Ontology highlight
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.
SUBMITTER: Ritter K
PROVIDER: S-EPMC4877756 | biostudies-literature | 2015 Jun
REPOSITORIES: biostudies-literature
Ritter Kerstin K Schumacher Julia J Weygandt Martin M Buchert Ralph R Allefeld Carsten C Haynes John-Dylan JD
Alzheimer's & dementia (Amsterdam, Netherlands) 20150430 2
<h4>Background</h4>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.<h4>Methods</h4>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 ...[more]