Genetic algorithms for feature selection when classifying severe chronic disorders of consciousness.

The diagnosis and prognosis of patients with severe chronic disorders of consciousness are still challenging issues and a high rate of misdiagnosis is evident. Hence, new tools are needed for an accurate diagnosis, which will also have an impact on the prognosis. In recent years, functional Magnetic Resonance Imaging (fMRI) has been gaining more and more importance when diagnosing this patient group. Especially resting state scans, i.e., an examination when the patient does not perform any task in particular, seems to be promising for these patient groups. After preprocessing the resting state fMRI data with a standard pipeline, we extracted the correlation matrices of 132 regions of interest. The aim was to find the regions of interest which contributed most to the distinction between the different patient groups and healthy controls. We performed feature selection using a genetic algorithm and a support vector machine. Moreover, we show by using only those regions of interest for classification that are most often selected by our algorithm, we get a much better performance of the classifier.

Functional magnetic resonance imaging under anaesthesia of a patient with severe chronic disorders of consciousness.

CLINICAL CASE: We report on a 19-year old male patient who is recovering from near-drowning. The patient was admitted for re-evaluation in a Minimally Conscious State. METHOD: A regular functional Magnetic Resonance Imaging was not possible due to complex motor tics of the patient with sudden flexion and extension movements of arms and legs as well as opisthotonic retroflexion of the head and trunk. Thus, the patient was anaesthetised and functional Magnetic Resonance Imaging was performed under general anaesthesia which was introduced and maintained with Sevoflorane and Fentanyl provided analgesia. Four functional runs were performed and the patient's responses were recorded. During each one of these runs one extremity (dorsum manus or pedis) was stimulated with a brush with an operator-paced frequency of about 2 Hz. RESULTS AND CONCLUSION: Clear responses were found in the somatosensory cortex contra lateral within the post central gyrus during stimulation of the left hand. Considering the other three extremities no significant responses were found. Nevertheless, we conclude that a functional Magnetic Resonance Imaging under anaesthesia is possible for patients with severe chronic disorders of consciousness and brain areas responding to stimuli can be detected.