Validation of a new approach for distinguishing anesthetized from awake state in patients using Directed Transfer Function applied to raw EEG

Abstract

AbstractAimIn a previous study, we found that the state of wakefulness in patients undergoing general anesthesia with propofol can effectively be monitored with high temporal resolution using an automatic measure of connectivity based on the Directed Transfer Function (DTF) calculated from short segments of electroencephalography (EEG) time-series. The study described here was designed to test whether the same measure can be used to monitor the state of the patients also during sevoflurane anesthesia.MethodsTwenty-five channel EEG recordings were collected from 8 patients undergoing surgical anesthesia with sevoflurane. The EEG data were segmented into one second epochs and labeled as awake or anesthetized in accordance with the clinician’s judgement, and the sensor space directed connectivity was quantified for every epoch using the DTF. The resulting DTF derived connectivity parameters were compared to corresponding parameters from our previous study using permutation statistics. A data driven classification algorithm was then employed to objectively classify the individual 1-second epochs as coming from awake or anesthetized state, using a leave-one-out cross-validation approach. The classifications were made for every epoch using the median DTF parameters across the five preceding 1-second EEG epochs.ResultsThe DTF derived connectivity parameters showed a significant difference between the awake and sevoflurane-induced general anesthesia at the group level (p<0.05). In contrast, the DTF parameters were not significantly different when comparing sevoflurane and propofol data neither in the awake nor in anesthetized state (p>0.05 for both comparisons). The classification algorithm reached a maximum accuracy of 96.8% (SE=0.63%). Optimizing the algorithm for simultaneously having high sensitivity and specificity in classification reduced the accuracy to 95.1% (SE=0.96%), with sensitivity of 98.4% (SE=0.80%) and specificity of 94.8% (SE=0.10%).ConclusionThese findings indicate that the DTF changes in a similar manner when humans undergo general anesthesia caused by two distinct anesthetic agents with different molecular mechanisms of action. This seems to support the idea that brain connectivity is related to the level of consciousness in humans, although further studies are needed to clarify whether our results may be contaminated by confounding factors.