Research ExplorerPublicationsMultimodal prediction of conversion to Alzheimer's disease b...

Multimodal prediction of conversion to Alzheimer's disease based on incomplete biomarkers

Standard

Multimodal prediction of conversion to Alzheimer's disease based on incomplete biomarkers. / Ritter, Kerstin; Schumacher, Julia; Weygandt, Martin; Buchert, Ralph; Allefeld, Carsten; Haynes, John-Dylan.

In: ALZH DEMENT-DADM, Vol. 1, No. 2, 06.2015, p. 206-15.

Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review

Harvard

Ritter, K, Schumacher, J, Weygandt, M, Buchert, R, Allefeld, C & Haynes, J-D 2015, 'Multimodal prediction of conversion to Alzheimer's disease based on incomplete biomarkers', ALZH DEMENT-DADM, vol. 1, no. 2, pp. 206-15. https://doi.org/10.1016/j.dadm.2015.01.006

APA

Ritter, K., Schumacher, J., Weygandt, M., Buchert, R., Allefeld, C., & Haynes, J-D. (2015). Multimodal prediction of conversion to Alzheimer's disease based on incomplete biomarkers. ALZH DEMENT-DADM, 1(2), 206-15. https://doi.org/10.1016/j.dadm.2015.01.006

Vancouver

Ritter K, Schumacher J, Weygandt M, Buchert R, Allefeld C, Haynes J-D. Multimodal prediction of conversion to Alzheimer's disease based on incomplete biomarkers. ALZH DEMENT-DADM. 2015 Jun;1(2):206-15. https://doi.org/10.1016/j.dadm.2015.01.006

Bibtex

@article{ca86476451194c67b76a1226e1fc3366,
title = "Multimodal prediction of conversion to Alzheimer's disease based on incomplete biomarkers",
abstract = "BACKGROUND: This study investigates the prediction of mild cognitive impairment-to-Alzheimer's disease (MCI-to-AD) conversion based on extensive multimodal data with varying degrees of missing values.METHODS: Based on Alzheimer's Disease Neuroimaging Initiative data from MCI-patients including all available modalities, we predicted the conversion to AD within 3 years. Different ways of replacing missing data in combination with different classification algorithms are compared. The performance was evaluated on features prioritized by experts and automatically selected features.RESULTS: The conversion to AD could be predicted with a maximal accuracy of 73% using support vector machines and features chosen by experts. Among data modalities, neuropsychological, magnetic resonance imaging, and positron emission tomography data were most informative. The best single feature was the functional activities questionnaire.CONCLUSION: Extensive multimodal and incomplete data can be adequately handled by a combination of missing data substitution, feature selection, and classification.",
author = "Kerstin Ritter and Julia Schumacher and Martin Weygandt and Ralph Buchert and Carsten Allefeld and John-Dylan Haynes",
year = "2015",
month = jun,
doi = "10.1016/j.dadm.2015.01.006",
language = "English",
volume = "1",
pages = "206--15",
journal = "ALZH DEMENT-DADM",
issn = "2352-8729",
publisher = "Elsevier BV",
number = "2",

}

RIS

TY - JOUR

T1 - Multimodal prediction of conversion to Alzheimer's disease based on incomplete biomarkers

AU - Ritter, Kerstin

AU - Schumacher, Julia

AU - Weygandt, Martin

AU - Buchert, Ralph

AU - Allefeld, Carsten

AU - Haynes, John-Dylan

PY - 2015/6

Y1 - 2015/6

N2 - BACKGROUND: This study investigates the prediction of mild cognitive impairment-to-Alzheimer's disease (MCI-to-AD) conversion based on extensive multimodal data with varying degrees of missing values.METHODS: Based on Alzheimer's Disease Neuroimaging Initiative data from MCI-patients including all available modalities, we predicted the conversion to AD within 3 years. Different ways of replacing missing data in combination with different classification algorithms are compared. The performance was evaluated on features prioritized by experts and automatically selected features.RESULTS: The conversion to AD could be predicted with a maximal accuracy of 73% using support vector machines and features chosen by experts. Among data modalities, neuropsychological, magnetic resonance imaging, and positron emission tomography data were most informative. The best single feature was the functional activities questionnaire.CONCLUSION: Extensive multimodal and incomplete data can be adequately handled by a combination of missing data substitution, feature selection, and classification.

AB - BACKGROUND: This study investigates the prediction of mild cognitive impairment-to-Alzheimer's disease (MCI-to-AD) conversion based on extensive multimodal data with varying degrees of missing values.METHODS: Based on Alzheimer's Disease Neuroimaging Initiative data from MCI-patients including all available modalities, we predicted the conversion to AD within 3 years. Different ways of replacing missing data in combination with different classification algorithms are compared. The performance was evaluated on features prioritized by experts and automatically selected features.RESULTS: The conversion to AD could be predicted with a maximal accuracy of 73% using support vector machines and features chosen by experts. Among data modalities, neuropsychological, magnetic resonance imaging, and positron emission tomography data were most informative. The best single feature was the functional activities questionnaire.CONCLUSION: Extensive multimodal and incomplete data can be adequately handled by a combination of missing data substitution, feature selection, and classification.

U2 - 10.1016/j.dadm.2015.01.006

DO - 10.1016/j.dadm.2015.01.006

M3 - SCORING: Journal article

C2 - 27239505

VL - 1

SP - 206

EP - 215

JO - ALZH DEMENT-DADM

JF - ALZH DEMENT-DADM

SN - 2352-8729

IS - 2

ER -