Artificial neural networks identify the predictive values of risk factors on the conversion of amnestic mild cognitive impairment

Massimo Tabaton, Patrizio Odetti, Sergio Cammarata, Roberta Borghi, Fiammetta Monacelli, Carlo Caltagirone, Paola Bossù, Massimo Buscema, Enzo Grossi

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

The search for markers that are able to predict the conversion of amnestic mild cognitive impairment (aMCI) to Alzheimer's disease (AD) is crucial for early mechanistic therapies. Using artificial neural networks (ANNs), 22 variables that are known risk factors of AD were analyzed in 80 patients with aMCI, for a period spanning at least 2 years. The cases were chosen from 195 aMCI subjects recruited by four Italian Alzheimer's disease units. The parameters of glucose metabolism disorder, female gender, and apolipoprotein E ε3/ε4 genotype were found to be the biological variables with high relevance for predicting the conversion of aMCI. The scores of attention and short term memory tests also were predictors. Surprisingly, the plasma concentration of amyloid-β42 had a low predictive value. The results support the utility of ANN analysis as a new tool in the interpretation of data from heterogeneous and distinct sources.

Original languageEnglish
Pages (from-to)1035-1040
Number of pages6
JournalJournal of Alzheimer's Disease
Volume19
Issue number3
DOIs
Publication statusPublished - 2010

Fingerprint

Alzheimer Disease
Glucose Metabolism Disorders
Apolipoprotein E3
Apolipoprotein E4
Secondary Prevention
Short-Term Memory
Amyloid
Genotype
Cognitive Dysfunction

Keywords

  • Alzheimer's disease
  • Artificial neural networks
  • Biological markers
  • Mild cognitive impairment

ASJC Scopus subject areas

  • Psychiatry and Mental health
  • Geriatrics and Gerontology
  • Clinical Psychology

Cite this

Artificial neural networks identify the predictive values of risk factors on the conversion of amnestic mild cognitive impairment. / Tabaton, Massimo; Odetti, Patrizio; Cammarata, Sergio; Borghi, Roberta; Monacelli, Fiammetta; Caltagirone, Carlo; Bossù, Paola; Buscema, Massimo; Grossi, Enzo.

In: Journal of Alzheimer's Disease, Vol. 19, No. 3, 2010, p. 1035-1040.

Research output: Contribution to journalArticle

Tabaton, Massimo ; Odetti, Patrizio ; Cammarata, Sergio ; Borghi, Roberta ; Monacelli, Fiammetta ; Caltagirone, Carlo ; Bossù, Paola ; Buscema, Massimo ; Grossi, Enzo. / Artificial neural networks identify the predictive values of risk factors on the conversion of amnestic mild cognitive impairment. In: Journal of Alzheimer's Disease. 2010 ; Vol. 19, No. 3. pp. 1035-1040.
@article{36128f7e853a4a7d8144f8cdfcc32642,
title = "Artificial neural networks identify the predictive values of risk factors on the conversion of amnestic mild cognitive impairment",
abstract = "The search for markers that are able to predict the conversion of amnestic mild cognitive impairment (aMCI) to Alzheimer's disease (AD) is crucial for early mechanistic therapies. Using artificial neural networks (ANNs), 22 variables that are known risk factors of AD were analyzed in 80 patients with aMCI, for a period spanning at least 2 years. The cases were chosen from 195 aMCI subjects recruited by four Italian Alzheimer's disease units. The parameters of glucose metabolism disorder, female gender, and apolipoprotein E ε3/ε4 genotype were found to be the biological variables with high relevance for predicting the conversion of aMCI. The scores of attention and short term memory tests also were predictors. Surprisingly, the plasma concentration of amyloid-β42 had a low predictive value. The results support the utility of ANN analysis as a new tool in the interpretation of data from heterogeneous and distinct sources.",
keywords = "Alzheimer's disease, Artificial neural networks, Biological markers, Mild cognitive impairment",
author = "Massimo Tabaton and Patrizio Odetti and Sergio Cammarata and Roberta Borghi and Fiammetta Monacelli and Carlo Caltagirone and Paola Boss{\`u} and Massimo Buscema and Enzo Grossi",
year = "2010",
doi = "10.3233/JAD-2010-1300",
language = "English",
volume = "19",
pages = "1035--1040",
journal = "Journal of Alzheimer's Disease",
issn = "1387-2877",
publisher = "IOS Press",
number = "3",

}

TY - JOUR

T1 - Artificial neural networks identify the predictive values of risk factors on the conversion of amnestic mild cognitive impairment

AU - Tabaton, Massimo

AU - Odetti, Patrizio

AU - Cammarata, Sergio

AU - Borghi, Roberta

AU - Monacelli, Fiammetta

AU - Caltagirone, Carlo

AU - Bossù, Paola

AU - Buscema, Massimo

AU - Grossi, Enzo

PY - 2010

Y1 - 2010

N2 - The search for markers that are able to predict the conversion of amnestic mild cognitive impairment (aMCI) to Alzheimer's disease (AD) is crucial for early mechanistic therapies. Using artificial neural networks (ANNs), 22 variables that are known risk factors of AD were analyzed in 80 patients with aMCI, for a period spanning at least 2 years. The cases were chosen from 195 aMCI subjects recruited by four Italian Alzheimer's disease units. The parameters of glucose metabolism disorder, female gender, and apolipoprotein E ε3/ε4 genotype were found to be the biological variables with high relevance for predicting the conversion of aMCI. The scores of attention and short term memory tests also were predictors. Surprisingly, the plasma concentration of amyloid-β42 had a low predictive value. The results support the utility of ANN analysis as a new tool in the interpretation of data from heterogeneous and distinct sources.

AB - The search for markers that are able to predict the conversion of amnestic mild cognitive impairment (aMCI) to Alzheimer's disease (AD) is crucial for early mechanistic therapies. Using artificial neural networks (ANNs), 22 variables that are known risk factors of AD were analyzed in 80 patients with aMCI, for a period spanning at least 2 years. The cases were chosen from 195 aMCI subjects recruited by four Italian Alzheimer's disease units. The parameters of glucose metabolism disorder, female gender, and apolipoprotein E ε3/ε4 genotype were found to be the biological variables with high relevance for predicting the conversion of aMCI. The scores of attention and short term memory tests also were predictors. Surprisingly, the plasma concentration of amyloid-β42 had a low predictive value. The results support the utility of ANN analysis as a new tool in the interpretation of data from heterogeneous and distinct sources.

KW - Alzheimer's disease

KW - Artificial neural networks

KW - Biological markers

KW - Mild cognitive impairment

UR - http://www.scopus.com/inward/record.url?scp=77149170369&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77149170369&partnerID=8YFLogxK

U2 - 10.3233/JAD-2010-1300

DO - 10.3233/JAD-2010-1300

M3 - Article

C2 - 20157257

AN - SCOPUS:77149170369

VL - 19

SP - 1035

EP - 1040

JO - Journal of Alzheimer's Disease

JF - Journal of Alzheimer's Disease

SN - 1387-2877

IS - 3

ER -