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
APA
Vancouver
Bibtex
}
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 -