AUTHOR=Caillet Benjamin , Maître Gilbert , Mirra Alessandro , Levionnois Olivier L. , Simalatsar Alena 

TITLE=Measure of the prediction capability of EEG features for depth of anesthesia in pigs

JOURNAL=Frontiers in Medical Engineering

VOLUME=Volume 2 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/medical-engineering/articles/10.3389/fmede.2024.1393224

DOI=10.3389/fmede.2024.1393224

ISSN=2813-687X

ABSTRACT=In the domain of Machine Learning (ML), there exists a large number of methods capable of performing automatic feature selection. In this paper, we explore how such methods can be applied to select features from electroencephalogram (EEG) signals to allow prediction of depth of anaesthesia (DoA) in pigs receiving propofol. We have evaluated numerous methods and observed that these algorithms can be classified into groups, based on similarities in selected feature sets explainable by the mathematical bases behind those approaches. In this paper, we limit our discussion to the group of methods that have, at their core, the computation of variances, such as Pearson and Spearman correlations, Principal Component Analysis (PCA), and ReliefF algorithms. From an extensive list of time and frequency domain EEG features, spectral power, its density ratio, and entropy applied specifically to high frequency intervals (gamma range) appeared on the top list of best predictors of DoA.