Researchers trained algorithms to make predictions about whether a patient was unconscious based on EEG readings of brain rhythms. Rhythms from a volunteer over time are shown in the spectrogram at the top. The predictions of three algorithms are shown as the height of dots in the rectangle on the bottom. They were very accurate in assessing the probability of unconsciousness, the data show.

New algorithms show accuracy, reliability in gauging unconsciousness

MIT News | June 1, 2021

MIT Institute for Data, Systems, and Society
Massachusetts Institute of Technology
77 Massachusetts Avenue
Cambridge, MA 02139-4307