Communications of the ACM
Computers Determine States of Consciousness
A new algorithm distinguishes unresponsive wakefulness syndrome (from which there is little hope of recovery) from a minimally conscious state (from which there is some likelihood of recovery) based on brainwave recordings.
Credit: Getty Images
Researchers at Pitie-Salpetriere Hospital in Paris, France have developed an algorithm that distinguishes unresponsive wakefulness syndrome (from which there is little hope of recovery) from a minimally conscious state (from which there is some likelihood of recovery), using electroencephalographic (EEG) brainwave recordings.
The algorithm, if put into use, could take some of the guesswork out of this diagnosis and likely would perform better than most human doctors.
The researchers took EEG recordings from 268 patients diagnosed with either unresponsive wakefulness or a minimally conscious state. The EEGs were recorded before and during a listening task designed to identify the conscious processing of sounds.
The data was fed into a machine learning algorithm called DOC-Forest, which properly diagnosed roughly three out of four cases.
From Scientific American
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found