2026-09-19T21:13:55Zhttps://orbi.uliege.be/oai/request

oai:orbi.ulg.ac.be:2268/2434772026-09-01T13:35:24Zcom_f00col_f03class_c05

doctoral thesis http://purl.org/coar/resource_type/c_db06 info:eu-repo/semantics/doctoralThesis restricted access http://purl.org/coar/access_right/c_16ec info:eu-repo/semantics/restrictedAccess Standardisation and automatisation of the diagnosis of patients with disorders of consciousness: a machine learning approach applied to electrophysiological brain and body signals. Normalisation et automatisation du diagnostic des patients atteints de troubles de la conscience: une approche par apprentissage automatique appliquée aux signaux électrophysiologiques du cerveau et du corps. Raimondo, Federico SITT, Jacobo FERNÁNDEZ SLEZAK, Diego COHEN, Laurent 2018-11-27 https://orbi.uliege.be/handle/2268/243477 info:hdl:2268/243477 en https://www.theses.fr/s232694 Engineering, computing & technology Computer science Ingénierie, informatique & technologie Sciences informatiques Advances in modern medicine have led to an increase of patients diagnosed with disorders of consciousness (DOC). In these conditions, patients are awake, but without behavioural signs of awareness. An accurate evaluation of DOC patients has medico-ethical and societal implications, and it is of crucial importance because it typically informs prognosis. Misdiagnosis of patients, however, is a major concern in clinics due to intrinsic limitations of behavioural tools. One accessible assisting methodology for clinicians is electroencephalography (EEG). In a previous study, we introduced the use of EEG-extracted markers and machine learning as a tool for the diagnosis of DOC patients. In this work, we developed an automated analysis tool, and analysed the applicability and limitations of this method. Additionally, we proposed two approaches to enhance the accuracy of this method: (1) the use of multiple stimulation modalities to include neural correlates of multisensory integration and (2) the analysis of consciousness-mediated modulations of cardiac activity. Our results exceed the current state of knowledge in two dimensions. Clinically, we found that the method can be used in heterogeneous contexts, confirming the utility of machine learning as an automated tool for clinical diagnosis. Scientifically, our results highlight that brain-body interactions might be the fundamental mechanism to support the fusion of multiple senses into a unique percept, leading to the emergence of consciousness. Taken together, this work illustrates the importance of machine learning to individualised clinical assessment, and paves the way for inclusion of bodily functions when quantifying global states of consciousness. Sorbonne Université