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

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.