Multivariate Pattern Decoding of fMRI Signals in Hierarchical Experiments for Assessing Disorders of Consciousness

Date(s) - 06/20/2014
11:00 am

Enrico Opri, MS Student

Evaluation of patients with disorder of consciousness (DOC) is conducted prevalently with bedside assessment. However, this approach has been known to produce misdiagnosis. Recent studies propose neuroimaging as a new diagnostic tool, potentially leading to the implementation of a more robust methodology to classify the patients depending on their status, as minimally conscious status (MCS) or persistent vegetative state (PVS).

A hierarchical protocol for functional neuroimaging studies has been suggested as being suitable for the above purpose (Owen et al. 2005), that begins with the simplest form of processing within a particular domain (e.g., auditory) and then progressing sequentially through more complex cognitive functions. It was also shown that that pattern classification of brain activations in different behavioral tasks could allow DOC patients to functionally communicate yes-or-no responses (Boly et al., 2007). In light of the above, the present study aimed to investigate the feasibility of using patterns of fMRI signals (Sitaram et al., 2010) to distinguish brain states of DOC patients in a battery of experiments testing intentional control, language competence, working memory, emotions and pain sensation.

Different tools were developed during the execution of the analysis, leading to a redesign and reimplementation of the Toolbox MANAS, a streamlines batch tool for fMRI analysis. Our preliminary results indicate that pattern classification is a potentially important tool for diagnosing the DOC.