Improved classification of Alzheimer's disease data via removal of nuisance variability

Juha Koikkalainen (Corresponding Author), Harri Pölönen, Jussi Mattila, Mark van Gils, Hilkka Soininen, Jyrki Lötjönen

Research output: Contribution to journalArticleScientificpeer-review

31 Citations (Scopus)

Abstract

Diagnosis of Alzheimer's disease is based on the results of neuropsychological tests and available supporting biomarkers such as the results of imaging studies. The results of the tests and the values of biomarkers are dependent on the nuisance features, such as age and gender. In order to improve diagnostic power, the effects of the nuisance features have to be removed from the data. In this paper, four types of interactions between classification features and nuisance features were identified. Three methods were tested to remove these interactions from the classification data. In stratified analysis, a homogeneous subgroup was generated from a training set. Data correction method utilized linear regression model to remove the effects of nuisance features from data. The third method was a combination of these two methods. The methods were tested using all the baseline data from the Alzheimer's Disease Neuroimaging Initiative database in two classification studies: classifying control subjects from Alzheimer's disease patients and discriminating stable and progressive mild cognitive impairment subjects. The results show that both stratified analysis and data correction are able to statistically significantly improve the classification accuracy of several neuropsychological tests and imaging biomarkers. The improvements were especially large for the classification of stable and progressive mild cognitive impairment subjects, where the best improvements observed were 6% units. The data correction method gave better results for imaging biomarkers, whereas stratified analysis worked well with the neuropsychological tests. In conclusion, the study shows that the excess variability caused by nuisance features should be removed from the data to improve the classification accuracy, and therefore, the reliability of diagnosis making.
Original languageEnglish
Article numbere31112
Number of pages12
JournalPLoS ONE
Volume7
Issue number2
DOIs
Publication statusPublished - 2012
MoE publication typeA1 Journal article-refereed

Fingerprint

Alzheimer disease
Alzheimer Disease
Biomarkers
Neuropsychological Tests
biomarkers
image analysis
Imaging techniques
Linear Models
methodology
testing
Neuroimaging
Linear regression
Databases
gender

Cite this

Koikkalainen, Juha ; Pölönen, Harri ; Mattila, Jussi ; van Gils, Mark ; Soininen, Hilkka ; Lötjönen, Jyrki. / Improved classification of Alzheimer's disease data via removal of nuisance variability. In: PLoS ONE. 2012 ; Vol. 7, No. 2.
@article{8814ceb04b394beab5508017e6700a3f,
title = "Improved classification of Alzheimer's disease data via removal of nuisance variability",
abstract = "Diagnosis of Alzheimer's disease is based on the results of neuropsychological tests and available supporting biomarkers such as the results of imaging studies. The results of the tests and the values of biomarkers are dependent on the nuisance features, such as age and gender. In order to improve diagnostic power, the effects of the nuisance features have to be removed from the data. In this paper, four types of interactions between classification features and nuisance features were identified. Three methods were tested to remove these interactions from the classification data. In stratified analysis, a homogeneous subgroup was generated from a training set. Data correction method utilized linear regression model to remove the effects of nuisance features from data. The third method was a combination of these two methods. The methods were tested using all the baseline data from the Alzheimer's Disease Neuroimaging Initiative database in two classification studies: classifying control subjects from Alzheimer's disease patients and discriminating stable and progressive mild cognitive impairment subjects. The results show that both stratified analysis and data correction are able to statistically significantly improve the classification accuracy of several neuropsychological tests and imaging biomarkers. The improvements were especially large for the classification of stable and progressive mild cognitive impairment subjects, where the best improvements observed were 6{\%} units. The data correction method gave better results for imaging biomarkers, whereas stratified analysis worked well with the neuropsychological tests. In conclusion, the study shows that the excess variability caused by nuisance features should be removed from the data to improve the classification accuracy, and therefore, the reliability of diagnosis making.",
author = "Juha Koikkalainen and Harri P{\"o}l{\"o}nen and Jussi Mattila and {van Gils}, Mark and Hilkka Soininen and Jyrki L{\"o}tj{\"o}nen",
note = "Project code: 18493",
year = "2012",
doi = "10.1371/journal.pone.0031112",
language = "English",
volume = "7",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "2",

}

Improved classification of Alzheimer's disease data via removal of nuisance variability. / Koikkalainen, Juha (Corresponding Author); Pölönen, Harri; Mattila, Jussi; van Gils, Mark; Soininen, Hilkka; Lötjönen, Jyrki.

In: PLoS ONE, Vol. 7, No. 2, e31112, 2012.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Improved classification of Alzheimer's disease data via removal of nuisance variability

AU - Koikkalainen, Juha

AU - Pölönen, Harri

AU - Mattila, Jussi

AU - van Gils, Mark

AU - Soininen, Hilkka

AU - Lötjönen, Jyrki

N1 - Project code: 18493

PY - 2012

Y1 - 2012

N2 - Diagnosis of Alzheimer's disease is based on the results of neuropsychological tests and available supporting biomarkers such as the results of imaging studies. The results of the tests and the values of biomarkers are dependent on the nuisance features, such as age and gender. In order to improve diagnostic power, the effects of the nuisance features have to be removed from the data. In this paper, four types of interactions between classification features and nuisance features were identified. Three methods were tested to remove these interactions from the classification data. In stratified analysis, a homogeneous subgroup was generated from a training set. Data correction method utilized linear regression model to remove the effects of nuisance features from data. The third method was a combination of these two methods. The methods were tested using all the baseline data from the Alzheimer's Disease Neuroimaging Initiative database in two classification studies: classifying control subjects from Alzheimer's disease patients and discriminating stable and progressive mild cognitive impairment subjects. The results show that both stratified analysis and data correction are able to statistically significantly improve the classification accuracy of several neuropsychological tests and imaging biomarkers. The improvements were especially large for the classification of stable and progressive mild cognitive impairment subjects, where the best improvements observed were 6% units. The data correction method gave better results for imaging biomarkers, whereas stratified analysis worked well with the neuropsychological tests. In conclusion, the study shows that the excess variability caused by nuisance features should be removed from the data to improve the classification accuracy, and therefore, the reliability of diagnosis making.

AB - Diagnosis of Alzheimer's disease is based on the results of neuropsychological tests and available supporting biomarkers such as the results of imaging studies. The results of the tests and the values of biomarkers are dependent on the nuisance features, such as age and gender. In order to improve diagnostic power, the effects of the nuisance features have to be removed from the data. In this paper, four types of interactions between classification features and nuisance features were identified. Three methods were tested to remove these interactions from the classification data. In stratified analysis, a homogeneous subgroup was generated from a training set. Data correction method utilized linear regression model to remove the effects of nuisance features from data. The third method was a combination of these two methods. The methods were tested using all the baseline data from the Alzheimer's Disease Neuroimaging Initiative database in two classification studies: classifying control subjects from Alzheimer's disease patients and discriminating stable and progressive mild cognitive impairment subjects. The results show that both stratified analysis and data correction are able to statistically significantly improve the classification accuracy of several neuropsychological tests and imaging biomarkers. The improvements were especially large for the classification of stable and progressive mild cognitive impairment subjects, where the best improvements observed were 6% units. The data correction method gave better results for imaging biomarkers, whereas stratified analysis worked well with the neuropsychological tests. In conclusion, the study shows that the excess variability caused by nuisance features should be removed from the data to improve the classification accuracy, and therefore, the reliability of diagnosis making.

U2 - 10.1371/journal.pone.0031112

DO - 10.1371/journal.pone.0031112

M3 - Article

VL - 7

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 2

M1 - e31112

ER -