Automated Measurement and Prediction of Consciousness in Vegetative and Minimally Conscious Patients

Abstract : Scientific advances in electrophysiology and clinical neuroscience have highlighted electroen-cephalography (EEG) biomarkers that allow to discriminate between different disorders of consciousness such as vegetative and minimally conscious state. In the current work, we present an automated approach to measuring consciousness disorders and guiding clinical diagnostics. This approach allows to extract scientifically validated biomarkers from incoming clinical EEG-recordings. Probabilistic predictions of an undi-agnosed patient's state of consciousness are then obtained by interrogating statistical models informed by database records of these biomark-ers. Predictions are subsequently summarized and deployed to the clinician in form of a self-contained HTML-report which supports interactive visualization and navigation. We additionally conducted replication and robustness analyses , which indicate that the EEG-biomarkers can be successfully employed in a wide range of practical contexts.
Type de document :
Communication dans un congrès
ICML Workshop on Statistics, Machine Learning and Neuroscience (Stamlins 2015), Jul 2015, Lille, France. 2015
Liste complète des métadonnées


https://hal.inria.fr/hal-01225254
Contributeur : Bertrand Thirion <>
Soumis le : jeudi 26 novembre 2015 - 23:00:35
Dernière modification le : lundi 29 mai 2017 - 15:33:21
Document(s) archivé(s) le : vendredi 28 avril 2017 - 04:53:24

Fichiers

paper_207.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01225254, version 1

Citation

Denis Engemann, Federico Raimondo, Jean-Remi King, Mainak Jas, Alexandre Gramfort, et al.. Automated Measurement and Prediction of Consciousness in Vegetative and Minimally Conscious Patients. ICML Workshop on Statistics, Machine Learning and Neuroscience (Stamlins 2015), Jul 2015, Lille, France. 2015. <hal-01225254>

Partager

Métriques

Consultations de
la notice

325

Téléchargements du document

329