The use of kernels in machine learning methods allows the identification of an optimal hyperplane for the separation of two classes (e.g., patients with a brain disorder of interest and healthy controls). When different acquisition modalities or different types of data are available, using a single kernel for all the available data is a disadvantage because data heterogeneity cannot be fully exploited. Multiple kernel learning (MKL) addresses this issue by allowing the integration of different kernels within the same machine learning model. It has been demonstrated that MKL methods outperform single kernel methods when applied to brain disorders data, while at the same time making it possible to understand which features (e.g., brain region) are the most informative for classification. In this chapter, we provide an overview of MKL methods and illustrate their potential by reviewing recent applications to Alzheimer's disease, Parkinson's disease, and psychosis.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.