Identification of biomarkers for early detection of Alzheimer's disease (AD) is an important research topic. Prior work has shown that multimodal imaging and biomarker data could provide complementary information for prediction of cognitive or AD status. However, the relationship among multiple data modalities are often ignored or oversimplified in prior studies. To address this issue, we propose a network-guided sparse learning model to embrace the complementary information and inter-relationships between modalities. We apply this model to predict cognitive outcome from imaging and proteomic data, and show that the proposed model not only outperforms traditional ones, but also yields stable multimodal biomarkers across cross-validation trials.
Keywords: Sparse learning; cognitive outcome; neuroimaging; proteomic biomarker; regression.