Automated Measurement and Prediction of Consciousness in Vegetative and Minimally Conscious Patients - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

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.
Fichier principal
Vignette du fichier
paper_v2018.pdf (3.16 Mo) Télécharger le fichier
supplement_207.pdf (2.46 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01225254 , version 1 (26-11-2015)
hal-01225254 , version 2 (27-12-2018)

Identifiers

  • HAL Id : hal-01225254 , version 2

Cite

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), Bertrand Thirion, Lars Kai Hansen, Sanmi Koyejo, Jul 2015, Lille, France. ⟨hal-01225254v2⟩
1424 View
894 Download

Share

Gmail Facebook X LinkedIn More