Depth Analysis of Anesthesia Using EEG Signals via Time Series Feature Extraction and Machine Learning

The term “anesthetic depth” refers to the extent which a general anesthetic agent sedates central nervous system with specific strength concentration at it is delivered. depth level of anesthesia plays crucial role in determining surgical complications, and imperative keep levels under control perform successful surgery. This study used electroencephalography (EEG) signals predict anesthesia. Traditional preprocessing methods such as signal decomposition model building using deep learning were classify levels. paper proposed novel approach based on concept time series feature extraction, by finding out relation between EEG bi-spectral Index over period time. Time extraction basis scalable hypothesis tests performed extract features analyzing Bi-Spectral Index, machine models support vector classifier, XG boost gradient decision trees random forest classifier are train best-trained was forest, gives an accuracy 83%. provides platform further research dig into series-based this area.