An EEG-Based Hypnotic State Monitor for Patients During General Anesthesia

Most surgical procedures are not possible without general anesthesia which necessitates continuous and accurate monitoring of the patients' level of hypnosis (LoH). Currently, the LoH is monitored using the conventional methods of either observing the patient's physiological parameters or using electroencephalogram (EEG)-based monitors. To overcome the limitations of the conventional methods, this work implements an accurate EEG-based LoH monitoring processor using a bagged tree machine-learning (BTML) classifier. It is based on 12 temporal and spectral features to incorporate robustness against age variation and achieve high classification accuracy. Spectral features are computed using discrete wavelet transform (DWT) that uses time-multiplexed filter (TMF) architecture. The TMF DWT consumes 110.6-nJ/feature vector for a 100-tap filter while reducing the area by 11% compared with the conventional method. Moreover, the BTML is implemented using a pipelined approach which enables an efficient on-chip implementation to reduce the hardware cost by 15x compared with the parallel approach. The proposed processor is implemented using a 180-nm CMOS process with an active area of 0.9 mm(2) while consuming 1.6 mW. The accuracy of the proposed hypnotic state monitor is verified using two EEG databases with a total of 95 patients and achieves a sensitivity and specificity of 95.4% and 97.7%, respectively.

Automated summary

This study presents an EEG-based hypnotic depth monitoring processor using a machine learning classifier, which achieves high accuracy classification and reduces hardware cost efficiently. By adjusting the bit rate, the processor enhances processing efficiency while maintaining accuracy of patient monitoring.