Machine learning reveals interhemispheric somatosensory coherence as indicator of anesthetic depth

Abstract

The goal of this study was to identify features in mouse electrocorticogram recordings that indicate the depth of anesthesia as approximated by the administered anesthetic dosage. Anesthetic depth in laboratory animals must be precisely monitored and controlled. However, for the most common lab species (mice) few indicators useful for monitoring anesthetic depth have been established. We used electrocorticogram recordings in mice, coupled with peripheral stimulation, in order to identify features of brain activity modulated by isoflurane anesthesia and explored their usefulness in monitoring anesthetic depth through machine learning techniques. Using a gradient boosting regressor framework we identified interhemispheric somatosensory coherence as the most informative and reliable electrocorticogram feature for determining anesthetic depth, yielding good generalization and performance over many subjects. Knowing that interhemispheric somatosensory coherence indicates the effectively administered isoflurane concentration is an important step for establishing better anesthetic monitoring protocols and closed-loop systems for animal surgeries.

Bayesian surprise shapes neural responses in somatosensory cortical circuits

“…32 Electrocorticographic recordings in human subjects demonstrated that anesthesia affected predictive activity mostly on longer timescales and in higher, prefrontal cortical areas and only very little in the core auditory cortex. 60 In principle, we took great care to keep the anesthesia as shallow and constant as 61 which, together with our awake recordings, supports the notion that the Bayesian surprise signals reported here reflect an elementary and early cortical computation that is less subject to brain states or arousal levels.…”

Application of Machine Learning in Predicting Perioperative Outcomes in Patients with Cancer: A Narrative Review for Clinicians

“…The machine learning technique of boosting builds models sequentially, starting with a smaller number of models and increasing the number of models in each iteration [41][42][43][44][45]. The most common boosting methods include adaptive boosting (AdaBoosting), gradient boosting (GBM), and extreme gradient boosting (XG Boost) [40,46,47].…”

“…Application to the Perioperative Setting (Key Finding) Supervised machine learning has become increasingly important in surgery, anesthesia, and perioperative care. Ensemble techniques, such as random forests and boosting, combine multiple models for improved prediction accuracy [41][42][43][44][45][46][47][48]. Neural network techniques are also being applied in anesthesiology and perioperative medicine to predict outcomes [51,53,56,57].…”