU - Grossi, Enzo

PY - 2007/6

Y1 - 2007/6

N2 - Objective: This paper presents the results obtained with the innovative use of special types of artificial neural networks (ANNs) assembled in a novel methodology named IFAST (implicit function as squashing time) capable of compressing the temporal sequence of electroencephalographic (EEG) data into spatial invariants. The aim of this study is to assess the potential of this parallel and nonlinear EEG analysis technique in distinguishing between subjects with mild cognitive impairment (MCI) and Alzheimer's disease (AD) patients with a high degree of accuracy in comparison with standard and advanced nonlinear techniques. The principal aim of the study was testing the hypothesis that automatic classification of MCI and AD subjects can be reasonably correct when the spatial content of the EEG voltage is properly extracted by ANNs. Methods and material: Resting eyes-closed EEG data were recorded in 180 AD patients and in 115 MCI subjects. The spatial content of the EEG voltage was extracted by IFAST step-wise procedure using ANNs. The data input for the classification operated by ANNs were not the EEG data, but the connections weights of a nonlinear auto-associative ANN trained to reproduce the recorded EEG tracks. These weights represented a good model of the peculiar spatial features of the EEG patterns at scalp surface. The classification based on these parameters was binary (MCI versus AD) and was performed by a supervised ANN. Half of the EEG database was used for the ANN training and the remaining half was utilised for the automatic classification phase (testing). Results: The best results distinguishing between AD and MCI reached to 92.33%. The comparative results obtained with the best method so far described in the literature, based on blind source separation and Wavelet pre-processing, were 80.43% (p <0.001). Conclusion: The results confirmed the working hypothesis that a correct automatic classification of MCI and AD subjects can be obtained extracting spatial information content of the resting EEG voltage by ANNs and represent the basis for research aimed at integrating spatial and temporal information content of the EEG.

AB - Objective: This paper presents the results obtained with the innovative use of special types of artificial neural networks (ANNs) assembled in a novel methodology named IFAST (implicit function as squashing time) capable of compressing the temporal sequence of electroencephalographic (EEG) data into spatial invariants. The aim of this study is to assess the potential of this parallel and nonlinear EEG analysis technique in distinguishing between subjects with mild cognitive impairment (MCI) and Alzheimer's disease (AD) patients with a high degree of accuracy in comparison with standard and advanced nonlinear techniques. The principal aim of the study was testing the hypothesis that automatic classification of MCI and AD subjects can be reasonably correct when the spatial content of the EEG voltage is properly extracted by ANNs. Methods and material: Resting eyes-closed EEG data were recorded in 180 AD patients and in 115 MCI subjects. The spatial content of the EEG voltage was extracted by IFAST step-wise procedure using ANNs. The data input for the classification operated by ANNs were not the EEG data, but the connections weights of a nonlinear auto-associative ANN trained to reproduce the recorded EEG tracks. These weights represented a good model of the peculiar spatial features of the EEG patterns at scalp surface. The classification based on these parameters was binary (MCI versus AD) and was performed by a supervised ANN. Half of the EEG database was used for the ANN training and the remaining half was utilised for the automatic classification phase (testing). Results: The best results distinguishing between AD and MCI reached to 92.33%. The comparative results obtained with the best method so far described in the literature, based on blind source separation and Wavelet pre-processing, were 80.43% (p <0.001). Conclusion: The results confirmed the working hypothesis that a correct automatic classification of MCI and AD subjects can be obtained extracting spatial information content of the resting EEG voltage by ANNs and represent the basis for research aimed at integrating spatial and temporal information content of the EEG.

KW - Alzheimer's disease

KW - Artificial neural networks

KW - Electroencephalography

KW - Mild cognitive impairment

UR - http://www.scopus.com/inward/record.url?scp=34249294071&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34249294071&partnerID=8YFLogxK

U2 - 10.1016/j.artmed.2007.02.006

DO - 10.1016/j.artmed.2007.02.006

M3 - Article

C2 - 17466496

AN - SCOPUS:34249294071

VL - 40

SP - 127

EP - 141

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

IS - 2

ER -